proxy: add /v1/responses and /v1/audio/voices endpoints (#448)

Updates #433
Fixes #442 #226

.coderabbit.yaml

@@ -8,8 +8,15 @@ reviews:
   poem: false
   review_status: true
   collapse_walkthrough: false
+  sequence_diagrams: false
+  finishing_touches:
+    docstrings:
+      enabled: false
   auto_review:
     enabled: true
     drafts: false
 chat:
   auto_reply: true
+issue_enrichment:
+  planning:
+    enabled: false

.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"

CLAUDE.md

@@ -11,8 +11,10 @@ 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-all` - runs at the end before completing work. Includes long running concurrency tests.
+- Follow test naming conventions like `TestProxyManager_<test name>`, `TestProcessGroup_<test name>`, etc.
+- Use `go test -v -run <name pattern for new tests>` to run any new tests you've written.
+- Use `make test-dev` after running new tests for a quick over all test run. This runs `go test` and `staticcheck`. Fix any static checking errors. Use this only when changes are made to any code under the `proxy/` directory
+- Use `make test-all` before completing work. This includes long running concurrency tests.
 
 ## Workflow Tasks
 

README.md

@@ -1,4 +1,4 @@
-![llama-swap header image](header2.png)
+![llama-swap header image](docs/assets/hero3.webp)
 ![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)
 ![GitHub Repo stars](https://img.shields.io/github/stars/mostlygeek/llama-swap)
@@ -13,14 +13,20 @@ Built in Go for performance and simplicity, llama-swap has zero dependencies and
 
 - ✅ Easy to deploy and configure: one binary, one configuration file. no external dependencies
 - ✅ On-demand model switching
-- ✅ Use any local OpenAI compatible server (llama.cpp, vllm, tabbyAPI, etc)
+- ✅ Use any local OpenAI compatible server (llama.cpp, vllm, tabbyAPI, etc.)
   - future proof, upgrade your inference servers at any time.
 - ✅ OpenAI API supported endpoints:
   - `v1/completions`
   - `v1/chat/completions`
+  - `v1/responses`
   - `v1/embeddings`
   - `v1/audio/speech` ([#36](https://github.com/mostlygeek/llama-swap/issues/36))
   - `v1/audio/transcriptions` ([docs](https://github.com/mostlygeek/llama-swap/issues/41#issuecomment-2722637867))
+  - `v1/audio/voices`
+  - `v1/images/generations`
+  - `v1/images/edits`
+- ✅ Anthropic API supported endpoints:
+  - `v1/messages`
 - ✅ llama-server (llama.cpp) supported endpoints
   - `v1/rerank`, `v1/reranking`, `/rerank`
   - `/infill` - for code infilling
@@ -32,6 +38,7 @@ Built in Go for performance and simplicity, llama-swap has zero dependencies and
   - `/running` - list currently running models ([#61](https://github.com/mostlygeek/llama-swap/issues/61))
   - `/log` - remote log monitoring
   - `/health` - just returns "OK"
+- ✅ API Key support - define keys to restrict access to API endpoints
 - ✅ Customizable
   - 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`
@@ -42,7 +49,7 @@ 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:
 
@@ -60,7 +67,7 @@ llama-swap can be installed in multiple ways
 
 ### Docker Install ([download images](https://github.com/mostlygeek/llama-swap/pkgs/container/llama-swap))
 
-Nightly container images with llama-swap and llama-server are built for multiple platforms (cuda, vulkan, intel, etc).
+Nightly container images with llama-swap and llama-server are built for multiple platforms (cuda, vulkan, intel, etc.) including [non-root variants with improved security](docs/container-security.md).
 
 ```shell
 $ docker pull ghcr.io/mostlygeek/llama-swap:cuda
@@ -70,6 +77,14 @@ $ docker run -it --rm --runtime nvidia -p 9292:8080 \
  -v /path/to/models:/models \
  -v /path/to/custom/config.yaml:/app/config.yaml \
  ghcr.io/mostlygeek/llama-swap:cuda
+
+# configuration hot reload supported with a
+# directory volume mount
+$ docker run -it --rm --runtime nvidia -p 9292:8080 \
+ -v /path/to/models:/models \
+ -v /path/to/custom/config.yaml:/app/config.yaml \
+ -v /path/to/config:/config \
+ ghcr.io/mostlygeek/llama-swap:cuda -config /config/config.yaml -watch-config
 ```
 
 <details>
@@ -88,6 +103,9 @@ docker pull ghcr.io/mostlygeek/llama-swap:musa
 # tagged llama-swap, platform and llama-server version images
 docker pull ghcr.io/mostlygeek/llama-swap:v166-cuda-b6795
 
+# non-root cuda
+docker pull ghcr.io/mostlygeek/llama-swap:cuda-non-root
+
 ```
 
 </details>
@@ -190,23 +208,26 @@ As a safeguard, llama-swap also sets `X-Accel-Buffering: no` on SSE responses. H
 
 ## Monitoring Logs on the CLI
 
-```shell
+```sh
 # sends up to the last 10KB of logs
-curl http://host/logs'
+$ curl http://host/logs
 
 # streams combined logs
-curl -Ns 'http://host/logs/stream'
+curl -Ns http://host/logs/stream
 
-# just llama-swap's logs
-curl -Ns 'http://host/logs/stream/proxy'
+# stream llama-swap's proxy status logs
+curl -Ns http://host/logs/stream/proxy
 
-# just upstream's logs
-curl -Ns 'http://host/logs/stream/upstream'
+# stream logs from upstream processes that llama-swap loads
+curl -Ns http://host/logs/stream/upstream
+
+# stream logs only from a specific model
+curl -Ns http://host/logs/stream/{model_id}
 
 # stream and filter logs with linux pipes
 curl -Ns http://host/logs/stream | grep 'eval time'
 
-# skips history and just streams new log entries
+# appending ?no-history will disable sending buffered history first
 curl -Ns 'http://host/logs/stream?no-history'
 ```
 

ai-plans/2025-12-14-efficient-ring-buffer.md

@@ -0,0 +1,85 @@
+# Replace ring.Ring with Efficient Circular Byte Buffer
+
+## Overview
+
+Replace the inefficient `container/ring.Ring` implementation in `logMonitor.go` with a simple circular byte buffer that uses a single contiguous `[]byte` slice. This eliminates per-write allocations, improves cache locality, and correctly implements a 10KB buffer.
+
+## Current Issues
+
+1. `ring.New(10 * 1024)` creates 10,240 ring **elements**, not 10KB of storage
+2. Every `Write()` call allocates a new `[]byte` slice inside the lock
+3. `GetHistory()` iterates all 10,240 elements and appends repeatedly (geometric reallocs)
+4. Linked list structure has poor cache locality and pointer overhead
+
+## Design Requirements
+
+### New CircularBuffer Type
+
+Create a simple circular byte buffer with:
+- Single pre-allocated `[]byte` of fixed capacity (10KB)
+- `head` and `size` integers to track write position and data length
+- No per-write allocations
+
+### API Requirements
+
+The new buffer must support:
+1. **Write(p []byte)** - Append bytes, overwriting oldest data when full
+2. **GetHistory() []byte** - Return all buffered data in correct order (oldest to newest)
+
+### Implementation Details
+
+```go
+type circularBuffer struct {
+    data []byte  // pre-allocated capacity
+    head int     // next write position
+    size int     // current number of bytes stored (0 to cap)
+}
+```
+
+**Write logic:**
+- If `len(p) >= capacity`: just keep the last `capacity` bytes
+- Otherwise: write bytes at `head`, wrapping around if needed
+- Update `head` and `size` accordingly
+- Data is copied into the internal buffer (not stored by reference)
+
+**GetHistory logic:**
+- Calculate start position: `(head - size + cap) % cap`
+- If not wrapped: single slice copy
+- If wrapped: two copies (end of buffer + beginning)
+- Returns a **new slice** (copy), not a view into internal buffer
+
+### Immutability Guarantees (must preserve)
+
+Per existing tests:
+1. Modifying input `[]byte` after `Write()` must not affect stored data
+2. `GetHistory()` returns independent copy - modifications don't affect buffer
+
+## Files to Modify
+
+- `proxy/logMonitor.go` - Replace `buffer *ring.Ring` with new circular buffer
+
+## Testing Plan
+
+Existing tests in `logMonitor_test.go` should continue to pass:
+- `TestLogMonitor` - Basic write/read and subscriber notification
+- `TestWrite_ImmutableBuffer` - Verify writes don't affect returned history
+- `TestWrite_LogTimeFormat` - Timestamp formatting
+
+Add new tests:
+- Test buffer wrap-around behavior
+- Test large writes that exceed buffer capacity
+- Test exact capacity boundary conditions
+
+## Checklist
+
+- [ ] Create `circularBuffer` struct in `logMonitor.go`
+- [ ] Implement `Write()` method for circular buffer
+- [ ] Implement `GetHistory()` method for circular buffer
+- [ ] Update `LogMonitor` struct to use new buffer
+- [ ] Update `NewLogMonitorWriter()` to initialize new buffer
+- [ ] Update `LogMonitor.Write()` to use new buffer
+- [ ] Update `LogMonitor.GetHistory()` to use new buffer
+- [ ] Remove `"container/ring"` import
+- [ ] Run `make test-dev` to verify existing tests pass
+- [ ] Add wrap-around test case
+- [ ] Run `make test-all` for final validation

