Containerized build and socket activation docs

- Add /api/version endpoint to ProxyManager that returns build date, commit hash, and version
- Implement SetVersion method to configure version info in ProxyManager
- Add version info fetching to APIProvider and display in ConnectionStatus component
- Include version info in UI context and update dependencies
- Add tests for version endpoint functionality

.github/workflows/config-schema.yml

@@ -0,0 +1,41 @@
+name: Validate JSON Schema
+
+on:
+  pull_request:
+    paths:
+      - "config-schema.json"
+  push:
+    branches:
+      - main
+    paths:
+      - "config-schema.json"
+
+  workflow_dispatch:
+
+jobs:
+  validate-schema:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Validate JSON Schema
+        run: |
+          # Check if the file is valid JSON
+          if ! jq empty config-schema.json 2>/dev/null; then
+            echo "Error: config-schema.json is not valid JSON"
+            exit 1
+          fi
+
+          # Validate that it's a valid JSON Schema
+          # Check for required $schema field
+          if ! jq -e '."$schema"' config-schema.json > /dev/null; then
+            echo "Warning: config-schema.json should have a \$schema field"
+          fi
+
+          # Check that it has either properties or definitions
+          if ! jq -e '.properties or .definitions or ."$defs"' config-schema.json > /dev/null; then
+            echo "Warning: JSON Schema should contain properties, definitions, or \$defs"
+          fi
+
+          echo "✓ config-schema.json is valid"

Build.Containerfile

@@ -0,0 +1,60 @@
+# Stage 1: Build UI with Node.js
+FROM node:25.2.1-trixie-slim AS ui-builder
+
+WORKDIR /app
+
+# Copy UI source
+COPY ui/package*.json ./
+RUN npm install -g typescript && npm ci --only=production
+RUN npm install --save-dev @types/react @types/react-dom
+
+# Build UI
+COPY ui/ ./
+RUN npm run build
+
+# Stage 2: Build Go binary with embedded UI
+FROM golang:1.25.4 AS go-builder
+
+WORKDIR /app
+
+# Copy go mod and sum files
+COPY go.mod go.sum ./
+
+# Download dependencies
+RUN go mod download
+
+# Copy all source code
+COPY . .
+
+# Copy UI build artifacts to embed directory
+#COPY --from=ui-builder /app/build ./ui/build
+COPY --from=ui-builder /proxy/ui_dist ./proxy/ui_dist
+# Build the binary (Linux AMD64)
+RUN CGO_ENABLED=0 GOOS=linux GOARCH=amd64 \
+    go build -ldflags="-X main.commit=$(git rev-parse --short HEAD) -X main.version=local_$(git rev-parse --short HEAD) -X main.date=$(date -u +"%Y-%m-%dT%H:%M:%SZ")" \
+    -o build/llama-swap
+
+
+FROM ghcr.io/ggml-org/llama.cpp:full-vulkan
+
+# has to be after the FROM
+ARG LS_VER=170
+
+# Add user/group
+ENV HOME=/app
+
+
+
+WORKDIR /app
+
+# Copy the binary from builder stage
+COPY --from=go-builder /app/build/llama-swap .
+
+
+COPY  ./docker/config.example.yaml /config.yaml
+
+
+ENTRYPOINT [ "/app/llama-swap", "-config", "/config.yaml" ]
+
+
+

README.md

@@ -1,3 +1,15 @@
+# Llama Swap fork with socket activation
+
+This is a fork of https://github.com/mostlygeek/llama-swap with the following changes
+ - Support for systemd socket activation
+ - Container file for fully containerized build with podman targetting Linux and Vulkan
+ - Documentation and example service files how to set up a socket activated 
+   podman container isolated with network=none
+   (see [Readme](docs/socket_activation/README.md) )
+ 
+# Original readme:
+
+
 ![llama-swap header image](header2.png)
 ![GitHub Downloads (all assets, all releases)](https://img.shields.io/github/downloads/mostlygeek/llama-swap/total)
 ![GitHub Actions Workflow Status](https://img.shields.io/github/actions/workflow/status/mostlygeek/llama-swap/go-ci.yml)
@@ -42,7 +54,8 @@ Built in Go for performance and simplicity, llama-swap has zero dependencies and
 
 llama-swap includes a real time web interface for monitoring logs and controlling models:
 
