Update proxymanager.go (#135)

* Add windows specific test changes
* Change the command line parsing library - Possible breaking changes for windows users!

.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

.github/ISSUE_TEMPLATE/bug-report.md

@@ -0,0 +1,37 @@
+---
+name: Bug Report
+about: Something is not working as expected...
+title: ''
+labels: bug
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**Expected behaviour**
+A clear and concise description of what you expected to happen.
+
+**Operating system and version**
+
+- OS: (linux, osx, windows, freebsd, etc)
+- GPUs: (list architecture)
+
+**My Configuration**
+
+```yaml
+# copy / paste your configuration here
+```
+
+**Proxy Logs**
+
+```
+# copy / paste from /logs
+```
+
+**Upstream Logs**
+
+```
+# copy/paste from /logs
+```

.github/workflows/closeinactive.yml

@@ -13,11 +13,11 @@ jobs:
     steps:
       - uses: actions/stale@v9
         with:
-          days-before-issue-stale: 30
+          days-before-issue-stale: 14
           days-before-issue-close: 14
           stale-issue-label: "stale"
-          stale-issue-message: "This issue is stale because it has been open for 30 days with no activity."
-          close-issue-message: "This issue was closed because it has been inactive for 14 days since being marked as stale."
+          stale-issue-message: "This issue is stale because it has been open for 2 weeks with no activity."
+          close-issue-message: "This issue was closed because it has been inactive for 2 weeks since being marked as stale."
           days-before-pr-stale: -1
           days-before-pr-close: -1
-          repo-token: ${{ secrets.GITHUB_TOKEN }}
+          repo-token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/go-ci-windows.yml

@@ -0,0 +1,50 @@
+name: Windows CI
+
+on:
+  push:
+    branches: [ "main" ]
+
+  pull_request:
+    branches: [ "main" ]
+
+  # Allows manual triggering of the workflow
+  workflow_dispatch:
+
+jobs:
+
+  run-tests:
+    runs-on: windows-latest
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Set up Go
+      uses: actions/setup-go@v4
+      with:
+        go-version: '1.23'
+
+    # cache simple-responder to save the build time
+    - name: Restore Simple Responder
+      id: restore-simple-responder
+      uses: actions/cache/restore@v4
+      with:
+        path: ./build
+        key: ${{ runner.os }}-simple-responder-${{ hashFiles('misc/simple-responder/simple-responder.go') }}
+
+    # necessary for testing proxy/Process swapping
+    - name: Create simple-responder
+      if: steps.restore-simple-responder.outputs.cache-hit != 'true'
+      shell: bash
+      run: make simple-responder-windows
+
+    - name: Save Simple Responder
+      # nothing new to save ... skip this step
+      if: steps.restore-simple-responder.outputs.cache-hit != 'true'
+      id: save-simple-responder
+      uses: actions/cache/save@v4
+      with:
+        path: ./build
+        key: ${{ runner.os }}-simple-responder-${{ hashFiles('misc/simple-responder/simple-responder.go') }}
+
+    - name: Test all
+      shell: bash
+      run: make test-all

.github/workflows/go-ci.yml

@@ -1,6 +1,4 @@
-# This workflow will build a golang project
-
-name: CI
+name: Linux CI
 
 on:
   push:
@@ -24,9 +22,26 @@ jobs:
       with:
         go-version: '1.23'
 
+    # cache simple-responder to save the build time
+    - name: Restore Simple Responder
+      id: restore-simple-responder
+      uses: actions/cache/restore@v4
+      with:
+        path: ./build
+        key: ${{ runner.os }}-simple-responder-${{ hashFiles('misc/simple-responder/simple-responder.go') }}
+
     # necessary for testing proxy/Process swapping
     - name: Create simple-responder
       run: make simple-responder
 
+    - name: Save Simple Responder
+      # nothing new to save ... skip this step
+      if: steps.restore-simple-responder.outputs.cache-hit != 'true'
+      id: save-simple-responder
+      uses: actions/cache/save@v4
+      with:
+        path: ./build
+        key: ${{ runner.os }}-simple-responder-${{ hashFiles('misc/simple-responder/simple-responder.go') }}
+
     - name: Test all
       run: make test-all

Makefile

@@ -20,10 +20,10 @@ clean:
 	rm -rf $(BUILD_DIR)
 
 test:
-	go test -short -v ./proxy
+	go test -short -v -count=1 ./proxy
 
 test-all:
-	go test -v ./proxy
+	go test -v -count=1 ./proxy
 
 # Build OSX binary
 mac:
@@ -46,6 +46,10 @@ simple-responder:
 	GOOS=darwin GOARCH=arm64 go build -o $(BUILD_DIR)/simple-responder_darwin_arm64 misc/simple-responder/simple-responder.go
 	GOOS=linux GOARCH=amd64 go build -o $(BUILD_DIR)/simple-responder_linux_amd64 misc/simple-responder/simple-responder.go
 
+simple-responder-windows:
+	@echo "Building simple responder for windows"
+	GOOS=windows GOARCH=amd64 go build -o $(BUILD_DIR)/simple-responder.exe misc/simple-responder/simple-responder.go
+
 # Ensure build directory exists
 $(BUILD_DIR):
 	mkdir -p $(BUILD_DIR)

README.md

@@ -26,7 +26,7 @@ Written in golang, it is very easy to install (single binary with no dependancie
   - `/upstream/:model_id` - direct access to upstream HTTP server ([demo](https://github.com/mostlygeek/llama-swap/pull/31))
   - `/unload` - manually unload running models ([#58](https://github.com/mostlygeek/llama-swap/issues/58))
   - `/running` - list currently running models ([#61](https://github.com/mostlygeek/llama-swap/issues/61))
-- ✅ Run multiple models at once with `profiles` ([docs](https://github.com/mostlygeek/llama-swap/issues/53#issuecomment-2660761741))
+- ✅ Run multiple models at once with `Groups` ([#107](https://github.com/mostlygeek/llama-swap/issues/107))
 - ✅ Automatic unloading of models after timeout by setting a `ttl`
 - ✅ Use any local OpenAI compatible server (llama.cpp, vllm, tabbyAPI, etc)
 - ✅ Docker and Podman support
@@ -36,7 +36,7 @@ Written in golang, it is very easy to install (single binary with no dependancie
 
 When a request is made to an OpenAI compatible endpoint, lama-swap will extract the `model` value and load the appropriate server configuration to serve it. If the wrong upstream server is running, it will be replaced with the correct one. This is where the "swap" part comes in. The upstream server is automatically swapped to the correct one to serve the request.
 
-In the most basic configuration llama-swap handles one model at a time. For more advanced use cases, the `profiles` feature can load multiple models at the same time. You have complete control over how your system resources are used.
+In the most basic configuration llama-swap handles one model at a time. For more advanced use cases, the `groups` feature allows multiple models to be loaded at the same time. You have complete control over how your system resources are used.
 
 ## config.yaml
 
@@ -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
@@ -109,27 +118,69 @@ 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'
 