cmd/wol-proxy/index.html

@@ -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>

cmd/wol-proxy/wol-proxy.go

@@ -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()

config-schema.json

@@ -0,0 +1,330 @@
+{
+    "$schema": "https://json-schema.org/draft-07/schema#",
+    "$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."
+        },
+        "logToStdout": {
+            "type": "string",
+            "enum": [
+                "proxy",
+                "upstream",
+                "both",
+                "none"
+            ],
+            "default": "proxy",
+            "description": "Controls what is logged to stdout. 'proxy': logs generated by llama-swap, 'upstream': copy of upstream process stdout logs, 'both': both interleaved together, 'none': no logs written to stdout."
+        },
+        "apiKeys": {
+            "type": "array",
+            "items": {
+                "type": "string",
+                "minLength": 1
+            },
+            "default": [],
+            "description": "Require an API key when making requests to inference endpoints. When empty, authorization will not be checked. Each key is a non-empty string."
+        },
+        "peers": {
+            "type": "object",
+            "additionalProperties": {
+                "type": "object",
+                "required": [
+                    "proxy",
+                    "models"
+                ],
+                "properties": {
+                    "proxy": {
+                        "type": "string",
+                        "format": "uri",
+                        "description": "A valid base URL to proxy requests to. Requested path to llama-swap will be appended to the end of the proxy value."
+                    },
+                    "apiKey": {
+                        "type": "string",
+                        "default": "",
+                        "description": "A string key to be injected into the request. If blank, no key will be added. Key will be injected into headers: Authorization: Bearer <key> and x-api-key: <key>."
+                    },
+                    "models": {
+                        "type": "array",
+                        "items": {
+                            "type": "string",
+                            "minLength": 1
+                        },
+                        "description": "A list of models served by the peer."
+                    }
+                }
+            },
+            "default": {},
+            "description": "A dictionary of remote peers and models they provide. Peers can be another llama-swap or any server that provides the /v1/ generative API endpoints supported by llama-swap."
+        }
+    }
+}

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 +26,24 @@ 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: ""
+
+# logToStdout: controls what is logged to stdout
+# - optional, default: "proxy"
+# - valid values:
+#   - "proxy": logs generated by llama-swap when swapping models,
+#      handling requests, etc.
+#   - "upstream": a copy of an upstream processes stdout logs
+#   - "both": both the proxy and upstream logs interleaved together
+#   - "none": no logs are ever written to stdout
+logToStdout: "proxy"
+
 # metricsMaxInMemory: maximum number of metrics to keep in memory
 # - optional, default: 1000
 # - controls how many metrics are stored in memory before older ones are discarded
@@ -35,6 +56,30 @@ metricsMaxInMemory: 1000
 # - it is automatically incremented for every model that uses it
 startPort: 10001
 
+# sendLoadingState: inject loading status updates into the reasoning (thinking)
+# field
+# - optional, default: false
+# - when true, a stream of loading messages will be sent to the client in the
+#   reasoning field so chat UIs can show that loading is in progress.
+# - see #366 for more details
+sendLoadingState: true
+
+# includeAliasesInList: present aliases within the /v1/models OpenAI API listing
+# - optional, default: false
+# - when true, model aliases will be output to the API model listing duplicating
+#   all fields except for Id so chat UIs can use the alias equivalent to the original.
+includeAliasesInList: false
+
+# apiKeys: require an API key when making requests to inference endpoints
+# - optional, default: []
+# - when empty (the default) authorization will not be checked as llama-swap is default-allow
+# - each key is a non-empty string
+apiKeys:
+  - "sk-hunter2"
+  # hint, one liner: printf "sk-%s\n" "$(head -c 48 /dev/urandom | base64 )"
+  - "sk-gyCPiKUcIfPlaM4OSMZekkprgijPx6+OsmQs8Rsg0xZ9qpy6gKWsIKqHOk+cgXVx"
+  - "sk-+QtIn0Zjj4UHjiaZYiZEnru4mrwKM9RzhmJeK5SobNXLl8QMFXxGz1/2lEuvQpkb"
+
 # macros: a dictionary of string substitutions
 # - optional, default: empty dictionary
 # - macros are reusable snippets
@@ -64,7 +109,6 @@ macros:
 # - the model's ID is available in the ${MODEL_ID} macro, also available in macros defined above
 # - below are examples of the all the settings a model can have
 models:
-
   # keys are the model names used in API requests
   "llama":
     # macros: a dictionary of string substitutions specific to this model
@@ -184,6 +228,10 @@ models:
     # - recommended to be omitted and the default used
     concurrencyLimit: 0
 
+    # sendLoadingState: overrides the global sendLoadingState setting for this model
+    # - optional, default: undefined (use global setting)
+    sendLoadingState: false
+
   # Unlisted model example:
   "qwen-unlisted":
     # unlisted: boolean, true or false
@@ -286,10 +334,42 @@ 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"
+
+# peers: a dictionary of remote peers and models they provide
+# - optional, default empty dictionary
+# - peers can be another llama-swap
+# - peers can be any server that provides the /v1/ generative api endpoints supported by llama-swap
+peers:
+  # keys is the peer'd ID
+  llama-swap-peer:
+    # proxy: a valid base URL to proxy requests to
+    # - required
+    # - requested path to llama-swap will be appended to the end of the proxy value
+    proxy: http://192.168.1.23
+    # models: a list of models served by the peer
+    # - required
+    models:
+      - model_a
+      - model_b
+      - embeddings/model_c
+  openrouter:
+    proxy: https://openrouter.ai/api
+    # apiKey: a string key to be injected into the request
+    # - optional, default: ""
+    # - if blank, no key will be added to the request
+    # - key will be injected into headers: Authorization: Bearer <key> and x-api-key: <key>
+    apiKey: sk-your-openrouter-key
+    models:
+      - meta-llama/llama-3.1-8b-instruct
+      - qwen/qwen3-235b-a22b-2507
+      - deepseek/deepseek-v3.2
+      - z-ai/glm-4.7
+      - moonshotai/kimi-k2-0905
+      - minimax/minimax-m2.1

docker/build-container.sh

@@ -20,36 +20,60 @@ if [[ -z "$GITHUB_TOKEN" ]]; then
   exit 1
 fi
 
+# Set llama.cpp base image, customizable using the BASE_LLAMACPP_IMAGE environment
+# variable, this permits testing with forked llama.cpp repositories
+BASE_IMAGE=${BASE_LLAMACPP_IMAGE:-ghcr.io/ggml-org/llama.cpp}
+
+# Set llama-swap repository, automatically uses GITHUB_REPOSITORY variable
+# to enable easy container builds on forked repos
+LS_REPO=${GITHUB_REPOSITORY:-mostlygeek/llama-swap}
+
 # the most recent llama-swap tag
 # have to strip out the 'v' due to .tar.gz file naming
-LS_VER=$(curl -s https://api.github.com/repos/mostlygeek/llama-swap/releases/latest | jq -r .tag_name | sed 's/v//')
+LS_VER=$(curl -s https://api.github.com/repos/${LS_REPO}/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 ${CONTAINER_LATEST}
-    fi
-fi
+for CONTAINER_TYPE in non-root root; do
+  CONTAINER_TAG="ghcr.io/${LS_REPO}:v${LS_VER}-${ARCH}-${LCPP_TAG}"
+  CONTAINER_LATEST="ghcr.io/${LS_REPO}:${ARCH}"
+  USER_UID=0
+  USER_GID=0
+  USER_HOME=/root
+
+  if [ "$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 LS_REPO=${LS_REPO} --build-arg GID=${USER_GID} --build-arg USER_HOME=${USER_HOME} -t ${CONTAINER_TAG} -t ${CONTAINER_LATEST} \
+    --build-arg BASE_IMAGE=${BASE_IMAGE} .
+  if [ "$PUSH_IMAGES" == "true" ]; then
+    docker push ${CONTAINER_TAG}
+    docker push ${CONTAINER_LATEST}
+  fi
+done

docker/llama-swap.Containerfile

@@ -1,16 +1,44 @@
+ARG BASE_IMAGE=ghcr.io/ggml-org/llama.cpp
 ARG BASE_TAG=server-cuda
-FROM ghcr.io/ggml-org/llama.cpp:${BASE_TAG}
+FROM ${BASE_IMAGE}:${BASE_TAG}
 