-<img width="1360" height="963" alt="image" src="https://github.com/user-attachments/assets/adef4a8e-de0b-49db-885a-8f6dedae6799" />
+<img width="1164" height="745" alt="image" src="https://github.com/user-attachments/assets/bacf3f9d-819f-430b-9ed2-1bfaa8d54579" />
+
 
 The Activity Page shows recent requests:
 

cmd/wol-proxy/wol-proxy.go

@@ -235,8 +235,9 @@ func (p *proxyServer) ServeHTTP(w http.ResponseWriter, r *http.Request) {
 			slog.Warn("failed to send magic WoL packet", "error", err)
 		}
 
-		// For root path requests, return loading page with status polling
+		// For root or UI path requests, return loading page with status polling
-		if path == "/" {
+		// the web page will do the polling and redirect when ready
+		if path == "/" || strings.HasPrefix(path, "/ui/") {
 			w.Header().Set("Content-Type", "text/html; charset=utf-8")
 			w.WriteHeader(http.StatusOK)
 			fmt.Fprint(w, loadingPageHTML)

config-schema.json

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

config.example.yaml

@@ -1,3 +1,6 @@
+# add this modeline for validation in vscode
+# yaml-language-server: $schema=https://raw.githubusercontent.com/mostlygeek/llama-swap/refs/heads/main/config-schema.json
+#
 # llama-swap YAML configuration example
 # -------------------------------------
 #
@@ -23,6 +26,14 @@ healthCheckTimeout: 500
 # - Valid log levels: debug, info, warn, error
 logLevel: info
 
+# logTimeFormat: enables and sets the logging timestamp format
+# - optional, default (disabled): ""
+# - Valid values: "", "ansic", "unixdate", "rubydate", "rfc822", "rfc822z",
+#   "rfc850", "rfc1123", "rfc1123z", "rfc3339", "rfc3339nano", "kitchen",
+#   "stamp", "stampmilli", "stampmicro", and "stampnano".
+# - For more info, read: https://pkg.go.dev/time#pkg-constants
+logTimeFormat: ""
+
 # metricsMaxInMemory: maximum number of metrics to keep in memory
 # - optional, default: 1000
 # - controls how many metrics are stored in memory before older ones are discarded
@@ -43,6 +54,12 @@ startPort: 10001
 # - see #366 for more details
 sendLoadingState: true
 
+# includeAliasesInList: present aliases within the /v1/models OpenAI API listing
+# - optional, default: false
+# - when true, model aliases will be output to the API model listing duplicating
+#   all fields except for Id so chat UIs can use the alias equivalent to the original.
+includeAliasesInList: false
+
 # macros: a dictionary of string substitutions
 # - optional, default: empty dictionary
 # - macros are reusable snippets
@@ -72,7 +89,6 @@ macros:
 # - the model's ID is available in the ${MODEL_ID} macro, also available in macros defined above
 # - below are examples of the all the settings a model can have
 models:
-
   # keys are the model names used in API requests
   "llama":
     # macros: a dictionary of string substitutions specific to this model
@@ -298,10 +314,10 @@ hooks:
   # - optional, default: empty dictionary
   # - the only supported action is preload
   on_startup:
-        # preload: a list of model ids to load on startup
+    # preload: a list of model ids to load on startup
-        # - optional, default: empty list
+    # - optional, default: empty list
-        # - model names must match keys in the models sections
+    # - model names must match keys in the models sections
-        # - when preloading multiple models at once, define a group
+    # - when preloading multiple models at once, define a group
-        #   otherwise models will be loaded and swapped out
+    #   otherwise models will be loaded and swapped out
     preload:
-      - "llama"
+      - "llama"

docs/socket_activation/README.md

@@ -0,0 +1,41 @@
+# Rootless podman container with Systemd Socket activation
+
+## Idea
+By passing in the socket from systemd we minimize resource use when not in use.
+Since no other network access is required for operation, we can configure the container
+with network=none and minimize the risk of the AI escaping. 
+
+## Set up 
+
+Optional, if you want to run this as a separate user
+```
+sudo useradd llama
+sudo machinectl shell llama@
+```
+
+Check out this repository, navigate to its root directory and build the llama.cpp/llama swap 
+container with
+```
+podman build -t localhost/lamaswap:latest -f Build.Containerfile
+```
+
+Place llama.socket in ` ~/.config/systemd/user`, adjust ports and interfaces if needed.
+Place llama.container in `~/.config/containers/systemd`. Adjust paths for models and config if desired.
+The files are in `docs/socket_activation`, next to this readme.
+
+Put model files into the models directory (`~/models`).
+Create a llama swap `config.yaml` (by default in `~`) according to the docs.
+
+Start the socket:
+```
+systemctl --user daemon-reload
+systemctl --user enable --now llama.socket
+```
+
+If you want to run the service also when the user is not logged in, enable lingering:
+```
+sudo loginctl enable-linger <user>
+```
+
+Check that you can access the llama swap control panel in browser. For troubleshooting, use, e. g., `journalctl -xe`.
+