-# profiles eliminates swapping by running multiple models at the same time
+# Groups provide advanced controls over model swapping behaviour. Using groups
+# some models can be kept loaded indefinitely, while others are swapped out.
 #
 # Tips:
-#  - each model must be listening on a unique address and port
-#  - the model name is in this format: "profile_name:model", like "coding:qwen"
-#  - the profile will load and unload all models in the profile at the same time
-profiles:
-  coding:
-    - "llama"
-    - "qwen-unlisted"
+#
+#  - models must be defined above in the Models section
+#  - a model can only be a member of one group
+#  - group behaviour is controlled via the `swap`, `exclusive` and `persistent` fields
+#  - see issue #109 for details
+#
+# NOTE: the example below uses model names that are not defined above for demonstration purposes
+groups:
+  # group1 is the default behaviour of llama-swap where only one model is allowed
+  # to run a time across the whole llama-swap instance
+  "group1":
+    # swap controls the model swapping behaviour in within the group
+    # - true : only one model is allowed to run at a time
+    # - false: all models can run together, no swapping
+    swap: true
+
+    # exclusive controls how the group affects other groups
+    # - true: causes all other groups to unload their models when this group runs a model
+    # - false: does not affect other groups
+    exclusive: true
+
+    # members references the models defined above
+    members:
+      - "llama"
+      - "qwen-unlisted"
+
+  # models in this group are never unloaded
+  "group2":
+    swap: false
+    exclusive: false
+    members:
+      - "docker-llama"
+      # (not defined above, here for example)
+      - "modelA"
+      - "modelB"
+
+  "forever":
+    # setting persistent to true causes the group to never be affected by the swapping behaviour of
+    # other groups. It is a shortcut to keeping some models always loaded.
+    persistent: true
+
+    # set swap/exclusive to false to prevent swapping inside the group and effect on other groups
+    swap: false
+    exclusive: false
+    members:
+      - "forever-modelA"
+      - "forever-modelB"
+      - "forever-modelc"
 ```
 
 ### Use Case Examples
@@ -138,18 +189,13 @@ profiles:
 - [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
 
@@ -185,7 +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 \
@@ -200,7 +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
 
@@ -215,7 +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
-    proxy: http://127.0.0.1:9002
+    cmd: models/llama-server-osx --port ${PORT} -m models/qwen2.5-0.5b-instruct-q8_0.gguf
     aliases:
-    - gpt-3.5-turbo
+      - 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
-    proxy: http://127.0.0.1:8999
+    cmd: build/simple-responder --port ${PORT}
     unlisted: true
 
     # use "none" to skip check. Caution this may cause some requests to fail
@@ -83,10 +85,4 @@ models:
   "broken_timeout":
     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"
+    unlisted: true

go.mod

@@ -3,8 +3,8 @@ 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
 	github.com/tidwall/gjson v1.18.0
 	github.com/tidwall/sjson v1.2.5
@@ -12,6 +12,7 @@ require (
 )
 
 require (
+	github.com/billziss-gh/golib v0.2.0 // indirect
 	github.com/bytedance/sonic v1.11.6 // indirect
 	github.com/bytedance/sonic/loader v0.1.1 // indirect
 	github.com/cloudwego/base64x v0.1.4 // indirect

go.sum

@@ -1,3 +1,5 @@
+github.com/billziss-gh/golib v0.2.0 h1:NyvcAQdfvM8xokKkKotiligKjKXzuQD4PPykg1nKc/8=
+github.com/billziss-gh/golib v0.2.0/go.mod h1:mZpUYANXZkDKSnyYbX9gfnyxwe0ddRhUtfXcsD5r8dw=
 github.com/bytedance/sonic v1.11.6 h1:oUp34TzMlL+OY1OUWxHqsdkgC/Zfc85zGqw9siXjrc0=
 github.com/bytedance/sonic v1.11.6/go.mod h1:LysEHSvpvDySVdC2f87zGWf6CIKJcAvqab1ZaiQtds4=
 github.com/bytedance/sonic/loader v0.1.1 h1:c+e5Pt1k/cy5wMveRDyk2X4B9hF4g7an8N3zCYjJFNM=
@@ -9,12 +11,16 @@ 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 +29,8 @@ 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 +82,18 @@ 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 commit string = "abcd1234"
-var date = "unknown"
+var (
+	version string = "0"
+	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
 
@@ -34,6 +43,10 @@ func main() {
 		os.Exit(1)
 	}
 
+	if len(config.Profiles) > 0 {
+		fmt.Println("WARNING: Profile functionality has been removed in favor of Groups. See the README for more information.")
+	}
+
 	if mode := os.Getenv("GIN_MODE"); mode != "" {
 		gin.SetMode(mode)
 	} else {
@@ -42,18 +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
-		fmt.Println("Shutting down llama-swap")
-		proxyManager.Shutdown()
-		os.Exit(0)
+		if err := srv.ListenAndServe(); err != nil && err != http.ErrServerClosed {
+			fmt.Printf("Fatal server error: %v\n", err)
+			close(exitChan)
+		}
 	}()
 
-	fmt.Println("llama-swap listening on " + *listenStr)
-	if err := proxyManager.Run(*listenStr); err != nil {
-		fmt.Printf("Server error: %v\n", err)
-		os.Exit(1)
+	// Handle config reloads and signals
+	go func() {
+		currentManager := proxyManager
+		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(proxy.StopWaitForInflightRequest)
+				// 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

@@ -26,6 +26,8 @@ func main() {
 
 	silent := flag.Bool("silent", false, "disable all logging")
 
+	ignoreSigTerm := flag.Bool("ignore-sig-term", false, "ignore SIGTERM signal")
+
 	flag.Parse() // Parse the command-line flags
 
 	// Create a new Gin router
@@ -33,14 +35,17 @@ 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 +68,11 @@ func main() {
 	})
 
 	r.POST("/v1/completions", func(c *gin.Context) {
-		c.Header("Content-Type", "text/plain")
-		c.String(200, *responseMessage)
+		c.Header("Content-Type", "application/json")
+		c.JSON(http.StatusOK, gin.H{
+			"responseMessage": *responseMessage,
+		})
+
 	})
 
 	// issue #41
@@ -104,6 +112,10 @@ 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"),
 		})
 	})
 
@@ -180,6 +192,10 @@ func main() {
 		log.SetOutput(io.Discard)
 	}
 
+	if !*silent {
+		fmt.Printf("My PID: %d\n", os.Getpid())
+	}
+
 	go func() {
 		log.Printf("simple-responder listening on %s\n", address)
 		// service connections
@@ -190,11 +206,36 @@ func main() {
 
 	// Wait for interrupt signal to gracefully shutdown the server with
 	// a timeout of 5 seconds.
-	quit := make(chan os.Signal, 1)
+	sigChan := make(chan os.Signal, 1)
 	// kill (no param) default send syscall.SIGTERM
 	// kill -2 is syscall.SIGINT
 	// kill -9 is syscall.SIGKILL but can't be catch, so don't need add it
-	signal.Notify(quit, syscall.SIGINT, syscall.SIGTERM)
-	<-quit
+	signal.Notify(sigChan, syscall.SIGINT, syscall.SIGTERM)
+
+	countSigInt := 0
+
+runloop:
+	for {
+		signal := <-sigChan
+		switch signal {
+		case syscall.SIGINT:
+			countSigInt++
+			if countSigInt > 1 {
+				break runloop
+			} else {
+				log.Println("Recieved SIGINT, send another SIGINT to shutdown")
+			}
+		case syscall.SIGTERM:
+			if *ignoreSigTerm {
+				log.Println("Ignoring SIGTERM")
+			} else {
+				log.Println("Recieved SIGTERM, shutting down")
+				break runloop
+			}
+		default:
+			break runloop
+		}
+	}
+
 	log.Println("simple-responder shutting down")
 }

proxy/config.go

@@ -2,13 +2,19 @@ package proxy
 
 import (
 	"fmt"
+	"io"
 	"os"
+	"runtime"
+	"sort"
+	"strconv"
 	"strings"
 
-	"github.com/google/shlex"
+	"github.com/billziss-gh/golib/shlex"
 	"gopkg.in/yaml.v3"
 )
 
+const DEFAULT_GROUP_ID = "(default)"
+
 type ModelConfig struct {
 	Cmd           string   `yaml:"cmd"`
 	Proxy         string   `yaml:"proxy"`
@@ -18,21 +24,53 @@ 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) {
 	return SanitizeCommand(m.Cmd)
 }
 
+type GroupConfig struct {
+	Swap       bool     `yaml:"swap"`
+	Exclusive  bool     `yaml:"exclusive"`
+	Persistent bool     `yaml:"persistent"`
+	Members    []string `yaml:"members"`
+}
+
+// set default values for GroupConfig
+func (c *GroupConfig) UnmarshalYAML(unmarshal func(interface{}) error) error {
+	type rawGroupConfig GroupConfig
+	defaults := rawGroupConfig{
+		Swap:       true,
+		Exclusive:  true,
+		Persistent: false,
+		Members:    []string{},
+	}
+
+	if err := unmarshal(&defaults); err != nil {
+		return err
+	}
+
+	*c = GroupConfig(defaults)
+	return nil
+}
+
 type Config struct {
 	HealthCheckTimeout int                    `yaml:"healthCheckTimeout"`
 	LogRequests        bool                   `yaml:"logRequests"`
 	LogLevel           string                 `yaml:"logLevel"`
-	Models             map[string]ModelConfig `yaml:"models"`
+	Models             map[string]ModelConfig `yaml:"models"` /* key is model ID */
 	Profiles           map[string][]string    `yaml:"profiles"`
+	Groups             map[string]GroupConfig `yaml:"groups"` /* key is group ID */
 
 	// 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) {
@@ -53,42 +91,168 @@ func (c *Config) FindConfig(modelName string) (ModelConfig, string, bool) {
 	}
 }
 
-func LoadConfig(path string) (*Config, error) {
-	data, err := os.ReadFile(path)
+func LoadConfig(path string) (Config, error) {
+	file, err := os.Open(path)
 	if err != nil {
-		return nil, err
+		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
 	}
 
 	var config Config
 	err = yaml.Unmarshal(data, &config)
 	if err != nil {
-		return nil, err
+		return Config{}, err
 	}
 
 	if config.HealthCheckTimeout < 15 {
 		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
 		}
 	}
 
-	return &config, nil
+	// 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
+	for groupID, groupConfig := range config.Groups {
+		prevSet := make(map[string]bool)
+		for _, member := range groupConfig.Members {
+			// Check for duplicates within this group
+			if _, found := prevSet[member]; found {