 # has to be after the FROM
-ARG LS_VER=89
+ARG LS_VER=170
+ARG LS_REPO=mostlygeek/llama-swap
+
+# 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 \
-    curl -LO https://github.com/mostlygeek/llama-swap/releases/download/v"${LS_VER}"/llama-swap_"${LS_VER}"_linux_amd64.tar.gz && \
-    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
+# Add /app to PATH
+ENV PATH="/app:${PATH}"
+
+RUN \
+    curl -LO "https://github.com/${LS_REPO}/releases/download/v${LS_VER}/llama-swap_${LS_VER}_linux_amd64.tar.gz" && \
+    tar -zxf "llama-swap_${LS_VER}_linux_amd64.tar.gz" && \
+    rm "llama-swap_${LS_VER}_linux_amd64.tar.gz"
+
+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" ]

docs/configuration.md

@@ -86,9 +86,12 @@ llama-swap supports many more features to customize how you want to manage your
 ## Full Configuration Example
 
 > [!NOTE]
-> This is a copy of `config.example.yaml`. Always check that for the most up to date examples.
+> Always check [config.example.yaml](https://github.com/mostlygeek/llama-swap/blob/main/config.example.yaml) for the most up to date reference for all example configurations.
 
 ```yaml
+# 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
 # -------------------------------------
 #
@@ -114,6 +117,24 @@ 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: ""
+
+# logToStdout: controls what is logged to stdout
+# - optional, default: "proxy"
+# - valid values:
+#   - "proxy": logs generated by llama-swap when swapping models,
+#      handling requests, etc.
+#   - "upstream": a copy of an upstream processes stdout logs
+#   - "both": both the proxy and upstream logs interleaved together
+#   - "none": no logs are ever written to stdout
+logToStdout: "proxy"
+
 # 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
@@ -126,6 +147,30 @@ metricsMaxInMemory: 1000
 # - it is automatically incremented for every model that uses it
 startPort: 10001
 
+# sendLoadingState: inject loading status updates into the reasoning (thinking)
+# field
+# - optional, default: false
+# - when true, a stream of loading messages will be sent to the client in the
+#   reasoning field so chat UIs can show that loading is in progress.
+# - see #366 for more details
+sendLoadingState: true
+
+# includeAliasesInList: present aliases within the /v1/models OpenAI API listing
+# - optional, default: false
+# - when true, model aliases will be output to the API model listing duplicating
+#   all fields except for Id so chat UIs can use the alias equivalent to the original.
+includeAliasesInList: false
+
+# apiKeys: require an API key when making requests to inference endpoints
+# - optional, default: []
+# - when empty (the default) authorization will not be checked as llama-swap is default-allow
+# - each key is a non-empty string
+apiKeys:
+  - "sk-hunter2"
+  # hint, one liner: printf "sk-%s\n" "$(head -c 48 /dev/urandom | base64 )"
+  - "sk-gyCPiKUcIfPlaM4OSMZekkprgijPx6+OsmQs8Rsg0xZ9qpy6gKWsIKqHOk+cgXVx"
+  - "sk-+QtIn0Zjj4UHjiaZYiZEnru4mrwKM9RzhmJeK5SobNXLl8QMFXxGz1/2lEuvQpkb"
+
 # macros: a dictionary of string substitutions
 # - optional, default: empty dictionary
 # - macros are reusable snippets
@@ -274,6 +319,10 @@ models:
     # - recommended to be omitted and the default used
     concurrencyLimit: 0
 
+    # sendLoadingState: overrides the global sendLoadingState setting for this model
+    # - optional, default: undefined (use global setting)
+    sendLoadingState: false
+
   # Unlisted model example:
   "qwen-unlisted":
     # unlisted: boolean, true or false
@@ -383,4 +432,36 @@ hooks:
     #   otherwise models will be loaded and swapped out
     preload:
       - "llama"
+
+# peers: a dictionary of remote peers and models they provide
+# - optional, default empty dictionary
+# - peers can be another llama-swap
+# - peers can be any server that provides the /v1/ generative api endpoints supported by llama-swap
+peers:
+  # keys is the peer'd ID
+  llama-swap-peer:
+    # proxy: a valid base URL to proxy requests to
+    # - required
+    # - requested path to llama-swap will be appended to the end of the proxy value
+    proxy: http://192.168.1.23
+    # models: a list of models served by the peer
+    # - required
+    models:
+      - model_a
+      - model_b
+      - embeddings/model_c
+  openrouter:
+    proxy: https://openrouter.ai/api
+    # apiKey: a string key to be injected into the request
+    # - optional, default: ""
+    # - if blank, no key will be added to the request
+    # - key will be injected into headers: Authorization: Bearer <key> and x-api-key: <key>
+    apiKey: sk-your-openrouter-key
+    models:
+      - meta-llama/llama-3.1-8b-instruct
+      - qwen/qwen3-235b-a22b-2507
+      - deepseek/deepseek-v3.2
+      - z-ai/glm-4.7
+      - moonshotai/kimi-k2-0905
+      - minimax/minimax-m2.1
 ```

docs/container-security.md

@@ -0,0 +1,9 @@
+## Container Security
+
+For convenience, the default container images use the **root** user within the container. This permits simplified access to host resources including volume mounts and hardware devices under `/dev/dri` (_for Vulkan support_). But this can widen the attack surface to privilege escalation exploits.
+
+Alternative images, tagged as `non-root`, are also available. For example, `llama-swap:cpu-non-root` uses the unprivileged **app** user by default. Depending on deployment requirements, additional configuration may be necessary to ensure that the container retains access to required hosts resources. This might entail customizing host filesystem permissions/ownership appropriately or injecting host group membership into the container.
+
+Docker offers a [system-wide option enabling user namespace remapping](https://docs.docker.com/engine/security/userns-remap/) to accommodate situations were a **root** container user is required but also mentions that _"The best way to prevent privilege-escalation attacks from within a container is to configure your container's applications to run as unprivileged users."_ Podman offers similar capability, per-container, to [set UID/GID mapping in a new user namespace](https://docs.podman.io/en/latest/markdown/podman-run.1.html#set-uid-gid-mapping-in-a-new-user-namespace).
+
+The Large Language Model (_LLM/AI_) ecosystem is rapidly evolving and [serious security vulnerabilities have surfaced in the past](https://huggingface.co/docs/hub/security-pickle). These alternative _non-root_ images could reduce the impact of future unknown problems. However, proper planning and configuration is recommended to utilize them.