docs/socket_activation/llama.container

@@ -0,0 +1,20 @@
+[Unit]
+Description=LLama.cpp (full‑vulkan) inference server
+After=network-online.target
+Wants=network-online.target
+
+[Container]
+Image=localhost/lamaswap:latest
+#AutoRemove=yes
+#PublishPort=8080:8080
+Network=none
+Volume=%h/models:/models:ro,Z
+Volume=%h/config.yaml:/config.yaml:ro,Z
+AddDevice=/dev/dri
+Exec= 
+
+#[Service]
+#Restart=always
+
+[Install]
+WantedBy=default.target

docs/socket_activation/llama.socket

@@ -0,0 +1,8 @@
+[Unit]
+Description=llama socket
+
+[Socket]
+ListenStream=0.0.0.0:8080
+
+[Install]
+WantedBy=default.target

go.mod

@@ -17,6 +17,7 @@ require (
 	github.com/bytedance/sonic/loader v0.1.1 // indirect
 	github.com/cloudwego/base64x v0.1.4 // indirect
 	github.com/cloudwego/iasm v0.2.0 // indirect
+	github.com/coreos/go-systemd/v22 v22.6.0 // indirect
 	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/gabriel-vasile/mimetype v1.4.3 // indirect
 	github.com/gin-contrib/sse v0.1.0 // indirect

go.sum

@@ -8,6 +8,8 @@ github.com/cloudwego/base64x v0.1.4 h1:jwCgWpFanWmN8xoIUHa2rtzmkd5J2plF/dnLS6Xd/
 github.com/cloudwego/base64x v0.1.4/go.mod h1:0zlkT4Wn5C6NdauXdJRhSKRlJvmclQ1hhJgA0rcu/8w=
 github.com/cloudwego/iasm v0.2.0 h1:1KNIy1I1H9hNNFEEH3DVnI4UujN+1zjpuk6gwHLTssg=
 github.com/cloudwego/iasm v0.2.0/go.mod h1:8rXZaNYT2n95jn+zTI1sDr+IgcD2GVs0nlbbQPiEFhY=
+github.com/coreos/go-systemd/v22 v22.6.0 h1:aGVa/v8B7hpb0TKl0MWoAavPDmHvobFe5R5zn0bCJWo=
+github.com/coreos/go-systemd/v22 v22.6.0/go.mod h1:iG+pp635Fo7ZmV/j14KUcmEyWF+0X7Lua8rrTWzYgWU=
 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=

llama-swap.go

@@ -5,15 +5,16 @@ import (
 	"flag"
 	"fmt"
 	"log"
+	"net"
 	"net/http"
 	"os"
 	"os/signal"
 	"path/filepath"
 	"syscall"
 	"time"
-
 	"github.com/fsnotify/fsnotify"
 	"github.com/gin-gonic/gin"
+	"github.com/coreos/go-systemd/v22/activation"
 	"github.com/mostlygeek/llama-swap/event"
 	"github.com/mostlygeek/llama-swap/proxy"
 	"github.com/mostlygeek/llama-swap/proxy/config"
@@ -64,15 +65,33 @@ func main() {
 		fmt.Println("Error: Both --tls-cert-file and --tls-key-file must be provided for TLS.")
 		os.Exit(1)
 	}
-
+	// Check for systemd socket activation
-	// Set default ports.
+	var listener net.Listener
-	if *listenStr == "" {
+	files, err := activation.Listeners()
-		defaultPort := ":8080"
+	if err != nil {
-		if useTLS {
+		log.Fatalf("Systemd activation error: %v", err)
-			defaultPort = ":8443"
-		}
-		listenStr = &defaultPort
 	}
+	if len(files) > 0 {
+		if len(files) > 1 {
+			log.Fatalf("Expected a single activated socket, got %d", len(files))
+		}
+		listener = files[0]
+		log.Printf("Using systemd socket %s", listener.Addr())
+	} else {
+		// Set default ports.
+		if *listenStr == "" {
+			defaultPort := ":8080"
+			if useTLS {
+				defaultPort = ":8443"
+			}
+			listenStr = &defaultPort
+			listener, err = net.Listen("tcp", *listenStr)
+        		if err != nil {
+            			log.Fatal("Failed to listen:", err)
+        		}
+		}
+	}
+	defer listener.Close()
 
