docker: build both root and non-root container images (#412 )

Change the user back to root for containers. Additionally, built a "non-root" labeled container for users who wish to have the additional security of running llama-swap as a lower privileged user.
feat: add platform-specific process attributes support (#411 )
2025-11-25 10:44:13 -08:00 · 2025-11-24 21:39:56 -08:00 · 2025-11-17 10:43:47 -08:00 · 2025-11-16 10:21:59 -08:00 · 2025-11-15 14:35:26 -08:00 · 2025-11-08 15:29:37 -08:00
30 changed files with 2311 additions and 441 deletions
@@ -0,0 +1,41 @@
+name: Validate JSON Schema
+
+on:
+  pull_request:
+    paths:
+      - "config-schema.json"
+  push:
+    branches:
+      - main
+    paths:
+      - "config-schema.json"
+
+  workflow_dispatch:
+
+jobs:
+  validate-schema:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Validate JSON Schema
+        run: |
+          # Check if the file is valid JSON
+          if ! jq empty config-schema.json 2>/dev/null; then
+            echo "Error: config-schema.json is not valid JSON"
+            exit 1
+          fi
+
+          # Validate that it's a valid JSON Schema
+          # Check for required $schema field
+          if ! jq -e '."$schema"' config-schema.json > /dev/null; then
+            echo "Warning: config-schema.json should have a \$schema field"
+          fi
+
+          # Check that it has either properties or definitions
+          if ! jq -e '.properties or .definitions or ."$defs"' config-schema.json > /dev/null; then
+            echo "Warning: JSON Schema should contain properties, definitions, or \$defs"
+          fi
+
+          echo "✓ config-schema.json is valid"
@@ -11,7 +11,7 @@ llama-swap is a light weight, transparent proxy server that provides automatic m

 ## Testing

- `make test-dev` - Use this when making iterative changes. Runs `go test` and `staticcheck`. Fix any static checking errors.
+- `make test-dev` - Use this when making iterative changes. Runs `go test` and `staticcheck`. Fix any static checking errors. Use this only when changes are made to any code under the `proxy/` directory
 - `make test-all` - runs at the end before completing work. Includes long running concurrency tests.

 ## Workflow Tasks
@@ -90,7 +90,7 @@ GOOS ?= $(shell go env GOOS 2>/dev/null || echo linux)
 GOARCH ?= $(shell go env GOARCH 2>/dev/null || echo amd64)
 wol-proxy: $(BUILD_DIR)
 	@echo "Building wol-proxy"
-	go build -o $(BUILD_DIR)/wol-proxy-$(GOOS)-$(GOARCH) cmd/wol-proxy/wol-proxy.go
+	go build -o $(BUILD_DIR)/wol-proxy-$(GOOS)-$(GOARCH)-$(shell date +%Y-%m-%d) cmd/wol-proxy/wol-proxy.go

 # Phony targets
 .PHONY: all clean ui mac linux windows simple-responder simple-responder-windows test test-all test-dev wol-proxy
@@ -42,7 +42,8 @@ Built in Go for performance and simplicity, llama-swap has zero dependencies and

 llama-swap includes a real time web interface for monitoring logs and controlling models:

-<img width="1360" height="963" alt="image" src="https://github.com/user-attachments/assets/adef4a8e-de0b-49db-885a-8f6dedae6799" />
+<img width="1164" height="745" alt="image" src="https://github.com/user-attachments/assets/bacf3f9d-819f-430b-9ed2-1bfaa8d54579" />
+

 The Activity Page shows recent requests:

@@ -0,0 +1,64 @@
+<!DOCTYPE html>
+<html>
+<head>
+<meta charset="utf-8">
+<title>Loading...</title>
+<style>
+body {
+    font-family: sans-serif;
+    display: flex;
+    justify-content: center;
+    align-items: center;
+    height: 100vh;
+    margin: 0;
+    background: #f5f5f5;
+}
+.loader {
+    text-align: center;
+}
+.stats {
+    font-size: 18px;
+    color: #333;
+    margin: 20px 0;
+}
+.stats-label {
+    color: #666;
+    font-size: 14px;
+}
+</style>
+</head>
+<body>
+<div class="loader">
+    <p>Waking up upstream server...</p>
+    <div class="stats">
+        <div><span class="stats-label">Time elapsed:</span> <span id="elapsed">0s</span></div>
+        <div><span id="attempts">&nbsp;</span></div>
+    </div>
+</div>
+<script>
+var startTime = Date.now();
+var attempts = 0;
+
+setInterval(function() {
+    var elapsed = (Date.now() - startTime) / 1000;
+    document.getElementById('elapsed').textContent = elapsed.toFixed(1) + 's';
+}, 100);
+
+// Check status every second
+setInterval(function() {
+    attempts++;
+    var dots = '.'.repeat((attempts % 10) || 10);
+    document.getElementById('attempts').textContent = dots;
+
+    fetch('/status')
+        .then(function(r) { return r.text(); })
+        .then(function(t) {
+            if (t.indexOf('status: ready') !== -1) {
+                location.reload();
+            }
+        })
+        .catch(function() {});
+}, 1000);
+</script>
+</body>
+</html>
@@ -1,7 +1,9 @@
 package main

 import (
+	"bufio"
 	"context"
+	_ "embed"
 	"errors"
 	"flag"
 	"fmt"
@@ -13,10 +15,14 @@ import (
 	"net/url"
 	"os"
 	"os/signal"
+	"strings"
 	"sync"
 	"time"
 )

+//go:embed index.html
+var loadingPageHTML string
+
 var (
 	flagMac      = flag.String("mac", "", "mac address to send WoL packet to")
 	flagUpstream = flag.String("upstream", "", "upstream proxy address to send requests to")
@@ -92,14 +98,9 @@ func main() {
 	}()

 	// graceful shutdown
-	ctx, stop := signal.NotifyContext(context.Background(), os.Interrupt)
-	defer stop()
+	ctx, _ := signal.NotifyContext(context.Background(), os.Interrupt)
 	<-ctx.Done()
-	shutdownCtx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-	defer cancel()
-	if err := server.Shutdown(shutdownCtx); err != nil {
-		slog.Error("server shutdown error", "error", err)
-	}
+	server.Close()
 }

 type upstreamStatus string
@@ -124,37 +125,86 @@ func newProxy(url *url.URL) *proxyServer {
 		failCount:     0,
 	}

-	// start a goroutien to check upstream status
+	// start a goroutine to monitor upstream status via SSE
 	go func() {
-		checkUrl := url.Scheme + "://" + url.Host + "/wol-health"
-		client := &http.Client{Timeout: time.Second}
-		ticker := time.NewTicker(2 * time.Second)
-		defer ticker.Stop()
-		for range ticker.C {
+		eventsUrl := url.Scheme + "://" + url.Host + "/api/events"
+		client := &http.Client{
+			Timeout: 0, // No timeout for SSE connection
+		}

-			slog.Debug("checking upstream status at", "url", checkUrl)
-			resp, err := client.Get(checkUrl)
+		waitDuration := 10 * time.Second

-			// drain the body
-			if err == nil && resp != nil {
+		for {
+			slog.Debug("connecting to SSE endpoint", "url", eventsUrl)
+
+			req, err := http.NewRequest("GET", eventsUrl, nil)
+			if err != nil {
+				slog.Warn("failed to create SSE request", "error", err)
+				proxy.setStatus(notready)
+				proxy.incFail(1)
+				time.Sleep(waitDuration)
+				continue
+			}
+
+			req.Header.Set("Accept", "text/event-stream")
+			req.Header.Set("Cache-Control", "no-cache")
+			req.Header.Set("Connection", "keep-alive")
+
+			resp, err := client.Do(req)
+			if err != nil {
+				slog.Error("failed to connect to SSE endpoint", "error", err)
+				proxy.setStatus(notready)
+				proxy.incFail(1)
+				time.Sleep(10 * time.Second)
+				continue
+			}
+
+			if resp.StatusCode != http.StatusOK {
+				slog.Warn("SSE endpoint returned non-OK status", "status", resp.StatusCode)
 				_, _ = io.Copy(io.Discard, resp.Body)
 				_ = resp.Body.Close()
-			}
-
-			if err == nil && resp != nil && resp.StatusCode == http.StatusOK {
-				slog.Debug("upstream status: ready")
-				proxy.setStatus(ready)
-				proxy.statusMutex.Lock()
-				proxy.failCount = 0
-				proxy.statusMutex.Unlock()
-			} else {
-				slog.Debug("upstream status: notready", "error", err)
 				proxy.setStatus(notready)
-				proxy.statusMutex.Lock()
-				proxy.failCount++
-				proxy.statusMutex.Unlock()
+				proxy.incFail(1)
+				time.Sleep(10 * time.Second)
+				continue
 			}

+			// Successfully connected to SSE endpoint
+			slog.Info("connected to SSE endpoint, upstream ready")
+			proxy.setStatus(ready)
+			proxy.resetFailures()
+
+			// Read from the SSE stream to detect disconnection
+			scanner := bufio.NewScanner(resp.Body)
+
+			// use a fairly large buffer to avoid scanner errors when reading large SSE events
+			buf := make([]byte, 0, 1024*1024*2)
+			scanner.Buffer(buf, 1024*1024*2)
+			events := 0
+			if slog.Default().Enabled(context.Background(), slog.LevelDebug) {
+				fmt.Print("Events: ")
+			}
+			for scanner.Scan() {
+				if slog.Default().Enabled(context.Background(), slog.LevelDebug) {
+					// Just read the events to keep connection alive
+					// We don't need to process the event data
+					events++
+					fmt.Printf("%d, ", events)
+				}
+			}
+			fmt.Println()
+			if err := scanner.Err(); err != nil {
+				slog.Error("error reading from SSE stream", "error", err)
+			}
+
+			// Connection closed or error occurred
+			_ = resp.Body.Close()
+			slog.Info("SSE connection closed, upstream not ready")
+			proxy.setStatus(notready)
+			proxy.incFail(1)
+
+			// Wait before reconnecting
+			time.Sleep(waitDuration)
 		}
 	}()

@@ -163,10 +213,8 @@ func newProxy(url *url.URL) *proxyServer {

 func (p *proxyServer) ServeHTTP(w http.ResponseWriter, r *http.Request) {
 	if r.Method == "GET" && r.URL.Path == "/status" {
-		p.statusMutex.RLock()
-		status := string(p.status)
-		failCount := p.failCount
-		p.statusMutex.RUnlock()
+		status := string(p.getStatus())
+		failCount := p.getFailures()
 		w.Header().Set("Content-Type", "text/plain")
 		w.WriteHeader(200)
 		fmt.Fprintf(w, "status: %s\n", status)
@@ -175,10 +223,27 @@ func (p *proxyServer) ServeHTTP(w http.ResponseWriter, r *http.Request) {
 	}

 	if p.getStatus() == notready {
-		slog.Info("upstream not ready, sending magic packet", "mac", *flagMac)
+		path := r.URL.Path
+		if strings.HasPrefix(path, "/api/events") {
+			slog.Debug("Skipping wake up", "req", path)
+			w.WriteHeader(http.StatusNoContent)
+			return
+		}
+
+		slog.Info("upstream not ready, sending magic packet", "req", path, "from", r.RemoteAddr)
 		if err := sendMagicPacket(*flagMac); err != nil {
 			slog.Warn("failed to send magic WoL packet", "error", err)
 		}
+
+		// For root or UI path requests, return loading page with status polling
+		// the web page will do the polling and redirect when ready
+		if path == "/" || strings.HasPrefix(path, "/ui/") {
+			w.Header().Set("Content-Type", "text/html; charset=utf-8")
+			w.WriteHeader(http.StatusOK)
+			fmt.Fprint(w, loadingPageHTML)
+			return
+		}
+
 		ticker := time.NewTicker(250 * time.Millisecond)
 		timeout, cancel := context.WithTimeout(context.Background(), time.Duration(*flagTimeout)*time.Second)
 		defer cancel()
@@ -213,6 +278,24 @@ func (p *proxyServer) setStatus(status upstreamStatus) {
 	p.status = status
 }

