Add a concurrency limit to Process.ProxyRequest (#123)

introduce --watch-config command line option to reload ProxyManager when configuration changes.

.coderabbit.yaml

@@ -0,0 +1,15 @@
+# yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json
+language: "en-US"
+early_access: false
+reviews:
+  profile: "chill"
+  request_changes_workflow: false
+  high_level_summary: true
+  poem: false
+  review_status: true
+  collapse_walkthrough: false
+  auto_review:
+    enabled: true
+    drafts: false
+chat:
+  auto_reply: true

README.md

@@ -70,6 +70,14 @@ healthCheckTimeout: 60
 # Valid log levels: debug, info (default), warn, error
 logLevel: info
 
+# Automatic Port Values
+# use ${PORT} in model.cmd and model.proxy to use an automatic port number
+# when you use ${PORT} you can omit a custom model.proxy value, as it will
+# default to http://localhost:${PORT}
+
+# override the default port (5800) for automatic port values
+startPort: 10001
+
 # define valid model values and the upstream server start
 models:
   "llama":
@@ -83,6 +91,7 @@ models:
       - "CUDA_VISIBLE_DEVICES=0"
 
     # where to reach the server started by cmd, make sure the ports match
+    # can be omitted if you use an automatic ${PORT} in cmd
     proxy: http://127.0.0.1:8999
 
     # aliases names to use this model for
@@ -109,14 +118,14 @@ models:
   # but they can still be requested as normal
   "qwen-unlisted":
     unlisted: true
-    cmd: llama-server --port 9999 -m Llama-3.2-1B-Instruct-Q4_K_M.gguf -ngl 0
+    cmd: llama-server --port ${PORT} -m Llama-3.2-1B-Instruct-Q4_K_M.gguf -ngl 0
 
   # Docker Support (v26.1.4+ required!)
   "docker-llama":
-    proxy: "http://127.0.0.1:9790"
+    proxy: "http://127.0.0.1:${PORT}"
     cmd: >
       docker run --name dockertest
-      --init --rm -p 9790:8080 -v /mnt/nvme/models:/models
+      --init --rm -p ${PORT}:8080 -v /mnt/nvme/models:/models
       ghcr.io/ggerganov/llama.cpp:server
       --model '/models/Qwen2.5-Coder-0.5B-Instruct-Q4_K_M.gguf'
 
@@ -180,18 +189,13 @@ groups:
 - [Speculative Decoding](examples/speculative-decoding/README.md) - using a small draft model can increase inference speeds from 20% to 40%. This example includes a configurations Qwen2.5-Coder-32B (2.5x increase) and Llama-3.1-70B (1.4x increase) in the best cases.
 - [Optimizing Code Generation](examples/benchmark-snakegame/README.md) - find the optimal settings for your machine. This example demonstrates defining multiple configurations and testing which one is fastest.
 - [Restart on Config Change](examples/restart-on-config-change/README.md) - automatically restart llama-swap when trying out different configurations.
-
-## Configuration
-
-llama-s
-
 </details>
 
 ## Docker Install ([download images](https://github.com/mostlygeek/llama-swap/pkgs/container/llama-swap))
 
 Docker is the quickest way to try out llama-swap:
 
-```
+```shell
 # use CPU inference
 $ docker run -it --rm -p 9292:8080 ghcr.io/mostlygeek/llama-swap:cpu
 
@@ -227,7 +231,7 @@ Specific versions are also available and are tagged with the llama-swap, archite
 
 Beyond the demo you will likely want to run the containers with your downloaded models and custom configuration.
 
-```
+```shell
 $ docker run -it --rm --runtime nvidia -p 9292:8080 \
   -v /path/to/models:/models \
   -v /path/to/custom/config.yaml:/app/config.yaml \
@@ -242,7 +246,12 @@ Pre-built binaries are available for Linux, FreeBSD and Darwin (OSX). These are
 
 1. Create a configuration file, see [config.example.yaml](config.example.yaml)
 1. Download a [release](https://github.com/mostlygeek/llama-swap/releases) appropriate for your OS and architecture.
-1. Run the binary with `llama-swap --config path/to/config.yaml`
+1. Run the binary with `llama-swap --config path/to/config.yaml`.
+  Available flags:
+    - `--config`: Path to the configuration file (default: `config.yaml`).
+    - `--listen`: Address and port to listen on (default: `:8080`).
+    - `--version`: Show version information and exit.
+    - `--watch-config`: Automatically reload the configuration file when it changes. This will wait for in-flight requests to complete then stop all running models (default: `false`).
 
 ### Building from source
 
@@ -257,7 +266,7 @@ Open the `http://<host>/logs` with your browser to get a web interface with stre
 
 Of course, CLI access is also supported:
 
-```
+```shell
 # sends up to the last 10KB of logs
 curl http://host/logs'
 

config.example.yaml

@@ -5,13 +5,20 @@ healthCheckTimeout: 90
 # valid log levels: debug, info (default), warn, error
 logLevel: debug
 
+# creating a coding profile with models for code generation and general questions
+groups:
+  coding:
+    swap: false
+    members:
+      - "qwen"
+      - "llama"
+
 models:
   "llama":
     cmd: >
       models/llama-server-osx
-      --port 9001
+      --port ${PORT}
       -m models/Llama-3.2-1B-Instruct-Q4_0.gguf
-    proxy: http://127.0.0.1:9001
 
     # list of model name aliases this llama.cpp instance can serve
     aliases:
@@ -24,17 +31,15 @@ models:
     ttl: 5
 
   "qwen":
-    cmd: models/llama-server-osx --port 9002 -m models/qwen2.5-0.5b-instruct-q8_0.gguf
+    cmd: models/llama-server-osx --port ${PORT} -m models/qwen2.5-0.5b-instruct-q8_0.gguf
-    proxy: http://127.0.0.1:9002
     aliases:
       - gpt-3.5-turbo
 
   # Embedding example with Nomic
   # https://huggingface.co/nomic-ai/nomic-embed-text-v1.5-GGUF
   "nomic":
-    proxy: http://127.0.0.1:9005
     cmd: >
-      models/llama-server-osx --port 9005
+      models/llama-server-osx --port ${PORT}
       -m models/nomic-embed-text-v1.5.Q8_0.gguf
       --ctx-size 8192
       --batch-size 8192
@@ -46,19 +51,17 @@ models:
   # Reranking example with bge-reranker
   # https://huggingface.co/gpustack/bge-reranker-v2-m3-GGUF
   "bge-reranker":
-    proxy: http://127.0.0.1:9006
     cmd: >
-      models/llama-server-osx --port 9006
+      models/llama-server-osx --port ${PORT}
       -m models/bge-reranker-v2-m3-Q4_K_M.gguf
       --ctx-size 8192
       --reranking
 