+				return Config{}, fmt.Errorf("duplicate model member %s found in group: %s", member, groupID)
+			}
+			prevSet[member] = true
+
+			// Check if member is used in another group
+			if existingGroup, exists := memberUsage[member]; exists {
+				return Config{}, fmt.Errorf("model member %s is used in multiple groups: %s and %s", member, existingGroup, groupID)
+			}
+			memberUsage[member] = groupID
+		}
+	}
+
+	return config, nil
+}
+
+// rewrites the yaml to include a default group with any orphaned models
+func AddDefaultGroupToConfig(config Config) Config {
+
+	if config.Groups == nil {
+		config.Groups = make(map[string]GroupConfig)
+	}
+
+	defaultGroup := GroupConfig{
+		Swap:      true,
+		Exclusive: true,
+		Members:   []string{},
+	}
+	// if groups is empty, create a default group and put
+	// all models into it
+	if len(config.Groups) == 0 {
+		for modelName := range config.Models {
+			defaultGroup.Members = append(defaultGroup.Members, modelName)
+		}
+	} else {
+		// iterate over existing group members and add non-grouped models into the default group
+		for modelName, _ := range config.Models {
+			foundModel := false
+		found:
+			// search for the model in existing groups
+			for _, groupConfig := range config.Groups {
+				for _, member := range groupConfig.Members {
+					if member == modelName {
+						foundModel = true
+						break found
+					}
+				}
+			}
+
+			if !foundModel {
+				defaultGroup.Members = append(defaultGroup.Members, modelName)
+			}
+		}
+	}
+
+	sort.Strings(defaultGroup.Members) // make consistent ordering for testing
+	config.Groups[DEFAULT_GROUP_ID] = defaultGroup
+
+	return config
 }
 
 func SanitizeCommand(cmdStr string) ([]string, error) {
-	// Remove trailing backslashes
-	cmdStr = strings.ReplaceAll(cmdStr, "\\ \n", " ")
-	cmdStr = strings.ReplaceAll(cmdStr, "\\\n", " ")
+	var cleanedLines []string
+	for _, line := range strings.Split(cmdStr, "\n") {
+		trimmed := strings.TrimSpace(line)
+		// Skip comment lines
+		if strings.HasPrefix(trimmed, "#") {
+			continue
+		}
+		// Handle trailing backslashes by replacing with space
+		if strings.HasSuffix(trimmed, "\\") {
+			cleanedLines = append(cleanedLines, strings.TrimSuffix(trimmed, "\\")+" ")
+		} else {
+			cleanedLines = append(cleanedLines, line)
+		}
+	}
+
+	// put it back together
+	cmdStr = strings.Join(cleanedLines, "\n")
 
 	// Split the command into arguments
-	args, err := shlex.Split(cmdStr)
-	if err != nil {
-		return nil, err
+	var args []string
+	if runtime.GOOS == "windows" {
+		args = shlex.Windows.Split(cmdStr)
+	} else {
+		args = shlex.Posix.Split(cmdStr)
 	}
 
 	// Ensure the command is not empty

proxy/config_posix_test.go

@@ -0,0 +1,42 @@
+//go:build !windows
+
+package proxy
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestConfig_SanitizeCommand(t *testing.T) {
+	// Test a command with spaces and newlines
+	args, err := SanitizeCommand(`python model1.py \
+		-a "double quotes" \
+		--arg2 'single quotes'
+		-s
+		# comment 1
+		--arg3 123 \
+
+		  # comment 2
+		--arg4 '"string in string"'
+
+
+		# this will get stripped out as well as the white space above
+		-c "'single quoted'"
+		`)
+	assert.NoError(t, err)
+	assert.Equal(t, []string{
+		"python", "model1.py",
+		"-a", "double quotes",
+		"--arg2", "single quotes",
+		"-s",
+		"--arg3", "123",
+		"--arg4", `"string in string"`,
+		"-c", `'single quoted'`,
+	}, args)
+
+	// Test an empty command
+	args, err = SanitizeCommand("")
+	assert.Error(t, err)
+	assert.Nil(t, args)
+}

proxy/config_test.go

@@ -3,6 +3,7 @@ package proxy
 import (
 	"os"
 	"path/filepath"
+	"strings"
 	"testing"
 
 	"github.com/stretchr/testify/assert"
@@ -35,11 +36,32 @@ models:
     aliases:
       - "m2"
     checkEndpoint: "/"
+  model3:
+    cmd: path/to/cmd --arg1 one
+    proxy: "http://localhost:8081"
+    aliases:
+      - "mthree"
+    checkEndpoint: "/"
+  model4:
+    cmd: path/to/cmd --arg1 one
+    proxy: "http://localhost:8082"
+    checkEndpoint: "/"
+
 healthCheckTimeout: 15
 profiles:
   test:
     - model1
     - model2
+groups:
+  group1:
+    swap: true
+    exclusive: false
+    members: ["model2"]
+  forever:
+    exclusive: false
+    persistent: true
+    members:
+      - "model4"
 `
 
 	if err := os.WriteFile(tempFile, []byte(content), 0644); err != nil {
@@ -52,7 +74,8 @@ profiles:
 		t.Fatalf("Failed to load config: %v", err)
 	}
 
-	expected := &Config{
+	expected := Config{
+		StartPort: 5800,
 		Models: map[string]ModelConfig{
 			"model1": {
 				Cmd:           "path/to/cmd --arg1 one",
@@ -68,6 +91,18 @@ profiles:
 				Env:           nil,
 				CheckEndpoint: "/",
 			},
+			"model3": {
+				Cmd:           "path/to/cmd --arg1 one",
+				Proxy:         "http://localhost:8081",
+				Aliases:       []string{"mthree"},
+				Env:           nil,
+				CheckEndpoint: "/",
+			},
+			"model4": {
+				Cmd:           "path/to/cmd --arg1 one",
+				Proxy:         "http://localhost:8082",
+				CheckEndpoint: "/",
+			},
 		},
 		HealthCheckTimeout: 15,
 		Profiles: map[string][]string{
@@ -77,6 +112,25 @@ profiles:
 			"m1":        "model1",
 			"model-one": "model1",
 			"m2":        "model2",
+			"mthree":    "model3",
+		},
+		Groups: map[string]GroupConfig{
+			DEFAULT_GROUP_ID: {
+				Swap:      true,
+				Exclusive: true,
+				Members:   []string{"model1", "model3"},
+			},
+			"group1": {
+				Swap:      true,
+				Exclusive: false,
+				Members:   []string{"model2"},
+			},
+			"forever": {
+				Swap:       true,
+				Exclusive:  false,
+				Persistent: true,
+				Members:    []string{"model4"},
+			},
 		},
 	}
 
@@ -87,6 +141,63 @@ profiles:
 	assert.Equal(t, "model1", realname)
 }
 
+func TestConfig_GroupMemberIsUnique(t *testing.T) {
+	content := `
+models:
+  model1:
+    cmd: path/to/cmd --arg1 one
+    proxy: "http://localhost:8080"
+  model2:
+    cmd: path/to/cmd --arg1 one
+    proxy: "http://localhost:8081"
+    checkEndpoint: "/"
+  model3:
+    cmd: path/to/cmd --arg1 one
+    proxy: "http://localhost:8081"
+    checkEndpoint: "/"
+
+healthCheckTimeout: 15
+groups:
+  group1:
+    swap: true
+    exclusive: false
+    members: ["model2"]
+  group2:
+    swap: true
+    exclusive: false
+    members: ["model2"]
+`
+	// Load the config and verify
+	_, err := LoadConfigFromReader(strings.NewReader(content))
+
+	// 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) {
 	config := &ModelConfig{
 		Cmd: `python model1.py \
@@ -147,30 +258,76 @@ func TestConfig_FindConfig(t *testing.T) {
 	assert.Equal(t, ModelConfig{}, modelConfig)
 }
 
-func TestConfig_SanitizeCommand(t *testing.T) {
+func TestConfig_AutomaticPortAssignments(t *testing.T) {
 
-	// Test a command with spaces and newlines
-	args, err := SanitizeCommand(`python model1.py \
-    -a "double quotes" \
-    --arg2 'single quotes'
-	-s
-	--arg3 123 \
-	--arg4 '"string in string"'
-	-c "'single quoted'"
-	`)
-	assert.NoError(t, err)
-	assert.Equal(t, []string{
-		"python", "model1.py",
-		"-a", "double quotes",
-		"--arg2", "single quotes",
-		"-s",
-		"--arg3", "123",
-		"--arg4", `"string in string"`,
-		"-c", `'single quoted'`,
-	}, args)
+	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)
+		}
 
-	// Test an empty command
-	args, err = SanitizeCommand("")
-	assert.Error(t, err)
-	assert.Nil(t, args)
+		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/config_windows_test.go

@@ -0,0 +1,42 @@
+//go:build windows
+
+package proxy
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestConfig_SanitizeCommand(t *testing.T) {
+	// does not support single quoted strings like in config_posix_test.go
+	args, err := SanitizeCommand(`python model1.py \
+
+	-a "double quotes" \
+	-s
+	--arg3 123 \
+
+	   # comment 2
+	--arg4 '"string in string"'
+
+
+
+	# this will get stripped out as well as the white space above
+	-c "'single quoted'"
+	`)
+	assert.NoError(t, err)
+	assert.Equal(t, []string{
+		"python", "model1.py",
+		"-a", "double quotes",
+		"-s",
+		"--arg3", "123",
+		"--arg4", "'string in string'", // this is a little weird but the lexer says so...?
+		"-c", `'single quoted'`,
+	}, args)
+
+	// Test an empty command
+	args, err = SanitizeCommand("")
+	assert.Error(t, err)
+	assert.Nil(t, args)
+
+}

proxy/helpers_test.go

@@ -14,6 +14,7 @@ import (
 var (
 	nextTestPort int = 12000
 	portMutex    sync.Mutex
+	testLogger   = NewLogMonitorWriter(os.Stdout)
 )
 
 // Check if the binary exists
@@ -26,6 +27,17 @@ func TestMain(m *testing.M) {
 
 	gin.SetMode(gin.TestMode)
 
+	switch os.Getenv("LOG_LEVEL") {
+	case "debug":
+		testLogger.SetLogLevel(LevelDebug)
+	case "warn":
+		testLogger.SetLogLevel(LevelWarn)
+	case "info":
+		testLogger.SetLogLevel(LevelInfo)
+	default:
+		testLogger.SetLogLevel(LevelWarn)
+	}
+
 	m.Run()
 }
 
@@ -33,17 +45,26 @@ func TestMain(m *testing.M) {
 func getSimpleResponderPath() string {
 	goos := runtime.GOOS
 	goarch := runtime.GOARCH
-	return filepath.Join("..", "build", fmt.Sprintf("simple-responder_%s_%s", goos, goarch))
+
+	if goos == "windows" {
+		return filepath.Join("..", "build", "simple-responder.exe")
+	} else {
+		return filepath.Join("..", "build", fmt.Sprintf("simple-responder_%s_%s", goos, goarch))
+	}
 }
 
-func getTestSimpleResponderConfig(expectedMessage string) ModelConfig {
+func getTestPort() int {
 	portMutex.Lock()
 	defer portMutex.Unlock()
 
 	port := nextTestPort
 	nextTestPort++
 
-	return getTestSimpleResponderConfigPort(expectedMessage, port)
+	return port
+}
+
+func getTestSimpleResponderConfig(expectedMessage string) ModelConfig {
+	return getTestSimpleResponderConfigPort(expectedMessage, getTestPort())
 }
 
 func getTestSimpleResponderConfigPort(expectedMessage string, port int) ModelConfig {

proxy/html/logs.html

@@ -170,6 +170,7 @@
 
                     this.eventSource.onmessage = (event) => {
                         this.logData += event.data;