+func (p *proxyServer) incFail(num int) {
+	p.statusMutex.Lock()
+	defer p.statusMutex.Unlock()
+	p.failCount += num
+}
+
+func (p *proxyServer) getFailures() int {
+	p.statusMutex.RLock()
+	defer p.statusMutex.RUnlock()
+	return p.failCount
+}
+
+func (p *proxyServer) resetFailures() {
+	p.statusMutex.Lock()
+	defer p.statusMutex.Unlock()
+	p.failCount = 0
+}
+
 func sendMagicPacket(macAddr string) error {
 	hwAddr, err := net.ParseMAC(macAddr)
 	if err != nil {
@@ -0,0 +1,278 @@
+{
+    "$schema": "https://json-schema.org/draft-07/schema#",
+    "$id": "llama-swap-config-schema.json",
+    "title": "llama-swap configuration",
+    "description": "Configuration file for llama-swap",
+    "type": "object",
+    "required": [
+        "models"
+    ],
+    "definitions": {
+        "macros": {
+            "type": "object",
+            "additionalProperties": {
+                "oneOf": [
+                    {
+                        "type": "string",
+                        "minLength": 0,
+                        "maxLength": 1024
+                    },
+                    {
+                        "type": "number"
+                    },
+                    {
+                        "type": "boolean"
+                    }
+                ]
+            },
+            "propertyNames": {
+                "type": "string",
+                "minLength": 1,
+                "maxLength": 64,
+                "pattern": "^[a-zA-Z0-9_-]+$",
+                "not": {
+                    "enum": [
+                        "PORT",
+                        "MODEL_ID"
+                    ]
+                }
+            },
+            "default": {},
+            "description": "A dictionary of string substitutions. Macros are reusable snippets used in model cmd, cmdStop, proxy, checkEndpoint, filters.stripParams. Macro names must be <64 chars, match ^[a-zA-Z0-9_-]+$, and not be PORT or MODEL_ID. Values can be string, number, or boolean. Macros can reference other macros defined before them."
+        }
+    },
+    "properties": {
+        "healthCheckTimeout": {
+            "type": "integer",
+            "minimum": 15,
+            "default": 120,
+            "description": "Number of seconds to wait for a model to be ready to serve requests."
+        },
+        "logLevel": {
+            "type": "string",
+            "enum": [
+                "debug",
+                "info",
+                "warn",
+                "error"
+            ],
+            "default": "info",
+            "description": "Sets the logging value. Valid values: debug, info, warn, error."
+        },
+        "logTimeFormat": {
+            "type": "string",
+            "enum": [
+                "",
+                "ansic",
+                "unixdate",
+                "rubydate",
+                "rfc822",
+                "rfc822z",
+                "rfc850",
+                "rfc1123",
+                "rfc1123z",
+                "rfc3339",
+                "rfc3339nano",
+                "kitchen",
+                "stamp",
+                "stampmilli",
+                "stampmicro",
+                "stampnano"
+            ],
+            "default": "",
+            "description": "Enables and sets the logging timestamp format. Valid values: \"\", \"ansic\", \"unixdate\", \"rubydate\", \"rfc822\", \"rfc822z\", \"rfc850\", \"rfc1123\", \"rfc1123z\", \"rfc3339\", \"rfc3339nano\", \"kitchen\", \"stamp\", \"stampmilli\", \"stampmicro\", and \"stampnano\". For more info, read: https://pkg.go.dev/time#pkg-constants"
+        },
+        "metricsMaxInMemory": {
+            "type": "integer",
+            "default": 1000,
+            "description": "Maximum number of metrics to keep in memory. Controls how many metrics are stored before older ones are discarded."
+        },
+        "startPort": {
+            "type": "integer",
+            "default": 5800,
+            "description": "Starting port number for the automatic ${PORT} macro. The ${PORT} macro is incremented for every model that uses it."
+        },
+        "sendLoadingState": {
+            "type": "boolean",
+            "default": false,
+            "description": "Inject loading status updates into the reasoning field. When true, a stream of loading messages will be sent to the client."
+        },
+        "includeAliasesInList": {
+            "type": "boolean",
+            "default": false,
+            "description": "Present aliases within the /v1/models OpenAI API listing. when true, model aliases will be output to the API model listing duplicating all fields except for Id so chat UIs can use the alias equivalent to the original."
+        },
+        "macros": {
+            "$ref": "#/definitions/macros"
+        },
+        "models": {
+            "type": "object",
+            "description": "A dictionary of model configurations. Each key is a model's ID. Model settings have defaults if not defined. The model's ID is available as ${MODEL_ID}.",
+            "additionalProperties": {
+                "type": "object",
+                "required": [
+                    "cmd"
+                ],
+                "properties": {
+                    "macros": {
+                        "$ref": "#/definitions/macros"
+                    },
+                    "cmd": {
+                        "type": "string",
+                        "minLength": 1,
+                        "description": "Command to run to start the inference server. Macros can be used. Comments allowed with |."
+                    },
+                    "cmdStop": {
+                        "type": "string",
+                        "default": "",
+                        "description": "Command to run to stop the model gracefully. Uses ${PID} macro for upstream process id. If empty, default shutdown behavior is used."
+                    },
+                    "name": {
+                        "type": "string",
+                        "default": "",
+                        "maxLength": 128,
+                        "description": "Display name for the model. Used in v1/models API response."
+                    },
+                    "description": {
+                        "type": "string",
+                        "default": "",
+                        "maxLength": 1024,
+                        "description": "Description for the model. Used in v1/models API response."
+                    },
+                    "env": {
+                        "type": "array",
+                        "items": {
+                            "type": "string",
+                            "pattern": "^[A-Z_][A-Z0-9_]*=.*$"
+                        },
+                        "default": [],
+                        "description": "Array of environment variables to inject into cmd's environment. Each value is a string in ENV_NAME=value format."
+                    },
+                    "proxy": {
+                        "type": "string",
+                        "default": "http://localhost:${PORT}",
+                        "format": "uri",
+                        "description": "URL where llama-swap routes API requests. If custom port is used in cmd, this must be set."
+                    },
+                    "aliases": {
+                        "type": "array",
+                        "items": {
+                            "type": "string",
+                            "minLength": 1
+                        },
+                        "default": [],
+                        "description": "Alternative model names for this configuration. Must be unique globally."
+                    },
+                    "checkEndpoint": {
+                        "type": "string",
+                        "default": "/health",
+                        "pattern": "^/.*$|^none$",
+                        "description": "URL path to check if the server is ready. Use 'none' to skip health checking."
+                    },
+                    "ttl": {
+                        "type": "integer",
+                        "minimum": 0,
+                        "default": 0,
+                        "description": "Automatically unload the model after ttl seconds. 0 disables unloading. Must be >0 to enable."
+                    },
+                    "useModelName": {
+                        "type": "string",
+                        "default": "",
+                        "description": "Override the model name sent to upstream server. Useful if upstream expects a different name."
+                    },
+                    "filters": {
+                        "type": "object",
+                        "properties": {
+                            "stripParams": {
+                                "type": "string",
+                                "default": "",
+                                "pattern": "^[a-zA-Z0-9_, ]*$",
+                                "description": "Comma separated list of parameters to remove from the request. Used for server-side enforcement of sampling parameters."
+                            }
+                        },
+                        "additionalProperties": false,
+                        "default": {},
+                        "description": "Dictionary of filter settings. Only stripParams is supported."
+                    },
+                    "metadata": {
+                        "type": "object",
+                        "additionalProperties": true,
+                        "default": {},
+                        "description": "Dictionary of arbitrary values included in /v1/models. Can contain complex types. Only passed through in /v1/models responses."
+                    },
+                    "concurrencyLimit": {
+                        "type": "integer",
+                        "minimum": 0,
+                        "default": 0,
+                        "description": "Overrides allowed number of active parallel requests to a model. 0 uses internal default of 10. >0 overrides default. Requests exceeding limit get HTTP 429."
+                    },
+                    "sendLoadingState": {
+                        "type": "boolean",
+                        "description": "Overrides the global sendLoadingState for this model. Ommitting this property will use the global setting."
+                    },
+                    "unlisted": {
+                        "type": "boolean",
+                        "default": false,
+                        "description": "If true the model will not show up in /v1/models responses. It can still be used as normal in API requests."
+                    }
+                }
+            }
+        },
+        "groups": {
+            "type": "object",
+            "additionalProperties": {
+                "type": "object",
+                "required": [
+                    "members"
+                ],
+                "properties": {
+                    "swap": {
+                        "type": "boolean",
+                        "default": true,
+                        "description": "Controls model swapping behaviour within the group. True: only one model runs at a time. False: all models can run together."
+                    },
+                    "exclusive": {
+                        "type": "boolean",
+                        "default": true,
+                        "description": "Controls how the group affects other groups. True: causes all other groups to unload when this group runs a model. False: does not affect other groups."
+                    },
+                    "persistent": {
+                        "type": "boolean",
+                        "default": false,
+                        "description": "Prevents other groups from unloading the models in this group. Does not affect individual model behaviour."
+                    },
+                    "members": {
+                        "type": "array",
+                        "items": {
+                            "type": "string"
+                        },
+                        "description": "Array of model IDs that are members of this group. Model IDs must be defined in models."
+                    }
+                }
+            },
+            "description": "A dictionary of group settings. Provides advanced controls over model swapping behaviour. Model IDs must be defined in models. A model can only be a member of one group. Behaviour controlled via swap, exclusive, persistent."
+        },
+        "hooks": {
+            "type": "object",
+            "properties": {
+                "on_startup": {
+                    "type": "object",
+                    "properties": {
+                        "preload": {
+                            "type": "array",
+                            "items": {
+                                "type": "string"
+                            },
+                            "default": [],
+                            "description": "List of model IDs to load on startup. Model names must match keys in models. When preloading multiple models, define a group to prevent swapping."
+                        }
+                    },
+                    "additionalProperties": false,
+                    "description": "Actions to perform on startup. Only supported action is preload."
+                }
+            },
+            "additionalProperties": false,
+            "description": "A dictionary of event triggers and actions. Only supported hook is on_startup."
+        }
+    }
+}
@@ -1,3 +1,6 @@
+# add this modeline for validation in vscode
+# yaml-language-server: $schema=https://raw.githubusercontent.com/mostlygeek/llama-swap/refs/heads/main/config-schema.json
+#
 # llama-swap YAML configuration example
 # -------------------------------------
 #
@@ -23,6 +26,14 @@ healthCheckTimeout: 500
 # - Valid log levels: debug, info, warn, error
 logLevel: info

+# logTimeFormat: enables and sets the logging timestamp format
+# - optional, default (disabled): ""
+# - Valid values: "", "ansic", "unixdate", "rubydate", "rfc822", "rfc822z",
+#   "rfc850", "rfc1123", "rfc1123z", "rfc3339", "rfc3339nano", "kitchen",
+#   "stamp", "stampmilli", "stampmicro", and "stampnano".
+# - For more info, read: https://pkg.go.dev/time#pkg-constants
+logTimeFormat: ""
+
 # 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
@@ -35,6 +46,20 @@ metricsMaxInMemory: 1000
 # - it is automatically incremented for every model that uses it
 startPort: 10001

+# sendLoadingState: inject loading status updates into the reasoning (thinking)
+# field
+# - optional, default: false
+# - when true, a stream of loading messages will be sent to the client in the
+#   reasoning field so chat UIs can show that loading is in progress.
+# - see #366 for more details
+sendLoadingState: true
+
+# includeAliasesInList: present aliases within the /v1/models OpenAI API listing
+# - optional, default: false
+# - when true, model aliases will be output to the API model listing duplicating
+#   all fields except for Id so chat UIs can use the alias equivalent to the original.
+includeAliasesInList: false
+
 # macros: a dictionary of string substitutions
 # - optional, default: empty dictionary
 # - macros are reusable snippets
@@ -64,7 +89,6 @@ macros:
 # - the model's ID is available in the ${MODEL_ID} macro, also available in macros defined above
 # - below are examples of the all the settings a model can have
 models:
-
  # keys are the model names used in API requests
  "llama":
    # macros: a dictionary of string substitutions specific to this model
@@ -184,6 +208,10 @@ models:
    # - recommended to be omitted and the default used
    concurrencyLimit: 0

+    # sendLoadingState: overrides the global sendLoadingState setting for this model
+    # - optional, default: undefined (use global setting)
+    sendLoadingState: false
+
  # Unlisted model example:
  "qwen-unlisted":
    # unlisted: boolean, true or false
@@ -286,10 +314,10 @@ hooks:
  # - optional, default: empty dictionary
  # - the only supported action is preload
  on_startup:
-        # preload: a list of model ids to load on startup
-        # - optional, default: empty list
-        # - model names must match keys in the models sections
-        # - when preloading multiple models at once, define a group
-        #   otherwise models will be loaded and swapped out
+    # preload: a list of model ids to load on startup
+    # - optional, default: empty list
+    # - model names must match keys in the models sections
+    # - when preloading multiple models at once, define a group
+    #   otherwise models will be loaded and swapped out
    preload:
-      - "llama"
+      - "llama"
@@ -25,31 +25,46 @@ fi
 LS_VER=$(curl -s https://api.github.com/repos/mostlygeek/llama-swap/releases/latest | jq -r .tag_name | sed 's/v//')

 if [ "$ARCH" == "cpu" ]; then
-    # cpu only containers just use the latest available
-    CONTAINER_LATEST="ghcr.io/mostlygeek/llama-swap:cpu"
-    echo "Building ${CONTAINER_LATEST} $LS_VER"
-    docker build -f llama-swap.Containerfile --build-arg BASE_TAG=server --build-arg LS_VER=${LS_VER} -t ${CONTAINER_LATEST} .
-    if [ "$PUSH_IMAGES" == "true" ]; then
-      docker push ${CONTAINER_LATEST}
-    fi
+    # cpu only containers just use the server tag
+    LCPP_TAG=$(curl -s -H "Authorization: Bearer $GITHUB_TOKEN" \
+        "https://api.github.com/users/ggml-org/packages/container/llama.cpp/versions" \
+        | jq -r '.[] | select(.metadata.container.tags[] | startswith("server")) | .metadata.container.tags[]' \
+        | sort -r | head -n1 | awk -F '-' '{print $3}')
+    BASE_TAG=server-${LCPP_TAG}
 else
    LCPP_TAG=$(curl -s -H "Authorization: Bearer $GITHUB_TOKEN" \
        "https://api.github.com/users/ggml-org/packages/container/llama.cpp/versions" \
        | jq -r --arg arch "$ARCH" '.[] | select(.metadata.container.tags[] | startswith("server-\($arch)")) | .metadata.container.tags[]' \
        | sort -r | head -n1 | awk -F '-' '{print $3}')
+    BASE_TAG=server-${ARCH}-${LCPP_TAG}
+fi

-    # Abort if LCPP_TAG is empty.
-    if [[ -z "$LCPP_TAG" ]]; then
-        echo "Abort: Could not find llama-server container for arch: $ARCH"
-        exit 1
-    fi
+# Abort if LCPP_TAG is empty.
+if [[ -z "$LCPP_TAG" ]]; then
+    echo "Abort: Could not find llama-server container for arch: $ARCH"
+    exit 1
+fi

-    CONTAINER_TAG="ghcr.io/mostlygeek/llama-swap:v${LS_VER}-${ARCH}-${LCPP_TAG}"
-    CONTAINER_LATEST="ghcr.io/mostlygeek/llama-swap:${ARCH}"
-    echo "Building ${CONTAINER_TAG} $LS_VER"
-    docker build -f llama-swap.Containerfile --build-arg BASE_TAG=server-${ARCH}-${LCPP_TAG} --build-arg LS_VER=${LS_VER} -t ${CONTAINER_TAG} -t ${CONTAINER_LATEST} .
-    if [ "$PUSH_IMAGES" == "true" ]; then
-      docker push ${CONTAINER_TAG}
-      docker push ${CONTAINER_LATEST}
-    fi
-fi
+for CONTAINER_TYPE in non-root root; do
+  CONTAINER_TAG="ghcr.io/mostlygeek/llama-swap:v${LS_VER}-${ARCH}-${LCPP_TAG}"
+  CONTAINER_LATEST="ghcr.io/mostlygeek/llama-swap:${ARCH}"
+  USER_UID=0
+  USER_GID=0
+  USER_HOME=/root
+
+  if [ "$CONTAINER_TYPE" == "non-root" ]; then
+    CONTAINER_TAG="${CONTAINER_TAG}-non-root"
+    CONTAINER_LATEST="${CONTAINER_LATEST}-non-root"
+    USER_UID=10001
+    USER_GID=10001
+    USER_HOME=/app
+  fi
+
+  echo "Building $CONTAINER_TYPE $CONTAINER_TAG $LS_VER"
+  docker build -f llama-swap.Containerfile --build-arg BASE_TAG=${BASE_TAG} --build-arg LS_VER=${LS_VER} --build-arg UID=${USER_UID} \
+    --build-arg GID=${USER_GID} --build-arg USER_HOME=${USER_HOME} -t ${CONTAINER_TAG} -t ${CONTAINER_LATEST} .
+  if [ "$PUSH_IMAGES" == "true" ]; then
+    docker push ${CONTAINER_TAG}
+    docker push ${CONTAINER_LATEST}
+  fi
+done
@@ -2,7 +2,29 @@ ARG BASE_TAG=server-cuda
 FROM ghcr.io/ggml-org/llama.cpp:${BASE_TAG}