   # Docker Support (v26.1.4+ required!)
   "dockertest":
-    proxy: "http://127.0.0.1:9790"
     cmd: >
       docker run --name dockertest
-      --init --rm -p 9790:8080 -v /mnt/nvme/models:/models
+      --init --rm -p ${PORT}:8080 -v /mnt/nvme/models:/models
       ghcr.io/ggerganov/llama.cpp:server
       --model '/models/Qwen2.5-Coder-0.5B-Instruct-Q4_K_M.gguf'
 
@@ -67,8 +70,7 @@ models:
     env:
       - CUDA_VISIBLE_DEVICES=0,1
       - env1=hello
-    cmd: build/simple-responder --port 8999
+    cmd: build/simple-responder --port ${PORT}
-    proxy: http://127.0.0.1:8999
     unlisted: true
 
     # use "none" to skip check. Caution this may cause some requests to fail
@@ -84,9 +86,3 @@ models:
     cmd: models/llama-server-osx --port 8999 -m models/qwen2.5-0.5b-instruct-q8_0.gguf
     proxy: http://127.0.0.1:9000
     unlisted: true
-
-# creating a coding profile with models for code generation and general questions
-profiles:
-  coding:
-    - "qwen"
-    - "llama"

go.mod

@@ -3,6 +3,7 @@ module github.com/mostlygeek/llama-swap
 go 1.23.0
 
 require (
+	github.com/fsnotify/fsnotify v1.9.0
 	github.com/gin-gonic/gin v1.10.0
 	github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510
 	github.com/stretchr/testify v1.9.0

go.sum

@@ -9,12 +9,16 @@ github.com/cloudwego/iasm v0.2.0/go.mod h1:8rXZaNYT2n95jn+zTI1sDr+IgcD2GVs0nlbbQ
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/fsnotify/fsnotify v1.9.0 h1:2Ml+OJNzbYCTzsxtv8vKSFD9PbJjmhYF14k/jKC7S9k=
+github.com/fsnotify/fsnotify v1.9.0/go.mod h1:8jBTzvmWwFyi3Pb8djgCCO5IBqzKJ/Jwo8TRcHyHii0=
 github.com/gabriel-vasile/mimetype v1.4.3 h1:in2uUcidCuFcDKtdcBxlR0rJ1+fsokWf+uqxgUFjbI0=
 github.com/gabriel-vasile/mimetype v1.4.3/go.mod h1:d8uq/6HKRL6CGdk+aubisF/M5GcPfT7nKyLpA0lbSSk=
 github.com/gin-contrib/sse v0.1.0 h1:Y/yl/+YNO8GZSjAhjMsSuLt29uWRFHdHYUb5lYOV9qE=
 github.com/gin-contrib/sse v0.1.0/go.mod h1:RHrZQHXnP2xjPF+u1gW/2HnVO7nvIa9PG3Gm+fLHvGI=
 github.com/gin-gonic/gin v1.10.0 h1:nTuyha1TYqgedzytsKYqna+DfLos46nTv2ygFy86HFU=
 github.com/gin-gonic/gin v1.10.0/go.mod h1:4PMNQiOhvDRa013RKVbsiNwoyezlm2rm0uX/T7kzp5Y=
+github.com/go-playground/assert/v2 v2.2.0 h1:JvknZsQTYeFEAhQwI4qEt9cyV5ONwRHC+lYKSsYSR8s=
+github.com/go-playground/assert/v2 v2.2.0/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4=
 github.com/go-playground/locales v0.14.1 h1:EWaQ/wswjilfKLTECiXz7Rh+3BjFhfDFKv/oXslEjJA=
 github.com/go-playground/locales v0.14.1/go.mod h1:hxrqLVvrK65+Rwrd5Fc6F2O76J/NuW9t0sjnWqG1slY=
 github.com/go-playground/universal-translator v0.18.1 h1:Bcnm0ZwsGyWbCzImXv+pAJnYK9S473LQFuzCbDbfSFY=
@@ -23,6 +27,8 @@ github.com/go-playground/validator/v10 v10.20.0 h1:K9ISHbSaI0lyB2eWMPJo+kOS/FBEx
 github.com/go-playground/validator/v10 v10.20.0/go.mod h1:dbuPbCMFw/DrkbEynArYaCwl3amGuJotoKCe95atGMM=
 github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU=
 github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
+github.com/google/go-cmp v0.5.5 h1:Khx7svrCpmxxtHBq5j2mp/xVjsi8hQMfNLvJFAlrGgU=
+github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
 github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510 h1:El6M4kTTCOh6aBiKaUGG7oYTSPP8MxqL4YI3kZKwcP4=
 github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510/go.mod h1:pupxD2MaaD3pAXIBCelhxNneeOaAeabZDe5s4K6zSpQ=
@@ -74,34 +80,18 @@ github.com/ugorji/go/codec v1.2.12/go.mod h1:UNopzCgEMSXjBc6AOMqYvWC1ktqTAfzJZUZ
 golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8=
 golang.org/x/arch v0.8.0 h1:3wRIsP3pM4yUptoR96otTUOXI367OS0+c9eeRi9doIc=
 golang.org/x/arch v0.8.0/go.mod h1:FEVrYAQjsQXMVJ1nsMoVVXPZg6p2JE2mx8psSWTDQys=
-golang.org/x/crypto v0.23.0 h1:dIJU/v2J8Mdglj/8rJ6UUOM3Zc9zLZxVZwwxMooUSAI=
-golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8=
-golang.org/x/crypto v0.31.0 h1:ihbySMvVjLAeSH1IbfcRTkD/iNscyz8rGzjF/E5hV6U=
-golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=
 golang.org/x/crypto v0.36.0 h1:AnAEvhDddvBdpY+uR+MyHmuZzzNqXSe/GvuDeob5L34=
 golang.org/x/crypto v0.36.0/go.mod h1:Y4J0ReaxCR1IMaabaSMugxJES1EpwhBHhv2bDHklZvc=
-golang.org/x/net v0.25.0 h1:d/OCCoBEUq33pjydKrGQhw7IlUPI2Oylr+8qLx49kac=
-golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
-golang.org/x/net v0.33.0 h1:74SYHlV8BIgHIFC/LrYkOGIwL19eTYXQ5wc6TBuO36I=
-golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4=
-golang.org/x/net v0.37.0 h1:1zLorHbz+LYj7MQlSf1+2tPIIgibq2eL5xkrGk6f+2c=
-golang.org/x/net v0.37.0/go.mod h1:ivrbrMbzFq5J41QOQh0siUuly180yBYtLp+CKbEaFx8=
 golang.org/x/net v0.38.0 h1:vRMAPTMaeGqVhG5QyLJHqNDwecKTomGeqbnfZyKlBI8=
 golang.org/x/net v0.38.0/go.mod h1:ivrbrMbzFq5J41QOQh0siUuly180yBYtLp+CKbEaFx8=
 golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.20.0 h1:Od9JTbYCk261bKm4M/mw7AklTlFYIa0bIp9BgSm1S8Y=
-golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
-golang.org/x/sys v0.28.0 h1:Fksou7UEQUWlKvIdsqzJmUmCX3cZuD2+P3XyyzwMhlA=
-golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/sys v0.31.0 h1:ioabZlmFYtWhL+TRYpcnNlLwhyxaM9kWTDEmfnprqik=
 golang.org/x/sys v0.31.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
-golang.org/x/text v0.15.0 h1:h1V/4gjBv8v9cjcR6+AR5+/cIYK5N/WAgiv4xlsEtAk=
-golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
-golang.org/x/text v0.21.0 h1:zyQAAkrwaneQ066sspRyJaG9VNi/YJ1NfzcGB3hZ/qo=
-golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ=
 golang.org/x/text v0.23.0 h1:D71I7dUrlY+VX0gQShAThNGHFxZ13dGLBHQLVl1mJlY=
 golang.org/x/text v0.23.0/go.mod h1:/BLNzu4aZCJ1+kcD0DNRotWKage4q2rGVAg4o22unh4=
+golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543 h1:E7g+9GITq07hpfrRu66IVDexMakfv52eLZ2CXBWiKr4=
+golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 google.golang.org/protobuf v1.34.1 h1:9ddQBjfCyZPOHPUiPxpYESBLc+T8P3E+Vo4IbKZgFWg=
 google.golang.org/protobuf v1.34.1/go.mod h1:c6P6GXX6sHbq/GpV6MGZEdwhWPcYBgnhAHhKbcUYpos=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=