go.mod

@@ -1,6 +1,6 @@
 module github.com/mostlygeek/llama-swap
 
-go 1.23.0
+go 1.25.4
 
 require (
 	github.com/billziss-gh/golib v0.2.0
@@ -37,9 +37,9 @@ require (
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
 	github.com/ugorji/go/codec v1.2.12 // indirect
 	golang.org/x/arch v0.8.0 // indirect
-	golang.org/x/crypto v0.36.0 // indirect
-	golang.org/x/net v0.38.0 // indirect
-	golang.org/x/sys v0.31.0 // indirect
-	golang.org/x/text v0.23.0 // indirect
+	golang.org/x/crypto v0.45.0 // indirect
+	golang.org/x/net v0.47.0 // indirect
+	golang.org/x/sys v0.38.0 // indirect
+	golang.org/x/text v0.31.0 // indirect
 	google.golang.org/protobuf v1.34.1 // indirect
 )

go.sum

@@ -80,16 +80,16 @@ 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 v0.36.0 h1:AnAEvhDddvBdpY+uR+MyHmuZzzNqXSe/GvuDeob5L34=
-golang.org/x/crypto v0.36.0/go.mod h1:Y4J0ReaxCR1IMaabaSMugxJES1EpwhBHhv2bDHklZvc=
-golang.org/x/net v0.38.0 h1:vRMAPTMaeGqVhG5QyLJHqNDwecKTomGeqbnfZyKlBI8=
-golang.org/x/net v0.38.0/go.mod h1:ivrbrMbzFq5J41QOQh0siUuly180yBYtLp+CKbEaFx8=
+golang.org/x/crypto v0.45.0 h1:jMBrvKuj23MTlT0bQEOBcAE0mjg8mK9RXFhRH6nyF3Q=
+golang.org/x/crypto v0.45.0/go.mod h1:XTGrrkGJve7CYK7J8PEww4aY7gM3qMCElcJQ8n8JdX4=
+golang.org/x/net v0.47.0 h1:Mx+4dIFzqraBXUugkia1OOvlD6LemFo1ALMHjrXDOhY=
+golang.org/x/net v0.47.0/go.mod h1:/jNxtkgq5yWUGYkaZGqo27cfGZ1c5Nen03aYrrKpVRU=
 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 v0.31.0 h1:ioabZlmFYtWhL+TRYpcnNlLwhyxaM9kWTDEmfnprqik=
-golang.org/x/sys v0.31.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
-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/sys v0.38.0 h1:3yZWxaJjBmCWXqhN1qh02AkOnCQ1poK6oF+a7xWL6Gc=
+golang.org/x/sys v0.38.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks=
+golang.org/x/text v0.31.0 h1:aC8ghyu4JhP8VojJ2lEHBnochRno1sgL6nEi9WGFGMM=
+golang.org/x/text v0.31.0/go.mod h1:tKRAlv61yKIjGGHX/4tP1LTbc13YSec1pxVEWXzfoeM=
 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=

llama-swap.go

@@ -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
 		}
 	}
 

proxy/config/config.go

@@ -15,6 +15,12 @@ import (
 )
 
 const DEFAULT_GROUP_ID = "(default)"
+const (
+	LogToStdoutProxy    = "proxy"
+	LogToStdoutUpstream = "upstream"
+	LogToStdoutBoth     = "both"
+	LogToStdoutNone     = "none"
+)
 
 type MacroEntry struct {
 	Name  string
@@ -113,6 +119,8 @@ type Config struct {
 	HealthCheckTimeout int                    `yaml:"healthCheckTimeout"`
 	LogRequests        bool                   `yaml:"logRequests"`
 	LogLevel           string                 `yaml:"logLevel"`
+	LogTimeFormat      string                 `yaml:"logTimeFormat"`
+	LogToStdout        string                 `yaml:"logToStdout"`
 	MetricsMaxInMemory int                    `yaml:"metricsMaxInMemory"`
 	Models             map[string]ModelConfig `yaml:"models"` /* key is model ID */
 	Profiles           map[string][]string    `yaml:"profiles"`
@@ -129,6 +137,18 @@ type Config struct {
 
 	// hooks, see: #209
 	Hooks HooksConfig `yaml:"hooks"`
+
+	// send loading state in reasoning
+	SendLoadingState bool `yaml:"sendLoadingState"`
+
+	// present aliases to /v1/models OpenAI API listing
+	IncludeAliasesInList bool `yaml:"includeAliasesInList"`
+
+	// support API keys, see issue #433, #50, #251
+	RequiredAPIKeys []string `yaml:"apiKeys"`
+
+	// support remote peers, see issue #433, #296
+	Peers PeerDictionaryConfig `yaml:"peers"`
 }
 
 func (c *Config) RealModelName(search string) (string, bool) {
@@ -169,6 +189,8 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		HealthCheckTimeout: 120,
 		StartPort:          5800,
 		LogLevel:           "info",
+		LogTimeFormat:      "",
+		LogToStdout:        LogToStdoutProxy,
 		MetricsMaxInMemory: 1000,
 	}
 	err = yaml.Unmarshal(data, &config)
@@ -185,6 +207,12 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		return Config{}, fmt.Errorf("startPort must be greater than 1")
 	}
 
+	switch config.LogToStdout {
+	case LogToStdoutProxy, LogToStdoutUpstream, LogToStdoutBoth, LogToStdoutNone:
+	default:
+		return Config{}, fmt.Errorf("logToStdout must be one of: proxy, upstream, both, none")
+	}
+
 	// Populate the aliases map
 	config.aliases = make(map[string]string)
 	for modelName, modelConfig := range config.Models {
@@ -350,6 +378,13 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 			)
 		}
 
+		// if sendLoadingState is nil, set it to the global config value
+		// see #366
+		if modelConfig.SendLoadingState == nil {
+			v := config.SendLoadingState // copy it
+			modelConfig.SendLoadingState = &v
+		}
+
 		config.Models[modelId] = modelConfig
 	}
 
@@ -389,6 +424,17 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		config.Hooks.OnStartup.Preload = toPreload
 	}
 
+	// check api keys validatity
+	for _, apikey := range config.RequiredAPIKeys {
+		if apikey == "" {
+			return Config{}, fmt.Errorf("empty api key found in apiKeys")
+		}
+
+		if strings.Contains(apikey, " ") {
+			return Config{}, fmt.Errorf("api key cannot contain spaces: `%s`", apikey)
+		}
+	}
+
 	return config, nil
 }
 

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)"]
@@ -160,9 +161,13 @@ groups:
 		t.Fatalf("Failed to load config: %v", err)
 	}
 
+	modelLoadingState := false
+
 	expected := Config{
-		LogLevel:  "info",
-		StartPort: 5800,
+		LogLevel:      "info",
+		LogTimeFormat: "",
+		LogToStdout:   LogToStdoutProxy,
+		StartPort:     5800,
 		Macros: MacroList{
 			{"svr-path", "path/to/server"},
 		},
@@ -171,36 +176,41 @@ groups:
 				Preload: []string{"model1", "model2"},
 			},
 		},
+		SendLoadingState: false,
 		Models: map[string]ModelConfig{
 			"model1": {
-				Cmd:           "path/to/cmd --arg1 one",
-				Proxy:         "http://localhost:8080",
-				Aliases:       []string{"m1", "model-one"},
-				Env:           []string{"VAR1=value1", "VAR2=value2"},
-				CheckEndpoint: "/health",
-				Name:          "Model 1",
-				Description:   "This is model 1",
+				Cmd:              "path/to/cmd --arg1 one",
+				Proxy:            "http://localhost:8080",
+				Aliases:          []string{"m1", "model-one"},
+				Env:              []string{"VAR1=value1", "VAR2=value2"},
+				CheckEndpoint:    "/health",
+				Name:             "Model 1",
+				Description:      "This is model 1",
+				SendLoadingState: &modelLoadingState,
 			},
 			"model2": {
-				Cmd:           "path/to/server --arg1 one",
-				Proxy:         "http://localhost:8081",
-				Aliases:       []string{"m2"},
-				Env:           []string{},
-				CheckEndpoint: "/",
+				Cmd:              "path/to/server --arg1 one",
+				Proxy:            "http://localhost:8081",
+				Aliases:          []string{"m2"},
+				Env:              []string{},
+				CheckEndpoint:    "/",
+				SendLoadingState: &modelLoadingState,
 			},
 			"model3": {
-				Cmd:           "path/to/cmd --arg1 one",
-				Proxy:         "http://localhost:8081",
-				Aliases:       []string{"mthree"},
-				Env:           []string{},
-				CheckEndpoint: "/",
+				Cmd:              "path/to/cmd --arg1 one",
+				Proxy:            "http://localhost:8081",
+				Aliases:          []string{"mthree"},
+				Env:              []string{},
+				CheckEndpoint:    "/",
+				SendLoadingState: &modelLoadingState,
 			},
 			"model4": {
-				Cmd:           "path/to/cmd --arg1 one",
-				Proxy:         "http://localhost:8082",
-				CheckEndpoint: "/",
-				Aliases:       []string{},
-				Env:           []string{},
+				Cmd:              "path/to/cmd --arg1 one",
+				Proxy:            "http://localhost:8082",
+				CheckEndpoint:    "/",
+				Aliases:          []string{},
+				Env:              []string{},
+				SendLoadingState: &modelLoadingState,
 			},
 		},
 		HealthCheckTimeout: 15,