 # has to be after the FROM
-ARG LS_VER=89
+ARG LS_VER=170
+
+# Set default UID/GID arguments
+ARG UID=10001
+ARG GID=10001
+ARG USER_HOME=/app
+
+# Add user/group
+ENV HOME=$USER_HOME
+RUN if [ $UID -ne 0 ]; then \
+      if [ $GID -ne 0 ]; then \
+        groupadd --system --gid $GID app; \
+      fi; \
+      useradd --system --uid $UID --gid $GID \
+      --home $USER_HOME app; \
+    fi
+
+# Handle paths
+RUN mkdir --parents $HOME /app
+RUN chown --recursive $UID:$GID $HOME /app
+
+# Switch user
+USER $UID:$GID

 WORKDIR /app
 RUN \
@@ -10,7 +32,7 @@ RUN \
    tar -zxf llama-swap_"${LS_VER}"_linux_amd64.tar.gz && \
    rm llama-swap_"${LS_VER}"_linux_amd64.tar.gz

-COPY config.example.yaml /app/config.yaml
+COPY --chown=$UID:$GID config.example.yaml /app/config.yaml

 HEALTHCHECK CMD curl -f http://localhost:8080/ || exit 1
-ENTRYPOINT [ "/app/llama-swap", "-config", "/app/config.yaml" ]
+ENTRYPOINT [ "/app/llama-swap", "-config", "/app/config.yaml" ]
@@ -95,7 +95,9 @@ func main() {

 			fmt.Println("Configuration Changed")
 			currentPM.Shutdown()
-			srv.Handler = proxy.New(conf)
+			newPM := proxy.New(conf)
+			newPM.SetVersion(date, commit, version)
+			srv.Handler = newPM
 			fmt.Println("Configuration Reloaded")

 			// wait a few seconds and tell any UI to reload
@@ -110,7 +112,9 @@ func main() {
 				fmt.Printf("Error, unable to load configuration: %v\n", err)
 				os.Exit(1)
 			}
-			srv.Handler = proxy.New(conf)
+			newPM := proxy.New(conf)
+			newPM.SetVersion(date, commit, version)
+			srv.Handler = newPM
 		}
 	}

@@ -113,6 +113,7 @@ type Config struct {
 	HealthCheckTimeout int                    `yaml:"healthCheckTimeout"`
 	LogRequests        bool                   `yaml:"logRequests"`
 	LogLevel           string                 `yaml:"logLevel"`
+	LogTimeFormat      string                 `yaml:"logTimeFormat"`
 	MetricsMaxInMemory int                    `yaml:"metricsMaxInMemory"`
 	Models             map[string]ModelConfig `yaml:"models"` /* key is model ID */
 	Profiles           map[string][]string    `yaml:"profiles"`
@@ -129,6 +130,12 @@ type Config struct {

 	// hooks, see: #209
 	Hooks HooksConfig `yaml:"hooks"`
+
+	// send loading state in reasoning
+	SendLoadingState bool `yaml:"sendLoadingState"`
+
+	// present aliases to /v1/models OpenAI API listing
+	IncludeAliasesInList bool `yaml:"includeAliasesInList"`
 }

 func (c *Config) RealModelName(search string) (string, bool) {
@@ -169,6 +176,7 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		HealthCheckTimeout: 120,
 		StartPort:          5800,
 		LogLevel:           "info",
+		LogTimeFormat:      "",
 		MetricsMaxInMemory: 1000,
 	}
 	err = yaml.Unmarshal(data, &config)
@@ -350,6 +358,13 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 			)
 		}

+		// if sendLoadingState is nil, set it to the global config value
+		// see #366
+		if modelConfig.SendLoadingState == nil {
+			v := config.SendLoadingState // copy it
+			modelConfig.SendLoadingState = &v
+		}
+
 		config.Models[modelId] = modelConfig
 	}

@@ -58,6 +58,7 @@ models:
 	assert.Equal(t, 120, config.HealthCheckTimeout)
 	assert.Equal(t, 5800, config.StartPort)
 	assert.Equal(t, "info", config.LogLevel)
+	assert.Equal(t, "", config.LogTimeFormat)

 	// Test default group exists
 	defaultGroup, exists := config.Groups["(default)"]
@@ -160,9 +161,12 @@ groups:
 		t.Fatalf("Failed to load config: %v", err)
 	}

+	modelLoadingState := false
+
 	expected := Config{
-		LogLevel:  "info",
-		StartPort: 5800,
+		LogLevel:      "info",
+		LogTimeFormat: "",
+		StartPort:     5800,
 		Macros: MacroList{
 			{"svr-path", "path/to/server"},
 		},
@@ -171,36 +175,41 @@ groups:
 				Preload: []string{"model1", "model2"},
 			},
 		},
+		SendLoadingState: false,
 		Models: map[string]ModelConfig{
 			"model1": {
-				Cmd:           "path/to/cmd --arg1 one",
-				Proxy:         "http://localhost:8080",
-				Aliases:       []string{"m1", "model-one"},
-				Env:           []string{"VAR1=value1", "VAR2=value2"},
-				CheckEndpoint: "/health",
-				Name:          "Model 1",
-				Description:   "This is model 1",
+				Cmd:              "path/to/cmd --arg1 one",
+				Proxy:            "http://localhost:8080",
+				Aliases:          []string{"m1", "model-one"},
+				Env:              []string{"VAR1=value1", "VAR2=value2"},
+				CheckEndpoint:    "/health",
+				Name:             "Model 1",
+				Description:      "This is model 1",
+				SendLoadingState: &modelLoadingState,
 			},
 			"model2": {
-				Cmd:           "path/to/server --arg1 one",
-				Proxy:         "http://localhost:8081",
-				Aliases:       []string{"m2"},
-				Env:           []string{},
-				CheckEndpoint: "/",
+				Cmd:              "path/to/server --arg1 one",
+				Proxy:            "http://localhost:8081",
+				Aliases:          []string{"m2"},
+				Env:              []string{},
+				CheckEndpoint:    "/",
+				SendLoadingState: &modelLoadingState,
 			},
 			"model3": {
-				Cmd:           "path/to/cmd --arg1 one",
-				Proxy:         "http://localhost:8081",
-				Aliases:       []string{"mthree"},
-				Env:           []string{},
-				CheckEndpoint: "/",
+				Cmd:              "path/to/cmd --arg1 one",
+				Proxy:            "http://localhost:8081",
+				Aliases:          []string{"mthree"},
+				Env:              []string{},
+				CheckEndpoint:    "/",
+				SendLoadingState: &modelLoadingState,
 			},
 			"model4": {
-				Cmd:           "path/to/cmd --arg1 one",
-				Proxy:         "http://localhost:8082",
-				CheckEndpoint: "/",
-				Aliases:       []string{},
-				Env:           []string{},
+				Cmd:              "path/to/cmd --arg1 one",
+				Proxy:            "http://localhost:8082",
+				CheckEndpoint:    "/",
+				Aliases:          []string{},
+				Env:              []string{},
+				SendLoadingState: &modelLoadingState,
 			},
 		},
 		HealthCheckTimeout: 15,
@@ -55,6 +55,7 @@ models:
 	assert.Equal(t, 120, config.HealthCheckTimeout)
 	assert.Equal(t, 5800, config.StartPort)
 	assert.Equal(t, "info", config.LogLevel)
+	assert.Equal(t, "", config.LogTimeFormat)

 	// Test default group exists
 	defaultGroup, exists := config.Groups["(default)"]
@@ -152,44 +153,52 @@ groups:
 		t.Fatalf("Failed to load config: %v", err)
 	}

+	modelLoadingState := false
+
 	expected := Config{
-		LogLevel:  "info",
-		StartPort: 5800,
+		LogLevel:      "info",
+		LogTimeFormat: "",
+		StartPort:     5800,
 		Macros: MacroList{
 			{"svr-path", "path/to/server"},
 		},
+		SendLoadingState: false,
 		Models: map[string]ModelConfig{
 			"model1": {
-				Cmd:           "path/to/cmd --arg1 one",
-				CmdStop:       "taskkill /f /t /pid ${PID}",
-				Proxy:         "http://localhost:8080",
-				Aliases:       []string{"m1", "model-one"},
-				Env:           []string{"VAR1=value1", "VAR2=value2"},
-				CheckEndpoint: "/health",
+				Cmd:              "path/to/cmd --arg1 one",
+				CmdStop:          "taskkill /f /t /pid ${PID}",
+				Proxy:            "http://localhost:8080",
+				Aliases:          []string{"m1", "model-one"},
+				Env:              []string{"VAR1=value1", "VAR2=value2"},
+				CheckEndpoint:    "/health",
+				SendLoadingState: &modelLoadingState,
 			},
 			"model2": {
-				Cmd:           "path/to/server --arg1 one",
-				CmdStop:       "taskkill /f /t /pid ${PID}",
-				Proxy:         "http://localhost:8081",
-				Aliases:       []string{"m2"},
-				Env:           []string{},
-				CheckEndpoint: "/",
+				Cmd:              "path/to/server --arg1 one",
+				CmdStop:          "taskkill /f /t /pid ${PID}",
+				Proxy:            "http://localhost:8081",
+				Aliases:          []string{"m2"},
+				Env:              []string{},
+				CheckEndpoint:    "/",
+				SendLoadingState: &modelLoadingState,
 			},
 			"model3": {
-				Cmd:           "path/to/cmd --arg1 one",
-				CmdStop:       "taskkill /f /t /pid ${PID}",
-				Proxy:         "http://localhost:8081",
-				Aliases:       []string{"mthree"},
-				Env:           []string{},
-				CheckEndpoint: "/",
+				Cmd:              "path/to/cmd --arg1 one",
+				CmdStop:          "taskkill /f /t /pid ${PID}",
+				Proxy:            "http://localhost:8081",
+				Aliases:          []string{"mthree"},
+				Env:              []string{},
+				CheckEndpoint:    "/",
+				SendLoadingState: &modelLoadingState,
 			},
 			"model4": {
-				Cmd:           "path/to/cmd --arg1 one",
-				CmdStop:       "taskkill /f /t /pid ${PID}",
-				Proxy:         "http://localhost:8082",
-				CheckEndpoint: "/",
-				Aliases:       []string{},
-				Env:           []string{},
+				Cmd:              "path/to/cmd --arg1 one",
+				CmdStop:          "taskkill /f /t /pid ${PID}",
+				Proxy:            "http://localhost:8082",
+				CheckEndpoint:    "/",
+				Aliases:          []string{},
+				Env:              []string{},
+				SendLoadingState: &modelLoadingState,
 			},
 		},
 		HealthCheckTimeout: 15,
@@ -35,6 +35,9 @@ type ModelConfig struct {
 	// Metadata: see #264
 	// Arbitrary metadata that can be exposed through the API
 	Metadata map[string]any `yaml:"metadata"`
+
+	// override global setting
+	SendLoadingState *bool `yaml:"sendLoadingState"`
 }

 func (m *ModelConfig) UnmarshalYAML(unmarshal func(interface{}) error) error {
@@ -50,5 +50,25 @@ models:
 			}
 		})
 	}
-
+}
+
+func TestConfig_ModelSendLoadingState(t *testing.T) {
+	content := `
+sendLoadingState: true
+models:
+  model1:
+    cmd: path/to/cmd --port ${PORT}
+    sendLoadingState: false
+  model2:
+    cmd: path/to/cmd --port ${PORT}
+`
+	config, err := LoadConfigFromReader(strings.NewReader(content))
+	assert.NoError(t, err)
+	assert.True(t, config.SendLoadingState)
+	if assert.NotNil(t, config.Models["model1"].SendLoadingState) {
+		assert.False(t, *config.Models["model1"].SendLoadingState)
+	}
+	if assert.NotNil(t, config.Models["model2"].SendLoadingState) {
+		assert.True(t, *config.Models["model2"].SendLoadingState)
+	}
 }
@@ -7,6 +7,7 @@ import (
 	"io"
 	"os"
 	"sync"
+	"time"

 	"github.com/mostlygeek/llama-swap/event"
 )
@@ -32,6 +33,9 @@ type LogMonitor struct {
 	// logging levels
 	level  LogLevel
 	prefix string
+
+	// timestamps
+	timeFormat string
 }

 func NewLogMonitor() *LogMonitor {
@@ -40,11 +44,12 @@ func NewLogMonitor() *LogMonitor {

 func NewLogMonitorWriter(stdout io.Writer) *LogMonitor {
 	return &LogMonitor{
-		eventbus: event.NewDispatcherConfig(1000),
-		buffer:   ring.New(10 * 1024), // keep 10KB of buffered logs
-		stdout:   stdout,
-		level:    LevelInfo,
-		prefix:   "",
+		eventbus:   event.NewDispatcherConfig(1000),
+		buffer:     ring.New(10 * 1024), // keep 10KB of buffered logs
+		stdout:     stdout,
+		level:      LevelInfo,
+		prefix:     "",
+		timeFormat: "",
 	}
 }

@@ -106,12 +111,22 @@ func (w *LogMonitor) SetLogLevel(level LogLevel) {
 	w.level = level
 }