llama-swap.go

@@ -1,25 +1,34 @@
 package main
 
 import (
+	"context"
 	"flag"
 	"fmt"
+	"log"
+	"net/http"
 	"os"
 	"os/signal"
+	"path/filepath"
 	"syscall"
+	"time"
 
+	"github.com/fsnotify/fsnotify"
 	"github.com/gin-gonic/gin"
 	"github.com/mostlygeek/llama-swap/proxy"
 )
 
-var version string = "0"
+var (
-var commit string = "abcd1234"
+	version string = "0"
-var date = "unknown"
+	commit  string = "abcd1234"
+	date    string = "unknown"
+)
 
 func main() {
 	// Define a command-line flag for the port
 	configPath := flag.String("config", "config.yaml", "config file name")
 	listenStr := flag.String("listen", ":8080", "listen ip/port")
 	showVersion := flag.Bool("version", false, "show version of build")
+	watchConfig := flag.Bool("watch-config", false, "Automatically reload config file on change")
 
 	flag.Parse() // Parse the command-line flags
 
@@ -46,18 +55,135 @@ func main() {
 
 	proxyManager := proxy.New(config)
 
+	// Setup channels for server management
+	reloadChan := make(chan *proxy.ProxyManager)
+	exitChan := make(chan struct{})
 	sigChan := make(chan os.Signal, 1)
 	signal.Notify(sigChan, syscall.SIGINT, syscall.SIGTERM)
+
+	// Create server with initial handler
+	srv := &http.Server{
+		Addr:    *listenStr,
+		Handler: proxyManager,
+	}
+
+	// Start server
+	fmt.Printf("llama-swap listening on %s\n", *listenStr)
 	go func() {
-		<-sigChan
+		if err := srv.ListenAndServe(); err != nil && err != http.ErrServerClosed {
-		fmt.Println("Shutting down llama-swap")
+			fmt.Printf("Fatal server error: %v\n", err)
-		proxyManager.Shutdown()
+			close(exitChan)
-		os.Exit(0)
+		}
 	}()
 
-	fmt.Println("llama-swap listening on " + *listenStr)
+	// Handle config reloads and signals
-	if err := proxyManager.Run(*listenStr); err != nil {
+	go func() {
-		fmt.Printf("Server error: %v\n", err)
+		currentManager := proxyManager
-		os.Exit(1)
+		for {
+			select {
+			case newManager := <-reloadChan:
+				log.Println("Config change detected, waiting for in-flight requests to complete...")
+				// Stop old manager processes gracefully (this waits for in-flight requests)
+				currentManager.StopProcesses()
+				// Now do a full shutdown to clear the process map
+				currentManager.Shutdown()
+				currentManager = newManager
+				srv.Handler = newManager
+				log.Println("Server handler updated with new config")
+			case sig := <-sigChan:
+				fmt.Printf("Received signal %v, shutting down...\n", sig)
+				ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+				defer cancel()
+				currentManager.Shutdown()
+				if err := srv.Shutdown(ctx); err != nil {
+					fmt.Printf("Server shutdown error: %v\n", err)
+				}
+				close(exitChan)
+				return
+			}
+		}
+	}()
+
+	// Start file watcher if requested
+	if *watchConfig {
+		absConfigPath, err := filepath.Abs(*configPath)
+		if err != nil {
+			log.Printf("Error getting absolute path for config: %v. File watching disabled.", err)
+		} else {
+			go watchConfigFileWithReload(absConfigPath, reloadChan)
+		}
+	}
+
+	// Wait for exit signal
+	<-exitChan
+}
+
+// watchConfigFileWithReload monitors the configuration file and sends new ProxyManager instances through reloadChan.
+func watchConfigFileWithReload(configPath string, reloadChan chan<- *proxy.ProxyManager) {
+	watcher, err := fsnotify.NewWatcher()
+	if err != nil {
+		log.Printf("Error creating file watcher: %v. File watching disabled.", err)
+		return
+	}
+	defer watcher.Close()
+
+	err = watcher.Add(configPath)
+	if err != nil {
+		log.Printf("Error adding config path (%s) to watcher: %v. File watching disabled.", configPath, err)
+		return
+	}
+
+	log.Printf("Watching config file for changes: %s", configPath)
+
+	var debounceTimer *time.Timer
+	debounceDuration := 2 * time.Second
+
+	for {
+		select {
+		case event, ok := <-watcher.Events:
+			if !ok {
+				return
+			}
+			// We only care about writes to the specific config file
+			if event.Name == configPath && event.Has(fsnotify.Write) {
+				// Reset or start the debounce timer
+				if debounceTimer != nil {
+					debounceTimer.Stop()
+				}
+				debounceTimer = time.AfterFunc(debounceDuration, func() {
+					log.Printf("Config file modified: %s, reloading...", event.Name)
+
+					// Try up to 3 times with exponential backoff
+					var newConfig proxy.Config
+					var err error
+					for retries := 0; retries < 3; retries++ {
+						// Load new configuration
+						newConfig, err = proxy.LoadConfig(configPath)
+						if err == nil {
+							break
+						}
+						log.Printf("Error loading new config (attempt %d/3): %v", retries+1, err)
+						if retries < 2 {
+							time.Sleep(time.Duration(1<<retries) * time.Second)
+						}
+					}
+					if err != nil {
+						log.Printf("Failed to load new config after retries: %v", err)
+						return
+					}
+
+					// Create new ProxyManager with new config
+					newPM := proxy.New(newConfig)
+					reloadChan <- newPM
+					log.Println("Config reloaded successfully")
+				})
+			}
+		case err, ok := <-watcher.Errors:
+			if !ok {
+				log.Println("File watcher error channel closed.")
+				return
+			}
+			log.Printf("File watcher error: %v", err)
+		}
 	}
 }