+                        this.logData = this.logData.slice(-1024 * 100);
                         this.render();
                     };
 

proxy/process.go

@@ -8,6 +8,7 @@ import (
 	"net/http"
 	"net/url"
 	"os/exec"
+	"strconv"
 	"strings"
 	"sync"
 	"syscall"
@@ -29,6 +30,13 @@ const (
 	StateShutdown ProcessState = ProcessState("shutdown")
 )
 
+type StopStrategy int
+
+const (
+	StopImmediately StopStrategy = iota
+	StopWaitForInflightRequest
+)
+
 type Process struct {
 	ID     string
 	config ModelConfig
@@ -56,10 +64,25 @@ type Process struct {
 	// for managing shutdown state
 	shutdownCtx    context.Context
 	shutdownCancel context.CancelFunc
+
+	// for managing concurrency limits
+	concurrencyLimitSemaphore chan struct{}
+
+	// stop timeout waiting for graceful shutdown
+	gracefulStopTimeout time.Duration
+
+	// track that this happened
+	upstreamWasStoppedWithKill bool
 }
 
 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 +95,13 @@ func NewProcess(ID string, healthCheckTimeout int, config ModelConfig, processLo
 		state:                   StateStopped,
 		shutdownCtx:             ctx,
 		shutdownCancel:          cancel,
+
+		// concurrency limit
+		concurrencyLimitSemaphore: make(chan struct{}, concurrentLimit),
+
+		// stop timeout
+		gracefulStopTimeout:        5 * time.Second,
+		upstreamWasStoppedWithKill: false,
 	}
 }
 
@@ -184,10 +214,19 @@ 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)
+
+		// there is a race condition when SIGKILL is used, p.cmd.Wait() returns, and then
+		// the code below fires, putting an error into cmdWaitChan. This code is to prevent this
+		if p.upstreamWasStoppedWithKill {
+			p.proxyLogger.Debugf("<%s> process was killed, NOT sending exitErr: %v", p.ID, exitErr)
+			p.upstreamWasStoppedWithKill = false
+			return
+		}
+
 		p.cmdWaitChan <- exitErr
 	}()
 
@@ -259,9 +298,9 @@ 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)
 					}
 				}
 			}
@@ -300,9 +339,25 @@ func (p *Process) start() error {
 	}
 }
 
+// Stop will wait for inflight requests to complete before stopping the process.
 func (p *Process) Stop() {
+	if !isValidTransition(p.CurrentState(), StateStopping) {
+		return
+	}
+
 	// wait for any inflight requests before proceeding
+	p.proxyLogger.Debugf("<%s> Stop(): Waiting for inflight requests to complete", p.ID)
 	p.inFlightRequests.Wait()
+	p.StopImmediately()
+}
+
+// StopImmediately will transition the process to the stopping state and stop the process with a SIGTERM.
+// If the process does not stop within the specified timeout, it will be forcefully stopped with a SIGKILL.
+func (p *Process) StopImmediately() {
+	if !isValidTransition(p.CurrentState(), StateStopping) {
+		return
+	}
+
 	p.proxyLogger.Debugf("<%s> Stopping process", p.ID)
 
 	// calling Stop() when state is invalid is a no-op
@@ -312,7 +367,7 @@ func (p *Process) Stop() {
 	}
 
 	// stop the process with a graceful exit timeout
-	p.stopCommand(5 * time.Second)
+	p.stopCommand(p.gracefulStopTimeout)
 
 	if curState, err := p.swapState(StateStopping, StateStopped); err != nil {
 		p.proxyLogger.Infof("<%s> Stop() StateStopping -> StateStopped err: %v, current state: %v", p.ID, err, curState)
@@ -321,10 +376,11 @@ func (p *Process) Stop() {
 
 // Shutdown is called when llama-swap is shutting down. It will give a little bit
 // of time for any inflight requests to complete before shutting down. If the Process
-// is in the state of starting, it will cancel it and shut it down
+// is in the state of starting, it will cancel it and shut it down. Once a process is in
+// the StateShutdown state, it can not be started again.
 func (p *Process) Shutdown() {
 	p.shutdownCancel()
-	p.stopCommand(5 * time.Second)
+	p.stopCommand(p.gracefulStopTimeout)
 	p.state = StateShutdown
 }
 
@@ -340,31 +396,34 @@ 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.cmd.Process.Kill()
+		p.proxyLogger.Debugf("<%s> Process timed out waiting to stop, sending KILL signal (normal during shutdown)", p.ID)
+		p.upstreamWasStoppedWithKill = true
+		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())
 				}
@@ -410,6 +469,14 @@ 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()
@@ -435,6 +502,12 @@ 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

@@ -5,6 +5,7 @@ import (
 	"net/http"
 	"net/http/httptest"
 	"os"
+	"runtime"
 	"sync"
 	"testing"
 	"time"
@@ -340,3 +341,111 @@ 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)
+}
+
+func TestProcess_StopImmediately(t *testing.T) {
+	expectedMessage := "test_stop_immediate"
+	config := getTestSimpleResponderConfig(expectedMessage)
+
+	process := NewProcess("stop_immediate", 2, config, debugLogger, debugLogger)
+	defer process.Stop()
+
+	err := process.start()
+	assert.Nil(t, err)
+	assert.Equal(t, process.CurrentState(), StateReady)
+	go func() {
+		// slow, but will get killed by StopImmediate
+		req := httptest.NewRequest("GET", "/slow-respond?echo=12345&delay=1s", nil)
+		w := httptest.NewRecorder()
+		process.ProxyRequest(w, req)
+	}()
+	<-time.After(time.Millisecond)
+	process.StopImmediately()
+	assert.Equal(t, process.CurrentState(), StateStopped)
+}
+
+// Test that SIGKILL is sent when gracefulStopTimeout is reached and properly terminates
+// the upstream command
+func TestProcess_ForceStopWithKill(t *testing.T) {
+
+	expectedMessage := "test_sigkill"
+	binaryPath := getSimpleResponderPath()
+	port := getTestPort()
+
+	config := ModelConfig{
+		// note --ignore-sig-term which ignores the SIGTERM signal so a SIGKILL must be sent
+		// to force the process to exit
+		Cmd:           fmt.Sprintf("%s --port %d --respond %s --silent --ignore-sig-term", binaryPath, port, expectedMessage),
+		Proxy:         fmt.Sprintf("http://127.0.0.1:%d", port),
+		CheckEndpoint: "/health",
+	}
+
+	process := NewProcess("stop_immediate", 2, config, debugLogger, debugLogger)
+	defer process.Stop()
+
+	// reduce to make testing go faster
+	process.gracefulStopTimeout = time.Second
+
+	err := process.start()
+	assert.Nil(t, err)
+	assert.Equal(t, process.CurrentState(), StateReady)
+
+	waitChan := make(chan struct{})
+	go func() {
+		// slow, but will get killed by StopImmediate
+		req := httptest.NewRequest("GET", "/slow-respond?echo=12345&delay=2s", nil)
+		w := httptest.NewRecorder()
+		process.ProxyRequest(w, req)
+
+		// StatusOK because that was already sent before the kill
+		assert.Equal(t, http.StatusOK, w.Code)
+
+		// unexpected EOF because the kill happened, the "1" is sent before the kill
+		// then the unexpected EOF is sent after the kill
+		if runtime.GOOS == "windows" {
+			assert.Contains(t, w.Body.String(), "wsarecv: An existing connection was forcibly closed by the remote host")
+		} else {
+			assert.Contains(t, w.Body.String(), "unexpected EOF")
+		}
+
+		close(waitChan)
+	}()
+
+	<-time.After(time.Millisecond)
+	process.StopImmediately()
+	assert.Equal(t, process.CurrentState(), StateStopped)
+
+	// the request should have been interrupted by SIGKILL
+	<-waitChan
+}

proxy/processgroup.go

@@ -0,0 +1,114 @@
+package proxy
+
+import (
+	"fmt"
+	"net/http"
+	"slices"
+	"sync"
+)
+
+type ProcessGroup struct {
+	sync.Mutex
+
+	config     Config
+	id         string
+	swap       bool
+	exclusive  bool
+	persistent bool
+
+	proxyLogger    *LogMonitor
+	upstreamLogger *LogMonitor
+
+	// map of current processes
+	processes       map[string]*Process
+	lastUsedProcess string
+}
+
+func NewProcessGroup(id string, config Config, proxyLogger *LogMonitor, upstreamLogger *LogMonitor) *ProcessGroup {
+	groupConfig, ok := config.Groups[id]
+	if !ok {
+		panic("Unable to find configuration for group id: " + id)
+	}
+
+	pg := &ProcessGroup{
+		id:             id,
+		config:         config,
+		swap:           groupConfig.Swap,
+		exclusive:      groupConfig.Exclusive,
+		persistent:     groupConfig.Persistent,
+		proxyLogger:    proxyLogger,
+		upstreamLogger: upstreamLogger,
+		processes:      make(map[string]*Process),
+	}
+
+	// Create a Process for each member in the group
+	for _, modelID := range groupConfig.Members {
+		modelConfig, modelID, _ := pg.config.FindConfig(modelID)
+		process := NewProcess(modelID, pg.config.HealthCheckTimeout, modelConfig, pg.upstreamLogger, pg.proxyLogger)
+		pg.processes[modelID] = process
+	}
+
+	return pg
+}
+
+// ProxyRequest proxies a request to the specified model
+func (pg *ProcessGroup) ProxyRequest(modelID string, writer http.ResponseWriter, request *http.Request) error {
+	if !pg.HasMember(modelID) {
+		return fmt.Errorf("model %s not part of group %s", modelID, pg.id)
+	}
+
+	if pg.swap {
+		pg.Lock()
+		if pg.lastUsedProcess != modelID {
+			if pg.lastUsedProcess != "" {
+				pg.processes[pg.lastUsedProcess].Stop()
+			}
+			pg.lastUsedProcess = modelID
+		}
+		pg.Unlock()
+	}
+
+	pg.processes[modelID].ProxyRequest(writer, request)
+	return nil
+}
+
+func (pg *ProcessGroup) HasMember(modelName string) bool {
+	return slices.Contains(pg.config.Groups[pg.id].Members, modelName)
+}
+
+func (pg *ProcessGroup) StopProcesses(strategy StopStrategy) {
+	pg.Lock()
+	defer pg.Unlock()
+
+	if len(pg.processes) == 0 {
+		return
+	}
+
+	// stop Processes in parallel
+	var wg sync.WaitGroup
+	for _, process := range pg.processes {
+		wg.Add(1)
+		go func(process *Process) {
+			defer wg.Done()
+			switch strategy {
+			case StopImmediately:
+				process.StopImmediately()
+			default:
+				process.Stop()
+			}
+		}(process)
+	}
+	wg.Wait()
+}
+
+func (pg *ProcessGroup) Shutdown() {
+	var wg sync.WaitGroup
+	for _, process := range pg.processes {
+		wg.Add(1)
+		go func(process *Process) {
+			defer wg.Done()
+			process.Shutdown()
+		}(process)
+	}
+	wg.Wait()
+}

proxy/processgroup_test.go

@@ -0,0 +1,96 @@
+package proxy
+
+import (
+	"bytes"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+var processGroupTestConfig = AddDefaultGroupToConfig(Config{
+	HealthCheckTimeout: 15,