+func (w *LogMonitor) SetLogTimeFormat(timeFormat string) {
+	w.mu.Lock()
+	defer w.mu.Unlock()
+	w.timeFormat = timeFormat
+}
+
 func (w *LogMonitor) formatMessage(level string, msg string) []byte {
 	prefix := ""
 	if w.prefix != "" {
 		prefix = fmt.Sprintf("[%s] ", w.prefix)
 	}
-	return []byte(fmt.Sprintf("%s[%s] %s\n", prefix, level, msg))
+	timestamp := ""
+	if w.timeFormat != "" {
+		timestamp = fmt.Sprintf("%s ", time.Now().Format(w.timeFormat))
+	}
+	return []byte(fmt.Sprintf("%s%s[%s] %s\n", timestamp, prefix, level, msg))
 }

 func (w *LogMonitor) log(level LogLevel, msg string) {
@@ -3,8 +3,10 @@ package proxy
 import (
 	"bytes"
 	"io"
+	"strings"
 	"sync"
 	"testing"
+	"time"
 )

 func TestLogMonitor(t *testing.T) {
@@ -84,3 +86,30 @@ func TestWrite_ImmutableBuffer(t *testing.T) {
 		t.Errorf("Expected history to be %q, got %q", expected, history)
 	}
 }
+
+func TestWrite_LogTimeFormat(t *testing.T) {
+	// Create a new LogMonitor instance
+	lm := NewLogMonitorWriter(io.Discard)
+
+	// Enable timestamps
+	lm.timeFormat = time.RFC3339
+
+	// Write the message to the LogMonitor
+	lm.Info("Hello, World!")
+
+	// Get the history from the LogMonitor
+	history := lm.GetHistory()
+
+	timestamp := ""
+	fields := strings.Fields(string(history))
+	if len(fields) > 0 {
+		timestamp = fields[0]
+	} else {
+		t.Fatalf("Cannot extract string from history")
+	}
+
+	_, err := time.Parse(time.RFC3339, timestamp)
+	if err != nil {
+		t.Fatalf("Cannot find timestamp: %v", err)
+	}
+}
@@ -1,184 +0,0 @@
-package proxy
-
-import (
-	"bytes"
-	"fmt"
-	"io"
-	"net/http"
-	"strings"
-	"time"
-
-	"github.com/gin-gonic/gin"
-	"github.com/tidwall/gjson"
-)
-
-type MetricsRecorder struct {
-	metricsMonitor *MetricsMonitor
-	realModelName  string
-	//	isStreaming    bool
-	startTime time.Time
-}
-
-// 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,
-				startTime:      time.Now(),
-			},
-		}
-		c.Writer = writer
-		c.Next()
-
-		// check for streaming response
-		if strings.Contains(c.Writer.Header().Get("Content-Type"), "text/event-stream") {
-			writer.metricsRecorder.processStreamingResponse(writer.body)
-		} else {
-			writer.metricsRecorder.processNonStreamingResponse(writer.body)
-		}
-	}
-}
-
-func (rec *MetricsRecorder) parseAndRecordMetrics(jsonData gjson.Result) bool {
-	usage := jsonData.Get("usage")
-	timings := jsonData.Get("timings")
-	if !usage.Exists() && !timings.Exists() {
-		return false
-	}
-
-	// default values
-	cachedTokens := -1 // unknown or missing data
-	outputTokens := 0
-	inputTokens := 0
-
-	// timings data
-	tokensPerSecond := -1.0
-	promptPerSecond := -1.0
-	durationMs := int(time.Since(rec.startTime).Milliseconds())
-
-	if usage.Exists() {
-		outputTokens = int(jsonData.Get("usage.completion_tokens").Int())
-		inputTokens = int(jsonData.Get("usage.prompt_tokens").Int())
-	}
-
-	// use llama-server's timing data for tok/sec and duration as it is more accurate
-	if timings.Exists() {
-		inputTokens = int(jsonData.Get("timings.prompt_n").Int())
-		outputTokens = int(jsonData.Get("timings.predicted_n").Int())
-		promptPerSecond = jsonData.Get("timings.prompt_per_second").Float()
-		tokensPerSecond = jsonData.Get("timings.predicted_per_second").Float()
-		durationMs = int(jsonData.Get("timings.prompt_ms").Float() + jsonData.Get("timings.predicted_ms").Float())
-
-		if cachedValue := jsonData.Get("timings.cache_n"); cachedValue.Exists() {
-			cachedTokens = int(cachedValue.Int())
-		}
-	}
-
-	rec.metricsMonitor.addMetrics(TokenMetrics{
-		Timestamp:       time.Now(),
-		Model:           rec.realModelName,
-		CachedTokens:    cachedTokens,
-		InputTokens:     inputTokens,
-		OutputTokens:    outputTokens,
-		PromptPerSecond: promptPerSecond,
-		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()
-}
@@ -1,12 +1,18 @@
 package proxy

 import (
+	"bytes"
 	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"strings"
 	"sync"
 	"time"

+	"github.com/gin-gonic/gin"
 	"github.com/mostlygeek/llama-swap/event"
-	"github.com/mostlygeek/llama-swap/proxy/config"
+	"github.com/tidwall/gjson"
 )

 // TokenMetrics represents parsed token statistics from llama-server logs
@@ -31,21 +37,18 @@ func (e TokenMetricsEvent) Type() uint32 {
 	return TokenMetricsEventID // defined in events.go
 }

-// MetricsMonitor parses llama-server output for token statistics
-type MetricsMonitor struct {
+// metricsMonitor parses llama-server output for token statistics
+type metricsMonitor struct {
 	mu         sync.RWMutex
 	metrics    []TokenMetrics
 	maxMetrics int
 	nextID     int
+	logger     *LogMonitor
 }

-func NewMetricsMonitor(config *config.Config) *MetricsMonitor {
-	maxMetrics := config.MetricsMaxInMemory
-	if maxMetrics <= 0 {
-		maxMetrics = 1000 // Default fallback
-	}
-
-	mp := &MetricsMonitor{
+func newMetricsMonitor(logger *LogMonitor, maxMetrics int) *metricsMonitor {
+	mp := &metricsMonitor{
+		logger:     logger,
 		maxMetrics: maxMetrics,
 	}

@@ -53,7 +56,7 @@ func NewMetricsMonitor(config *config.Config) *MetricsMonitor {
 }

 // addMetrics adds a new metric to the collection and publishes an event
-func (mp *MetricsMonitor) addMetrics(metric TokenMetrics) {
+func (mp *metricsMonitor) addMetrics(metric TokenMetrics) {
 	mp.mu.Lock()
 	defer mp.mu.Unlock()

@@ -66,8 +69,8 @@ func (mp *MetricsMonitor) addMetrics(metric TokenMetrics) {
 	event.Emit(TokenMetricsEvent{Metrics: metric})
 }

-// GetMetrics returns a copy of the current metrics
-func (mp *MetricsMonitor) GetMetrics() []TokenMetrics {
+// getMetrics returns a copy of the current metrics
+func (mp *metricsMonitor) getMetrics() []TokenMetrics {
 	mp.mu.RLock()
 	defer mp.mu.RUnlock()

@@ -76,9 +79,189 @@ func (mp *MetricsMonitor) GetMetrics() []TokenMetrics {
 	return result
 }

