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

Change the user back to root for containers. Additionally, built a "non-root" labeled container for users who wish to have the additional security of running llama-swap as a lower privileged user.
feat: add platform-specific process attributes support (#411 )
2025-11-25 10:44:13 -08:00 · 2025-11-24 21:39:56 -08:00 · 2025-11-17 10:43:47 -08:00 · 2025-11-16 10:21:59 -08:00 · 2025-11-15 14:35:26 -08:00 · 2025-11-08 15:29:37 -08:00
23 changed files with 809 additions and 65 deletions
@@ -0,0 +1,41 @@
+name: Validate JSON Schema
+
+on:
+  pull_request:
+    paths:
+      - "config-schema.json"
+  push:
+    branches:
+      - main
+    paths:
+      - "config-schema.json"
+
+  workflow_dispatch:
+
+jobs:
+  validate-schema:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Validate JSON Schema
+        run: |
+          # Check if the file is valid JSON
+          if ! jq empty config-schema.json 2>/dev/null; then
+            echo "Error: config-schema.json is not valid JSON"
+            exit 1
+          fi
+
+          # Validate that it's a valid JSON Schema
+          # Check for required $schema field
+          if ! jq -e '."$schema"' config-schema.json > /dev/null; then
+            echo "Warning: config-schema.json should have a \$schema field"
+          fi
+
+          # Check that it has either properties or definitions
+          if ! jq -e '.properties or .definitions or ."$defs"' config-schema.json > /dev/null; then
+            echo "Warning: JSON Schema should contain properties, definitions, or \$defs"
+          fi
+
+          echo "✓ config-schema.json is valid"
@@ -11,7 +11,7 @@ llama-swap is a light weight, transparent proxy server that provides automatic m

 ## Testing

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

 ## Workflow Tasks
@@ -42,7 +42,8 @@ Built in Go for performance and simplicity, llama-swap has zero dependencies and

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

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

 The Activity Page shows recent requests:

@@ -0,0 +1,64 @@
+<!DOCTYPE html>
+<html>
+<head>
+<meta charset="utf-8">
+<title>Loading...</title>
+<style>
+body {
+    font-family: sans-serif;
+    display: flex;
+    justify-content: center;
+    align-items: center;
+    height: 100vh;
+    margin: 0;
+    background: #f5f5f5;
+}
+.loader {
+    text-align: center;
+}
+.stats {
+    font-size: 18px;
+    color: #333;
+    margin: 20px 0;
+}
+.stats-label {
+    color: #666;
+    font-size: 14px;
+}
+</style>
+</head>
+<body>
+<div class="loader">
+    <p>Waking up upstream server...</p>
+    <div class="stats">
+        <div><span class="stats-label">Time elapsed:</span> <span id="elapsed">0s</span></div>
+        <div><span id="attempts">&nbsp;</span></div>
+    </div>
+</div>
+<script>
+var startTime = Date.now();
+var attempts = 0;
+
+setInterval(function() {
+    var elapsed = (Date.now() - startTime) / 1000;
+    document.getElementById('elapsed').textContent = elapsed.toFixed(1) + 's';
+}, 100);
+
+// Check status every second
+setInterval(function() {
+    attempts++;
+    var dots = '.'.repeat((attempts % 10) || 10);
+    document.getElementById('attempts').textContent = dots;
+
+    fetch('/status')
+        .then(function(r) { return r.text(); })
+        .then(function(t) {
+            if (t.indexOf('status: ready') !== -1) {
+                location.reload();
+            }
+        })
+        .catch(function() {});
+}, 1000);
+</script>
+</body>
+</html>
@@ -3,6 +3,7 @@ package main
 import (
 	"bufio"
 	"context"
+	_ "embed"
 	"errors"
 	"flag"
 	"fmt"
@@ -19,6 +20,9 @@ import (
 	"time"
 )