+	Models: map[string]ModelConfig{
+		"model1": getTestSimpleResponderConfig("model1"),
+		"model2": getTestSimpleResponderConfig("model2"),
+		"model3": getTestSimpleResponderConfig("model3"),
+		"model4": getTestSimpleResponderConfig("model4"),
+		"model5": getTestSimpleResponderConfig("model5"),
+	},
+	Groups: map[string]GroupConfig{
+		"G1": {
+			Swap:      true,
+			Exclusive: true,
+			Members:   []string{"model1", "model2"},
+		},
+		"G2": {
+			Swap:      false,
+			Exclusive: true,
+			Members:   []string{"model3", "model4"},
+		},
+	},
+})
+
+func TestProcessGroup_DefaultHasCorrectModel(t *testing.T) {
+	pg := NewProcessGroup(DEFAULT_GROUP_ID, processGroupTestConfig, testLogger, testLogger)
+	assert.True(t, pg.HasMember("model5"))
+}
+
+func TestProcessGroup_HasMember(t *testing.T) {
+	pg := NewProcessGroup("G1", processGroupTestConfig, testLogger, testLogger)
+	assert.True(t, pg.HasMember("model1"))
+	assert.True(t, pg.HasMember("model2"))
+	assert.False(t, pg.HasMember("model3"))
+}
+
+func TestProcessGroup_ProxyRequestSwapIsTrue(t *testing.T) {
+	pg := NewProcessGroup("G1", processGroupTestConfig, testLogger, testLogger)
+	defer pg.StopProcesses(StopWaitForInflightRequest)
+
+	tests := []string{"model1", "model2"}
+
+	for _, modelName := range tests {
+		t.Run(modelName, func(t *testing.T) {
+			reqBody := `{"x", "y"}`
+			req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+			w := httptest.NewRecorder()
+
+			assert.NoError(t, pg.ProxyRequest(modelName, w, req))
+			assert.Equal(t, http.StatusOK, w.Code)
+			assert.Contains(t, w.Body.String(), modelName)
+
+			// make sure only one process is in the running state
+			count := 0
+			for _, process := range pg.processes {
+				if process.CurrentState() == StateReady {
+					count++
+				}
+			}
+			assert.Equal(t, 1, count)
+		})
+	}
+}
+
+func TestProcessGroup_ProxyRequestSwapIsFalse(t *testing.T) {
+	pg := NewProcessGroup("G2", processGroupTestConfig, testLogger, testLogger)
+	defer pg.StopProcesses(StopWaitForInflightRequest)
+
+	tests := []string{"model3", "model4"}
+
+	for _, modelName := range tests {
+		t.Run(modelName, func(t *testing.T) {
+			reqBody := `{"x", "y"}`
+			req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+			w := httptest.NewRecorder()
+			assert.NoError(t, pg.ProxyRequest(modelName, w, req))
+			assert.Equal(t, http.StatusOK, w.Code)
+			assert.Contains(t, w.Body.String(), modelName)
+		})
+	}
+
+	// make sure all the processes are running
+	for _, process := range pg.processes {
+		assert.Equal(t, StateReady, process.CurrentState())
+	}
+}

proxy/proxymanager.go

@@ -26,17 +26,18 @@ const (
 type ProxyManager struct {
 	sync.Mutex
 
-	config           *Config
-	currentProcesses map[string]*Process
-	ginEngine        *gin.Engine
+	config    Config
+	ginEngine *gin.Engine
 
 	// logging
 	proxyLogger    *LogMonitor
 	upstreamLogger *LogMonitor
 	muxLogger      *LogMonitor
+
+	processGroups map[string]*ProcessGroup
 }
 
-func New(config *Config) *ProxyManager {
+func New(config Config) *ProxyManager {
 	// set up loggers
 	stdoutLogger := NewLogMonitorWriter(os.Stdout)
 	upstreamLogger := NewLogMonitorWriter(stdoutLogger)
@@ -65,15 +66,27 @@ func New(config *Config) *ProxyManager {
 	}
 
 	pm := &ProxyManager{
-		config:           config,
-		currentProcesses: make(map[string]*Process),
-		ginEngine:        gin.New(),
+		config:    config,
+		ginEngine: gin.New(),
 
 		proxyLogger:    proxyLogger,
 		muxLogger:      stdoutLogger,
 		upstreamLogger: upstreamLogger,
+
+		processGroups: make(map[string]*ProcessGroup),
 	}
 
+	// create the process groups
+	for groupID := range config.Groups {
+		processGroup := NewProcessGroup(groupID, config, proxyLogger, upstreamLogger)
+		pm.processGroups[groupID] = processGroup
+	}
+
+	pm.setupGinEngine()
+	return pm
+}
+
+func (pm *ProxyManager) setupGinEngine() {
 	pm.ginEngine.Use(func(c *gin.Context) {
 		// Start timer
 		start := time.Now()
@@ -184,63 +197,77 @@ func New(config *Config) *ProxyManager {
 
 	// Disable console color for testing
 	gin.DisableConsoleColor()
-
-	return pm
 }
 
-func (pm *ProxyManager) Run(addr ...string) error {
-	return pm.ginEngine.Run(addr...)
-}
-
-func (pm *ProxyManager) HandlerFunc(w http.ResponseWriter, r *http.Request) {
+// ServeHTTP implements http.Handler interface
+func (pm *ProxyManager) ServeHTTP(w http.ResponseWriter, r *http.Request) {
 	pm.ginEngine.ServeHTTP(w, r)
 }
 
-func (pm *ProxyManager) StopProcesses() {
+// 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(strategy StopStrategy) {
 	pm.Lock()
 	defer pm.Unlock()
 
-	pm.stopProcesses()
-}
-
-// for internal usage
-func (pm *ProxyManager) stopProcesses() {
-	if len(pm.currentProcesses) == 0 {
-		return
-	}
-
 	// stop Processes in parallel
 	var wg sync.WaitGroup
-	for _, process := range pm.currentProcesses {
+	for _, processGroup := range pm.processGroups {
 		wg.Add(1)
-		go func(process *Process) {
+		go func(processGroup *ProcessGroup) {
 			defer wg.Done()
-			process.Stop()
-		}(process)
+			processGroup.StopProcesses(strategy)
+		}(processGroup)
 	}
-	wg.Wait()
 
-	pm.currentProcesses = make(map[string]*Process)
+	wg.Wait()
 }
 
-// Shutdown is called to shutdown all upstream processes
-// when llama-swap is shutting down.
+// Shutdown stops all processes managed by this ProxyManager
 func (pm *ProxyManager) Shutdown() {
 	pm.Lock()
 	defer pm.Unlock()
 
-	// shutdown process in parallel
+	pm.proxyLogger.Debug("Shutdown() called in proxy manager")
+
 	var wg sync.WaitGroup
-	for _, process := range pm.currentProcesses {
+	// Send shutdown signal to all process in groups
+	for _, processGroup := range pm.processGroups {
 		wg.Add(1)
-		go func(process *Process) {
+		go func(processGroup *ProcessGroup) {
 			defer wg.Done()
-			process.Shutdown()
-		}(process)
+			processGroup.Shutdown()
+		}(processGroup)
 	}
 	wg.Wait()
 }
 
+func (pm *ProxyManager) swapProcessGroup(requestedModel string) (*ProcessGroup, string, error) {
+	// de-alias the real model name and get a real one
+	realModelName, found := pm.config.RealModelName(requestedModel)
+	if !found {
+		return nil, realModelName, fmt.Errorf("could not find real modelID for %s", requestedModel)
+	}
+
+	processGroup := pm.findGroupByModelName(realModelName)
+	if processGroup == nil {
+		return nil, realModelName, fmt.Errorf("could not find process group for model %s", requestedModel)
+	}
+
+	if processGroup.exclusive {
+		pm.proxyLogger.Debugf("Exclusive mode for group %s, stopping other process groups", processGroup.id)
+		for groupId, otherGroup := range pm.processGroups {
+			if groupId != processGroup.id && !otherGroup.persistent {
+				otherGroup.StopProcesses(StopWaitForInflightRequest)
+			}
+		}
+	}
+
+	return processGroup, realModelName, nil
+}
+
 func (pm *ProxyManager) listModelsHandler(c *gin.Context) {
 	data := []interface{}{}
 	for id, modelConfig := range pm.config.Models {
@@ -270,79 +297,6 @@ func (pm *ProxyManager) listModelsHandler(c *gin.Context) {
 	}
 }
 
-func (pm *ProxyManager) swapModel(requestedModel string) (*Process, error) {
-	pm.Lock()
-	defer pm.Unlock()
-
-	// Check if requestedModel contains a PROFILE_SPLIT_CHAR
-	profileName, modelName := splitRequestedModel(requestedModel)
-
-	if profileName != "" {
-		if _, found := pm.config.Profiles[profileName]; !found {
-			return nil, fmt.Errorf("model group not found %s", profileName)
-		}
-	}
-
-	// de-alias the real model name and get a real one
-	realModelName, found := pm.config.RealModelName(modelName)
-	if !found {
-		return nil, fmt.Errorf("could not find modelID for %s", requestedModel)
-	}
-
-	// check if model is part of the profile
-	if profileName != "" {
-		found := false
-		for _, item := range pm.config.Profiles[profileName] {
-			if item == realModelName {
-				found = true
-				break
-			}
-		}
-
-		if !found {
-			return nil, fmt.Errorf("model %s part of profile %s", realModelName, profileName)
-		}
-	}
-
-	// exit early when already running, otherwise stop everything and swap
-	requestedProcessKey := ProcessKeyName(profileName, realModelName)
-
-	if process, found := pm.currentProcesses[requestedProcessKey]; found {
-		pm.proxyLogger.Debugf("No-swap, using existing process for model [%s]", requestedModel)
-		return process, nil
-	}
-
-	// stop all running models
-	pm.proxyLogger.Infof("Swapping model to [%s]", requestedModel)
-	pm.stopProcesses()
-	if profileName == "" {
-		modelConfig, modelID, found := pm.config.FindConfig(realModelName)
-		if !found {
-			return nil, fmt.Errorf("could not find configuration for %s", realModelName)
-		}
-
-		process := NewProcess(modelID, pm.config.HealthCheckTimeout, modelConfig, pm.upstreamLogger, pm.proxyLogger)
-		processKey := ProcessKeyName(profileName, modelID)
-		pm.currentProcesses[processKey] = process
-	} else {
-		for _, modelName := range pm.config.Profiles[profileName] {
-			if realModelName, found := pm.config.RealModelName(modelName); found {
-				modelConfig, modelID, found := pm.config.FindConfig(realModelName)
-				if !found {
-					return nil, fmt.Errorf("could not find configuration for %s in group %s", realModelName, profileName)
-				}
-
-				process := NewProcess(modelID, pm.config.HealthCheckTimeout, modelConfig, pm.upstreamLogger, pm.proxyLogger)
-				processKey := ProcessKeyName(profileName, modelID)
-				pm.currentProcesses[processKey] = process
-			}
-		}
-	}
-
-	// requestedProcessKey should exist due to swap
-	return pm.currentProcesses[requestedProcessKey], nil
-}
-
 func (pm *ProxyManager) proxyToUpstream(c *gin.Context) {
 	requestedModel := c.Param("model_id")
 
@@ -351,13 +305,15 @@ func (pm *ProxyManager) proxyToUpstream(c *gin.Context) {
 		return
 	}
 
-	if process, err := pm.swapModel(requestedModel); err != nil {
-		pm.sendErrorResponse(c, http.StatusNotFound, fmt.Sprintf("unable to swap to model, %s", err.Error()))