-// GetMetricsJSON returns metrics as JSON
-func (mp *MetricsMonitor) GetMetricsJSON() ([]byte, error) {
+// getMetricsJSON returns metrics as JSON
+func (mp *metricsMonitor) getMetricsJSON() ([]byte, error) {
 	mp.mu.RLock()
 	defer mp.mu.RUnlock()
 	return json.Marshal(mp.metrics)
 }
+
+// wrapHandler wraps the proxy handler to extract token metrics
+// if wrapHandler returns an error it is safe to assume that no
+// data was sent to the client
+func (mp *metricsMonitor) wrapHandler(
+	modelID string,
+	writer gin.ResponseWriter,
+	request *http.Request,
+	next func(modelID string, w http.ResponseWriter, r *http.Request) error,
+) error {
+	recorder := newBodyCopier(writer)
+	if err := next(modelID, recorder, request); err != nil {
+		return err
+	}
+
+	// after this point we have to assume that data was sent to the client
+	// and we can only log errors but not send them to clients
+
+	if recorder.Status() != http.StatusOK {
+		mp.logger.Warnf("metrics skipped, HTTP status=%d, path=%s", recorder.Status(), request.URL.Path)
+		return nil
+	}
+
+	body := recorder.body.Bytes()
+	if len(body) == 0 {
+		mp.logger.Warn("metrics skipped, empty body")
+		return nil
+	}
+
+	if strings.Contains(recorder.Header().Get("Content-Type"), "text/event-stream") {
+		if tm, err := processStreamingResponse(modelID, recorder.StartTime(), body); err != nil {
+			mp.logger.Warnf("error processing streaming response: %v, path=%s", err, request.URL.Path)
+		} else {
+			mp.addMetrics(tm)
+		}
+	} else {
+		if gjson.ValidBytes(body) {
+			if tm, err := parseMetrics(modelID, recorder.StartTime(), gjson.ParseBytes(body)); err != nil {
+				mp.logger.Warnf("error parsing metrics: %v, path=%s", err, request.URL.Path)
+			} else {
+				mp.addMetrics(tm)
+			}
+		} else {
+			mp.logger.Warnf("metrics skipped, invalid JSON in response body path=%s", request.URL.Path)
+		}
+	}
+
+	return nil
+}
+
+func processStreamingResponse(modelID string, start time.Time, body []byte) (TokenMetrics, error) {
+	// Iterate **backwards** through the body looking for the data payload with
+	// usage data. This avoids allocating a slice of all lines via bytes.Split.
+
+	// Start from the end of the body and scan backwards for newlines
+	pos := len(body)
+	for pos > 0 {
+		// Find the previous newline (or start of body)
+		lineStart := bytes.LastIndexByte(body[:pos], '\n')
+		if lineStart == -1 {
+			lineStart = 0
+		} else {
+			lineStart++ // Move past the newline
+		}
+
+		line := bytes.TrimSpace(body[lineStart:pos])
+		pos = lineStart - 1 // Move position before the newline for next iteration
+
+		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) {
+			return parseMetrics(modelID, start, gjson.ParseBytes(data))
+		}
+	}
+
+	return TokenMetrics{}, fmt.Errorf("no valid JSON data found in stream")
+}
+
+func parseMetrics(modelID string, start time.Time, jsonData gjson.Result) (TokenMetrics, error) {
+	usage := jsonData.Get("usage")
+	timings := jsonData.Get("timings")
+	if !usage.Exists() && !timings.Exists() {
+		return TokenMetrics{}, fmt.Errorf("no usage or timings data found")
+	}
+	// default values
+	cachedTokens := -1 // unknown or missing data
+	outputTokens := 0
+	inputTokens := 0
+
+	// timings data
+	tokensPerSecond := -1.0
+	promptPerSecond := -1.0
+	durationMs := int(time.Since(start).Milliseconds())
+
+	if usage.Exists() {
+		outputTokens = int(jsonData.Get("usage.completion_tokens").Int())
+		inputTokens = int(jsonData.Get("usage.prompt_tokens").Int())
+	}
+
+	// use llama-server's timing data for tok/sec and duration as it is more accurate
+	if timings.Exists() {
+		inputTokens = int(jsonData.Get("timings.prompt_n").Int())
+		outputTokens = int(jsonData.Get("timings.predicted_n").Int())
+		promptPerSecond = jsonData.Get("timings.prompt_per_second").Float()
+		tokensPerSecond = jsonData.Get("timings.predicted_per_second").Float()
+		durationMs = int(jsonData.Get("timings.prompt_ms").Float() + jsonData.Get("timings.predicted_ms").Float())
+
+		if cachedValue := jsonData.Get("timings.cache_n"); cachedValue.Exists() {
+			cachedTokens = int(cachedValue.Int())
+		}
+	}
+
+	return TokenMetrics{
+		Timestamp:       time.Now(),
+		Model:           modelID,
+		CachedTokens:    cachedTokens,
+		InputTokens:     inputTokens,
+		OutputTokens:    outputTokens,
+		PromptPerSecond: promptPerSecond,
+		TokensPerSecond: tokensPerSecond,
+		DurationMs:      durationMs,
+	}, nil
+}
+
+// responseBodyCopier records the response body and writes to the original response writer
+// while also capturing it in a buffer for later processing
+type responseBodyCopier struct {
+	gin.ResponseWriter
+	body  *bytes.Buffer
+	tee   io.Writer
+	start time.Time
+}
+
+func newBodyCopier(w gin.ResponseWriter) *responseBodyCopier {
+	bodyBuffer := &bytes.Buffer{}
+	return &responseBodyCopier{
+		ResponseWriter: w,
+		body:           bodyBuffer,
+		tee:            io.MultiWriter(w, bodyBuffer),
+	}
+}
+
+func (w *responseBodyCopier) Write(b []byte) (int, error) {
+	if w.start.IsZero() {
+		w.start = time.Now()
+	}
+
+	// Single write operation that writes to both the response and buffer
+	return w.tee.Write(b)
+}
+
+func (w *responseBodyCopier) WriteHeader(statusCode int) {
+	w.ResponseWriter.WriteHeader(statusCode)
+}
+
+func (w *responseBodyCopier) Header() http.Header {
+	return w.ResponseWriter.Header()
+}
+
+func (w *responseBodyCopier) StartTime() time.Time {
+	return w.start
+}
@@ -0,0 +1,693 @@
+package proxy
+
+import (
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/gin-gonic/gin"
+	"github.com/mostlygeek/llama-swap/event"
+	"github.com/stretchr/testify/assert"
+)
+
+func TestMetricsMonitor_AddMetrics(t *testing.T) {
+	t.Run("adds metrics and assigns ID", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		metric := TokenMetrics{
+			Model:        "test-model",
+			InputTokens:  100,
+			OutputTokens: 50,
+		}
+
+		mm.addMetrics(metric)
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, 0, metrics[0].ID)
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 100, metrics[0].InputTokens)
+		assert.Equal(t, 50, metrics[0].OutputTokens)
+	})
+
+	t.Run("increments ID for each metric", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		for i := 0; i < 5; i++ {
+			mm.addMetrics(TokenMetrics{Model: "model"})
+		}
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, 5, len(metrics))
+		for i := 0; i < 5; i++ {
+			assert.Equal(t, i, metrics[i].ID)
+		}
+	})
+
+	t.Run("respects max metrics limit", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 3)
+
+		// Add 5 metrics
+		for i := 0; i < 5; i++ {
+			mm.addMetrics(TokenMetrics{
+				Model:       "model",
+				InputTokens: i,
+			})
+		}
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, 3, len(metrics))
+
+		// Should keep the last 3 metrics (IDs 2, 3, 4)
+		assert.Equal(t, 2, metrics[0].ID)
+		assert.Equal(t, 3, metrics[1].ID)
+		assert.Equal(t, 4, metrics[2].ID)
+	})
+
+	t.Run("emits TokenMetricsEvent", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		receivedEvent := make(chan TokenMetricsEvent, 1)
+		cancel := event.On(func(e TokenMetricsEvent) {
+			receivedEvent <- e
+		})
+		defer cancel()
+
+		metric := TokenMetrics{
+			Model:        "test-model",
+			InputTokens:  100,
+			OutputTokens: 50,
+		}
+
+		mm.addMetrics(metric)
+
+		select {
+		case evt := <-receivedEvent:
+			assert.Equal(t, 0, evt.Metrics.ID)
+			assert.Equal(t, "test-model", evt.Metrics.Model)
+			assert.Equal(t, 100, evt.Metrics.InputTokens)
+			assert.Equal(t, 50, evt.Metrics.OutputTokens)
+		case <-time.After(1 * time.Second):
+			t.Fatal("timeout waiting for event")
+		}
+	})
+}
+
+func TestMetricsMonitor_GetMetrics(t *testing.T) {
+	t.Run("returns empty slice when no metrics", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+		metrics := mm.getMetrics()
+		assert.NotNil(t, metrics)
+		assert.Equal(t, 0, len(metrics))
+	})
+
+	t.Run("returns copy of metrics", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+		mm.addMetrics(TokenMetrics{Model: "model1"})
+		mm.addMetrics(TokenMetrics{Model: "model2"})
+
+		metrics1 := mm.getMetrics()
+		metrics2 := mm.getMetrics()
+
+		// Verify we got copies
+		assert.Equal(t, 2, len(metrics1))
+		assert.Equal(t, 2, len(metrics2))
+
+		// Modify the returned slice shouldn't affect the original
+		metrics1[0].Model = "modified"
+		metrics3 := mm.getMetrics()
+		assert.Equal(t, "model1", metrics3[0].Model)
+	})
+}
+
+func TestMetricsMonitor_GetMetricsJSON(t *testing.T) {
+	t.Run("returns valid JSON for empty metrics", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+		jsonData, err := mm.getMetricsJSON()
+		assert.NoError(t, err)
+		assert.NotNil(t, jsonData)
+
+		var metrics []TokenMetrics
+		err = json.Unmarshal(jsonData, &metrics)
+		assert.NoError(t, err)
+		assert.Equal(t, 0, len(metrics))
+	})
+
+	t.Run("returns valid JSON with metrics", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+		mm.addMetrics(TokenMetrics{
+			Model:           "model1",
+			InputTokens:     100,
+			OutputTokens:    50,
+			TokensPerSecond: 25.5,
+		})
+		mm.addMetrics(TokenMetrics{
+			Model:           "model2",
+			InputTokens:     200,
+			OutputTokens:    100,
+			TokensPerSecond: 30.0,
+		})
+
+		jsonData, err := mm.getMetricsJSON()
+		assert.NoError(t, err)
+
+		var metrics []TokenMetrics
+		err = json.Unmarshal(jsonData, &metrics)
+		assert.NoError(t, err)
+		assert.Equal(t, 2, len(metrics))
+		assert.Equal(t, "model1", metrics[0].Model)
+		assert.Equal(t, "model2", metrics[1].Model)
+	})
+}
+
+func TestMetricsMonitor_WrapHandler(t *testing.T) {
+	t.Run("successful non-streaming request with usage data", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		responseBody := `{
+			"usage": {
+				"prompt_tokens": 100,
+				"completion_tokens": 50
+			}
+		}`
+
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			w.Header().Set("Content-Type", "application/json")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte(responseBody))
+			return nil
+		}
+
+		req := httptest.NewRequest("POST", "/test", 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, 100, metrics[0].InputTokens)
+		assert.Equal(t, 50, metrics[0].OutputTokens)
+	})
+
+	t.Run("successful request with timings data", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		responseBody := `{
+			"timings": {
+				"prompt_n": 100,
+				"predicted_n": 50,
+				"prompt_per_second": 150.5,
+				"predicted_per_second": 25.5,
+				"prompt_ms": 500.0,
+				"predicted_ms": 1500.0,
+				"cache_n": 20
+			}
+		}`
+
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			w.Header().Set("Content-Type", "application/json")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte(responseBody))
+			return nil
+		}
+
+		req := httptest.NewRequest("POST", "/test", 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, 100, metrics[0].InputTokens)
+		assert.Equal(t, 50, metrics[0].OutputTokens)
+		assert.Equal(t, 20, metrics[0].CachedTokens)
+		assert.Equal(t, 150.5, metrics[0].PromptPerSecond)
+		assert.Equal(t, 25.5, metrics[0].TokensPerSecond)
+		assert.Equal(t, 2000, metrics[0].DurationMs) // 500 + 1500
+	})
+
+	t.Run("streaming request with SSE format", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		// Note: SSE format requires proper line breaks - each data line followed by blank line
+		responseBody := `data: {"choices":[{"text":"Hello"}]}
+
+data: {"choices":[{"text":" World"}]}
+
+data: {"usage":{"prompt_tokens":10,"completion_tokens":20},"timings":{"prompt_n":10,"predicted_n":20,"prompt_per_second":100.0,"predicted_per_second":50.0,"prompt_ms":100.0,"predicted_ms":400.0}}
+
+data: [DONE]
+
+`
+
+		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", "/test", 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)
+		// When timings data is present, it takes precedence
+		assert.Equal(t, 10, metrics[0].InputTokens)
+		assert.Equal(t, 20, metrics[0].OutputTokens)
+	})
+
+	t.Run("non-OK status code does not record metrics", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			w.WriteHeader(http.StatusBadRequest)
+			w.Write([]byte("error"))
+			return nil
+		}
+
+		req := httptest.NewRequest("POST", "/test", 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, 0, len(metrics))
+	})
+
+	t.Run("empty response body does not record metrics", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			w.WriteHeader(http.StatusOK)
+			return nil
+		}
+
+		req := httptest.NewRequest("POST", "/test", 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, 0, len(metrics))
+	})
+
+	t.Run("invalid JSON does not record metrics", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			w.Header().Set("Content-Type", "application/json")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte("not valid json"))
+			return nil
+		}
+
+		req := httptest.NewRequest("POST", "/test", nil)
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+
+		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
+		assert.NoError(t, err) // Errors after response is sent are logged, not returned
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, 0, len(metrics))
+	})
+
+	t.Run("next handler error is propagated", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		expectedErr := assert.AnError
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			return expectedErr
+		}
+
+		req := httptest.NewRequest("POST", "/test", nil)
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+
+		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
+		assert.Equal(t, expectedErr, err)
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, 0, len(metrics))
+	})
+
+	t.Run("response without usage or timings does not record metrics", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		responseBody := `{"result": "ok"}`
+
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			w.Header().Set("Content-Type", "application/json")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte(responseBody))
+			return nil
+		}
+
+		req := httptest.NewRequest("POST", "/test", nil)
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+
+		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
+		assert.NoError(t, err) // Errors after response is sent are logged, not returned
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, 0, len(metrics))
+	})
+}
+
+func TestMetricsMonitor_ResponseBodyCopier(t *testing.T) {
+	t.Run("captures response body", func(t *testing.T) {
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+		copier := newBodyCopier(ginCtx.Writer)
+
+		testData := []byte("test response body")
+		n, err := copier.Write(testData)
+
+		assert.NoError(t, err)
+		assert.Equal(t, len(testData), n)
+		assert.Equal(t, testData, copier.body.Bytes())
+		assert.Equal(t, string(testData), rec.Body.String())
+	})
+
+	t.Run("sets start time on first write", func(t *testing.T) {
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+		copier := newBodyCopier(ginCtx.Writer)
+
+		assert.True(t, copier.StartTime().IsZero())
+
+		copier.Write([]byte("test"))
+
+		assert.False(t, copier.StartTime().IsZero())
+	})
+
+	t.Run("preserves headers", func(t *testing.T) {
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+		copier := newBodyCopier(ginCtx.Writer)
+
+		copier.Header().Set("X-Test", "value")
+
+		assert.Equal(t, "value", rec.Header().Get("X-Test"))
+	})
+
+	t.Run("preserves status code", func(t *testing.T) {
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+		copier := newBodyCopier(ginCtx.Writer)
+
+		copier.WriteHeader(http.StatusCreated)
+
+		// Gin's ResponseWriter tracks status internally
+		assert.Equal(t, http.StatusCreated, copier.Status())
+	})
+}
+
+func TestMetricsMonitor_Concurrent(t *testing.T) {
+	t.Run("concurrent addMetrics is safe", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 1000)
+
+		var wg sync.WaitGroup
+		numGoroutines := 10
+		metricsPerGoroutine := 100
+
+		for i := 0; i < numGoroutines; i++ {
+			wg.Add(1)
+			go func(id int) {
+				defer wg.Done()
+				for j := 0; j < metricsPerGoroutine; j++ {
+					mm.addMetrics(TokenMetrics{
+						Model:        "test-model",
+						InputTokens:  id*1000 + j,
+						OutputTokens: j,
+					})
+				}
+			}(i)
+		}
+
+		wg.Wait()
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, numGoroutines*metricsPerGoroutine, len(metrics))
+	})
+
+	t.Run("concurrent reads and writes are safe", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 100)
+
+		done := make(chan bool)
+
+		// Writer goroutine
+		go func() {
+			for i := 0; i < 50; i++ {
+				mm.addMetrics(TokenMetrics{Model: "test-model"})
+				time.Sleep(1 * time.Millisecond)
+			}
+			done <- true
+		}()
+
+		// Multiple reader goroutines
+		var wg sync.WaitGroup
+		for i := 0; i < 5; i++ {
+			wg.Add(1)
+			go func() {
+				defer wg.Done()
+				for j := 0; j < 20; j++ {
+					_ = mm.getMetrics()
+					_, _ = mm.getMetricsJSON()
+					time.Sleep(2 * time.Millisecond)
+				}
+			}()
+		}
+
+		<-done
+		wg.Wait()
+
+		// Final check
+		metrics := mm.getMetrics()
+		assert.Equal(t, 50, len(metrics))
+	})
+}
+
+func TestMetricsMonitor_ParseMetrics(t *testing.T) {
+	t.Run("prefers timings over usage data", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		// Timings should take precedence over usage
+		responseBody := `{
+			"usage": {
+				"prompt_tokens": 50,
+				"completion_tokens": 25
+			},
+			"timings": {
+				"prompt_n": 100,
+				"predicted_n": 50,
+				"prompt_per_second": 150.5,
+				"predicted_per_second": 25.5,
+				"prompt_ms": 500.0,
+				"predicted_ms": 1500.0
+			}
+		}`
+
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			w.Header().Set("Content-Type", "application/json")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte(responseBody))
+			return nil
+		}
+
+		req := httptest.NewRequest("POST", "/test", 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))
+		// Should use timings values, not usage values
+		assert.Equal(t, 100, metrics[0].InputTokens)
+		assert.Equal(t, 50, metrics[0].OutputTokens)
+	})
+
+	t.Run("handles missing cache_n in timings", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		responseBody := `{
+			"timings": {
+				"prompt_n": 100,
+				"predicted_n": 50,
+				"prompt_per_second": 150.5,
+				"predicted_per_second": 25.5,
+				"prompt_ms": 500.0,
+				"predicted_ms": 1500.0
+			}
+		}`
+
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			w.Header().Set("Content-Type", "application/json")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte(responseBody))
+			return nil
+		}
+
+		req := httptest.NewRequest("POST", "/test", 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, -1, metrics[0].CachedTokens) // Default value when not present
+	})
+}
+
+func TestMetricsMonitor_StreamingResponse(t *testing.T) {
+	t.Run("finds metrics in last valid SSE data", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		// Metrics should be found in the last data line before [DONE]
+		responseBody := `data: {"choices":[{"text":"First"}]}
+
+data: {"choices":[{"text":"Second"}]}
+
+data: {"usage":{"prompt_tokens":100,"completion_tokens":50}}
+
+data: [DONE]
+
+`
+
+		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", "/test", 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, 100, metrics[0].InputTokens)
+		assert.Equal(t, 50, metrics[0].OutputTokens)
+	})
+
+	t.Run("handles streaming with no valid JSON", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		responseBody := `data: not json
+
+data: [DONE]
+
+`
+
+		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", "/test", nil)
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+
+		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
+		assert.NoError(t, err) // Errors after response is sent are logged, not returned
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, 0, len(metrics))
+	})
+
+	t.Run("handles empty streaming response", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		responseBody := ``
+
+		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", "/test", nil)
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+
+		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
+		// Empty body should not trigger WrapHandler processing
+		assert.NoError(t, err)
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, 0, len(metrics))
+	})
+}
+
+// Benchmark tests
+func BenchmarkMetricsMonitor_AddMetrics(b *testing.B) {
+	mm := newMetricsMonitor(testLogger, 1000)
+
+	metric := TokenMetrics{
+		Model:           "test-model",
+		CachedTokens:    100,
+		InputTokens:     500,
+		OutputTokens:    250,
+		PromptPerSecond: 1200.5,
+		TokensPerSecond: 45.8,
+		DurationMs:      5000,
+		Timestamp:       time.Now(),
+	}
+
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		mm.addMetrics(metric)
+	}
+}
+
+func BenchmarkMetricsMonitor_AddMetrics_SmallBuffer(b *testing.B) {
+	// Test performance with a smaller buffer where wrapping occurs more frequently
+	mm := newMetricsMonitor(testLogger, 100)
+
+	metric := TokenMetrics{
+		Model:           "test-model",
+		CachedTokens:    100,
+		InputTokens:     500,
+		OutputTokens:    250,
+		PromptPerSecond: 1200.5,
+		TokensPerSecond: 45.8,
+		DurationMs:      5000,
+		Timestamp:       time.Now(),
+	}
+
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		mm.addMetrics(metric)
+	}
+}
@@ -2,8 +2,10 @@ package proxy

 import (
 	"context"
+	"encoding/json"
 	"errors"
 	"fmt"
+	"math/rand"
 	"net"
 	"net/http"
 	"net/http/httputil"
@@ -254,6 +256,7 @@ func (p *Process) start() error {
 	p.cmd.Env = append(p.cmd.Environ(), p.config.Env...)
 	p.cmd.Cancel = p.cmdStopUpstreamProcess
 	p.cmd.WaitDelay = p.gracefulStopTimeout
+	setProcAttributes(p.cmd)

 	p.cmdMutex.Lock()
 	p.cancelUpstream = ctxCancelUpstream
@@ -462,6 +465,12 @@ func (p *Process) checkHealthEndpoint(healthURL string) error {
 }

 func (p *Process) ProxyRequest(w http.ResponseWriter, r *http.Request) {
+
+	if p.reverseProxy == nil {
+		http.Error(w, fmt.Sprintf("No reverse proxy available for %s", p.ID), http.StatusInternalServerError)
+		return
+	}
+
 	requestBeginTime := time.Now()
 	var startDuration time.Duration