+//go:embed index.html
+var loadingPageHTML string
+
 var (
 	flagMac      = flag.String("mac", "", "mac address to send WoL packet to")
 	flagUpstream = flag.String("upstream", "", "upstream proxy address to send requests to")
@@ -230,6 +234,16 @@ func (p *proxyServer) ServeHTTP(w http.ResponseWriter, r *http.Request) {
 		if err := sendMagicPacket(*flagMac); err != nil {
 			slog.Warn("failed to send magic WoL packet", "error", err)
 		}
+
+		// For root or UI path requests, return loading page with status polling
+		// the web page will do the polling and redirect when ready
+		if path == "/" || strings.HasPrefix(path, "/ui/") {
+			w.Header().Set("Content-Type", "text/html; charset=utf-8")
+			w.WriteHeader(http.StatusOK)
+			fmt.Fprint(w, loadingPageHTML)
+			return
+		}
+
 		ticker := time.NewTicker(250 * time.Millisecond)
 		timeout, cancel := context.WithTimeout(context.Background(), time.Duration(*flagTimeout)*time.Second)
 		defer cancel()
@@ -0,0 +1,278 @@
+{
+    "$schema": "https://json-schema.org/draft-07/schema#",
+    "$id": "llama-swap-config-schema.json",
+    "title": "llama-swap configuration",
+    "description": "Configuration file for llama-swap",
+    "type": "object",
+    "required": [
+        "models"
+    ],
+    "definitions": {
+        "macros": {
+            "type": "object",
+            "additionalProperties": {
+                "oneOf": [
+                    {
+                        "type": "string",
+                        "minLength": 0,
+                        "maxLength": 1024
+                    },
+                    {
+                        "type": "number"
+                    },
+                    {
+                        "type": "boolean"
+                    }
+                ]
+            },
+            "propertyNames": {
+                "type": "string",
+                "minLength": 1,
+                "maxLength": 64,
+                "pattern": "^[a-zA-Z0-9_-]+$",
+                "not": {
+                    "enum": [
+                        "PORT",
+                        "MODEL_ID"
+                    ]
+                }
+            },
+            "default": {},
+            "description": "A dictionary of string substitutions. Macros are reusable snippets used in model cmd, cmdStop, proxy, checkEndpoint, filters.stripParams. Macro names must be <64 chars, match ^[a-zA-Z0-9_-]+$, and not be PORT or MODEL_ID. Values can be string, number, or boolean. Macros can reference other macros defined before them."
+        }
+    },
+    "properties": {
+        "healthCheckTimeout": {
+            "type": "integer",
+            "minimum": 15,
+            "default": 120,
+            "description": "Number of seconds to wait for a model to be ready to serve requests."
+        },
+        "logLevel": {
+            "type": "string",
+            "enum": [
+                "debug",
+                "info",
+                "warn",
+                "error"
+            ],
+            "default": "info",
+            "description": "Sets the logging value. Valid values: debug, info, warn, error."
+        },
+        "logTimeFormat": {
+            "type": "string",
+            "enum": [
+                "",
+                "ansic",
+                "unixdate",
+                "rubydate",
+                "rfc822",
+                "rfc822z",
+                "rfc850",
+                "rfc1123",
+                "rfc1123z",
+                "rfc3339",
+                "rfc3339nano",
+                "kitchen",
+                "stamp",
+                "stampmilli",
+                "stampmicro",
+                "stampnano"
+            ],
+            "default": "",
+            "description": "Enables and sets the logging timestamp format. Valid values: \"\", \"ansic\", \"unixdate\", \"rubydate\", \"rfc822\", \"rfc822z\", \"rfc850\", \"rfc1123\", \"rfc1123z\", \"rfc3339\", \"rfc3339nano\", \"kitchen\", \"stamp\", \"stampmilli\", \"stampmicro\", and \"stampnano\". For more info, read: https://pkg.go.dev/time#pkg-constants"
+        },
+        "metricsMaxInMemory": {
+            "type": "integer",
+            "default": 1000,
+            "description": "Maximum number of metrics to keep in memory. Controls how many metrics are stored before older ones are discarded."
+        },
+        "startPort": {
+            "type": "integer",
+            "default": 5800,
+            "description": "Starting port number for the automatic ${PORT} macro. The ${PORT} macro is incremented for every model that uses it."
+        },
+        "sendLoadingState": {
+            "type": "boolean",
+            "default": false,
+            "description": "Inject loading status updates into the reasoning field. When true, a stream of loading messages will be sent to the client."
+        },
+        "includeAliasesInList": {
+            "type": "boolean",
+            "default": false,
+            "description": "Present aliases within the /v1/models OpenAI API listing. when true, model aliases will be output to the API model listing duplicating all fields except for Id so chat UIs can use the alias equivalent to the original."
+        },
+        "macros": {
+            "$ref": "#/definitions/macros"
+        },
+        "models": {
+            "type": "object",
+            "description": "A dictionary of model configurations. Each key is a model's ID. Model settings have defaults if not defined. The model's ID is available as ${MODEL_ID}.",
+            "additionalProperties": {
+                "type": "object",
+                "required": [
+                    "cmd"
+                ],
+                "properties": {
+                    "macros": {
+                        "$ref": "#/definitions/macros"
+                    },
+                    "cmd": {
+                        "type": "string",
+                        "minLength": 1,
+                        "description": "Command to run to start the inference server. Macros can be used. Comments allowed with |."
+                    },
+                    "cmdStop": {
+                        "type": "string",
+                        "default": "",
+                        "description": "Command to run to stop the model gracefully. Uses ${PID} macro for upstream process id. If empty, default shutdown behavior is used."
+                    },
+                    "name": {
+                        "type": "string",
+                        "default": "",
+                        "maxLength": 128,
+                        "description": "Display name for the model. Used in v1/models API response."
+                    },
+                    "description": {
+                        "type": "string",
+                        "default": "",
+                        "maxLength": 1024,
+                        "description": "Description for the model. Used in v1/models API response."
+                    },
+                    "env": {
+                        "type": "array",
+                        "items": {
+                            "type": "string",
+                            "pattern": "^[A-Z_][A-Z0-9_]*=.*$"
+                        },
+                        "default": [],