-	} else {
-		// rewrite the path
-		c.Request.URL.Path = c.Param("upstreamPath")
-		process.ProxyRequest(c.Writer, c.Request)
+	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
+	c.Request.URL.Path = c.Param("upstreamPath")
+	processGroup.ProxyRequest(requestedModel, c.Writer, c.Request)
 }
 
 func (pm *ProxyManager) upstreamIndex(c *gin.Context) {
@@ -378,7 +334,31 @@ func (pm *ProxyManager) upstreamIndex(c *gin.Context) {
 
 	// Iterate over sorted keys
 	for _, modelID := range modelIDs {
-		html.WriteString(fmt.Sprintf("<li><a href=\"/upstream/%s\">%s</a></li>", modelID, modelID))
+		// Get process state
+		processGroup := pm.findGroupByModelName(modelID)
+		var state string
+		if processGroup != nil {
+			process := processGroup.processes[modelID]
+			if process != nil {
+				var stateStr string
+				switch process.CurrentState() {
+				case StateReady:
+					stateStr = "Ready"
+				case StateStarting:
+					stateStr = "Starting"
+				case StateStopping:
+					stateStr = "Stopping"
+				case StateFailed:
+					stateStr = "Failed"
+				case StateShutdown:
+					stateStr = "Shutdown"
+				default:
+					stateStr = "Unknown"
+				}
+				state = stateStr
+			}
+		}
+		html.WriteString(fmt.Sprintf("<li><a href=\"/upstream/%s\">%s</a> - %s</li>", modelID, modelID, state))
 	}
 	html.WriteString("</ul></body></html>")
 	c.Header("Content-Type", "text/html")
@@ -395,49 +375,40 @@ 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
 	}
 
-	process, err := pm.swapModel(requestedModel)
-
+	processGroup, realModelName, err := pm.swapProcessGroup(requestedModel)
 	if err != nil {
-		pm.sendErrorResponse(c, http.StatusNotFound, fmt.Sprintf("unable to swap to model, %s", err.Error()))
+		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
-	if process.config.UseModelName != "" {
-		bodyBytes, err = sjson.SetBytes(bodyBytes, "model", process.config.UseModelName)
+	useModelName := pm.config.Models[realModelName].UseModelName
+	if useModelName != "" {
+		bodyBytes, err = sjson.SetBytes(bodyBytes, "model", useModelName)
 		if err != nil {
-			pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error updating JSON: %s", err.Error()))
+			pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error rewriting model name in JSON: %s", err.Error()))
 			return
 		}
-	} else {
-		profileName, modelName := splitRequestedModel(requestedModel)
-		if profileName != "" {
-			bodyBytes, err = sjson.SetBytes(bodyBytes, "model", modelName)
-			if err != nil {
-				pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error updating JSON: %s", err.Error()))
-				return
-			}
-		}
 	}
 
 	c.Request.Body = io.NopCloser(bytes.NewBuffer(bodyBytes))
 
 	// dechunk it as we already have all the body bytes see issue #11
 	c.Request.Header.Del("transfer-encoding")
-	c.Request.Header.Add("content-length", strconv.Itoa(len(bodyBytes)))
-
-	process.ProxyRequest(c.Writer, c.Request)
+	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
+	}
 }
 
 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()))
@@ -451,15 +422,16 @@ func (pm *ProxyManager) proxyOAIPostFormHandler(c *gin.Context) {
 		return
 	}
 
-	// Swap to the requested model
-	process, err := pm.swapModel(requestedModel)
+	processGroup, realModelName, err := pm.swapProcessGroup(requestedModel)
 	if err != nil {
-		pm.sendErrorResponse(c, http.StatusNotFound, fmt.Sprintf("unable to swap to model, %s", err.Error()))
+		pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error swapping process group: %s", err.Error()))
 		return
 	}
 
-	// Get profile name and model name from the requested model
-	profileName, modelName := splitRequestedModel(requestedModel)
+	// 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 {
@@ -467,10 +439,13 @@ func (pm *ProxyManager) proxyOAIPostFormHandler(c *gin.Context) {
 			fieldValue := value
 			// If this is the model field and we have a profile, use just the model name
 			if key == "model" {
-				if process.config.UseModelName != "" {
-					fieldValue = process.config.UseModelName
-				} else if profileName != "" {
-					fieldValue = modelName
+				// # issue #69 allow custom model names to be sent to upstream
+				useModelName := pm.config.Models[realModelName].UseModelName
+
+				if useModelName != "" {
+					fieldValue = useModelName
+				} else {
+					fieldValue = requestedModel
 				}
 			}
 			field, err := multipartWriter.CreateFormField(key)
@@ -531,8 +506,16 @@ 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
-	process.ProxyRequest(c.Writer, modifiedReq)
+	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
+	}
 }
 
 func (pm *ProxyManager) sendErrorResponse(c *gin.Context, statusCode int, message string) {
@@ -546,7 +529,7 @@ func (pm *ProxyManager) sendErrorResponse(c *gin.Context, statusCode int, messag
 }
 
 func (pm *ProxyManager) unloadAllModelsHandler(c *gin.Context) {
-	pm.StopProcesses()
+	pm.StopProcesses(StopImmediately)
 	c.String(http.StatusOK, "OK")
 }
 
@@ -554,14 +537,15 @@ func (pm *ProxyManager) listRunningProcessesHandler(context *gin.Context) {
 	context.Header("Content-Type", "application/json")
 	runningProcesses := make([]gin.H, 0) // Default to an empty response.
 
-	for _, process := range pm.currentProcesses {
-
-		// Append the process ID and State (multiple entries if profiles are being used).
-		runningProcesses = append(runningProcesses, gin.H{
-			"model": process.ID,
-			"state": process.state,
-		})
-
+	for _, processGroup := range pm.processGroups {
+		for _, process := range processGroup.processes {
+			if process.CurrentState() == StateReady {
+				runningProcesses = append(runningProcesses, gin.H{
+					"model": process.ID,
+					"state": process.state,
+				})
+			}
+		}
 	}
 
 	// Put the results under the `running` key.
@@ -572,15 +556,11 @@ func (pm *ProxyManager) listRunningProcessesHandler(context *gin.Context) {
 	context.JSON(http.StatusOK, response) // Always return 200 OK
 }
 
-func ProcessKeyName(groupName, modelName string) string {
-	return groupName + PROFILE_SPLIT_CHAR + modelName
-}
-
-func splitRequestedModel(requestedModel string) (string, string) {
-	profileName, modelName := "", requestedModel
-	if idx := strings.Index(requestedModel, PROFILE_SPLIT_CHAR); idx != -1 {
-		profileName = requestedModel[:idx]
-		modelName = requestedModel[idx+1:]
+func (pm *ProxyManager) findGroupByModelName(modelName string) *ProcessGroup {
+	for _, group := range pm.processGroups {
+		if group.HasMember(modelName) {
+			return group
+		}
 	}
-	return profileName, modelName
+	return nil
 }

proxy/proxymanager_test.go

@@ -8,87 +8,120 @@ import (
 	"mime/multipart"
 	"net/http"
 	"net/http/httptest"
+	"strconv"
 	"sync"
 	"testing"
 	"time"
 
 	"github.com/stretchr/testify/assert"
+	"github.com/tidwall/gjson"
 )
 
 func TestProxyManager_SwapProcessCorrectly(t *testing.T) {
-	config := &Config{
+	config := AddDefaultGroupToConfig(Config{
 		HealthCheckTimeout: 15,
 		Models: map[string]ModelConfig{
 			"model1": getTestSimpleResponderConfig("model1"),
 			"model2": getTestSimpleResponderConfig("model2"),
 		},
 		LogLevel: "error",
-	}
+	})
 
 	proxy := New(config)
-	defer proxy.StopProcesses()
+	defer proxy.StopProcesses(StopWaitForInflightRequest)
 
 	for _, modelName := range []string{"model1", "model2"} {
 		reqBody := fmt.Sprintf(`{"model":"%s"}`, modelName)
 		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)
-
-		_, exists := proxy.currentProcesses[ProcessKeyName("", modelName)]
-		assert.True(t, exists, "expected %s key in currentProcesses", modelName)
-
 	}
-
-	// make sure there's only one loaded model
-	assert.Len(t, proxy.currentProcesses, 1)
 }
 
 func TestProxyManager_SwapMultiProcess(t *testing.T) {
-
-	model1 := "path1/model1"
-	model2 := "path2/model2"
-
-	profileModel1 := ProcessKeyName("test", model1)
-	profileModel2 := ProcessKeyName("test", model2)
-
-	config := &Config{
+	config := AddDefaultGroupToConfig(Config{
 		HealthCheckTimeout: 15,
 		Models: map[string]ModelConfig{
-			model1: getTestSimpleResponderConfig("model1"),
-			model2: getTestSimpleResponderConfig("model2"),
-		},
-		Profiles: map[string][]string{
-			"test": {model1, model2},
+			"model1": getTestSimpleResponderConfig("model1"),
+			"model2": getTestSimpleResponderConfig("model2"),
 		},
 		LogLevel: "error",
-	}
+		Groups: map[string]GroupConfig{
+			"G1": {
+				Swap:      true,
+				Exclusive: false,
+				Members:   []string{"model1"},
+			},
+			"G2": {
+				Swap:      true,
+				Exclusive: false,
+				Members:   []string{"model2"},
+			},
+		},
+	})
 
 	proxy := New(config)
-	defer proxy.StopProcesses()
+	defer proxy.StopProcesses(StopWaitForInflightRequest)
 
-	for modelID, requestedModel := range map[string]string{
-		"model1": profileModel1,
-		"model2": profileModel2,
-	} {
+	tests := []string{"model1", "model2"}
+	for _, requestedModel := range tests {
+		t.Run(requestedModel, func(t *testing.T) {
+			reqBody := fmt.Sprintf(`{"model":"%s"}`, requestedModel)
+			req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+			w := httptest.NewRecorder()
+
+			proxy.ServeHTTP(w, req)
+			assert.Equal(t, http.StatusOK, w.Code)
+			assert.Contains(t, w.Body.String(), requestedModel)
+		})
+	}
+
+	// make sure there's two loaded models
+	assert.Equal(t, proxy.findGroupByModelName("model1").processes["model1"].CurrentState(), StateReady)
+	assert.Equal(t, proxy.findGroupByModelName("model2").processes["model2"].CurrentState(), StateReady)
+}
+
+// Test that a persistent group is not affected by the swapping behaviour of
+// other groups.
+func TestProxyManager_PersistentGroupsAreNotSwapped(t *testing.T) {
+	config := AddDefaultGroupToConfig(Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]ModelConfig{
+			"model1": getTestSimpleResponderConfig("model1"), // goes into the default group
+			"model2": getTestSimpleResponderConfig("model2"),