 	// Setup channels for server management
 	exitChan := make(chan struct{})
@@ -81,7 +100,7 @@ func main() {
 
 	// Create server with initial handler
 	srv := &http.Server{
-		Addr: *listenStr,
+		//Addr: *listenStr,
 	}
 
 	// Support for watching config and reloading when it changes
@@ -95,7 +114,9 @@ func main() {
 
 			fmt.Println("Configuration Changed")
 			currentPM.Shutdown()
-			srv.Handler = proxy.New(conf)
+			newPM := proxy.New(conf)
+			newPM.SetVersion(date, commit, version)
+			srv.Handler = newPM
 			fmt.Println("Configuration Reloaded")
 
 			// wait a few seconds and tell any UI to reload
@@ -110,7 +131,9 @@ func main() {
 				fmt.Printf("Error, unable to load configuration: %v\n", err)
 				os.Exit(1)
 			}
-			srv.Handler = proxy.New(conf)
+			newPM := proxy.New(conf)
+			newPM.SetVersion(date, commit, version)
+			srv.Handler = newPM
 		}
 	}
 
@@ -190,10 +213,10 @@ func main() {
 		var err error
 		if useTLS {
 			fmt.Printf("llama-swap listening with TLS on https://%s\n", *listenStr)
-			err = srv.ListenAndServeTLS(*certFile, *keyFile)
+			err = srv.ServeTLS(listener, *certFile, *keyFile)
 		} else {
 			fmt.Printf("llama-swap listening on http://%s\n", *listenStr)
-			err = srv.ListenAndServe()
+			err = srv.Serve(listener)
 		}
 		if err != nil && err != http.ErrServerClosed {
 			log.Fatalf("Fatal server error: %v\n", err)

proxy/config/config.go

@@ -113,6 +113,7 @@ type Config struct {
 	HealthCheckTimeout int                    `yaml:"healthCheckTimeout"`
 	LogRequests        bool                   `yaml:"logRequests"`
 	LogLevel           string                 `yaml:"logLevel"`
+	LogTimeFormat      string                 `yaml:"logTimeFormat"`
 	MetricsMaxInMemory int                    `yaml:"metricsMaxInMemory"`
 	Models             map[string]ModelConfig `yaml:"models"` /* key is model ID */
 	Profiles           map[string][]string    `yaml:"profiles"`
@@ -132,6 +133,9 @@ type Config struct {
 
 	// send loading state in reasoning
 	SendLoadingState bool `yaml:"sendLoadingState"`
+
+	// present aliases to /v1/models OpenAI API listing
+	IncludeAliasesInList bool `yaml:"includeAliasesInList"`
 }
 
 func (c *Config) RealModelName(search string) (string, bool) {
@@ -172,6 +176,7 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		HealthCheckTimeout: 120,
 		StartPort:          5800,
 		LogLevel:           "info",
+		LogTimeFormat:      "",
 		MetricsMaxInMemory: 1000,
 	}
 	err = yaml.Unmarshal(data, &config)

proxy/config/config_posix_test.go

@@ -58,6 +58,7 @@ models:
 	assert.Equal(t, 120, config.HealthCheckTimeout)
 	assert.Equal(t, 5800, config.StartPort)
 	assert.Equal(t, "info", config.LogLevel)
+	assert.Equal(t, "", config.LogTimeFormat)
 
 	// Test default group exists
 	defaultGroup, exists := config.Groups["(default)"]
@@ -163,8 +164,9 @@ groups:
 	modelLoadingState := false
 
 	expected := Config{
-		LogLevel:  "info",
+		LogLevel:      "info",
-		StartPort: 5800,
+		LogTimeFormat: "",
+		StartPort:     5800,
 		Macros: MacroList{
 			{"svr-path", "path/to/server"},
 		},

proxy/config/config_windows_test.go

@@ -55,6 +55,7 @@ models:
 	assert.Equal(t, 120, config.HealthCheckTimeout)
 	assert.Equal(t, 5800, config.StartPort)
 	assert.Equal(t, "info", config.LogLevel)
+	assert.Equal(t, "", config.LogTimeFormat)
 