+                        "description": "Array of environment variables to inject into cmd's environment. Each value is a string in ENV_NAME=value format."
+                    },
+                    "proxy": {
+                        "type": "string",
+                        "default": "http://localhost:${PORT}",
+                        "format": "uri",
+                        "description": "URL where llama-swap routes API requests. If custom port is used in cmd, this must be set."
+                    },
+                    "aliases": {
+                        "type": "array",
+                        "items": {
+                            "type": "string",
+                            "minLength": 1
+                        },
+                        "default": [],
+                        "description": "Alternative model names for this configuration. Must be unique globally."
+                    },
+                    "checkEndpoint": {
+                        "type": "string",
+                        "default": "/health",
+                        "pattern": "^/.*$|^none$",
+                        "description": "URL path to check if the server is ready. Use 'none' to skip health checking."
+                    },
+                    "ttl": {
+                        "type": "integer",
+                        "minimum": 0,
+                        "default": 0,
+                        "description": "Automatically unload the model after ttl seconds. 0 disables unloading. Must be >0 to enable."
+                    },
+                    "useModelName": {
+                        "type": "string",
+                        "default": "",
+                        "description": "Override the model name sent to upstream server. Useful if upstream expects a different name."
+                    },
+                    "filters": {
+                        "type": "object",
+                        "properties": {
+                            "stripParams": {
+                                "type": "string",
+                                "default": "",
+                                "pattern": "^[a-zA-Z0-9_, ]*$",
+                                "description": "Comma separated list of parameters to remove from the request. Used for server-side enforcement of sampling parameters."
+                            }
+                        },
+                        "additionalProperties": false,
+                        "default": {},
+                        "description": "Dictionary of filter settings. Only stripParams is supported."
+                    },
+                    "metadata": {
+                        "type": "object",
+                        "additionalProperties": true,
+                        "default": {},
+                        "description": "Dictionary of arbitrary values included in /v1/models. Can contain complex types. Only passed through in /v1/models responses."
+                    },
+                    "concurrencyLimit": {
+                        "type": "integer",
+                        "minimum": 0,
+                        "default": 0,
+                        "description": "Overrides allowed number of active parallel requests to a model. 0 uses internal default of 10. >0 overrides default. Requests exceeding limit get HTTP 429."
+                    },
+                    "sendLoadingState": {
+                        "type": "boolean",
+                        "description": "Overrides the global sendLoadingState for this model. Ommitting this property will use the global setting."
+                    },
+                    "unlisted": {
+                        "type": "boolean",
+                        "default": false,
+                        "description": "If true the model will not show up in /v1/models responses. It can still be used as normal in API requests."
+                    }
+                }
+            }
+        },
+        "groups": {
+            "type": "object",
+            "additionalProperties": {
+                "type": "object",
+                "required": [
+                    "members"
+                ],
+                "properties": {
+                    "swap": {
+                        "type": "boolean",
+                        "default": true,
+                        "description": "Controls model swapping behaviour within the group. True: only one model runs at a time. False: all models can run together."
+                    },
+                    "exclusive": {
+                        "type": "boolean",
+                        "default": true,
+                        "description": "Controls how the group affects other groups. True: causes all other groups to unload when this group runs a model. False: does not affect other groups."
+                    },
+                    "persistent": {
+                        "type": "boolean",
+                        "default": false,
+                        "description": "Prevents other groups from unloading the models in this group. Does not affect individual model behaviour."
+                    },
+                    "members": {
+                        "type": "array",
+                        "items": {
+                            "type": "string"
+                        },
+                        "description": "Array of model IDs that are members of this group. Model IDs must be defined in models."
+                    }
+                }
+            },
+            "description": "A dictionary of group settings. Provides advanced controls over model swapping behaviour. Model IDs must be defined in models. A model can only be a member of one group. Behaviour controlled via swap, exclusive, persistent."
+        },
+        "hooks": {
+            "type": "object",
+            "properties": {
+                "on_startup": {
+                    "type": "object",
+                    "properties": {
+                        "preload": {
+                            "type": "array",
+                            "items": {
+                                "type": "string"
+                            },
+                            "default": [],
+                            "description": "List of model IDs to load on startup. Model names must match keys in models. When preloading multiple models, define a group to prevent swapping."
+                        }
+                    },
+                    "additionalProperties": false,
+                    "description": "Actions to perform on startup. Only supported action is preload."
+                }
+            },
+            "additionalProperties": false,
+            "description": "A dictionary of event triggers and actions. Only supported hook is on_startup."
+        }
+    }
+}
@@ -1,3 +1,6 @@
+# add this modeline for validation in vscode
+# yaml-language-server: $schema=https://raw.githubusercontent.com/mostlygeek/llama-swap/refs/heads/main/config-schema.json
+#
 # llama-swap YAML configuration example
 # -------------------------------------
 #
@@ -23,6 +26,14 @@ healthCheckTimeout: 500
 # - Valid log levels: debug, info, warn, error
 logLevel: info