+		},
+		LogLevel: "error",
+		Groups: map[string]GroupConfig{
+			// the forever group is persistent and should not be affected by model1
+			"forever": {
+				Swap:       true,
+				Exclusive:  false,
+				Persistent: true,
+				Members:    []string{"model2"},
+			},
+		},
+	})
+
+	proxy := New(config)
+	defer proxy.StopProcesses(StopWaitForInflightRequest)
+
+	// make requests to load all models, loading model1 should not affect model2
+	tests := []string{"model2", "model1"}
+	for _, requestedModel := range tests {
 		reqBody := fmt.Sprintf(`{"model":"%s"}`, requestedModel)
 		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(), modelID)
+		assert.Contains(t, w.Body.String(), requestedModel)
 	}
 
-	// make sure there's two loaded models
-	assert.Len(t, proxy.currentProcesses, 2)
-	_, exists := proxy.currentProcesses[profileModel1]
-	assert.True(t, exists, "expected "+profileModel1+" key in currentProcesses")
-
-	_, exists = proxy.currentProcesses[profileModel2]
-	assert.True(t, exists, "expected "+profileModel2+" key in currentProcesses")
+	assert.Equal(t, proxy.findGroupByModelName("model2").processes["model2"].CurrentState(), StateReady)
+	assert.Equal(t, proxy.findGroupByModelName("model1").processes["model1"].CurrentState(), StateReady)
 }
 
 // When a request for a different model comes in ProxyManager should wait until
@@ -98,7 +131,7 @@ func TestProxyManager_SwapMultiProcessParallelRequests(t *testing.T) {
 		t.Skip("skipping slow test")
 	}
 
-	config := &Config{
+	config := AddDefaultGroupToConfig(Config{
 		HealthCheckTimeout: 15,
 		Models: map[string]ModelConfig{
 			"model1": getTestSimpleResponderConfig("model1"),
@@ -106,10 +139,10 @@ func TestProxyManager_SwapMultiProcessParallelRequests(t *testing.T) {
 			"model3": getTestSimpleResponderConfig("model3"),
 		},
 		LogLevel: "error",
-	}
+	})
 
 	proxy := New(config)
-	defer proxy.StopProcesses()
+	defer proxy.StopProcesses(StopWaitForInflightRequest)
 
 	results := map[string]string{}
 
@@ -125,15 +158,16 @@ 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()
-
-			results[key] = w.Body.String()
+			var response map[string]string
+			assert.NoError(t, json.Unmarshal(w.Body.Bytes(), &response))
+			results[key] = response["responseMessage"]
 			mu.Unlock()
 		}(key)
 
@@ -149,7 +183,7 @@ func TestProxyManager_SwapMultiProcessParallelRequests(t *testing.T) {
 }
 
 func TestProxyManager_ListModelsHandler(t *testing.T) {
-	config := &Config{
+	config := Config{
 		HealthCheckTimeout: 15,
 		Models: map[string]ModelConfig{
 			"model1": getTestSimpleResponderConfig("model1"),
@@ -167,7 +201,7 @@ 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)
@@ -217,51 +251,6 @@ func TestProxyManager_ListModelsHandler(t *testing.T) {
 	assert.Empty(t, expectedModels, "not all expected models were returned")
 }
 
-func TestProxyManager_ProfileNonMember(t *testing.T) {
-
-	model1 := "path1/model1"
-	model2 := "path2/model2"
-
-	profileMemberName := ProcessKeyName("test", model1)
-	profileNonMemberName := ProcessKeyName("test", model2)
-
-	config := &Config{
-		HealthCheckTimeout: 15,
-		Models: map[string]ModelConfig{
-			model1: getTestSimpleResponderConfig("model1"),
-			model2: getTestSimpleResponderConfig("model2"),
-		},
-		Profiles: map[string][]string{
-			"test": {model1},
-		},
-		LogLevel: "error",
-	}
-
-	proxy := New(config)
-	defer proxy.StopProcesses()
-
-	// actual member of profile
-	{
-		reqBody := fmt.Sprintf(`{"model":"%s"}`, profileMemberName)
-		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
-		w := httptest.NewRecorder()
-
-		proxy.HandlerFunc(w, req)
-		assert.Equal(t, http.StatusOK, w.Code)
-		assert.Contains(t, w.Body.String(), "model1")
-	}
-
-	// actual model, but non-member will 404
-	{
-		reqBody := fmt.Sprintf(`{"model":"%s"}`, profileNonMemberName)
-		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
-		w := httptest.NewRecorder()
-
-		proxy.HandlerFunc(w, req)
-		assert.Equal(t, http.StatusNotFound, w.Code)
-	}
-}
-
 func TestProxyManager_Shutdown(t *testing.T) {
 	// make broken model configurations
 	model1Config := getTestSimpleResponderConfigPort("model1", 9991)
@@ -273,24 +262,27 @@ func TestProxyManager_Shutdown(t *testing.T) {
 	model3Config := getTestSimpleResponderConfigPort("model3", 9993)
 	model3Config.Proxy = "http://localhost:10003/"
 
-	config := &Config{
+	config := AddDefaultGroupToConfig(Config{
 		HealthCheckTimeout: 15,
-		Profiles: map[string][]string{
-			"test": {"model1", "model2", "model3"},
-		},
 		Models: map[string]ModelConfig{
 			"model1": model1Config,
 			"model2": model2Config,
 			"model3": model3Config,
 		},
 		LogLevel: "error",
-	}
+		Groups: map[string]GroupConfig{
+			"test": {
+				Swap:    false,
+				Members: []string{"model1", "model2", "model3"},
+			},
+		},
+	})
 
 	proxy := New(config)
 
 	// Start all the processes
 	var wg sync.WaitGroup
-	for _, modelName := range []string{"test:model1", "test:model2", "test:model3"} {
+	for _, modelName := range []string{"model1", "model2", "model3"} {
 		wg.Add(1)
 		go func(modelName string) {
 			defer wg.Done()
@@ -298,11 +290,10 @@ func TestProxyManager_Shutdown(t *testing.T) {
 			req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
 			w := httptest.NewRecorder()
 
-			// send a request to trigger the proxy to load
-			proxy.HandlerFunc(w, req)
+			// send a request to trigger the proxy to load ... this should hang waiting for start up
+			proxy.ServeHTTP(w, req)
 			assert.Equal(t, http.StatusBadGateway, w.Code)
 			assert.Contains(t, w.Body.String(), "health check interrupted due to shutdown")
-			//fmt.Println(w.Code, w.Body.String())
 		}(modelName)
 	}
 
@@ -314,67 +305,43 @@ func TestProxyManager_Shutdown(t *testing.T) {
 }
 
 func TestProxyManager_Unload(t *testing.T) {
-	config := &Config{
+	config := AddDefaultGroupToConfig(Config{
 		HealthCheckTimeout: 15,
 		Models: map[string]ModelConfig{
 			"model1": getTestSimpleResponderConfig("model1"),
 		},
 		LogLevel: "error",
-	}
+	})
 
 	proxy := New(config)
-	proc, err := proxy.swapModel("model1")
-	assert.NoError(t, err)
-	assert.NotNil(t, proc)
-
-	assert.Len(t, proxy.currentProcesses, 1)
-	req := httptest.NewRequest("GET", "/unload", nil)
+	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.ServeHTTP(w, req)
 	assert.Equal(t, http.StatusOK, w.Code)
 	assert.Equal(t, w.Body.String(), "OK")
-	assert.Len(t, proxy.currentProcesses, 0)
-}
 
-// issue 62, strip profile slug from model name
-func TestProxyManager_StripProfileSlug(t *testing.T) {
-	config := &Config{
-		HealthCheckTimeout: 15,
-		Profiles: map[string][]string{
-			"test": {"TheExpectedModel"}, // TheExpectedModel is default in simple-responder.go
-		},
-		Models: map[string]ModelConfig{
-			"TheExpectedModel": getTestSimpleResponderConfig("TheExpectedModel"),
-		},
-		LogLevel: "error",
-	}
-
-	proxy := New(config)
-	defer proxy.StopProcesses()
-
-	reqBody := fmt.Sprintf(`{"model":"%s"}`, "test:TheExpectedModel")
-	req := httptest.NewRequest("POST", "/v1/audio/speech", bytes.NewBufferString(reqBody))
-	w := httptest.NewRecorder()
-	proxy.HandlerFunc(w, req)
-	assert.Equal(t, http.StatusOK, w.Code)
-	assert.Contains(t, w.Body.String(), "ok")
+	// give it a bit of time to stop
+	<-time.After(time.Millisecond * 250)
+	assert.Equal(t, proxy.processGroups[DEFAULT_GROUP_ID].processes["model1"].CurrentState(), StateStopped)
 }
 
 // Test issue #61 `Listing the current list of models and the loaded model.`
 func TestProxyManager_RunningEndpoint(t *testing.T) {
-
 	// Shared configuration
-	config := &Config{
+	config := AddDefaultGroupToConfig(Config{
 		HealthCheckTimeout: 15,
 		Models: map[string]ModelConfig{
 			"model1": getTestSimpleResponderConfig("model1"),
 			"model2": getTestSimpleResponderConfig("model2"),
 		},
-		Profiles: map[string][]string{
-			"test": {"model1", "model2"},
-		},
-		LogLevel: "error",
-	}
+		LogLevel: "warn",
+	})
 
 	// Define a helper struct to parse the JSON response.
 	type RunningResponse struct {
@@ -386,12 +353,12 @@ func TestProxyManager_RunningEndpoint(t *testing.T) {
 
 	// Create proxy once for all tests
 	proxy := New(config)
-	defer proxy.StopProcesses()
+	defer proxy.StopProcesses(StopWaitForInflightRequest)
 
 	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)
 
@@ -409,13 +376,13 @@ 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))
@@ -429,238 +396,132 @@ func TestProxyManager_RunningEndpoint(t *testing.T) {
 		// Is the model loaded?
 		assert.Equal(t, "ready", response.Running[0].State)
 	})
-
-	t.Run("multiple models via profile", func(t *testing.T) {
-		// Load more than one model.
-		for _, model := range []string{"model1", "model2"} {
-			profileModel := ProcessKeyName("test", model)
-			reqBody := fmt.Sprintf(`{"model":"%s"}`, profileModel)
-			req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
-			w := httptest.NewRecorder()
-			proxy.HandlerFunc(w, req)
-			assert.Equal(t, http.StatusOK, w.Code)
-		}
-
-		// Simulate the browser call.
-		req := httptest.NewRequest("GET", "/running", nil)
-		w := httptest.NewRecorder()
-		proxy.HandlerFunc(w, req)
-
-		var response RunningResponse
-
-		// The JSON response must be valid.
-		assert.NoError(t, json.Unmarshal(w.Body.Bytes(), &response))
-
-		// The response should contain 2 models.
-		assert.Len(t, response.Running, 2)
-
-		expectedModels := map[string]struct{}{
-			"model1": {},
-			"model2": {},
-		}
-
-		// Iterate through the models and check their states as well.
-		for _, entry := range response.Running {
-			_, exists := expectedModels[entry.Model]
-			assert.True(t, exists, "unexpected model %s", entry.Model)
-			assert.Equal(t, "ready", entry.State)
-			delete(expectedModels, entry.Model)
-		}
-
-		// Since we deleted each model while testing for its validity we should have no more models in the response.