misc/simple-responder/simple-responder.go

@@ -33,14 +33,17 @@ func main() {
 
 	// Set up the handler function using the provided response message
 	r.POST("/v1/chat/completions", func(c *gin.Context) {
-		c.Header("Content-Type", "text/plain")
+		c.Header("Content-Type", "application/json")
 
 		// add a wait to simulate a slow query
 		if wait, err := time.ParseDuration(c.Query("wait")); err == nil {
 			time.Sleep(wait)
 		}
 
-		c.String(200, *responseMessage)
+		c.JSON(http.StatusOK, gin.H{
+			"responseMessage":  *responseMessage,
+			"h_content_length": c.Request.Header.Get("Content-Length"),
+		})
 	})
 
 	// for issue #62 to check model name strips profile slug
@@ -63,8 +66,11 @@ func main() {
 	})
 
 	r.POST("/v1/completions", func(c *gin.Context) {
-		c.Header("Content-Type", "text/plain")
+		c.Header("Content-Type", "application/json")
-		c.String(200, *responseMessage)
+		c.JSON(http.StatusOK, gin.H{
+			"responseMessage": *responseMessage,
+		})
+
 	})
 
 	// issue #41
@@ -104,6 +110,10 @@ func main() {
 		c.JSON(http.StatusOK, gin.H{
 			"text":  fmt.Sprintf("The length of the file is %d bytes", fileSize),
 			"model": model,
+
+			// expose some header values for testing
+			"h_content_type":   c.GetHeader("Content-Type"),
+			"h_content_length": c.GetHeader("Content-Length"),
 		})
 	})
 

proxy/config.go

@@ -2,8 +2,10 @@ package proxy
 
 import (
 	"fmt"
+	"io"
 	"os"
 	"sort"
+	"strconv"
 	"strings"
 
 	"github.com/google/shlex"
@@ -21,6 +23,9 @@ type ModelConfig struct {
 	UnloadAfter   int      `yaml:"ttl"`
 	Unlisted      bool     `yaml:"unlisted"`
 	UseModelName  string   `yaml:"useModelName"`
+
+	// Limit concurrency of HTTP requests to process
+	ConcurrencyLimit int `yaml:"concurrencyLimit"`
 }
 
 func (m *ModelConfig) SanitizedCommand() ([]string, error) {
@@ -62,6 +67,9 @@ type Config struct {
 
 	// map aliases to actual model IDs
 	aliases map[string]string
+
+	// automatic port assignments
+	StartPort int `yaml:"startPort"`
 }
 
 func (c *Config) RealModelName(search string) (string, bool) {
@@ -83,7 +91,16 @@ func (c *Config) FindConfig(modelName string) (ModelConfig, string, bool) {
 }
 
 func LoadConfig(path string) (Config, error) {
-	data, err := os.ReadFile(path)
+	file, err := os.Open(path)
+	if err != nil {
+		return Config{}, err
+	}
+	defer file.Close()
+	return LoadConfigFromReader(file)
+}
+
+func LoadConfigFromReader(r io.Reader) (Config, error) {
+	data, err := io.ReadAll(r)
 	if err != nil {
 		return Config{}, err
 	}
@@ -98,14 +115,50 @@ func LoadConfig(path string) (Config, error) {
 		config.HealthCheckTimeout = 15
 	}
 
+	// set default port ranges
+	if config.StartPort == 0 {
+		// default to 5800
+		config.StartPort = 5800
+	} else if config.StartPort < 1 {
+		return Config{}, fmt.Errorf("startPort must be greater than 1")
+	}
+
 	// Populate the aliases map
 	config.aliases = make(map[string]string)
 	for modelName, modelConfig := range config.Models {
 		for _, alias := range modelConfig.Aliases {
+			if _, found := config.aliases[alias]; found {
+				return Config{}, fmt.Errorf("duplicate alias %s found in model: %s", alias, modelName)
+			}
 			config.aliases[alias] = modelName
 		}
 	}
 
+	// iterate over the models and replace any ${PORT} with the next available port
+	// Get and sort all model IDs first, makes testing more consistent
+	modelIds := make([]string, 0, len(config.Models))
+	for modelId := range config.Models {
+		modelIds = append(modelIds, modelId)
+	}
+	sort.Strings(modelIds) // This guarantees stable iteration order
+
+	// iterate over the sorted models
+	nextPort := config.StartPort
+	for _, modelId := range modelIds {
+		modelConfig := config.Models[modelId]
+		if strings.Contains(modelConfig.Cmd, "${PORT}") {
+			modelConfig.Cmd = strings.ReplaceAll(modelConfig.Cmd, "${PORT}", strconv.Itoa(nextPort))
+			if modelConfig.Proxy == "" {
+				modelConfig.Proxy = fmt.Sprintf("http://localhost:%d", nextPort)
+			} else {
+				modelConfig.Proxy = strings.ReplaceAll(modelConfig.Proxy, "${PORT}", strconv.Itoa(nextPort))
+			}
+			nextPort++
+			config.Models[modelId] = modelConfig
+		} else if modelConfig.Proxy == "" {
+			return Config{}, fmt.Errorf("model %s requires a proxy value when not using automatic ${PORT}", modelId)
+		}
+	}
 	config = AddDefaultGroupToConfig(config)
 	// check that members are all unique in the groups
 	memberUsage := make(map[string]string) // maps member to group it appears in

proxy/config_test.go

@@ -3,6 +3,7 @@ package proxy
 import (
 	"os"
 	"path/filepath"
+	"strings"
 	"testing"
 