 	// Test default group exists
 	defaultGroup, exists := config.Groups["(default)"]
@@ -155,8 +156,9 @@ groups:
 	modelLoadingState := false
 
 	expected := Config{
-		LogLevel:  "info",
+		LogLevel:      "info",
-		StartPort: 5800,
+		LogTimeFormat: "",
+		StartPort:     5800,
 		Macros: MacroList{
 			{"svr-path", "path/to/server"},
 		},

proxy/logMonitor.go

@@ -7,6 +7,7 @@ import (
 	"io"
 	"os"
 	"sync"
+	"time"
 
 	"github.com/mostlygeek/llama-swap/event"
 )
@@ -32,6 +33,9 @@ type LogMonitor struct {
 	// logging levels
 	level  LogLevel
 	prefix string
+
+	// timestamps
+	timeFormat string
 }
 
 func NewLogMonitor() *LogMonitor {
@@ -40,11 +44,12 @@ func NewLogMonitor() *LogMonitor {
 
 func NewLogMonitorWriter(stdout io.Writer) *LogMonitor {
 	return &LogMonitor{
-		eventbus: event.NewDispatcherConfig(1000),
+		eventbus:   event.NewDispatcherConfig(1000),
-		buffer:   ring.New(10 * 1024), // keep 10KB of buffered logs
+		buffer:     ring.New(10 * 1024), // keep 10KB of buffered logs
-		stdout:   stdout,
+		stdout:     stdout,
-		level:    LevelInfo,
+		level:      LevelInfo,
-		prefix:   "",
+		prefix:     "",
+		timeFormat: "",
 	}
 }
 
@@ -106,12 +111,22 @@ func (w *LogMonitor) SetLogLevel(level LogLevel) {
 	w.level = level
 }
 
+func (w *LogMonitor) SetLogTimeFormat(timeFormat string) {
+	w.mu.Lock()
+	defer w.mu.Unlock()
+	w.timeFormat = timeFormat
+}
+
 func (w *LogMonitor) formatMessage(level string, msg string) []byte {
 	prefix := ""
 	if w.prefix != "" {
 		prefix = fmt.Sprintf("[%s] ", w.prefix)
 	}
-	return []byte(fmt.Sprintf("%s[%s] %s\n", prefix, level, msg))
+	timestamp := ""
+	if w.timeFormat != "" {
+		timestamp = fmt.Sprintf("%s ", time.Now().Format(w.timeFormat))
+	}
+	return []byte(fmt.Sprintf("%s%s[%s] %s\n", timestamp, prefix, level, msg))
 }
 
 func (w *LogMonitor) log(level LogLevel, msg string) {

proxy/logMonitor_test.go

@@ -3,8 +3,10 @@ package proxy
 import (
 	"bytes"
 	"io"
+	"strings"
 	"sync"
 	"testing"
+	"time"
 )
 
 func TestLogMonitor(t *testing.T) {
@@ -84,3 +86,30 @@ func TestWrite_ImmutableBuffer(t *testing.T) {
 		t.Errorf("Expected history to be %q, got %q", expected, history)
 	}
 }
+
+func TestWrite_LogTimeFormat(t *testing.T) {
+	// Create a new LogMonitor instance
+	lm := NewLogMonitorWriter(io.Discard)
+
+	// Enable timestamps
+	lm.timeFormat = time.RFC3339
+
+	// Write the message to the LogMonitor
+	lm.Info("Hello, World!")
+
+	// Get the history from the LogMonitor
+	history := lm.GetHistory()
+
+	timestamp := ""
+	fields := strings.Fields(string(history))
+	if len(fields) > 0 {
+		timestamp = fields[0]
+	} else {
+		t.Fatalf("Cannot extract string from history")
+	}
+
+	_, err := time.Parse(time.RFC3339, timestamp)
+	if err != nil {
+		t.Fatalf("Cannot find timestamp: %v", err)
+	}
+}

proxy/proxymanager.go

@@ -45,6 +45,11 @@ type ProxyManager struct {
 	// shutdown signaling
 	shutdownCtx    context.Context
 	shutdownCancel context.CancelFunc
+
+	// version info
+	buildDate string
+	commit    string
+	version   string
 }
 
 func New(config config.Config) *ProxyManager {
@@ -75,6 +80,30 @@ func New(config config.Config) *ProxyManager {
 		upstreamLogger.SetLogLevel(LevelInfo)
 	}
 