+# logTimeFormat: enables and sets the logging timestamp format
+# - optional, default (disabled): ""
+# - Valid values: "", "ansic", "unixdate", "rubydate", "rfc822", "rfc822z",
+#   "rfc850", "rfc1123", "rfc1123z", "rfc3339", "rfc3339nano", "kitchen",
+#   "stamp", "stampmilli", "stampmicro", and "stampnano".
+# - For more info, read: https://pkg.go.dev/time#pkg-constants
+logTimeFormat: ""
+
 # metricsMaxInMemory: maximum number of metrics to keep in memory
 # - optional, default: 1000
 # - controls how many metrics are stored in memory before older ones are discarded
@@ -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 ${MODEL_ID} macro, also available in macros defined above
 # - below are examples of the all the settings a model can have
 models:
-
  # keys are the model names used in API requests
  "llama":
    # macros: a dictionary of string substitutions specific to this model
@@ -298,10 +314,10 @@ hooks:
  # - optional, default: empty dictionary
  # - the only supported action is preload
  on_startup:
-        # preload: a list of model ids to load on startup
-        # - optional, default: empty list
-        # - model names must match keys in the models sections
-        # - when preloading multiple models at once, define a group
-        #   otherwise models will be loaded and swapped out
+    # preload: a list of model ids to load on startup
+    # - optional, default: empty list
+    # - model names must match keys in the models sections
+    # - when preloading multiple models at once, define a group
+    #   otherwise models will be loaded and swapped out
    preload:
-      - "llama"
+      - "llama"
@@ -25,31 +25,46 @@ fi
 LS_VER=$(curl -s https://api.github.com/repos/mostlygeek/llama-swap/releases/latest | jq -r .tag_name | sed 's/v//')