 	"github.com/stretchr/testify/assert"
@@ -43,6 +44,7 @@ models:
     checkEndpoint: "/"
   model4:
     cmd: path/to/cmd --arg1 one
+    proxy: "http://localhost:8082"
     checkEndpoint: "/"
 
 healthCheckTimeout: 15
@@ -73,6 +75,7 @@ groups:
 	}
 
 	expected := Config{
+		StartPort: 5800,
 		Models: map[string]ModelConfig{
 			"model1": {
 				Cmd:           "path/to/cmd --arg1 one",
@@ -97,6 +100,7 @@ groups:
 			},
 			"model4": {
 				Cmd:           "path/to/cmd --arg1 one",
+				Proxy:         "http://localhost:8082",
 				CheckEndpoint: "/",
 			},
 		},
@@ -138,14 +142,6 @@ groups:
 }
 
 func TestConfig_GroupMemberIsUnique(t *testing.T) {
-	// Create a temporary YAML file for testing
-	tempDir, err := os.MkdirTemp("", "test-config")
-	if err != nil {
-		t.Fatalf("Failed to create temporary directory: %v", err)
-	}
-	defer os.RemoveAll(tempDir)
-
-	tempFile := filepath.Join(tempDir, "config.yaml")
 	content := `
 models:
   model1:
@@ -171,15 +167,35 @@ groups:
     exclusive: false
     members: ["model2"]
 `
-
-	if err := os.WriteFile(tempFile, []byte(content), 0644); err != nil {
-		t.Fatalf("Failed to write temporary file: %v", err)
-	}
-
 	// Load the config and verify
-	_, err = LoadConfig(tempFile)
+	_, err := LoadConfigFromReader(strings.NewReader(content))
-	assert.NotNil(t, err)
 
+	// a Contains as order of the map is not guaranteed
+	assert.Contains(t, err.Error(), "model member model2 is used in multiple groups:")
+}
+
+func TestConfig_ModelAliasesAreUnique(t *testing.T) {
+	content := `
+models:
+  model1:
+    cmd: path/to/cmd --arg1 one
+    proxy: "http://localhost:8080"
+    aliases:
+      - m1
+  model2:
+    cmd: path/to/cmd --arg1 one
+    proxy: "http://localhost:8081"
+    checkEndpoint: "/"
+    aliases:
+      - m1
+      - m2
+`
+	// Load the config and verify
+	_, err := LoadConfigFromReader(strings.NewReader(content))
+
+	// this is a contains because it could be `model1` or `model2` depending on the order
+	// go decided on the order of the map
+	assert.Contains(t, err.Error(), "duplicate alias m1 found in model: model")
 }
 
 func TestConfig_ModelConfigSanitizedCommand(t *testing.T) {
@@ -269,3 +285,77 @@ func TestConfig_SanitizeCommand(t *testing.T) {
 	assert.Error(t, err)
 	assert.Nil(t, args)
 }
+
+func TestConfig_AutomaticPortAssignments(t *testing.T) {
+
+	t.Run("Default Port Ranges", func(t *testing.T) {
+		content := ``
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		if !assert.NoError(t, err) {
+			t.Fatalf("Failed to load config: %v", err)
+		}
+
+		assert.Equal(t, 5800, config.StartPort)
+	})
+	t.Run("User specific port ranges", func(t *testing.T) {
+		content := `startPort: 1000`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		if !assert.NoError(t, err) {
+			t.Fatalf("Failed to load config: %v", err)
+		}
+
+		assert.Equal(t, 1000, config.StartPort)
+	})
+
+	t.Run("Invalid start port", func(t *testing.T) {
+		content := `startPort: abcd`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NotNil(t, err)
+	})
+
+	t.Run("start port must be greater than 1", func(t *testing.T) {
+		content := `startPort: -99`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NotNil(t, err)
+	})
+
+	t.Run("Automatic port assignments", func(t *testing.T) {
+		content := `
+startPort: 5800
+models:
+  model1:
+    cmd: svr --port ${PORT}
+  model2:
+    cmd: svr --port ${PORT}
+    proxy: "http://172.11.22.33:${PORT}"
+  model3:
+    cmd: svr --port 1999
+    proxy: "http://1.2.3.4:1999"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		if !assert.NoError(t, err) {
+			t.Fatalf("Failed to load config: %v", err)
+		}
+
+		assert.Equal(t, 5800, config.StartPort)
+		assert.Equal(t, "svr --port 5800", config.Models["model1"].Cmd)
+		assert.Equal(t, "http://localhost:5800", config.Models["model1"].Proxy)
+
+		assert.Equal(t, "svr --port 5801", config.Models["model2"].Cmd)
+		assert.Equal(t, "http://172.11.22.33:5801", config.Models["model2"].Proxy)
+
+		assert.Equal(t, "svr --port 1999", config.Models["model3"].Cmd)
+		assert.Equal(t, "http://1.2.3.4:1999", config.Models["model3"].Proxy)
+
+	})
+
+	t.Run("Proxy value required if no ${PORT} in cmd", func(t *testing.T) {
+		content := `
+models:
+  model1:
+    cmd: svr --port 111
+`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.Equal(t, "model model1 requires a proxy value when not using automatic ${PORT}", err.Error())
+	})
+}

proxy/process.go

@@ -8,6 +8,7 @@ import (
 	"net/http"
 	"net/url"
 	"os/exec"
+	"strconv"
 	"strings"
 	"sync"
 	"syscall"
@@ -56,10 +57,19 @@ type Process struct {
 	// for managing shutdown state
 	shutdownCtx    context.Context
 	shutdownCancel context.CancelFunc
+
+	// for managing concurrency limits
+	concurrencyLimitSemaphore chan struct{}
 }
 
 func NewProcess(ID string, healthCheckTimeout int, config ModelConfig, processLogger *LogMonitor, proxyLogger *LogMonitor) *Process {
 	ctx, cancel := context.WithCancel(context.Background())
+	concurrentLimit := 10
+	if config.ConcurrencyLimit > 0 {
+		concurrentLimit = config.ConcurrencyLimit
+	} else {
+		proxyLogger.Debugf("Concurrency limit for model %s not set, defaulting to 10", ID)
+	}
 	return &Process{
 		ID:                      ID,
 		config:                  config,
@@ -72,6 +82,9 @@ func NewProcess(ID string, healthCheckTimeout int, config ModelConfig, processLo
 		state:                   StateStopped,
 		shutdownCtx:             ctx,
 		shutdownCancel:          cancel,
+
+		// concurrency limit
+		concurrencyLimitSemaphore: make(chan struct{}, concurrentLimit),
 	}
 }
 