proxy/config/config_test.go

@@ -761,3 +761,51 @@ models:
 		})
 	}
 }
+
+func TestConfig_APIKeys_Invalid(t *testing.T) {
+	tests := []struct {
+		name        string
+		content     string
+		expectedErr string
+	}{
+		{
+			name:        "empty string",
+			content:     `apiKeys: [""]`,
+			expectedErr: "empty api key found in apiKeys",
+		},
+		{
+			name:        "blank spaces only",
+			content:     `apiKeys: ["   "]`,
+			expectedErr: "api key cannot contain spaces: `   `",
+		},
+		{
+			name:        "contains leading space",
+			content:     `apiKeys: [" key123"]`,
+			expectedErr: "api key cannot contain spaces: ` key123`",
+		},
+		{
+			name:        "contains trailing space",
+			content:     `apiKeys: ["key123 "]`,
+			expectedErr: "api key cannot contain spaces: `key123 `",
+		},
+		{
+			name:        "contains middle space",
+			content:     `apiKeys: ["key 123"]`,
+			expectedErr: "api key cannot contain spaces: `key 123`",
+		},
+		{
+			name:        "empty in list with valid keys",
+			content:     `apiKeys: ["valid-key", "", "another-key"]`,
+			expectedErr: "empty api key found in apiKeys",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			_, err := LoadConfigFromReader(strings.NewReader(tt.content))
+			if assert.Error(t, err) {
+				assert.Equal(t, tt.expectedErr, err.Error())
+			}
+		})
+	}
+}

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)"]
@@ -152,44 +153,53 @@ groups:
 		t.Fatalf("Failed to load config: %v", err)
 	}
 
+	modelLoadingState := false
+
 	expected := Config{
-		LogLevel:  "info",
-		StartPort: 5800,
+		LogLevel:      "info",
+		LogTimeFormat: "",
+		LogToStdout:   LogToStdoutProxy,
+		StartPort:     5800,
 		Macros: MacroList{
 			{"svr-path", "path/to/server"},
 		},
+		SendLoadingState: false,
 		Models: map[string]ModelConfig{
 			"model1": {
-				Cmd:           "path/to/cmd --arg1 one",
-				CmdStop:       "taskkill /f /t /pid ${PID}",
-				Proxy:         "http://localhost:8080",
-				Aliases:       []string{"m1", "model-one"},
-				Env:           []string{"VAR1=value1", "VAR2=value2"},
-				CheckEndpoint: "/health",
+				Cmd:              "path/to/cmd --arg1 one",
+				CmdStop:          "taskkill /f /t /pid ${PID}",
+				Proxy:            "http://localhost:8080",
+				Aliases:          []string{"m1", "model-one"},
+				Env:              []string{"VAR1=value1", "VAR2=value2"},
+				CheckEndpoint:    "/health",
+				SendLoadingState: &modelLoadingState,
 			},
 			"model2": {
-				Cmd:           "path/to/server --arg1 one",
-				CmdStop:       "taskkill /f /t /pid ${PID}",
-				Proxy:         "http://localhost:8081",
-				Aliases:       []string{"m2"},
-				Env:           []string{},
-				CheckEndpoint: "/",
+				Cmd:              "path/to/server --arg1 one",
+				CmdStop:          "taskkill /f /t /pid ${PID}",
+				Proxy:            "http://localhost:8081",
+				Aliases:          []string{"m2"},
+				Env:              []string{},
+				CheckEndpoint:    "/",
+				SendLoadingState: &modelLoadingState,
 			},
 			"model3": {
-				Cmd:           "path/to/cmd --arg1 one",
-				CmdStop:       "taskkill /f /t /pid ${PID}",
-				Proxy:         "http://localhost:8081",
-				Aliases:       []string{"mthree"},
-				Env:           []string{},
-				CheckEndpoint: "/",
+				Cmd:              "path/to/cmd --arg1 one",
+				CmdStop:          "taskkill /f /t /pid ${PID}",
+				Proxy:            "http://localhost:8081",
+				Aliases:          []string{"mthree"},
+				Env:              []string{},
+				CheckEndpoint:    "/",
+				SendLoadingState: &modelLoadingState,
 			},
 			"model4": {
-				Cmd:           "path/to/cmd --arg1 one",
-				CmdStop:       "taskkill /f /t /pid ${PID}",
-				Proxy:         "http://localhost:8082",
-				CheckEndpoint: "/",
-				Aliases:       []string{},
-				Env:           []string{},
+				Cmd:              "path/to/cmd --arg1 one",
+				CmdStop:          "taskkill /f /t /pid ${PID}",
+				Proxy:            "http://localhost:8082",
+				CheckEndpoint:    "/",
+				Aliases:          []string{},
+				Env:              []string{},
+				SendLoadingState: &modelLoadingState,
 			},
 		},
 		HealthCheckTimeout: 15,

proxy/config/model_config.go

@@ -35,6 +35,9 @@ type ModelConfig struct {
 	// Metadata: see #264
 	// Arbitrary metadata that can be exposed through the API
 	Metadata map[string]any `yaml:"metadata"`
+
+	// override global setting
+	SendLoadingState *bool `yaml:"sendLoadingState"`
 }
 
 func (m *ModelConfig) UnmarshalYAML(unmarshal func(interface{}) error) error {

proxy/config/model_config_test.go

@@ -50,5 +50,25 @@ models:
 			}
 		})
 	}
-
+}
+
+func TestConfig_ModelSendLoadingState(t *testing.T) {
+	content := `
+sendLoadingState: true
+models:
+  model1:
+    cmd: path/to/cmd --port ${PORT}
+    sendLoadingState: false
+  model2:
+    cmd: path/to/cmd --port ${PORT}
+`
+	config, err := LoadConfigFromReader(strings.NewReader(content))
+	assert.NoError(t, err)
+	assert.True(t, config.SendLoadingState)
+	if assert.NotNil(t, config.Models["model1"].SendLoadingState) {
+		assert.False(t, *config.Models["model1"].SendLoadingState)
+	}
+	if assert.NotNil(t, config.Models["model2"].SendLoadingState) {
+		assert.True(t, *config.Models["model2"].SendLoadingState)
+	}
 }

proxy/config/peer.go

@@ -0,0 +1,47 @@
+package config
+
+import (
+	"fmt"
+	"net/url"
+)
+
+type PeerDictionaryConfig map[string]PeerConfig
+type PeerConfig struct {
+	Proxy    string   `yaml:"proxy"`
+	ProxyURL *url.URL `yaml:"-"`
+	ApiKey   string   `yaml:"apiKey"`
+	Models   []string `yaml:"models"`
+}
+
+func (c *PeerConfig) UnmarshalYAML(unmarshal func(interface{}) error) error {
+	type rawPeerConfig PeerConfig
+	defaults := rawPeerConfig{
+		Proxy:  "",
+		ApiKey: "",
+		Models: []string{},
+	}
+
+	if err := unmarshal(&defaults); err != nil {
+		return err
+	}
+
+	// Validate proxy is not empty
+	if defaults.Proxy == "" {
+		return fmt.Errorf("proxy is required")
+	}
+
+	// Validate proxy is a valid URL and store the parsed value
+	parsedURL, err := url.Parse(defaults.Proxy)
+	if err != nil {
+		return fmt.Errorf("invalid peer proxy URL (%s): %w", defaults.Proxy, err)
+	}
+	defaults.ProxyURL = parsedURL
+
+	// Validate models is not empty
+	if len(defaults.Models) == 0 {
+		return fmt.Errorf("peer models can not be empty")
+	}
+
+	*c = PeerConfig(defaults)
+	return nil
+}