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

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

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

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

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

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

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

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

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

@@ -113,6 +113,7 @@ type Config struct {
 	HealthCheckTimeout int                    `yaml:"healthCheckTimeout"`
 	LogRequests        bool                   `yaml:"logRequests"`
 	LogLevel           string                 `yaml:"logLevel"`
+	LogTimeFormat      string                 `yaml:"logTimeFormat"`
 	MetricsMaxInMemory int                    `yaml:"metricsMaxInMemory"`
 	Models             map[string]ModelConfig `yaml:"models"` /* key is model ID */
 	Profiles           map[string][]string    `yaml:"profiles"`
@@ -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)
@@ -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",
-		StartPort: 5800,
+		LogLevel:      "info",
+		LogTimeFormat: "",
+		StartPort:     5800,
 		Macros: MacroList{
 			{"svr-path", "path/to/server"},
 		},
@@ -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",
-		StartPort: 5800,
+		LogLevel:      "info",
+		LogTimeFormat: "",
+		StartPort:     5800,
 		Macros: MacroList{
 			{"svr-path", "path/to/server"},
 		},
@@ -7,6 +7,7 @@ import (
 	"io"
 	"os"
 	"sync"
+	"time"

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

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

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

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

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

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

 func TestLogMonitor(t *testing.T) {
@@ -84,3 +86,30 @@ func TestWrite_ImmutableBuffer(t *testing.T) {
 		t.Errorf("Expected history to be %q, got %q", expected, history)
 	}
 }
+
+func TestWrite_LogTimeFormat(t *testing.T) {
+	// Create a new LogMonitor instance
+	lm := NewLogMonitorWriter(io.Discard)
+
+	// Enable timestamps
+	lm.timeFormat = time.RFC3339
+
+	// Write the message to the LogMonitor
+	lm.Info("Hello, World!")
+
+	// Get the history from the LogMonitor
+	history := lm.GetHistory()
+
+	timestamp := ""
+	fields := strings.Fields(string(history))
+	if len(fields) > 0 {
+		timestamp = fields[0]
+	} else {
+		t.Fatalf("Cannot extract string from history")
+	}
+
+	_, err := time.Parse(time.RFC3339, timestamp)
+	if err != nil {
+		t.Fatalf("Cannot find timestamp: %v", err)
+	}
+}
@@ -256,6 +256,7 @@ func (p *Process) start() error {
 	p.cmd.Env = append(p.cmd.Environ(), p.config.Env...)
 	p.cmd.Cancel = p.cmdStopUpstreamProcess
 	p.cmd.WaitDelay = p.gracefulStopTimeout
+	setProcAttributes(p.cmd)

 	p.cmdMutex.Lock()
 	p.cancelUpstream = ctxCancelUpstream
@@ -625,6 +626,7 @@ func (p *Process) cmdStopUpstreamProcess() error {
 		stopCmd := exec.Command(stopArgs[0], stopArgs[1:]...)
 		stopCmd.Stdout = p.processLogger
 		stopCmd.Stderr = p.processLogger
+		setProcAttributes(stopCmd)
 		stopCmd.Env = p.cmd.Env

 		if err := stopCmd.Run(); err != nil {
@@ -733,6 +735,14 @@ func (s *statusResponseWriter) statusUpdates(ctx context.Context) {
 	s.wg.Add(1)
 	defer s.wg.Done()

+	// Recover from panics caused by client disconnection
+	// Note: recover() only works within the same goroutine, so we need it here
+	defer func() {
+		if r := recover(); r != nil {
+			s.process.proxyLogger.Debugf("<%s> statusUpdates recovered from panic (likely client disconnect): %v", s.process.ID, r)
+		}
+	}()
+
 	defer func() {
 		duration := time.Since(s.start)
 		s.sendLine(fmt.Sprintf("\nDone! (%.2fs)", duration.Seconds()))
@@ -0,0 +1,12 @@
+//go:build !windows
+
+package proxy
+
+import (
+	"os/exec"
+)
+
+// setProcAttributes sets platform-specific process attributes
+func setProcAttributes(cmd *exec.Cmd) {
+	// No-op on Unix systems
+}
@@ -0,0 +1,16 @@
+//go:build windows
+
+package proxy
+
+import (
+	"os/exec"
+	"syscall"
+)
+
+// setProcAttributes sets platform-specific process attributes
+func setProcAttributes(cmd *exec.Cmd) {
+	cmd.SysProcAttr = &syscall.SysProcAttr{
+		HideWindow:    true,
+		CreationFlags: 0x08000000, // CREATE_NO_WINDOW
+	}
+}
@@ -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{
-			"id":       id,
-			"object":   "model",
-			"created":  createdTime,
-			"owned_by": "llama-swap",
+		newRecord := func(modelId string) gin.H {
+			record := gin.H{
+				"id":       modelId,
+				"object":   "model",
+				"created":  createdTime,
+				"owned_by": "llama-swap",
+			}
+
+			if name := strings.TrimSpace(modelConfig.Name); name != "" {
+				record["name"] = name
+			}
+			if desc := strings.TrimSpace(modelConfig.Description); desc != "" {
+				record["description"] = desc
+			}
+
+			// Add metadata if present
+			if len(modelConfig.Metadata) > 0 {
+				record["meta"] = gin.H{
+					"llamaswap": modelConfig.Metadata,
+				}
+			}
+			return record
 		}

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

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

 	// Sort by the "id" key
@@ -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
+}
@@ -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,
+	})
+}
@@ -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])
+	}
+}
@@ -2,7 +2,7 @@ import { useAPI } from "../contexts/APIProvider";
 import { useMemo } from "react";