@@ -184,7 +197,7 @@ func (p *Process) start() error {
 		return fmt.Errorf("start() failed: %v", err)
 	}
 
-	// Capture the exit error for later signaling
+	// Capture the exit error for later signalling
 	go func() {
 		exitErr := p.cmd.Wait()
 		p.proxyLogger.Debugf("<%s> cmd.Wait() returned error: %v", p.ID, exitErr)
@@ -259,9 +272,9 @@ func (p *Process) start() error {
 					if strings.Contains(err.Error(), "connection refused") {
 						endTime, _ := checkDeadline.Deadline()
 						ttl := time.Until(endTime)
-						p.proxyLogger.Infof("<%s> Connection refused on %s, giving up in %.0fs", p.ID, healthURL, ttl.Seconds())
+						p.proxyLogger.Debugf("<%s> Connection refused on %s, giving up in %.0fs (normal during startup)", p.ID, healthURL, ttl.Seconds())
 					} else {
-						p.proxyLogger.Infof("<%s> Health check error on %s, %v", p.ID, healthURL, err)
+						p.proxyLogger.Debugf("<%s> Health check error on %s, %v (normal during startup)", p.ID, healthURL, err)
 					}
 				}
 			}
@@ -344,31 +357,33 @@ func (p *Process) stopCommand(sigtermTTL time.Duration) {
 	defer cancelTimeout()
 
 	if p.cmd == nil || p.cmd.Process == nil {
-		p.proxyLogger.Warnf("<%s> cmd or cmd.Process is nil", p.ID)
+		p.proxyLogger.Debugf("<%s> cmd or cmd.Process is nil (normal during config reload)", p.ID)
 		return
 	}
 
 	if err := p.terminateProcess(); err != nil {
-		p.proxyLogger.Infof("<%s> Failed to gracefully terminate process: %v", p.ID, err)
+		p.proxyLogger.Debugf("<%s> Process already terminated: %v (normal during shutdown)", p.ID, err)
 	}
 
 	select {
 	case <-sigtermTimeout.Done():
-		p.proxyLogger.Infof("<%s> Process timed out waiting to stop, sending KILL signal", p.ID)
+		p.proxyLogger.Debugf("<%s> Process timed out waiting to stop, sending KILL signal (normal during shutdown)", p.ID)
-		p.cmd.Process.Kill()
+		if err := p.cmd.Process.Kill(); err != nil {
+			p.proxyLogger.Errorf("<%s> Failed to kill process: %v", p.ID, err)
+		}
 	case err := <-p.cmdWaitChan:
 		// Note: in start(), p.cmdWaitChan also has a select { ... }. That should be OK
 		// because if we make it here then the cmd has been successfully running and made it
-		// through the health check. There is a possibility that ithe cmd crashed after the health check
+		// through the health check. There is a possibility that the cmd crashed after the health check
 		// succeeded but that's not a case llama-swap is handling for now.
 		if err != nil {
 			if errno, ok := err.(syscall.Errno); ok {
 				p.proxyLogger.Errorf("<%s> errno >> %v", p.ID, errno)
 			} else if exitError, ok := err.(*exec.ExitError); ok {
 				if strings.Contains(exitError.String(), "signal: terminated") {
-					p.proxyLogger.Infof("<%s> Process stopped OK", p.ID)
+					p.proxyLogger.Debugf("<%s> Process stopped OK", p.ID)
 				} else if strings.Contains(exitError.String(), "signal: interrupt") {
-					p.proxyLogger.Infof("<%s> Process interrupted OK", p.ID)
+					p.proxyLogger.Debugf("<%s> Process interrupted OK", p.ID)
 				} else {
 					p.proxyLogger.Warnf("<%s> ExitError >> %v, exit code: %d", p.ID, exitError, exitError.ExitCode())
 				}
@@ -414,6 +429,14 @@ func (p *Process) ProxyRequest(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 
+	select {
+	case p.concurrencyLimitSemaphore <- struct{}{}:
+		defer func() { <-p.concurrencyLimitSemaphore }()
+	default:
+		http.Error(w, "Too many requests", http.StatusTooManyRequests)
+		return
+	}
+
 	p.inFlightRequests.Add(1)
 	defer func() {
 		p.lastRequestHandled = time.Now()
@@ -439,6 +462,12 @@ func (p *Process) ProxyRequest(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 	req.Header = r.Header.Clone()
+
+	contentLength, err := strconv.ParseInt(req.Header.Get("content-length"), 10, 64)
+	if err == nil {
+		req.ContentLength = contentLength
+	}
+
 	resp, err := client.Do(req)
 	if err != nil {
 		http.Error(w, err.Error(), http.StatusBadGateway)

proxy/process_test.go

@@ -340,3 +340,35 @@ func TestProcess_ExitInterruptsHealthCheck(t *testing.T) {
 	assert.Equal(t, "upstream command exited prematurely but successfully", err.Error())
 	assert.Equal(t, process.CurrentState(), StateFailed)
 }
+
+func TestProcess_ConcurrencyLimit(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping long concurrency limit test")
+	}
+
+	expectedMessage := "concurrency_limit_test"
+	config := getTestSimpleResponderConfig(expectedMessage)
+
+	// only allow 1 concurrent request at a time
+	config.ConcurrencyLimit = 1
+
+	process := NewProcess("ttl_test", 2, config, debugLogger, debugLogger)
+	assert.Equal(t, 1, cap(process.concurrencyLimitSemaphore))
+	defer process.Stop()
+
+	// launch a goroutine first to take up the semaphore
+	go func() {
+		req1 := httptest.NewRequest("GET", "/slow-respond?echo=12345&delay=75ms", nil)
+		w := httptest.NewRecorder()
+		process.ProxyRequest(w, req1)
+		assert.Equal(t, http.StatusOK, w.Code)
+	}()
+
+	// let the goroutine start
+	<-time.After(time.Millisecond * 25)
+
+	denied := httptest.NewRequest("GET", "/test", nil)
+	w := httptest.NewRecorder()
+	process.ProxyRequest(w, denied)
+	assert.Equal(t, http.StatusTooManyRequests, w.Code)
+}

proxy/proxymanager.go

@@ -82,6 +82,11 @@ func New(config Config) *ProxyManager {
 		pm.processGroups[groupID] = processGroup
 	}
 
+	pm.setupGinEngine()
+	return pm
+}
+
+func (pm *ProxyManager) setupGinEngine() {
 	pm.ginEngine.Use(func(c *gin.Context) {
 		// Start timer
 		start := time.Now()
@@ -192,18 +197,17 @@ func New(config Config) *ProxyManager {
 
 	// Disable console color for testing
 	gin.DisableConsoleColor()
-
-	return pm
 }
 