proxy/config/peer_test.go

@@ -0,0 +1,139 @@
+package config
+
+import (
+	"testing"
+
+	"gopkg.in/yaml.v3"
+)
+
+func TestPeerConfig_UnmarshalYAML(t *testing.T) {
+	tests := []struct {
+		name    string
+		yaml    string
+		wantErr string
+	}{
+		{
+			name: "valid config",
+			yaml: `
+proxy: http://192.168.1.23
+models:
+  - model_a
+  - model_b
+`,
+			wantErr: "",
+		},
+		{
+			name: "valid config with apiKey",
+			yaml: `
+proxy: https://openrouter.ai/api
+apiKey: sk-test-key
+models:
+  - meta-llama/llama-3.1-8b-instruct
+`,
+			wantErr: "",
+		},
+		{
+			name: "missing proxy",
+			yaml: `
+models:
+  - model_a
+`,
+			wantErr: "proxy is required",
+		},
+		{
+			name: "empty proxy",
+			yaml: `
+proxy: ""
+models:
+  - model_a
+`,
+			wantErr: "proxy is required",
+		},
+		{
+			name: "invalid proxy URL",
+			yaml: `
+proxy: "://invalid"
+models:
+  - model_a
+`,
+			wantErr: "invalid peer proxy URL",
+		},
+		{
+			name: "missing models",
+			yaml: `
+proxy: http://localhost:8080
+`,
+			wantErr: "peer models can not be empty",
+		},
+		{
+			name: "empty models",
+			yaml: `
+proxy: http://localhost:8080
+models: []
+`,
+			wantErr: "peer models can not be empty",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			var config PeerConfig
+			err := yaml.Unmarshal([]byte(tt.yaml), &config)
+
+			if tt.wantErr == "" {
+				if err != nil {
+					t.Errorf("unexpected error: %v", err)
+				}
+			} else {
+				if err == nil {
+					t.Errorf("expected error containing %q, got nil", tt.wantErr)
+				} else if !contains(err.Error(), tt.wantErr) {
+					t.Errorf("expected error containing %q, got %q", tt.wantErr, err.Error())
+				}
+			}
+		})
+	}
+}
+
+func TestPeerConfig_ProxyURL(t *testing.T) {
+	yamlData := `
+proxy: http://192.168.1.23:8080/api
+apiKey: sk-test
+models:
+  - model_a
+`
+	var config PeerConfig
+	err := yaml.Unmarshal([]byte(yamlData), &config)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+
+	if config.ProxyURL == nil {
+		t.Fatal("ProxyURL should not be nil")
+	}
+
+	if config.ProxyURL.Host != "192.168.1.23:8080" {
+		t.Errorf("expected host %q, got %q", "192.168.1.23:8080", config.ProxyURL.Host)
+	}
+
+	if config.ProxyURL.Scheme != "http" {
+		t.Errorf("expected scheme %q, got %q", "http", config.ProxyURL.Scheme)
+	}
+
+	if config.ProxyURL.Path != "/api" {
+		t.Errorf("expected path %q, got %q", "/api", config.ProxyURL.Path)
+	}
+}
+
+func contains(s, substr string) bool {
+	return len(s) >= len(substr) && searchSubstring(s, substr)
+}
+
+func searchSubstring(s, substr string) bool {
+	for i := 0; i <= len(s)-len(substr); i++ {
+		if s[i:i+len(substr)] == substr {
+			return true
+		}
+	}
+	return false
+}

proxy/logMonitor.go

@@ -1,16 +1,95 @@
 package proxy
 
 import (
-	"container/ring"
 	"context"
 	"fmt"
 	"io"
 	"os"
 	"sync"
+	"time"
 
 	"github.com/mostlygeek/llama-swap/event"
 )
 
+// circularBuffer is a fixed-size circular byte buffer that overwrites
+// oldest data when full. It provides O(1) writes and O(n) reads.
+type circularBuffer struct {
+	data []byte // pre-allocated capacity
+	head int    // next write position
+	size int    // current number of bytes stored (0 to cap)
+}
+
+func newCircularBuffer(capacity int) *circularBuffer {
+	return &circularBuffer{
+		data: make([]byte, capacity),
+		head: 0,
+		size: 0,
+	}
+}
+
+// Write appends bytes to the buffer, overwriting oldest data when full.
+// Data is copied into the internal buffer (not stored by reference).
+func (cb *circularBuffer) Write(p []byte) {
+	if len(p) == 0 {
+		return
+	}
+
+	cap := len(cb.data)
+
+	// If input is larger than capacity, only keep the last cap bytes
+	if len(p) >= cap {
+		copy(cb.data, p[len(p)-cap:])
+		cb.head = 0
+		cb.size = cap
+		return
+	}
+
+	// Calculate how much space is available from head to end of buffer
+	firstPart := cap - cb.head
+	if firstPart >= len(p) {
+		// All data fits without wrapping
+		copy(cb.data[cb.head:], p)
+		cb.head = (cb.head + len(p)) % cap
+	} else {
+		// Data wraps around
+		copy(cb.data[cb.head:], p[:firstPart])
+		copy(cb.data[:len(p)-firstPart], p[firstPart:])
+		cb.head = len(p) - firstPart
+	}
+
+	// Update size
+	cb.size += len(p)
+	if cb.size > cap {
+		cb.size = cap
+	}
+}
+
+// GetHistory returns all buffered data in correct order (oldest to newest).
+// Returns a new slice (copy), not a view into internal buffer.
+func (cb *circularBuffer) GetHistory() []byte {
+	if cb.size == 0 {
+		return nil
+	}
+
+	result := make([]byte, cb.size)
+	cap := len(cb.data)
+
+	// Calculate start position (oldest data)
+	start := (cb.head - cb.size + cap) % cap
+
+	if start+cb.size <= cap {
+		// Data is contiguous, single copy
+		copy(result, cb.data[start:start+cb.size])
+	} else {
+		// Data wraps around, two copies
+		firstPart := cap - start
+		copy(result[:firstPart], cb.data[start:])
+		copy(result[firstPart:], cb.data[:cb.size-firstPart])
+	}
+
+	return result
+}
+
 type LogLevel int
 
 const (
@@ -18,12 +97,14 @@ const (
 	LevelInfo
 	LevelWarn
 	LevelError
+
+	LogBufferSize = 100 * 1024
 )
 
 type LogMonitor struct {
 	eventbus *event.Dispatcher
 	mu       sync.RWMutex
-	buffer   *ring.Ring
+	buffer   *circularBuffer
 	bufferMu sync.RWMutex
 
 	// typically this can be os.Stdout
@@ -32,6 +113,9 @@ type LogMonitor struct {
 	// logging levels
 	level  LogLevel
 	prefix string
+
+	// timestamps
+	timeFormat string
 }
 
 func NewLogMonitor() *LogMonitor {
@@ -40,11 +124,12 @@ 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:     nil, // lazy initialized on first Write
+		stdout:     stdout,
+		level:      LevelInfo,
+		prefix:     "",
+		timeFormat: "",
 	}
 }
 
@@ -59,12 +144,15 @@ func (w *LogMonitor) Write(p []byte) (n int, err error) {
 	}
 
 	w.bufferMu.Lock()
-	bufferCopy := make([]byte, len(p))
-	copy(bufferCopy, p)
-	w.buffer.Value = bufferCopy
-	w.buffer = w.buffer.Next()
+	if w.buffer == nil {
+		w.buffer = newCircularBuffer(LogBufferSize)
+	}
+	w.buffer.Write(p)
 	w.bufferMu.Unlock()
 
+	// Make a copy for broadcast to preserve immutability
+	bufferCopy := make([]byte, len(p))
+	copy(bufferCopy, p)
 	w.broadcast(bufferCopy)
 	return n, nil
 }
@@ -72,16 +160,18 @@ func (w *LogMonitor) Write(p []byte) (n int, err error) {
 func (w *LogMonitor) GetHistory() []byte {
 	w.bufferMu.RLock()
 	defer w.bufferMu.RUnlock()
+	if w.buffer == nil {
+		return nil
+	}
+	return w.buffer.GetHistory()
+}
 
-	var history []byte
-	w.buffer.Do(func(p any) {
-		if p != nil {
-			if content, ok := p.([]byte); ok {
-				history = append(history, content...)
-			}
-		}
-	})
-	return history
+// Clear releases the buffer memory, making it eligible for GC.
+// The buffer will be lazily re-allocated on the next Write.
+func (w *LogMonitor) Clear() {
+	w.bufferMu.Lock()
+	w.buffer = nil
+	w.bufferMu.Unlock()
 }
 