+	// see: https://go.dev/src/time/format.go
+	timeFormats := map[string]string{
+		"ansic":       time.ANSIC,
+		"unixdate":    time.UnixDate,
+		"rubydate":    time.RubyDate,
+		"rfc822":      time.RFC822,
+		"rfc822z":     time.RFC822Z,
+		"rfc850":      time.RFC850,
+		"rfc1123":     time.RFC1123,
+		"rfc1123z":    time.RFC1123Z,
+		"rfc3339":     time.RFC3339,
+		"rfc3339nano": time.RFC3339Nano,
+		"kitchen":     time.Kitchen,
+		"stamp":       time.Stamp,
+		"stampmilli":  time.StampMilli,
+		"stampmicro":  time.StampMicro,
+		"stampnano":   time.StampNano,
+	}
+
+	if timeFormat, ok := timeFormats[strings.ToLower(strings.TrimSpace(config.LogTimeFormat))]; ok {
+		proxyLogger.SetLogTimeFormat(timeFormat)
+		upstreamLogger.SetLogTimeFormat(timeFormat)
+	}
+
 	shutdownCtx, shutdownCancel := context.WithCancel(context.Background())
 
 	var maxMetrics int
@@ -98,6 +127,10 @@ func New(config config.Config) *ProxyManager {
 
 		shutdownCtx:    shutdownCtx,
 		shutdownCancel: shutdownCancel,
+
+		buildDate: "unknown",
+		commit:    "abcd1234",
+		version:   "0",
 	}
 
 	// create the process groups
@@ -376,28 +409,40 @@ func (pm *ProxyManager) listModelsHandler(c *gin.Context) {
 			continue
 		}
 
-		record := gin.H{
+		newRecord := func(modelId string) gin.H {
-			"id":       id,
+			record := gin.H{
-			"object":   "model",
+				"id":       modelId,
-			"created":  createdTime,
+				"object":   "model",
-			"owned_by": "llama-swap",
+				"created":  createdTime,
+				"owned_by": "llama-swap",
+			}
+
+			if name := strings.TrimSpace(modelConfig.Name); name != "" {
+				record["name"] = name
+			}
+			if desc := strings.TrimSpace(modelConfig.Description); desc != "" {
+				record["description"] = desc
+			}
+
+			// Add metadata if present
+			if len(modelConfig.Metadata) > 0 {
+				record["meta"] = gin.H{
+					"llamaswap": modelConfig.Metadata,
+				}
+			}
+			return record
 		}
 
-		if name := strings.TrimSpace(modelConfig.Name); name != "" {
+		data = append(data, newRecord(id))
-			record["name"] = name
-		}
-		if desc := strings.TrimSpace(modelConfig.Description); desc != "" {
-			record["description"] = desc
-		}
 
-		// Add metadata if present
+		// Include aliases
-		if len(modelConfig.Metadata) > 0 {
+		if pm.config.IncludeAliasesInList {
-			record["meta"] = gin.H{
+			for _, alias := range modelConfig.Aliases {
-				"llamaswap": modelConfig.Metadata,
+				if alias := strings.TrimSpace(alias); alias != "" {
+					data = append(data, newRecord(alias))
+				}
 			}
 		}
-
-		data = append(data, record)
 	}
 
 	// Sort by the "id" key
@@ -734,3 +779,11 @@ func (pm *ProxyManager) findGroupByModelName(modelName string) *ProcessGroup {
 	}
 	return nil
 }
+
+func (pm *ProxyManager) SetVersion(buildDate string, commit string, version string) {
+	pm.Lock()
+	defer pm.Unlock()
+	pm.buildDate = buildDate
+	pm.commit = commit
+	pm.version = version
+}

proxy/proxymanager_api.go

@@ -28,6 +28,7 @@ func addApiHandlers(pm *ProxyManager) {
 		apiGroup.POST("/models/unload/*model", pm.apiUnloadSingleModelHandler)
 		apiGroup.GET("/events", pm.apiSendEvents)
 		apiGroup.GET("/metrics", pm.apiGetMetrics)
+		apiGroup.GET("/version", pm.apiGetVersion)
 	}
 }
 