-func (pm *ProxyManager) Run(addr ...string) error {
+// ServeHTTP implements http.Handler interface
-	return pm.ginEngine.Run(addr...)
+func (pm *ProxyManager) ServeHTTP(w http.ResponseWriter, r *http.Request) {
-}
-
-func (pm *ProxyManager) HandlerFunc(w http.ResponseWriter, r *http.Request) {
 	pm.ginEngine.ServeHTTP(w, r)
 }
 
+// StopProcesses acquires a lock and stops all running upstream processes.
+// This is the public method safe for concurrent calls.
+// Unlike Shutdown, this method only stops the processes but doesn't perform
+// a complete shutdown, allowing for process replacement without full termination.
 func (pm *ProxyManager) StopProcesses() {
 	pm.Lock()
 	defer pm.Unlock()
@@ -221,8 +225,7 @@ func (pm *ProxyManager) StopProcesses() {
 	wg.Wait()
 }
 
-// Shutdown is called to shutdown all upstream processes
+// Shutdown stops all processes managed by this ProxyManager
-// when llama-swap is shutting down.
 func (pm *ProxyManager) Shutdown() {
 	pm.Lock()
 	defer pm.Unlock()
@@ -305,6 +308,7 @@ func (pm *ProxyManager) proxyToUpstream(c *gin.Context) {
 	processGroup, _, err := pm.swapProcessGroup(requestedModel)
 	if err != nil {
 		pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error swapping process group: %s", err.Error()))
+		return
 	}
 
 	// rewrite the path
@@ -347,11 +351,13 @@ func (pm *ProxyManager) proxyOAIHandler(c *gin.Context) {
 	requestedModel := gjson.GetBytes(bodyBytes, "model").String()
 	if requestedModel == "" {
 		pm.sendErrorResponse(c, http.StatusBadRequest, "missing or invalid 'model' key")
+		return
 	}
 
 	processGroup, realModelName, err := pm.swapProcessGroup(requestedModel)
 	if err != nil {
 		pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error swapping process group: %s", err.Error()))
+		return
 	}
 
 	// issue #69 allow custom model names to be sent to upstream
@@ -373,15 +379,11 @@ func (pm *ProxyManager) proxyOAIHandler(c *gin.Context) {
 	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
 	}
 }
 
 func (pm *ProxyManager) proxyOAIPostFormHandler(c *gin.Context) {
-	// We need to reconstruct the multipart form in any case since the body is consumed
-	// Create a new buffer for the reconstructed request
-	var requestBuffer bytes.Buffer
-	multipartWriter := multipart.NewWriter(&requestBuffer)
-
 	// Parse multipart form
 	if err := c.Request.ParseMultipartForm(32 << 20); err != nil { // 32MB max memory, larger files go to tmp disk
 		pm.sendErrorResponse(c, http.StatusBadRequest, fmt.Sprintf("error parsing multipart form: %s", err.Error()))
@@ -398,8 +400,14 @@ func (pm *ProxyManager) proxyOAIPostFormHandler(c *gin.Context) {
 	processGroup, realModelName, err := pm.swapProcessGroup(requestedModel)
 	if err != nil {
 		pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error swapping process group: %s", err.Error()))
+		return
 	}
 
+	// We need to reconstruct the multipart form in any case since the body is consumed
+	// Create a new buffer for the reconstructed request
+	var requestBuffer bytes.Buffer
+	multipartWriter := multipart.NewWriter(&requestBuffer)
+
 	// Copy all form values
 	for key, values := range c.Request.MultipartForm.Value {
 		for _, value := range values {
@@ -473,10 +481,15 @@ func (pm *ProxyManager) proxyOAIPostFormHandler(c *gin.Context) {
 	modifiedReq.Header = c.Request.Header.Clone()
 	modifiedReq.Header.Set("Content-Type", multipartWriter.FormDataContentType())
 
+	// set the content length of the body
+	modifiedReq.Header.Set("Content-Length", strconv.Itoa(requestBuffer.Len()))
+	modifiedReq.ContentLength = int64(requestBuffer.Len())
+
 	// Use the modified request for proxying
 	if err := processGroup.ProxyRequest(realModelName, c.Writer, modifiedReq); 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
 	}
 }
 

proxy/proxymanager_test.go

@@ -8,6 +8,7 @@ import (
 	"mime/multipart"
 	"net/http"
 	"net/http/httptest"
+	"strconv"
 	"sync"
 	"testing"
 	"time"
@@ -33,7 +34,7 @@ func TestProxyManager_SwapProcessCorrectly(t *testing.T) {
 		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
 		w := httptest.NewRecorder()
 
-		proxy.HandlerFunc(w, req)
+		proxy.ServeHTTP(w, req)
 		assert.Equal(t, http.StatusOK, w.Code)
 		assert.Contains(t, w.Body.String(), modelName)
 	}
@@ -71,10 +72,9 @@ func TestProxyManager_SwapMultiProcess(t *testing.T) {
 			req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
 			w := httptest.NewRecorder()
 
-			proxy.HandlerFunc(w, req)
+			proxy.ServeHTTP(w, req)
 			assert.Equal(t, http.StatusOK, w.Code)
 			assert.Contains(t, w.Body.String(), requestedModel)
-
 		})
 	}
 
@@ -114,7 +114,7 @@ func TestProxyManager_PersistentGroupsAreNotSwapped(t *testing.T) {
 		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
 		w := httptest.NewRecorder()
 
-		proxy.HandlerFunc(w, req)
+		proxy.ServeHTTP(w, req)
 		assert.Equal(t, http.StatusOK, w.Code)
 		assert.Contains(t, w.Body.String(), requestedModel)
 	}
@@ -157,15 +157,16 @@ func TestProxyManager_SwapMultiProcessParallelRequests(t *testing.T) {
 			req := httptest.NewRequest("POST", "/v1/chat/completions?wait=1000ms", bytes.NewBufferString(reqBody))
 			w := httptest.NewRecorder()
 
-			proxy.HandlerFunc(w, req)
+			proxy.ServeHTTP(w, req)
 
 			if w.Code != http.StatusOK {
 				t.Errorf("Expected status OK, got %d for key %s", w.Code, key)
 			}
 
 			mu.Lock()
-
+			var response map[string]string
-			results[key] = w.Body.String()
+			assert.NoError(t, json.Unmarshal(w.Body.Bytes(), &response))
+			results[key] = response["responseMessage"]
 			mu.Unlock()
 		}(key)
 
@@ -199,7 +200,7 @@ func TestProxyManager_ListModelsHandler(t *testing.T) {
 	w := httptest.NewRecorder()
 