 func (w *LogMonitor) OnLogData(callback func(data []byte)) context.CancelFunc {
@@ -106,12 +196,22 @@ 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 +86,231 @@ 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)
+	}
+}
+
+func TestCircularBuffer_WrapAround(t *testing.T) {
+	// Create a small buffer to test wrap-around
+	cb := newCircularBuffer(10)
+
+	// Write "hello" (5 bytes)
+	cb.Write([]byte("hello"))
+	if got := string(cb.GetHistory()); got != "hello" {
+		t.Errorf("Expected 'hello', got %q", got)
+	}
+
+	// Write "world" (5 bytes) - buffer now full
+	cb.Write([]byte("world"))
+	if got := string(cb.GetHistory()); got != "helloworld" {
+		t.Errorf("Expected 'helloworld', got %q", got)
+	}
+
+	// Write "12345" (5 bytes) - should overwrite "hello"
+	cb.Write([]byte("12345"))
+	if got := string(cb.GetHistory()); got != "world12345" {
+		t.Errorf("Expected 'world12345', got %q", got)
+	}
+
+	// Write data larger than buffer capacity
+	cb.Write([]byte("abcdefghijklmnop")) // 16 bytes, only last 10 kept
+	if got := string(cb.GetHistory()); got != "ghijklmnop" {
+		t.Errorf("Expected 'ghijklmnop', got %q", got)
+	}
+}
+
+func TestCircularBuffer_BoundaryConditions(t *testing.T) {
+	// Test empty buffer
+	cb := newCircularBuffer(10)
+	if got := cb.GetHistory(); got != nil {
+		t.Errorf("Expected nil for empty buffer, got %q", got)
+	}
+
+	// Test exact capacity
+	cb.Write([]byte("1234567890"))
+	if got := string(cb.GetHistory()); got != "1234567890" {
+		t.Errorf("Expected '1234567890', got %q", got)
+	}
+
+	// Test write exactly at capacity boundary
+	cb = newCircularBuffer(10)
+	cb.Write([]byte("12345"))
+	cb.Write([]byte("67890"))
+	if got := string(cb.GetHistory()); got != "1234567890" {
+		t.Errorf("Expected '1234567890', got %q", got)
+	}
+}
+
+func TestLogMonitor_LazyInit(t *testing.T) {
+	lm := NewLogMonitorWriter(io.Discard)
+
+	// Buffer should be nil before any writes
+	if lm.buffer != nil {
+		t.Error("Expected buffer to be nil before first write")
+	}
+
+	// GetHistory should return nil when buffer is nil
+	if got := lm.GetHistory(); got != nil {
+		t.Errorf("Expected nil history before first write, got %q", got)
+	}
+
+	// Write should lazily initialize the buffer
+	lm.Write([]byte("test"))
+
+	if lm.buffer == nil {
+		t.Error("Expected buffer to be initialized after write")
+	}
+
+	if got := string(lm.GetHistory()); got != "test" {
+		t.Errorf("Expected 'test', got %q", got)
+	}
+}
+
+func TestLogMonitor_Clear(t *testing.T) {
+	lm := NewLogMonitorWriter(io.Discard)
+
+	// Write some data
+	lm.Write([]byte("hello"))
+	if got := string(lm.GetHistory()); got != "hello" {
+		t.Errorf("Expected 'hello', got %q", got)
+	}
+
+	// Clear should release the buffer
+	lm.Clear()
+
+	if lm.buffer != nil {
+		t.Error("Expected buffer to be nil after Clear")
+	}
+
+	if got := lm.GetHistory(); got != nil {
+		t.Errorf("Expected nil history after Clear, got %q", got)
+	}
+}
+
+func TestLogMonitor_ClearAndReuse(t *testing.T) {
+	lm := NewLogMonitorWriter(io.Discard)
+
+	// Write, clear, then write again
+	lm.Write([]byte("first"))
+	lm.Clear()
+	lm.Write([]byte("second"))
+
+	if got := string(lm.GetHistory()); got != "second" {
+		t.Errorf("Expected 'second' after clear and reuse, got %q", got)
+	}
+}
+
+func BenchmarkLogMonitorWrite(b *testing.B) {
+	// Test data of varying sizes
+	smallMsg := []byte("small message\n")
+	mediumMsg := []byte(strings.Repeat("medium message content ", 10) + "\n")
+	largeMsg := []byte(strings.Repeat("large message content for benchmarking ", 100) + "\n")
+
+	b.Run("SmallWrite", func(b *testing.B) {
+		lm := NewLogMonitorWriter(io.Discard)
+		b.ResetTimer()
+		for i := 0; i < b.N; i++ {
+			lm.Write(smallMsg)
+		}
+	})
+
+	b.Run("MediumWrite", func(b *testing.B) {
+		lm := NewLogMonitorWriter(io.Discard)
+		b.ResetTimer()
+		for i := 0; i < b.N; i++ {
+			lm.Write(mediumMsg)
+		}
+	})
+
+	b.Run("LargeWrite", func(b *testing.B) {
+		lm := NewLogMonitorWriter(io.Discard)
+		b.ResetTimer()
+		for i := 0; i < b.N; i++ {
+			lm.Write(largeMsg)
+		}
+	})
+
+	b.Run("WithSubscribers", func(b *testing.B) {
+		lm := NewLogMonitorWriter(io.Discard)
+		// Add some subscribers
+		for i := 0; i < 5; i++ {
+			lm.OnLogData(func(data []byte) {})
+		}
+		b.ResetTimer()
+		for i := 0; i < b.N; i++ {
+			lm.Write(mediumMsg)
+		}
+	})
+
+	b.Run("GetHistory", func(b *testing.B) {
+		lm := NewLogMonitorWriter(io.Discard)
+		// Pre-populate with data
+		for i := 0; i < 1000; i++ {
+			lm.Write(mediumMsg)
+		}
+		b.ResetTimer()
+		for i := 0; i < b.N; i++ {
+			lm.GetHistory()
+		}
+	})
+}
+
+/*
+Benchmark Results - MBP M1 Pro
+
+Before (ring.Ring):
+| Benchmark                       | ns/op      | bytes/op | allocs/op |
+|---------------------------------|------------|----------|-----------|
+| SmallWrite (14B)                | 43 ns      | 40 B     | 2         |
+| MediumWrite (241B)              | 76 ns      | 264 B    | 2         |
+| LargeWrite (4KB)                | 504 ns     | 4,120 B  | 2         |
+| WithSubscribers (5 subs)        | 355 ns     | 264 B    | 2         |
+| GetHistory (after 1000 writes)  | 145,000 ns | 1.2 MB   | 22        |
+
+After (circularBuffer 10KB):
+| Benchmark                       | ns/op      | bytes/op | allocs/op |
+|---------------------------------|------------|----------|-----------|
+| SmallWrite (14B)                | 26 ns      | 16 B     | 1         |
+| MediumWrite (241B)              | 67 ns      | 240 B    | 1         |
+| LargeWrite (4KB)                | 774 ns     | 4,096 B  | 1         |
+| WithSubscribers (5 subs)        | 325 ns     | 240 B    | 1         |
+| GetHistory (after 1000 writes)  | 1,042 ns   | 10,240 B | 1         |
+
+After (circularBuffer 100KB):
+| Benchmark                       | ns/op      | bytes/op  | allocs/op |
+|---------------------------------|------------|-----------|-----------|
+| SmallWrite (14B)                | 26 ns      | 16 B      | 1         |
+| MediumWrite (241B)              | 66 ns      | 240 B     | 1         |
+| LargeWrite (4KB)                | 753 ns     | 4,096 B   | 1         |
+| WithSubscribers (5 subs)        | 309 ns     | 240 B     | 1         |
+| GetHistory (after 1000 writes)  | 7,788 ns   | 106,496 B | 1         |
+
+Summary:
+- GetHistory: 139x faster (10KB), 18x faster (100KB)
+- Allocations: reduced from 2 to 1 across all operations
+- Small/medium writes: ~1.1-1.6x faster
+*/

proxy/metrics_monitor.go

@@ -2,6 +2,8 @@ package proxy
 
 import (
 	"bytes"
+	"compress/flate"
+	"compress/gzip"
 	"encoding/json"
 	"fmt"
 	"io"
@@ -96,6 +98,12 @@ func (mp *metricsMonitor) wrapHandler(
 	next func(modelID string, w http.ResponseWriter, r *http.Request) error,
 ) error {
 	recorder := newBodyCopier(writer)
+
+	// Filter Accept-Encoding to only include encodings we can decompress for metrics
+	if ae := request.Header.Get("Accept-Encoding"); ae != "" {
+		request.Header.Set("Accept-Encoding", filterAcceptEncoding(ae))
+	}
+
 	if err := next(modelID, recorder, request); err != nil {
 		return err
 	}
@@ -108,30 +116,56 @@ func (mp *metricsMonitor) wrapHandler(
 		return nil
 	}
 
+	// Initialize default metrics - these will always be recorded
+	tm := TokenMetrics{
+		Timestamp:  time.Now(),
+		Model:      modelID,
+		DurationMs: int(time.Since(recorder.StartTime()).Milliseconds()),
+	}
+
 	body := recorder.body.Bytes()
 	if len(body) == 0 {
-		mp.logger.Warn("metrics skipped, empty body")
+		mp.logger.Warn("metrics: empty body, recording minimal metrics")
+		mp.addMetrics(tm)
 		return nil
 	}
 