@@ -488,21 +497,65 @@ func (p *Process) ProxyRequest(w http.ResponseWriter, r *http.Request) {
 		p.inFlightRequests.Done()
 	}()

+	// for #366
+	// - extract streaming param from request context, should have been set by proxymanager
+	var srw *statusResponseWriter
+	swapCtx, cancelLoadCtx := context.WithCancel(r.Context())
 	// start the process on demand
 	if p.CurrentState() != StateReady {
+		// start a goroutine to stream loading status messages into the response writer
+		// add a sync so the streaming client only runs when the goroutine has exited
+
+		isStreaming, _ := r.Context().Value(proxyCtxKey("streaming")).(bool)
+		if p.config.SendLoadingState != nil && *p.config.SendLoadingState && isStreaming {
+			srw = newStatusResponseWriter(p, w)
+			go srw.statusUpdates(swapCtx)
+		} else {
+			p.proxyLogger.Debugf("<%s> SendLoadingState is nil or false, not streaming loading state", p.ID)
+		}
+
 		beginStartTime := time.Now()
 		if err := p.start(); err != nil {
 			errstr := fmt.Sprintf("unable to start process: %s", err)
-			http.Error(w, errstr, http.StatusBadGateway)
+			cancelLoadCtx()
+			if srw != nil {
+				srw.sendData(fmt.Sprintf("Unable to swap model err: %s\n", errstr))
+				// Wait for statusUpdates goroutine to finish writing its deferred "Done!" messages
+				// before closing the connection. Without this, the connection would close before
+				// the goroutine can write its cleanup messages, causing incomplete SSE output.
+				srw.waitForCompletion(100 * time.Millisecond)
+			} else {
+				http.Error(w, errstr, http.StatusBadGateway)
+			}
 			return
 		}
 		startDuration = time.Since(beginStartTime)
 	}

-	if p.reverseProxy != nil {
-		p.reverseProxy.ServeHTTP(w, r)
+	// should trigger srw to stop sending loading events ...
+	cancelLoadCtx()
+
+	// recover from http.ErrAbortHandler panics that can occur when the client
+	// disconnects before the response is sent
+	defer func() {
+		if r := recover(); r != nil {
+			if r == http.ErrAbortHandler {
+				p.proxyLogger.Infof("<%s> recovered from client disconnection during streaming", p.ID)
+			} else {
+				p.proxyLogger.Infof("<%s> recovered from panic: %v", p.ID, r)
+			}
+		}
+	}()
+
+	if srw != nil {
+		// Wait for the goroutine to finish writing its final messages
+		const completionTimeout = 1 * time.Second
+		if !srw.waitForCompletion(completionTimeout) {
+			p.proxyLogger.Warnf("<%s> status updates goroutine did not complete within %v, proceeding with proxy request", p.ID, completionTimeout)
+		}
+		p.reverseProxy.ServeHTTP(srw, r)
 	} else {
-		http.Error(w, fmt.Sprintf("No reverse proxy available for %s", p.ID), http.StatusInternalServerError)
+		p.reverseProxy.ServeHTTP(w, r)
 	}

 	totalTime := time.Since(requestBeginTime)
@@ -573,6 +626,7 @@ func (p *Process) cmdStopUpstreamProcess() error {
 		stopCmd := exec.Command(stopArgs[0], stopArgs[1:]...)
 		stopCmd.Stdout = p.processLogger
 		stopCmd.Stderr = p.processLogger
+		setProcAttributes(stopCmd)
 		stopCmd.Env = p.cmd.Env

 		if err := stopCmd.Run(); err != nil {
@@ -588,3 +642,228 @@ func (p *Process) cmdStopUpstreamProcess() error {

 	return nil
 }
+
+var loadingRemarks = []string{
+	"Still faster than your last standup meeting...",
+	"Reticulating splines...",
+	"Waking up the hamsters...",
+	"Teaching the model manners...",
+	"Convincing the GPU to participate...",
+	"Loading weights (they're heavy)...",
+	"Herding electrons...",
+	"Compiling excuses for the delay...",
+	"Downloading more RAM...",
+	"Asking the model nicely to boot up...",
+	"Bribing CUDA with cookies...",
+	"Still loading (blame VRAM)...",
+	"The model is fashionably late...",
+	"Warming up those tensors...",
+	"Making the neural net do push-ups...",
+	"Your patience is appreciated (really)...",
+	"Almost there (probably)...",
+	"Loading like it's 1999...",
+	"The model forgot where it put its keys...",
+	"Quantum tunneling through layers...",
+	"Negotiating with the PCIe bus...",
+	"Defrosting frozen parameters...",
+	"Teaching attention heads to focus...",
+	"Running the matrix (slowly)...",
+	"Untangling transformer blocks...",
+	"Calibrating the flux capacitor...",
+	"Spinning up the probability wheels...",
+	"Waiting for the GPU to wake from its nap...",
+	"Converting caffeine to compute...",
+	"Allocating virtual patience...",
+	"Performing arcane CUDA rituals...",
+	"The model is stuck in traffic...",
+	"Inflating embeddings...",
+	"Summoning computational demons...",
+	"Pleading with the OOM killer...",
+	"Calculating the meaning of life (still at 42)...",
+	"Training the training wheels...",
+	"Optimizing the optimizer...",
+	"Bootstrapping the bootstrapper...",
+	"Loading loading screen...",
+	"Processing processing logs...",
+	"Buffering buffer overflow jokes...",
+	"The model hit snooze...",
+	"Debugging the debugger...",
+	"Compiling the compiler...",
+	"Parsing the parser (meta)...",
+	"Tokenizing tokens...",
+	"Encoding the encoder...",
+	"Hashing hash browns...",
+	"Forking spoons (not forks)...",
+	"The model is contemplating existence...",
+	"Transcending dimensional barriers...",
+	"Invoking elder tensor gods...",
+	"Unfurling probability clouds...",
+	"Synchronizing parallel universes...",
+	"The GPU is having second thoughts...",
+	"Recalibrating reality matrices...",
+	"Time is an illusion, loading doubly so...",
+	"Convincing bits to flip themselves...",
+	"The model is reading its own documentation...",
+}
+
+type statusResponseWriter struct {
+	hasWritten bool
+	writer     http.ResponseWriter
+	process    *Process
+	wg         sync.WaitGroup // Track goroutine completion
+	start      time.Time
+}
+
+func newStatusResponseWriter(p *Process, w http.ResponseWriter) *statusResponseWriter {
+	s := &statusResponseWriter{
+		writer:  w,
+		process: p,
+		start:   time.Now(),
+	}
+
+	s.Header().Set("Content-Type", "text/event-stream") // SSE
+	s.Header().Set("Cache-Control", "no-cache")         // no-cache
+	s.Header().Set("Connection", "keep-alive")          // keep-alive
+	s.WriteHeader(http.StatusOK)                        // send status code 200
+	s.sendLine("━━━━━")
+	s.sendLine(fmt.Sprintf("llama-swap loading model: %s", p.ID))
+	return s
+}
+
+// statusUpdates sends status updates to the client while the model is loading
+func (s *statusResponseWriter) statusUpdates(ctx context.Context) {
+	s.wg.Add(1)
+	defer s.wg.Done()
+
+	// Recover from panics caused by client disconnection
+	// Note: recover() only works within the same goroutine, so we need it here
+	defer func() {
+		if r := recover(); r != nil {
+			s.process.proxyLogger.Debugf("<%s> statusUpdates recovered from panic (likely client disconnect): %v", s.process.ID, r)
+		}
+	}()
+
+	defer func() {
+		duration := time.Since(s.start)
+		s.sendLine(fmt.Sprintf("\nDone! (%.2fs)", duration.Seconds()))
+		s.sendLine("━━━━━")
+		s.sendLine(" ")
+	}()
+
+	// Create a shuffled copy of loadingRemarks
+	remarks := make([]string, len(loadingRemarks))
+	copy(remarks, loadingRemarks)
+	rand.Shuffle(len(remarks), func(i, j int) {
+		remarks[i], remarks[j] = remarks[j], remarks[i]
+	})
+	ri := 0
+
+	// Pick a random duration to send a remark
+	nextRemarkIn := time.Duration(2+rand.Intn(4)) * time.Second
+	lastRemarkTime := time.Now()
+
+	ticker := time.NewTicker(time.Second)
+	defer ticker.Stop() // Ensure ticker is stopped to prevent resource leak
+	for {
+		select {
+		case <-ctx.Done():
+			return
+		case <-ticker.C:
+			if s.process.CurrentState() == StateReady {
+				return
+			}
+
+			// Check if it's time for a snarky remark
+			if time.Since(lastRemarkTime) >= nextRemarkIn {
+				remark := remarks[ri%len(remarks)]
+				ri++
+				s.sendLine(fmt.Sprintf("\n%s", remark))
+				lastRemarkTime = time.Now()
+				// Pick a new random duration for the next remark
+				nextRemarkIn = time.Duration(5+rand.Intn(5)) * time.Second
+			} else {
+				s.sendData(".")
+			}
+		}
+	}
+}
+
+// waitForCompletion waits for the statusUpdates goroutine to finish
+func (s *statusResponseWriter) waitForCompletion(timeout time.Duration) bool {
+	done := make(chan struct{})
+	go func() {
+		s.wg.Wait()
+		close(done)
+	}()
+
+	select {
+	case <-done:
+		return true
+	case <-time.After(timeout):
+		return false
+	}
+}
+
+func (s *statusResponseWriter) sendLine(line string) {
+	s.sendData(line + "\n")
+}
+
+func (s *statusResponseWriter) sendData(data string) {
+	// Create the proper SSE JSON structure
+	type Delta struct {
+		ReasoningContent string `json:"reasoning_content"`
+	}
+	type Choice struct {
+		Delta Delta `json:"delta"`
+	}
+	type SSEMessage struct {
+		Choices []Choice `json:"choices"`
+	}
+
+	msg := SSEMessage{
+		Choices: []Choice{
+			{
+				Delta: Delta{
+					ReasoningContent: data,
+				},
+			},
+		},
+	}
+
+	jsonData, err := json.Marshal(msg)
+	if err != nil {
+		s.process.proxyLogger.Errorf("<%s> Failed to marshal SSE message: %v", s.process.ID, err)
+		return
+	}
+
+	// Write SSE formatted data, panic if not able to write
+	_, err = fmt.Fprintf(s.writer, "data: %s\n\n", jsonData)
+	if err != nil {
+		panic(fmt.Sprintf("<%s> Failed to write SSE data: %v", s.process.ID, err))
+	}
+	s.Flush()
+}
+
+func (s *statusResponseWriter) Header() http.Header {
+	return s.writer.Header()
+}
+
+func (s *statusResponseWriter) Write(data []byte) (int, error) {
+	return s.writer.Write(data)
+}
+
+func (s *statusResponseWriter) WriteHeader(statusCode int) {
+	if s.hasWritten {
+		return
+	}
+	s.hasWritten = true
+	s.writer.WriteHeader(statusCode)
+	s.Flush()
+}
+
+// Add Flush method
+func (s *statusResponseWriter) Flush() {
+	if flusher, ok := s.writer.(http.Flusher); ok {
+		flusher.Flush()
+	}
+}
@@ -494,3 +494,74 @@ func TestProcess_EnvironmentSetCorrectly(t *testing.T) {
 	assert.Equal(t, len(process1.cmd.Environ())+2, len(process2.cmd.Environ()), "process2 should have 2 more environment variables than process1")