 	// Call the listModelsHandler
-	proxy.HandlerFunc(w, req)
+	proxy.ServeHTTP(w, req)
 
 	// Check the response status code
 	assert.Equal(t, http.StatusOK, w.Code)
@@ -289,7 +290,7 @@ func TestProxyManager_Shutdown(t *testing.T) {
 			w := httptest.NewRecorder()
 
 			// send a request to trigger the proxy to load ... this should hang waiting for start up
-			proxy.HandlerFunc(w, req)
+			proxy.ServeHTTP(w, req)
 			assert.Equal(t, http.StatusBadGateway, w.Code)
 			assert.Contains(t, w.Body.String(), "health check interrupted due to shutdown")
 		}(modelName)
@@ -315,12 +316,12 @@ func TestProxyManager_Unload(t *testing.T) {
 	reqBody := fmt.Sprintf(`{"model":"%s"}`, "model1")
 	req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
 	w := httptest.NewRecorder()
-	proxy.HandlerFunc(w, req)
+	proxy.ServeHTTP(w, req)
 
 	assert.Equal(t, proxy.processGroups[DEFAULT_GROUP_ID].processes["model1"].CurrentState(), StateReady)
 	req = httptest.NewRequest("GET", "/unload", nil)
 	w = httptest.NewRecorder()
-	proxy.HandlerFunc(w, req)
+	proxy.ServeHTTP(w, req)
 	assert.Equal(t, http.StatusOK, w.Code)
 	assert.Equal(t, w.Body.String(), "OK")
 
@@ -331,7 +332,6 @@ func TestProxyManager_Unload(t *testing.T) {
 
 // Test issue #61 `Listing the current list of models and the loaded model.`
 func TestProxyManager_RunningEndpoint(t *testing.T) {
-
 	// Shared configuration
 	config := AddDefaultGroupToConfig(Config{
 		HealthCheckTimeout: 15,
@@ -357,7 +357,7 @@ func TestProxyManager_RunningEndpoint(t *testing.T) {
 	t.Run("no models loaded", func(t *testing.T) {
 		req := httptest.NewRequest("GET", "/running", nil)
 		w := httptest.NewRecorder()
-		proxy.HandlerFunc(w, req)
+		proxy.ServeHTTP(w, req)
 
 		assert.Equal(t, http.StatusOK, w.Code)
 
@@ -375,13 +375,13 @@ func TestProxyManager_RunningEndpoint(t *testing.T) {
 		reqBody := `{"model":"model1"}`
 		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
 		w := httptest.NewRecorder()
-		proxy.HandlerFunc(w, req)
+		proxy.ServeHTTP(w, req)
 		assert.Equal(t, http.StatusOK, w.Code)
 
 		// Simulate browser call for the `/running` endpoint.
 		req = httptest.NewRequest("GET", "/running", nil)
 		w = httptest.NewRecorder()
-		proxy.HandlerFunc(w, req)
+		proxy.ServeHTTP(w, req)
 
 		var response RunningResponse
 		assert.NoError(t, json.Unmarshal(w.Body.Bytes(), &response))
@@ -433,7 +433,7 @@ func TestProxyManager_AudioTranscriptionHandler(t *testing.T) {
 	req := httptest.NewRequest("POST", "/v1/audio/transcriptions", &b)
 	req.Header.Set("Content-Type", w.FormDataContentType())
 	rec := httptest.NewRecorder()
-	proxy.HandlerFunc(rec, req)
+	proxy.ServeHTTP(rec, req)
 
 	// Verify the response
 	assert.Equal(t, http.StatusOK, rec.Code)
@@ -442,6 +442,7 @@ func TestProxyManager_AudioTranscriptionHandler(t *testing.T) {
 	assert.NoError(t, err)
 	assert.Equal(t, "TheExpectedModel", response["model"])
 	assert.Equal(t, response["text"], fmt.Sprintf("The length of the file is %d bytes", contentLength)) // matches simple-responder
+	assert.Equal(t, strconv.Itoa(370+contentLength), response["h_content_length"])
 }
 
 // Test useModelName in configuration sends overrides what is sent to upstream
@@ -469,7 +470,7 @@ func TestProxyManager_UseModelName(t *testing.T) {
 		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
 		w := httptest.NewRecorder()
 
-		proxy.HandlerFunc(w, req)
+		proxy.ServeHTTP(w, req)
 		assert.Equal(t, http.StatusOK, w.Code)
 		assert.Contains(t, w.Body.String(), upstreamModelName)
 	})
@@ -496,7 +497,7 @@ func TestProxyManager_UseModelName(t *testing.T) {
 		req := httptest.NewRequest("POST", "/v1/audio/transcriptions", &b)
 		req.Header.Set("Content-Type", w.FormDataContentType())
 		rec := httptest.NewRecorder()
-		proxy.HandlerFunc(rec, req)
+		proxy.ServeHTTP(rec, req)
 
 		// Verify the response
 		assert.Equal(t, http.StatusOK, rec.Code)
@@ -564,7 +565,7 @@ func TestProxyManager_CORSOptionsHandler(t *testing.T) {
 			}
 
 			w := httptest.NewRecorder()
-			proxy.ginEngine.ServeHTTP(w, req)
+			proxy.ServeHTTP(w, req)
 
 			assert.Equal(t, tt.expectedStatus, w.Code)
 
@@ -588,7 +589,31 @@ func TestProxyManager_Upstream(t *testing.T) {
 	defer proxy.StopProcesses()
 	req := httptest.NewRequest("GET", "/upstream/model1/test", nil)
 	rec := httptest.NewRecorder()
-	proxy.HandlerFunc(rec, req)
+	proxy.ServeHTTP(rec, req)
 	assert.Equal(t, http.StatusOK, rec.Code)
 	assert.Equal(t, "model1", rec.Body.String())
 }
+
+func TestProxyManager_ChatContentLength(t *testing.T) {
+	config := AddDefaultGroupToConfig(Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]ModelConfig{
+			"model1": getTestSimpleResponderConfig("model1"),
+		},
+		LogLevel: "error",
+	})
+
+	proxy := New(config)
+	defer proxy.StopProcesses()
+
+	reqBody := fmt.Sprintf(`{"model":"%s", "x": "this is just some content to push the length out a bit"}`, "model1")
+	req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+	w := httptest.NewRecorder()
+
+	proxy.ServeHTTP(w, req)
+	assert.Equal(t, http.StatusOK, w.Code)
+	var response map[string]string
+	assert.NoError(t, json.Unmarshal(w.Body.Bytes(), &response))
+	assert.Equal(t, "81", response["h_content_length"])
+	assert.Equal(t, "model1", response["responseMessage"])
+}