@@ -227,3 +228,11 @@ func (pm *ProxyManager) apiUnloadSingleModelHandler(c *gin.Context) {
 		c.String(http.StatusOK, "OK")
 	}
 }
+
+func (pm *ProxyManager) apiGetVersion(c *gin.Context) {
+	c.JSON(http.StatusOK, map[string]string{
+		"version":    pm.version,
+		"commit":     pm.commit,
+		"build_date": pm.buildDate,
+	})
+}

proxy/proxymanager_test.go

@@ -437,6 +437,70 @@ func TestProxyManager_ListModelsHandler_SortedByID(t *testing.T) {
 	}
 }
 
+func TestProxyManager_ListModelsHandler_IncludeAliasesInList(t *testing.T) {
+	// Configure alias
+	config := config.Config{
+		HealthCheckTimeout:   15,
+		IncludeAliasesInList: true,
+		Models: map[string]config.ModelConfig{
+			"model1": func() config.ModelConfig {
+				mc := getTestSimpleResponderConfig("model1")
+				mc.Name = "Model 1"
+				mc.Aliases = []string{"alias1"}
+				return mc
+			}(),
+		},
+		LogLevel: "error",
+	}
+
+	proxy := New(config)
+
+	// Request models list
+	req := httptest.NewRequest("GET", "/v1/models", nil)
+	w := CreateTestResponseRecorder()
+	proxy.ServeHTTP(w, req)
+
+	assert.Equal(t, http.StatusOK, w.Code)
+
+	var response struct {
+		Data []map[string]interface{} `json:"data"`
+	}
+	if err := json.Unmarshal(w.Body.Bytes(), &response); err != nil {
+		t.Fatalf("Failed to parse JSON response: %v", err)
+	}
+
+	// We expect both base id and alias
+	var model1Data, alias1Data map[string]any
+	for _, model := range response.Data {
+		if model["id"] == "model1" {
+			model1Data = model
+		} else if model["id"] == "alias1" {
+			alias1Data = model
+		}
+	}
+
+	// Verify model1 has name
+	assert.NotNil(t, model1Data)
+	_, exists := model1Data["name"]
+	if !assert.True(t, exists, "model1 should have name key") {
+		t.FailNow()
+	}
+	name1, ok := model1Data["name"].(string)
+	assert.True(t, ok, "name1 should be a string")
+
+	// Verify alias1 has name
+	assert.NotNil(t, alias1Data)
+	_, exists = alias1Data["name"]
+	if !assert.True(t, exists, "alias1 should have name key") {
+		t.FailNow()
+	}
+	name2, ok := alias1Data["name"].(string)
+	assert.True(t, ok, "name2 should be a string")
+
+	// Name keys should match
+	assert.Equal(t, name1, name2)
+}
+
 func TestProxyManager_Shutdown(t *testing.T) {
 	// make broken model configurations
 	model1Config := getTestSimpleResponderConfigPort("model1", 9991)
@@ -1083,3 +1147,41 @@ func TestProxyManager_ProxiedStreamingEndpointReturnsNoBufferingHeader(t *testin
 	assert.Equal(t, "no", rec.Header().Get("X-Accel-Buffering"))
 	assert.Contains(t, rec.Header().Get("Content-Type"), "text/event-stream")
 }
+
+func TestProxyManager_ApiGetVersion(t *testing.T) {
+	config := config.AddDefaultGroupToConfig(config.Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]config.ModelConfig{
+			"model1": getTestSimpleResponderConfig("model1"),
+		},
+		LogLevel: "error",
+	})
+
+	// Version test map
+	versionTest := map[string]string{
+		"build_date": "1970-01-01T00:00:00Z",
+		"commit":     "cc915ddb6f04a42d9cd1f524e1d46ec6ed069fdc",
+		"version":    "v001",
+	}
+
+	proxy := New(config)
+	proxy.SetVersion(versionTest["build_date"], versionTest["commit"], versionTest["version"])
+	defer proxy.StopProcesses(StopWaitForInflightRequest)
+
+	req := httptest.NewRequest("GET", "/api/version", nil)
+	w := CreateTestResponseRecorder()
+
+	proxy.ServeHTTP(w, req)
+
+	assert.Equal(t, http.StatusOK, w.Code)
+
+	// Ensure json response
+	assert.Equal(t, "application/json; charset=utf-8", w.Header().Get("Content-Type"))
+
+	// Check for attributes
+	response := map[string]string{}
+	assert.NoError(t, json.Unmarshal(w.Body.Bytes(), &response))
+	for key, value := range versionTest {
+		assert.Equal(t, value, response[key], "%s value %s should match response %s", key, value, response[key])
+	}
+}