-		assert.Empty(t, expectedModels, "unexpected additional models in response")
-	})
 }
 
 func TestProxyManager_AudioTranscriptionHandler(t *testing.T) {
-	config := &Config{
+	config := AddDefaultGroupToConfig(Config{
 		HealthCheckTimeout: 15,
-		Profiles: map[string][]string{
-			"test": {"TheExpectedModel"},
-		},
 		Models: map[string]ModelConfig{
 			"TheExpectedModel": getTestSimpleResponderConfig("TheExpectedModel"),
 		},
 		LogLevel: "error",
-	}
+	})
 
 	proxy := New(config)
-	defer proxy.StopProcesses()
+	defer proxy.StopProcesses(StopWaitForInflightRequest)
 
-	testCases := []struct {
-		name        string
-		modelInput  string
-		expectModel string
-	}{
-		{
-			name:        "With Profile Prefix",
-			modelInput:  "test:TheExpectedModel",
-			expectModel: "TheExpectedModel", // Profile prefix should be stripped
-		},
-		{
-			name:        "Without Profile Prefix",
-			modelInput:  "TheExpectedModel",
-			expectModel: "TheExpectedModel", // Should remain the same
-		},
-	}
+	// Create a buffer with multipart form data
+	var b bytes.Buffer
+	w := multipart.NewWriter(&b)
 
-	for _, tc := range testCases {
-		t.Run(tc.name, func(t *testing.T) {
-			// Create a buffer with multipart form data
-			var b bytes.Buffer
-			w := multipart.NewWriter(&b)
+	// Add the model field
+	fw, err := w.CreateFormField("model")
+	assert.NoError(t, err)
+	_, err = fw.Write([]byte("TheExpectedModel"))
+	assert.NoError(t, err)
 
-			// Add the model field
-			fw, err := w.CreateFormField("model")
-			assert.NoError(t, err)
-			_, err = fw.Write([]byte(tc.modelInput))
-			assert.NoError(t, err)
+	// Add a file field
+	fw, err = w.CreateFormFile("file", "test.mp3")
+	assert.NoError(t, err)
+	// Generate random content length between 10 and 20
+	contentLength := rand.Intn(11) + 10 // 10 to 20
+	content := make([]byte, contentLength)
+	_, err = fw.Write(content)
+	assert.NoError(t, err)
+	w.Close()
 
-			// Add a file field
-			fw, err = w.CreateFormFile("file", "test.mp3")
-			assert.NoError(t, err)
-			// Generate random content length between 10 and 20
-			contentLength := rand.Intn(11) + 10 // 10 to 20
-			content := make([]byte, contentLength)
-			_, err = fw.Write(content)
-			assert.NoError(t, err)
-			w.Close()
+	// Create the request with the multipart form data
+	req := httptest.NewRequest("POST", "/v1/audio/transcriptions", &b)
+	req.Header.Set("Content-Type", w.FormDataContentType())
+	rec := httptest.NewRecorder()
+	proxy.ServeHTTP(rec, req)
 
-			// Create the request with the multipart form data
-			req := httptest.NewRequest("POST", "/v1/audio/transcriptions", &b)
-			req.Header.Set("Content-Type", w.FormDataContentType())
-			rec := httptest.NewRecorder()
-			proxy.HandlerFunc(rec, req)
-
-			// Verify the response
-			assert.Equal(t, http.StatusOK, rec.Code)
-			var response map[string]string
-			err = json.Unmarshal(rec.Body.Bytes(), &response)
-			assert.NoError(t, err)
-			assert.Equal(t, tc.expectModel, response["model"])
-			assert.Equal(t, response["text"], fmt.Sprintf("The length of the file is %d bytes", contentLength)) // matches simple-responder
-		})
-	}
-}
-
-func TestProxyManager_SplitRequestedModel(t *testing.T) {
-
-	tests := []struct {
-		name            string
-		requestedModel  string
-		expectedProfile string
-		expectedModel   string
-	}{
-		{"no profile", "gpt-4", "", "gpt-4"},
-		{"with profile", "profile1:gpt-4", "profile1", "gpt-4"},
-		{"only profile", "profile1:", "profile1", ""},
-		{"empty model", ":gpt-4", "", "gpt-4"},
-		{"empty profile", ":", "", ""},
-		{"no split char", "gpt-4", "", "gpt-4"},
-		{"profile and model with delimiter", "profile1:delimiter:gpt-4", "profile1", "delimiter:gpt-4"},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			profileName, modelName := splitRequestedModel(tt.requestedModel)
-			if profileName != tt.expectedProfile {
-				t.Errorf("splitRequestedModel(%q) = %q, %q; want %q, %q", tt.requestedModel, profileName, modelName, tt.expectedProfile, tt.expectedModel)
-			}
-			if modelName != tt.expectedModel {
-				t.Errorf("splitRequestedModel(%q) = %q, %q; want %q, %q", tt.requestedModel, profileName, modelName, tt.expectedProfile, tt.expectedModel)
-			}
-		})
-	}
+	// Verify the response
+	assert.Equal(t, http.StatusOK, rec.Code)
+	var response map[string]string
+	err = json.Unmarshal(rec.Body.Bytes(), &response)
+	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
 func TestProxyManager_UseModelName(t *testing.T) {
-
 	upstreamModelName := "upstreamModel"
-
 	modelConfig := getTestSimpleResponderConfig(upstreamModelName)
 	modelConfig.UseModelName = upstreamModelName
 
-	config := &Config{
+	config := AddDefaultGroupToConfig(Config{
 		HealthCheckTimeout: 15,
-		Profiles: map[string][]string{
-			"test": {"model1"},
-		},
-
 		Models: map[string]ModelConfig{
 			"model1": modelConfig,
 		},
-
 		LogLevel: "error",
-	}
+	})
 
 	proxy := New(config)
-	defer proxy.StopProcesses()
+	defer proxy.StopProcesses(StopWaitForInflightRequest)
 
-	tests := []struct {
-		description    string
-		requestedModel string
-	}{
-		{"useModelName over rides requested model", "model1"},
-		{"useModelName over rides requested profile:model", "test:model1"},
-	}
+	requestedModel := "model1"
 
-	for _, tt := range tests {
-		t.Run(tt.description+": /v1/chat/completions", func(t *testing.T) {
-			reqBody := fmt.Sprintf(`{"model":"%s"}`, tt.requestedModel)
-			req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
-			w := httptest.NewRecorder()
+	t.Run("useModelName over rides requested model: /v1/chat/completions", func(t *testing.T) {
+		reqBody := fmt.Sprintf(`{"model":"%s"}`, requestedModel)
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := httptest.NewRecorder()
 
-			proxy.HandlerFunc(w, req)
-			assert.Equal(t, http.StatusOK, w.Code)
-			assert.Contains(t, w.Body.String(), upstreamModelName)
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+		assert.Contains(t, w.Body.String(), upstreamModelName)
 
-		})
-	}
+		// make sure the content length was set correctly
+		// simple-responder will return the content length it got in the response
+		body := w.Body.Bytes()
+		contentLength := int(gjson.GetBytes(body, "h_content_length").Int())
+		assert.Equal(t, len(fmt.Sprintf(`{"model":"%s"}`, upstreamModelName)), contentLength)
+	})
 
-	for _, tt := range tests {
-		t.Run(tt.description+": /v1/audio/transcriptions", func(t *testing.T) {
-			// Create a buffer with multipart form data
-			var b bytes.Buffer
-			w := multipart.NewWriter(&b)
+	t.Run("useModelName over rides requested model: /v1/audio/transcriptions", func(t *testing.T) {
+		// Create a buffer with multipart form data
+		var b bytes.Buffer
+		w := multipart.NewWriter(&b)
 
-			// Add the model field
-			fw, err := w.CreateFormField("model")
-			assert.NoError(t, err)
-			_, err = fw.Write([]byte(tt.requestedModel))
-			assert.NoError(t, err)
+		// Add the model field
+		fw, err := w.CreateFormField("model")
+		assert.NoError(t, err)
+		_, err = fw.Write([]byte(requestedModel))
+		assert.NoError(t, err)
 
-			// Add a file field
-			fw, err = w.CreateFormFile("file", "test.mp3")
-			assert.NoError(t, err)
-			_, err = fw.Write([]byte("test"))
-			assert.NoError(t, err)
-			w.Close()
+		// Add a file field
+		fw, err = w.CreateFormFile("file", "test.mp3")
+		assert.NoError(t, err)
+		_, err = fw.Write([]byte("test"))
+		assert.NoError(t, err)
+		w.Close()
 
-			// Create the request with the multipart form data
-			req := httptest.NewRequest("POST", "/v1/audio/transcriptions", &b)
-			req.Header.Set("Content-Type", w.FormDataContentType())
-			rec := httptest.NewRecorder()
-			proxy.HandlerFunc(rec, req)
+		// Create the request with the multipart form data
+		req := httptest.NewRequest("POST", "/v1/audio/transcriptions", &b)
+		req.Header.Set("Content-Type", w.FormDataContentType())
+		rec := httptest.NewRecorder()
+		proxy.ServeHTTP(rec, req)
 
-			// Verify the response
-			assert.Equal(t, http.StatusOK, rec.Code)
-			var response map[string]string
-			err = json.Unmarshal(rec.Body.Bytes(), &response)
-			assert.NoError(t, err)
-			assert.Equal(t, upstreamModelName, response["model"])
-		})
-	}
+		// Verify the response
+		assert.Equal(t, http.StatusOK, rec.Code)
+		var response map[string]string
+		err = json.Unmarshal(rec.Body.Bytes(), &response)
+		assert.NoError(t, err)
+		assert.Equal(t, upstreamModelName, response["model"])
+	})
 }
 
 func TestProxyManager_CORSOptionsHandler(t *testing.T) {
-	config := &Config{
+	config := AddDefaultGroupToConfig(Config{
 		HealthCheckTimeout: 15,
 		Models: map[string]ModelConfig{
 			"model1": getTestSimpleResponderConfig("model1"),
 		},
 		LogLevel: "error",
-	}
+	})
 
 	tests := []struct {
 		name            string
@@ -702,7 +563,7 @@ func TestProxyManager_CORSOptionsHandler(t *testing.T) {
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			proxy := New(config)
-			defer proxy.StopProcesses()
+			defer proxy.StopProcesses(StopWaitForInflightRequest)
 
 			req := httptest.NewRequest(tt.method, "/v1/chat/completions", nil)
 			for k, v := range tt.requestHeaders {
@@ -710,7 +571,7 @@ 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)
 
@@ -720,3 +581,45 @@ func TestProxyManager_CORSOptionsHandler(t *testing.T) {
 		})
 	}
 }
+
+func TestProxyManager_Upstream(t *testing.T) {
+	config := AddDefaultGroupToConfig(Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]ModelConfig{
+			"model1": getTestSimpleResponderConfig("model1"),
+		},
+		LogLevel: "error",
+	})
+
+	proxy := New(config)
+	defer proxy.StopProcesses(StopWaitForInflightRequest)
+	req := httptest.NewRequest("GET", "/upstream/model1/test", nil)
+	rec := httptest.NewRecorder()
+	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(StopWaitForInflightRequest)
+
+	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"])
+}