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

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

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

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

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

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

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

  return <APIContext.Provider value={value}>{children}</APIContext.Provider>;
Author	SHA1	Message	Date
Ryan Steed	b1dec8b735	docker: build both root and non-root container images (#412 ) Change the user back to root for containers. Additionally, built a "non-root" labeled container for users who wish to have the additional security of running llama-swap as a lower privileged user.	2025-11-25 10:44:13 -08:00
Nikesh Parajuli	06523d8c1e	feat: add platform-specific process attributes support (#411 ) Fixes issues on Windows showing new windows for every process llama-swap spawns.	2025-11-24 21:39:56 -08:00
Ryan Steed	86e9b93c37	proxy,ui: add version endpoint and display version info in UI (#395 ) - Add /api/version endpoint to ProxyManager that returns build date, commit hash, and version - Implement SetVersion method to configure version info in ProxyManager - Add version info fetching to APIProvider and display in ConnectionStatus component - Include version info in UI context and update dependencies - Add tests for version endpoint functionality	2025-11-17 10:43:47 -08:00
Ryan Steed	3acace810f	proxy: add configurable logging timestamp format (#401 ) introduces a new configuration option logTimeFormat that allows customizing the timestamp in log messages using golang's built in time format constants. The default remains no timestamp.	2025-11-16 10:21:59 -08:00
Ryan Steed	554d29e87d	feat: enhance model listing to include aliases (#400 ) introduce includeAliasesInList as a new configuration setting (default false) that includes aliases in v1/models Fixes #399	2025-11-15 14:35:26 -08:00
Benson Wong	3567b7df08	Update image in README.md for web UI section	2025-11-08 15:29:37 -08:00
Benson Wong	38738525c9	config.example.yaml: add modeline for schema validation	2025-11-08 15:08:55 -08:00
Benson Wong	c0fc858193	Add configuration file JSON schema (#393 ) * add json schema for configuration * add GH action to validate schema	2025-11-08 15:04:14 -08:00
Benson Wong	b429349e8a	add /ui/ to wol-proxy polling (#388 )	2025-11-08 14:16:12 -08:00
Ryan Steed	eab2efd7b5	feat: improve llama.cpp base image tag for cpu (#391 ) Refactor the container build script to resolve llama.cpp base image for CPU, also tag these builds accordingly. - For CPU containers, now fetch the latest 'server' tagged llama.cpp image instead of using a generic 'server' tag - Cleans up the docker build command to use dynamic BASE_TAG variable - Maintains existing push functionality for built images	2025-11-08 09:56:49 -08:00
Benson Wong	6aedbe121a	cmd/wol-proxy: show a loading page for / (#381 ) When requesting / wol-proxy will show a loading page that polls /status every second. When the upstream server is ready the loading page will refresh causing the actual root page to be displayed	2025-11-03 19:37:06 -08:00
Ryan Steed	b24467ab89	fix: update containerfile user/group management commands (#379 ) - Replace `addgroup` with `groupadd` for system group creation - Replace `adduser` with `useradd` for system user creation - Maintain same functionality while using more standard POSIX commands	2025-11-03 17:17:40 -05:00
Benson Wong	12b69fb718	proxy: recover from panic in Process.statusUpdate (#378 ) Process.statusUpdate() panics when it can not write data, usually from a client disconnect. Since it runs in a goroutine and did not have a recover() the result was a crash. ref: https://github.com/mostlygeek/llama-swap/discussions/326#discussioncomment-14856197	2025-11-03 05:30:09 -08:00
Ryan Steed	f91a8b2462	refactor: update Containerfile to support non-root user execution and improve security (#368 ) Set default container user/group to lower privilege app user * refactor: update Containerfile to support non-root user execution and improve security - Updated LS_VER argument from 89 to 170 to use the latest version - Added UID/GID arguments with default values of 0 (root) for backward compatibility - Added USER_HOME environment variable set to /root - Implemented conditional user/group creation logic that only runs when UID/GID are not 0 - Created necessary directory structure with proper ownership using mkdir and chown commands - Switched to non-root user execution for improved security posture - Updated COPY instruction to use --chown flag for proper file ownership * chore: update containerfile to use non-root user with proper UID/GID - Changed default UID and GID from 0 (root) to 10001 for security best practices - Updated USER_HOME from /root to /app to avoid running as root user	2025-10-31 17:01:04 -07:00