 }
+
+// TestProcess_ReverseProxyPanicIsHandled tests that panics from
+// httputil.ReverseProxy in Process.ProxyRequest(w, r) do not bubble up and are
+// handled appropriately.
+//
+// httputil.ReverseProxy will panic with http.ErrAbortHandler when it has sent headers
+// can't copy the body. This can be caused by a client disconnecting before the full
+// response is sent from some reason.
+//
+// bug: https://github.com/mostlygeek/llama-swap/issues/362
+// see: https://github.com/golang/go/issues/23643 (where panic was added to httputil.ReverseProxy)
+func TestProcess_ReverseProxyPanicIsHandled(t *testing.T) {
+	// Add defer/recover to catch any panics that aren't handled by ProxyRequest
+	// If this recover() is hit, it means ProxyRequest didn't handle the panic properly
+	defer func() {
+		if r := recover(); r != nil {
+			t.Fatalf("ProxyRequest should handle panics from reverseProxy.ServeHTTP, but panic was not caught: %v", r)
+		}
+	}()
+
+	expectedMessage := "panic_test"
+	config := getTestSimpleResponderConfig(expectedMessage)
+
+	process := NewProcess("panic-test", 5, config, debugLogger, debugLogger)
+	defer process.Stop()
+
+	// Start the process
+	err := process.start()
+	assert.Nil(t, err)
+	assert.Equal(t, StateReady, process.CurrentState())
+
+	// Create a custom ResponseWriter that simulates a client disconnect
+	// by panicking when Write is called after headers are sent
+	panicWriter := &panicOnWriteResponseWriter{
+		ResponseRecorder: httptest.NewRecorder(),
+		shouldPanic:      true,
+	}
+
+	// Make a request that will trigger the panic
+	req := httptest.NewRequest("GET", "/slow-respond?echo=test&delay=100ms", nil)
+
+	// This should panic inside reverseProxy.ServeHTTP when the panicWriter.Write() is called.
+	// ProxyRequest should catch and handle this panic gracefully.
+	process.ProxyRequest(panicWriter, req)
+
+	// If we get here, the panic was properly recovered in ProxyRequest
+	// The process should still be in a ready state
+	assert.Equal(t, StateReady, process.CurrentState())
+}
+
+// panicOnWriteResponseWriter is a ResponseWriter that panics on Write
+// to simulate a client disconnect after headers are sent
+// used by: TestProcess_ReverseProxyPanicIsHandled
+type panicOnWriteResponseWriter struct {
+	*httptest.ResponseRecorder
+	shouldPanic   bool
+	headerWritten bool
+}
+
+func (w *panicOnWriteResponseWriter) WriteHeader(statusCode int) {
+	w.headerWritten = true
+	w.ResponseRecorder.WriteHeader(statusCode)
+}
+
+func (w *panicOnWriteResponseWriter) Write(b []byte) (int, error) {
+	if w.shouldPanic && w.headerWritten {
+		// Simulate the panic that httputil.ReverseProxy throws
+		panic(http.ErrAbortHandler)
+	}
+	return w.ResponseRecorder.Write(b)
+}
@@ -0,0 +1,12 @@
+//go:build !windows
+
+package proxy
+
+import (
+	"os/exec"
+)
+
+// setProcAttributes sets platform-specific process attributes
+func setProcAttributes(cmd *exec.Cmd) {
+	// No-op on Unix systems
+}
@@ -0,0 +1,16 @@
+//go:build windows
+
+package proxy
+
+import (
+	"os/exec"
+	"syscall"
+)
+
+// setProcAttributes sets platform-specific process attributes
+func setProcAttributes(cmd *exec.Cmd) {
+	cmd.SysProcAttr = &syscall.SysProcAttr{
+		HideWindow:    true,
+		CreationFlags: 0x08000000, // CREATE_NO_WINDOW
+	}
+}
@@ -25,6 +25,8 @@ const (
 	PROFILE_SPLIT_CHAR = ":"
 )

+type proxyCtxKey string
+
 type ProxyManager struct {
 	sync.Mutex

@@ -36,13 +38,18 @@ type ProxyManager struct {
 	upstreamLogger *LogMonitor
 	muxLogger      *LogMonitor

-	metricsMonitor *MetricsMonitor
+	metricsMonitor *metricsMonitor

 	processGroups map[string]*ProcessGroup

 	// shutdown signaling
 	shutdownCtx    context.Context
 	shutdownCancel context.CancelFunc
+
+	// version info
+	buildDate string
+	commit    string
+	version   string
 }

 func New(config config.Config) *ProxyManager {
@@ -73,8 +80,39 @@ func New(config config.Config) *ProxyManager {
 		upstreamLogger.SetLogLevel(LevelInfo)
 	}

+	// see: https://go.dev/src/time/format.go
+	timeFormats := map[string]string{
+		"ansic":       time.ANSIC,
+		"unixdate":    time.UnixDate,
+		"rubydate":    time.RubyDate,
+		"rfc822":      time.RFC822,
+		"rfc822z":     time.RFC822Z,
+		"rfc850":      time.RFC850,
+		"rfc1123":     time.RFC1123,
+		"rfc1123z":    time.RFC1123Z,
+		"rfc3339":     time.RFC3339,
+		"rfc3339nano": time.RFC3339Nano,
+		"kitchen":     time.Kitchen,
+		"stamp":       time.Stamp,
+		"stampmilli":  time.StampMilli,
+		"stampmicro":  time.StampMicro,
+		"stampnano":   time.StampNano,
+	}
+
+	if timeFormat, ok := timeFormats[strings.ToLower(strings.TrimSpace(config.LogTimeFormat))]; ok {
+		proxyLogger.SetLogTimeFormat(timeFormat)
+		upstreamLogger.SetLogTimeFormat(timeFormat)
+	}
+
 	shutdownCtx, shutdownCancel := context.WithCancel(context.Background())

+	var maxMetrics int
+	if config.MetricsMaxInMemory <= 0 {
+		maxMetrics = 1000 // Default fallback
+	} else {
+		maxMetrics = config.MetricsMaxInMemory
+	}
+
 	pm := &ProxyManager{
 		config:    config,
 		ginEngine: gin.New(),
@@ -83,12 +121,16 @@ func New(config config.Config) *ProxyManager {
 		muxLogger:      stdoutLogger,
 		upstreamLogger: upstreamLogger,

-		metricsMonitor: NewMetricsMonitor(&config),
+		metricsMonitor: newMetricsMonitor(proxyLogger, maxMetrics),

 		processGroups: make(map[string]*ProcessGroup),

 		shutdownCtx:    shutdownCtx,
 		shutdownCancel: shutdownCancel,
+
+		buildDate: "unknown",
+		commit:    "abcd1234",
+		version:   "0",
 	}

 	// create the process groups
@@ -193,27 +235,25 @@ func (pm *ProxyManager) setupGinEngine() {
 		c.Next()
 	})

-	mm := MetricsMiddleware(pm)
-
 	// Set up routes using the Gin engine
-	pm.ginEngine.POST("/v1/chat/completions", mm, pm.proxyOAIHandler)
+	pm.ginEngine.POST("/v1/chat/completions", pm.proxyOAIHandler)
 	// Support legacy /v1/completions api, see issue #12
-	pm.ginEngine.POST("/v1/completions", mm, pm.proxyOAIHandler)
+	pm.ginEngine.POST("/v1/completions", pm.proxyOAIHandler)

 	// Support embeddings and reranking
-	pm.ginEngine.POST("/v1/embeddings", mm, pm.proxyOAIHandler)
+	pm.ginEngine.POST("/v1/embeddings", pm.proxyOAIHandler)

 	// llama-server's /reranking endpoint + aliases
-	pm.ginEngine.POST("/reranking", mm, pm.proxyOAIHandler)
-	pm.ginEngine.POST("/rerank", mm, pm.proxyOAIHandler)
-	pm.ginEngine.POST("/v1/rerank", mm, pm.proxyOAIHandler)
-	pm.ginEngine.POST("/v1/reranking", mm, pm.proxyOAIHandler)
+	pm.ginEngine.POST("/reranking", pm.proxyOAIHandler)
+	pm.ginEngine.POST("/rerank", pm.proxyOAIHandler)
+	pm.ginEngine.POST("/v1/rerank", pm.proxyOAIHandler)
+	pm.ginEngine.POST("/v1/reranking", pm.proxyOAIHandler)

 	// llama-server's /infill endpoint for code infilling
-	pm.ginEngine.POST("/infill", mm, pm.proxyOAIHandler)
+	pm.ginEngine.POST("/infill", pm.proxyOAIHandler)

 	// llama-server's /completion endpoint
-	pm.ginEngine.POST("/completion", mm, pm.proxyOAIHandler)
+	pm.ginEngine.POST("/completion", pm.proxyOAIHandler)

 	// Support audio/speech endpoint
 	pm.ginEngine.POST("/v1/audio/speech", pm.proxyOAIHandler)
@@ -369,28 +409,40 @@ func (pm *ProxyManager) listModelsHandler(c *gin.Context) {
 			continue
 		}

-		record := gin.H{
-			"id":       id,
-			"object":   "model",
-			"created":  createdTime,
-			"owned_by": "llama-swap",
+		newRecord := func(modelId string) gin.H {
+			record := gin.H{
+				"id":       modelId,
+				"object":   "model",
+				"created":  createdTime,
+				"owned_by": "llama-swap",
+			}
+
+			if name := strings.TrimSpace(modelConfig.Name); name != "" {
+				record["name"] = name
+			}
+			if desc := strings.TrimSpace(modelConfig.Description); desc != "" {
+				record["description"] = desc
+			}
+
+			// Add metadata if present
+			if len(modelConfig.Metadata) > 0 {
+				record["meta"] = gin.H{
+					"llamaswap": modelConfig.Metadata,
+				}
+			}
+			return record
 		}

-		if name := strings.TrimSpace(modelConfig.Name); name != "" {
-			record["name"] = name
-		}
-		if desc := strings.TrimSpace(modelConfig.Description); desc != "" {
-			record["description"] = desc
-		}
+		data = append(data, newRecord(id))

-		// Add metadata if present
-		if len(modelConfig.Metadata) > 0 {
-			record["meta"] = gin.H{
-				"llamaswap": modelConfig.Metadata,
+		// Include aliases
+		if pm.config.IncludeAliasesInList {
+			for _, alias := range modelConfig.Aliases {
+				if alias := strings.TrimSpace(alias); alias != "" {
+					data = append(data, newRecord(alias))
+				}
 			}
 		}
-
-		data = append(data, record)
 	}

 	// Sort by the "id" key
@@ -474,8 +526,23 @@ func (pm *ProxyManager) proxyToUpstream(c *gin.Context) {
 	}

 	// rewrite the path
+	originalPath := c.Request.URL.Path
 	c.Request.URL.Path = remainingPath
-	processGroup.ProxyRequest(realModelName, c.Writer, c.Request)
+
+	// attempt to record metrics if it is a POST request
+	if pm.metricsMonitor != nil && c.Request.Method == "POST" {
+		if err := pm.metricsMonitor.wrapHandler(realModelName, c.Writer, c.Request, processGroup.ProxyRequest); err != nil {
+			pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error proxying metrics wrapped request: %s", err.Error()))
+			pm.proxyLogger.Errorf("Error proxying wrapped upstream request for model %s, path=%s", realModelName, originalPath)
+			return
+		}
+	} else {
+		if err := processGroup.ProxyRequest(realModelName, c.Writer, c.Request); err != nil {
+			pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error proxying request: %s", err.Error()))
+			pm.proxyLogger.Errorf("Error proxying upstream request for model %s, path=%s", realModelName, originalPath)
+			return
+		}
+	}
 }

 func (pm *ProxyManager) proxyOAIHandler(c *gin.Context) {
@@ -535,10 +602,24 @@ func (pm *ProxyManager) proxyOAIHandler(c *gin.Context) {
 	c.Request.Header.Set("content-length", strconv.Itoa(len(bodyBytes)))
 	c.Request.ContentLength = int64(len(bodyBytes))

-	if err := processGroup.ProxyRequest(realModelName, c.Writer, c.Request); err != nil {
-		pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error proxying request: %s", err.Error()))
-		pm.proxyLogger.Errorf("Error Proxying Request for processGroup %s and model %s", processGroup.id, realModelName)
-		return
+	// issue #366 extract values that downstream handlers may need
+	isStreaming := gjson.GetBytes(bodyBytes, "stream").Bool()
+	ctx := context.WithValue(c.Request.Context(), proxyCtxKey("streaming"), isStreaming)
+	ctx = context.WithValue(ctx, proxyCtxKey("model"), realModelName)
+	c.Request = c.Request.WithContext(ctx)
+
+	if pm.metricsMonitor != nil && c.Request.Method == "POST" {
+		if err := pm.metricsMonitor.wrapHandler(realModelName, c.Writer, c.Request, processGroup.ProxyRequest); err != nil {
+			pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error proxying metrics wrapped request: %s", err.Error()))
+			pm.proxyLogger.Errorf("Error Proxying Metrics Wrapped Request for processGroup %s and model %s", processGroup.id, realModelName)
+			return
+		}
+	} else {
+		if err := processGroup.ProxyRequest(realModelName, c.Writer, c.Request); err != nil {
+			pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error proxying request: %s", err.Error()))
+			pm.proxyLogger.Errorf("Error Proxying Request for processGroup %s and model %s", processGroup.id, realModelName)
+			return
+		}
 	}
 }

@@ -698,3 +779,11 @@ func (pm *ProxyManager) findGroupByModelName(modelName string) *ProcessGroup {
 	}
 	return nil
 }
+
+func (pm *ProxyManager) SetVersion(buildDate string, commit string, version string) {
+	pm.Lock()
+	defer pm.Unlock()
+	pm.buildDate = buildDate
+	pm.commit = commit
+	pm.version = version
+}
@@ -28,6 +28,7 @@ func addApiHandlers(pm *ProxyManager) {
 		apiGroup.POST("/models/unload/*model", pm.apiUnloadSingleModelHandler)
 		apiGroup.GET("/events", pm.apiSendEvents)
 		apiGroup.GET("/metrics", pm.apiGetMetrics)
+		apiGroup.GET("/version", pm.apiGetVersion)
 	}
 }

@@ -180,7 +181,7 @@ func (pm *ProxyManager) apiSendEvents(c *gin.Context) {
 	sendLogData("proxy", pm.proxyLogger.GetHistory())
 	sendLogData("upstream", pm.upstreamLogger.GetHistory())
 	sendModels()
-	sendMetrics(pm.metricsMonitor.GetMetrics())
+	sendMetrics(pm.metricsMonitor.getMetrics())

 	for {
 		select {
@@ -198,7 +199,7 @@ func (pm *ProxyManager) apiSendEvents(c *gin.Context) {
 }

 func (pm *ProxyManager) apiGetMetrics(c *gin.Context) {
-	jsonData, err := pm.metricsMonitor.GetMetricsJSON()
+	jsonData, err := pm.metricsMonitor.getMetricsJSON()
 	if err != nil {
 		c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to get metrics"})
 		return
@@ -227,3 +228,11 @@ func (pm *ProxyManager) apiUnloadSingleModelHandler(c *gin.Context) {
 		c.String(http.StatusOK, "OK")
 	}
 }
+
+func (pm *ProxyManager) apiGetVersion(c *gin.Context) {
+	c.JSON(http.StatusOK, map[string]string{
+		"version":    pm.version,
+		"commit":     pm.commit,
+		"build_date": pm.buildDate,
+	})
+}
@@ -437,6 +437,70 @@ func TestProxyManager_ListModelsHandler_SortedByID(t *testing.T) {
 	}
 }