ui/src/components/ConnectionStatus.tsx

@@ -2,7 +2,7 @@ import { useAPI } from "../contexts/APIProvider";
 import { useMemo } from "react";
 
 const ConnectionStatusIcon = () => {
-  const { connectionStatus } = useAPI();
+  const { connectionStatus, versionInfo } = useAPI();
 
   const eventStatusColor = useMemo(() => {
     switch (connectionStatus) {
@@ -17,7 +17,7 @@ const ConnectionStatusIcon = () => {
   }, [connectionStatus]);
 
   return (
-    <div className="flex items-center" title={`event stream: ${connectionStatus}`}>
+    <div className="flex items-center" title={`Event Stream: ${connectionStatus ?? 'unknown'}\nAPI Version: ${versionInfo?.version ?? 'unknown'}\nCommit Hash: ${versionInfo?.commit?.substring(0,7) ?? 'unknown'}\nBuild Date: ${versionInfo?.build_date ?? 'unknown'}`}>
       <span className={`inline-block w-3 h-3 rounded-full ${eventStatusColor} mr-2`}></span>
     </div>
   );

ui/src/contexts/APIProvider.tsx

@@ -23,6 +23,7 @@ interface APIProviderType {
   upstreamLogs: string;
   metrics: Metrics[];
   connectionStatus: ConnectionState;
+  versionInfo: VersionInfo;
 }
 
 interface Metrics {
@@ -41,11 +42,18 @@ interface LogData {
   source: "upstream" | "proxy";
   data: string;
 }
+
 interface APIEventEnvelope {
   type: "modelStatus" | "logData" | "metrics";
   data: string;
 }
 
+interface VersionInfo {
+  build_date: string;
+  commit: string;
+  version: string;
+}
+
 const APIContext = createContext<APIProviderType | undefined>(undefined);
 type APIProviderProps = {
   children: ReactNode;
@@ -59,6 +67,11 @@ export function APIProvider({ children, autoStartAPIEvents = true }: APIProvider
   const [upstreamLogs, setUpstreamLogs] = useState("");
   const [metrics, setMetrics] = useState<Metrics[]>([]);
   const [connectionStatus, setConnectionState] = useState<ConnectionState>("disconnected");
+  const [versionInfo, setVersionInfo] = useState<VersionInfo>({
+    build_date: "unknown",
+    commit: "unknown",
+    version: "unknown"
+  });
   //const apiEventSource = useRef<EventSource | null>(null);
 
   const [models, setModels] = useState<Model[]>([]);
@@ -152,6 +165,26 @@ export function APIProvider({ children, autoStartAPIEvents = true }: APIProvider
     connect();
   }, []);
 
+  useEffect(() => {
+    // fetch version 
+    const fetchVersion = async () => {
+      try {
+        const response = await fetch("/api/version");
+        if (!response.ok) {
+          throw new Error(`HTTP error! status: ${response.status}`);
+        }
+        const data: VersionInfo = await response.json();
+        setVersionInfo(data);
+      } catch (error) {
+        console.error(error);
+      }
+    };
+
+    if (connectionStatus === 'connected') {
+      fetchVersion();
+    }
+  }, [connectionStatus]);
+
   useEffect(() => {
     if (autoStartAPIEvents) {
       enableAPIEvents(true);
@@ -230,8 +263,9 @@ export function APIProvider({ children, autoStartAPIEvents = true }: APIProvider
       upstreamLogs,
       metrics,
       connectionStatus,
+      versionInfo,
     }),
-    [models, listModels, unloadAllModels, loadModel, enableAPIEvents, proxyLogs, upstreamLogs, metrics]
+    [models, listModels, unloadAllModels, unloadSingleModel, loadModel, enableAPIEvents, proxyLogs, upstreamLogs, metrics, connectionStatus, versionInfo]
   );
 
   return <APIContext.Provider value={value}>{children}</APIContext.Provider>;