+func TestProxyManager_ListModelsHandler_IncludeAliasesInList(t *testing.T) {
+	// Configure alias
+	config := config.Config{
+		HealthCheckTimeout:   15,
+		IncludeAliasesInList: true,
+		Models: map[string]config.ModelConfig{
+			"model1": func() config.ModelConfig {
+				mc := getTestSimpleResponderConfig("model1")
+				mc.Name = "Model 1"
+				mc.Aliases = []string{"alias1"}
+				return mc
+			}(),
+		},
+		LogLevel: "error",
+	}
+
+	proxy := New(config)
+
+	// Request models list
+	req := httptest.NewRequest("GET", "/v1/models", nil)
+	w := CreateTestResponseRecorder()
+	proxy.ServeHTTP(w, req)
+
+	assert.Equal(t, http.StatusOK, w.Code)
+
+	var response struct {
+		Data []map[string]interface{} `json:"data"`
+	}
+	if err := json.Unmarshal(w.Body.Bytes(), &response); err != nil {
+		t.Fatalf("Failed to parse JSON response: %v", err)
+	}
+
+	// We expect both base id and alias
+	var model1Data, alias1Data map[string]any
+	for _, model := range response.Data {
+		if model["id"] == "model1" {
+			model1Data = model
+		} else if model["id"] == "alias1" {
+			alias1Data = model
+		}
+	}
+
+	// Verify model1 has name
+	assert.NotNil(t, model1Data)
+	_, exists := model1Data["name"]
+	if !assert.True(t, exists, "model1 should have name key") {
+		t.FailNow()
+	}
+	name1, ok := model1Data["name"].(string)
+	assert.True(t, ok, "name1 should be a string")
+
+	// Verify alias1 has name
+	assert.NotNil(t, alias1Data)
+	_, exists = alias1Data["name"]
+	if !assert.True(t, exists, "alias1 should have name key") {
+		t.FailNow()
+	}
+	name2, ok := alias1Data["name"].(string)
+	assert.True(t, ok, "name2 should be a string")
+
+	// Name keys should match
+	assert.Equal(t, name1, name2)
+}
+
 func TestProxyManager_Shutdown(t *testing.T) {
 	// make broken model configurations
 	model1Config := getTestSimpleResponderConfigPort("model1", 9991)
@@ -911,76 +975,6 @@ func TestProxyManager_FiltersStripParams(t *testing.T) {
 	// t.Logf("%v", response)
 }

-func TestProxyManager_MiddlewareWritesMetrics_NonStreaming(t *testing.T) {
-	config := config.AddDefaultGroupToConfig(config.Config{
-		HealthCheckTimeout: 15,
-		Models: map[string]config.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 := CreateTestResponseRecorder()
-
-	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 := config.AddDefaultGroupToConfig(config.Config{
-		HealthCheckTimeout: 15,
-		Models: map[string]config.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 := CreateTestResponseRecorder()
-
-	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 := config.AddDefaultGroupToConfig(config.Config{
 		HealthCheckTimeout: 15,
@@ -1153,3 +1147,41 @@ func TestProxyManager_ProxiedStreamingEndpointReturnsNoBufferingHeader(t *testin
 	assert.Equal(t, "no", rec.Header().Get("X-Accel-Buffering"))
 	assert.Contains(t, rec.Header().Get("Content-Type"), "text/event-stream")
 }
+
+func TestProxyManager_ApiGetVersion(t *testing.T) {
+	config := config.AddDefaultGroupToConfig(config.Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]config.ModelConfig{
+			"model1": getTestSimpleResponderConfig("model1"),
+		},
+		LogLevel: "error",
+	})
+
+	// Version test map
+	versionTest := map[string]string{
+		"build_date": "1970-01-01T00:00:00Z",
+		"commit":     "cc915ddb6f04a42d9cd1f524e1d46ec6ed069fdc",
+		"version":    "v001",
+	}
+
+	proxy := New(config)
+	proxy.SetVersion(versionTest["build_date"], versionTest["commit"], versionTest["version"])
+	defer proxy.StopProcesses(StopWaitForInflightRequest)
+
+	req := httptest.NewRequest("GET", "/api/version", nil)
+	w := CreateTestResponseRecorder()
+
+	proxy.ServeHTTP(w, req)
+
+	assert.Equal(t, http.StatusOK, w.Code)
+
+	// Ensure json response
+	assert.Equal(t, "application/json; charset=utf-8", w.Header().Get("Content-Type"))
+
+	// Check for attributes
+	response := map[string]string{}
+	assert.NoError(t, json.Unmarshal(w.Body.Bytes(), &response))
+	for key, value := range versionTest {
+		assert.Equal(t, value, response[key], "%s value %s should match response %s", key, value, response[key])
+	}
+}
@@ -2,7 +2,7 @@ import { useAPI } from "../contexts/APIProvider";
 import { useMemo } from "react";

 const ConnectionStatusIcon = () => {
-  const { connectionStatus } = useAPI();
+  const { connectionStatus, versionInfo } = useAPI();

  const eventStatusColor = useMemo(() => {
    switch (connectionStatus) {
@@ -17,7 +17,7 @@ const ConnectionStatusIcon = () => {
  }, [connectionStatus]);

  return (
-    <div className="flex items-center" title={`event stream: ${connectionStatus}`}>
+    <div className="flex items-center" title={`Event Stream: ${connectionStatus ?? 'unknown'}\nAPI Version: ${versionInfo?.version ?? 'unknown'}\nCommit Hash: ${versionInfo?.commit?.substring(0,7) ?? 'unknown'}\nBuild Date: ${versionInfo?.build_date ?? 'unknown'}`}>
      <span className={`inline-block w-3 h-3 rounded-full ${eventStatusColor} mr-2`}></span>
    </div>
  );
@@ -23,6 +23,7 @@ interface APIProviderType {
  upstreamLogs: string;
  metrics: Metrics[];
  connectionStatus: ConnectionState;
+  versionInfo: VersionInfo;
 }

 interface Metrics {
@@ -41,11 +42,18 @@ interface LogData {
  source: "upstream" | "proxy";
  data: string;
 }
+
 interface APIEventEnvelope {
  type: "modelStatus" | "logData" | "metrics";
  data: string;
 }

+interface VersionInfo {
+  build_date: string;
+  commit: string;
+  version: string;
+}
+
 const APIContext = createContext<APIProviderType | undefined>(undefined);
 type APIProviderProps = {
  children: ReactNode;
@@ -59,6 +67,11 @@ export function APIProvider({ children, autoStartAPIEvents = true }: APIProvider
  const [upstreamLogs, setUpstreamLogs] = useState("");
  const [metrics, setMetrics] = useState<Metrics[]>([]);
  const [connectionStatus, setConnectionState] = useState<ConnectionState>("disconnected");
+  const [versionInfo, setVersionInfo] = useState<VersionInfo>({
+    build_date: "unknown",
+    commit: "unknown",
+    version: "unknown"
+  });
  //const apiEventSource = useRef<EventSource | null>(null);

  const [models, setModels] = useState<Model[]>([]);
@@ -152,6 +165,26 @@ export function APIProvider({ children, autoStartAPIEvents = true }: APIProvider
    connect();
  }, []);

+  useEffect(() => {
+    // fetch version 
+    const fetchVersion = async () => {
+      try {
+        const response = await fetch("/api/version");
+        if (!response.ok) {
+          throw new Error(`HTTP error! status: ${response.status}`);
+        }
+        const data: VersionInfo = await response.json();
+        setVersionInfo(data);
+      } catch (error) {
+        console.error(error);
+      }
+    };
+
+    if (connectionStatus === 'connected') {
+      fetchVersion();
+    }
+  }, [connectionStatus]);
+
  useEffect(() => {
    if (autoStartAPIEvents) {
      enableAPIEvents(true);
@@ -230,8 +263,9 @@ export function APIProvider({ children, autoStartAPIEvents = true }: APIProvider
      upstreamLogs,
      metrics,
      connectionStatus,
+      versionInfo,
    }),
-    [models, listModels, unloadAllModels, loadModel, enableAPIEvents, proxyLogs, upstreamLogs, metrics]
+    [models, listModels, unloadAllModels, unloadSingleModel, loadModel, enableAPIEvents, proxyLogs, upstreamLogs, metrics, connectionStatus, versionInfo]
  );

  return <APIContext.Provider value={value}>{children}</APIContext.Provider>;
Author	SHA1	Message	Date
Ryan Steed	b1dec8b735	docker: build both root and non-root container images (#412 ) Change the user back to root for containers. Additionally, built a "non-root" labeled container for users who wish to have the additional security of running llama-swap as a lower privileged user.	2025-11-25 10:44:13 -08:00
Nikesh Parajuli	06523d8c1e	feat: add platform-specific process attributes support (#411 ) Fixes issues on Windows showing new windows for every process llama-swap spawns.	2025-11-24 21:39:56 -08:00
Ryan Steed	86e9b93c37	proxy,ui: add version endpoint and display version info in UI (#395 ) - Add /api/version endpoint to ProxyManager that returns build date, commit hash, and version - Implement SetVersion method to configure version info in ProxyManager - Add version info fetching to APIProvider and display in ConnectionStatus component - Include version info in UI context and update dependencies - Add tests for version endpoint functionality	2025-11-17 10:43:47 -08:00
Ryan Steed	3acace810f	proxy: add configurable logging timestamp format (#401 ) introduces a new configuration option logTimeFormat that allows customizing the timestamp in log messages using golang's built in time format constants. The default remains no timestamp.	2025-11-16 10:21:59 -08:00
Ryan Steed	554d29e87d	feat: enhance model listing to include aliases (#400 ) introduce includeAliasesInList as a new configuration setting (default false) that includes aliases in v1/models Fixes #399	2025-11-15 14:35:26 -08:00
Benson Wong	3567b7df08	Update image in README.md for web UI section	2025-11-08 15:29:37 -08:00
Benson Wong	38738525c9	config.example.yaml: add modeline for schema validation	2025-11-08 15:08:55 -08:00
Benson Wong	c0fc858193	Add configuration file JSON schema (#393 ) * add json schema for configuration * add GH action to validate schema	2025-11-08 15:04:14 -08:00
Benson Wong	b429349e8a	add /ui/ to wol-proxy polling (#388 )	2025-11-08 14:16:12 -08:00
Ryan Steed	eab2efd7b5	feat: improve llama.cpp base image tag for cpu (#391 ) Refactor the container build script to resolve llama.cpp base image for CPU, also tag these builds accordingly. - For CPU containers, now fetch the latest 'server' tagged llama.cpp image instead of using a generic 'server' tag - Cleans up the docker build command to use dynamic BASE_TAG variable - Maintains existing push functionality for built images	2025-11-08 09:56:49 -08:00
Benson Wong	6aedbe121a	cmd/wol-proxy: show a loading page for / (#381 ) When requesting / wol-proxy will show a loading page that polls /status every second. When the upstream server is ready the loading page will refresh causing the actual root page to be displayed	2025-11-03 19:37:06 -08:00
Ryan Steed	b24467ab89	fix: update containerfile user/group management commands (#379 ) - Replace `addgroup` with `groupadd` for system group creation - Replace `adduser` with `useradd` for system user creation - Maintain same functionality while using more standard POSIX commands	2025-11-03 17:17:40 -05:00
Benson Wong	12b69fb718	proxy: recover from panic in Process.statusUpdate (#378 ) Process.statusUpdate() panics when it can not write data, usually from a client disconnect. Since it runs in a goroutine and did not have a recover() the result was a crash. ref: https://github.com/mostlygeek/llama-swap/discussions/326#discussioncomment-14856197	2025-11-03 05:30:09 -08:00
Ryan Steed	f91a8b2462	refactor: update Containerfile to support non-root user execution and improve security (#368 ) Set default container user/group to lower privilege app user * refactor: update Containerfile to support non-root user execution and improve security - Updated LS_VER argument from 89 to 170 to use the latest version - Added UID/GID arguments with default values of 0 (root) for backward compatibility - Added USER_HOME environment variable set to /root - Implemented conditional user/group creation logic that only runs when UID/GID are not 0 - Created necessary directory structure with proper ownership using mkdir and chown commands - Switched to non-root user execution for improved security posture - Updated COPY instruction to use --chown flag for proper file ownership * chore: update containerfile to use non-root user with proper UID/GID - Changed default UID and GID from 0 (root) to 10001 for security best practices - Updated USER_HOME from /root to /app to avoid running as root user	2025-10-31 17:01:04 -07:00
Benson Wong	a89b803d4a	Stream loading state when swapping models (#371 ) Swapping models can take a long time and leave a lot of silence while the model is loading. Rather than silently load the model in the background, this PR allows llama-swap to send status updates in the reasoning_content of a streaming chat response. Fixes: #366	2025-10-29 00:09:39 -07:00
Benson Wong	f852689104	proxy: add panic recovery to Process.ProxyRequest (#363 ) Switching to use httputil.ReverseProxy in #342 introduced a possible panic if a client disconnects while streaming the body. Since llama-swap does not use http.Server the recover() is not automatically there. - introduce a recover() in Process.ProxyRequest to recover and log the event - add TestProcess_ReverseProxyPanicIsHandled to reproduce and test the fix fixes: #362	2025-10-25 20:40:05 -07:00
Benson Wong	e250e71e59	Include metrics from upstream chat requests (#361 ) * proxy: refactor metrics recording - remove metrics_middleware.go as this wrapper is no longer needed. This also eliminiates double body parsing for the modelID - move metrics parsing to be part of MetricsMonitor - refactor how metrics are recording in ProxyManager - add MetricsMonitor tests - improve mem efficiency of processStreamingResponse - add benchmarks for MetricsMonitor.addMetrics - proxy: refactor MetricsMonitor to be more safe handling errors	2025-10-25 17:38:18 -07:00
Benson Wong	d18dc26d01	cmd/wol-proxy: tweak logs to show what is causing wake ups (#356 ) fix the extra wake ups being caused by wol-proxy * cmd/wol-proxy: tweak logs to show what is causing wake ups * cmd/wol-proxy: add skip wakeup * cmd/wol-proxy: replace ticker with SSE connection * cmd/wol-proxy: increase scanner buffer size * cmd/wol-proxy: improve failure tracking	2025-10-25 11:04:31 -07:00