-	if strings.Contains(recorder.Header().Get("Content-Type"), "text/event-stream") {
-		if tm, err := processStreamingResponse(modelID, recorder.StartTime(), body); err != nil {
-			mp.logger.Warnf("error processing streaming response: %v, path=%s", err, request.URL.Path)
-		} else {
+	// Decompress if needed
+	if encoding := recorder.Header().Get("Content-Encoding"); encoding != "" {
+		var err error
+		body, err = decompressBody(body, encoding)
+		if err != nil {
+			mp.logger.Warnf("metrics: decompression failed: %v, path=%s, recording minimal metrics", err, request.URL.Path)
 			mp.addMetrics(tm)
-		}
-	} else {
-		if gjson.ValidBytes(body) {
-			if tm, err := parseMetrics(modelID, recorder.StartTime(), gjson.ParseBytes(body)); err != nil {
-				mp.logger.Warnf("error parsing metrics: %v, path=%s", err, request.URL.Path)
-			} else {
-				mp.addMetrics(tm)
-			}
-		} else {
-			mp.logger.Warnf("metrics skipped, invalid JSON in response body path=%s", request.URL.Path)
+			return nil
 		}
 	}
 
+	if strings.Contains(recorder.Header().Get("Content-Type"), "text/event-stream") {
+		if parsed, err := processStreamingResponse(modelID, recorder.StartTime(), body); err != nil {
+			mp.logger.Warnf("error processing streaming response: %v, path=%s, recording minimal metrics", err, request.URL.Path)
+		} else {
+			tm = parsed
+		}
+	} else {
+		if gjson.ValidBytes(body) {
+			parsed := gjson.ParseBytes(body)
+			usage := parsed.Get("usage")
+			timings := parsed.Get("timings")
+
+			if usage.Exists() || timings.Exists() {
+				if parsedMetrics, err := parseMetrics(modelID, recorder.StartTime(), usage, timings); err != nil {
+					mp.logger.Warnf("error parsing metrics: %v, path=%s, recording minimal metrics", err, request.URL.Path)
+				} else {
+					tm = parsedMetrics
+				}
+			}
+		} else {
+			mp.logger.Warnf("metrics: invalid JSON in response body path=%s, recording minimal metrics", request.URL.Path)
+		}
+	}
+
+	mp.addMetrics(tm)
 	return nil
 }
 
@@ -174,19 +208,20 @@ func processStreamingResponse(modelID string, start time.Time, body []byte) (Tok
 		}
 
 		if gjson.ValidBytes(data) {
-			return parseMetrics(modelID, start, gjson.ParseBytes(data))
+			parsed := gjson.ParseBytes(data)
+			usage := parsed.Get("usage")
+			timings := parsed.Get("timings")
+
+			if usage.Exists() || timings.Exists() {
+				return parseMetrics(modelID, start, usage, timings)
+			}
 		}
 	}
 
 	return TokenMetrics{}, fmt.Errorf("no valid JSON data found in stream")
 }
 
-func parseMetrics(modelID string, start time.Time, jsonData gjson.Result) (TokenMetrics, error) {
-	usage := jsonData.Get("usage")
-	timings := jsonData.Get("timings")
-	if !usage.Exists() && !timings.Exists() {
-		return TokenMetrics{}, fmt.Errorf("no usage or timings data found")
-	}
+func parseMetrics(modelID string, start time.Time, usage, timings gjson.Result) (TokenMetrics, error) {
 	// default values
 	cachedTokens := -1 // unknown or missing data
 	outputTokens := 0
@@ -198,19 +233,35 @@ func parseMetrics(modelID string, start time.Time, jsonData gjson.Result) (Token
 	durationMs := int(time.Since(start).Milliseconds())
 
 	if usage.Exists() {
-		outputTokens = int(jsonData.Get("usage.completion_tokens").Int())
-		inputTokens = int(jsonData.Get("usage.prompt_tokens").Int())
+		if pt := usage.Get("prompt_tokens"); pt.Exists() {
+			// v1/chat/completions
+			inputTokens = int(pt.Int())
+		} else if it := usage.Get("input_tokens"); it.Exists() {
+			// v1/messages
+			inputTokens = int(it.Int())
+		}
+
+		if ct := usage.Get("completion_tokens"); ct.Exists() {
+			// v1/chat/completions
+			outputTokens = int(ct.Int())
+		} else if ot := usage.Get("output_tokens"); ot.Exists() {
+			outputTokens = int(ot.Int())
+		}
+
+		if ct := usage.Get("cache_read_input_tokens"); ct.Exists() {
+			cachedTokens = int(ct.Int())
+		}
 	}
 
 	// use llama-server's timing data for tok/sec and duration as it is more accurate
 	if timings.Exists() {
-		inputTokens = int(jsonData.Get("timings.prompt_n").Int())
-		outputTokens = int(jsonData.Get("timings.predicted_n").Int())
-		promptPerSecond = jsonData.Get("timings.prompt_per_second").Float()
-		tokensPerSecond = jsonData.Get("timings.predicted_per_second").Float()
-		durationMs = int(jsonData.Get("timings.prompt_ms").Float() + jsonData.Get("timings.predicted_ms").Float())
+		inputTokens = int(timings.Get("prompt_n").Int())
+		outputTokens = int(timings.Get("predicted_n").Int())
+		promptPerSecond = timings.Get("prompt_per_second").Float()
+		tokensPerSecond = timings.Get("predicted_per_second").Float()
+		durationMs = int(timings.Get("prompt_ms").Float() + timings.Get("predicted_ms").Float())
 
-		if cachedValue := jsonData.Get("timings.cache_n"); cachedValue.Exists() {
+		if cachedValue := timings.Get("cache_n"); cachedValue.Exists() {
 			cachedTokens = int(cachedValue.Int())
 		}
 	}
@@ -227,6 +278,25 @@ func parseMetrics(modelID string, start time.Time, jsonData gjson.Result) (Token
 	}, nil
 }
 
+// decompressBody decompresses the body based on Content-Encoding header
+func decompressBody(body []byte, encoding string) ([]byte, error) {
+	switch strings.ToLower(strings.TrimSpace(encoding)) {
+	case "gzip":
+		reader, err := gzip.NewReader(bytes.NewReader(body))
+		if err != nil {
+			return nil, err
+		}
+		defer reader.Close()
+		return io.ReadAll(reader)
+	case "deflate":
+		reader := flate.NewReader(bytes.NewReader(body))
+		defer reader.Close()
+		return io.ReadAll(reader)
+	default:
+		return body, nil // Return as-is for unknown/no encoding
+	}
+}
+
 // responseBodyCopier records the response body and writes to the original response writer
 // while also capturing it in a buffer for later processing
 type responseBodyCopier struct {
@@ -265,3 +335,25 @@ func (w *responseBodyCopier) Header() http.Header {
 func (w *responseBodyCopier) StartTime() time.Time {
 	return w.start
 }
+
+// filterAcceptEncoding filters the Accept-Encoding header to only include
+// encodings we can decompress (gzip, deflate). This respects the client's
+// preferences while ensuring we can parse response bodies for metrics.
+func filterAcceptEncoding(acceptEncoding string) string {
+	if acceptEncoding == "" {
+		return ""
+	}
+
+	supported := map[string]bool{"gzip": true, "deflate": true}
+	var filtered []string
+
+	for _, part := range strings.Split(acceptEncoding, ",") {
+		// Parse encoding and optional quality value (e.g., "gzip;q=1.0")
+		encoding := strings.TrimSpace(strings.Split(part, ";")[0])
+		if supported[strings.ToLower(encoding)] {
+			filtered = append(filtered, strings.TrimSpace(part))
+		}
+	}
+
+	return strings.Join(filtered, ", ")
+}

proxy/metrics_monitor_test.go

@@ -1,6 +1,9 @@
 package proxy
 
 import (
+	"bytes"
+	"compress/flate"
+	"compress/gzip"
 	"encoding/json"
 	"net/http"
 	"net/http/httptest"
@@ -291,7 +294,7 @@ data: [DONE]
 		assert.Equal(t, 0, len(metrics))
 	})
 
-	t.Run("empty response body does not record metrics", func(t *testing.T) {
+	t.Run("empty response body records minimal metrics", func(t *testing.T) {
 		mm := newMetricsMonitor(testLogger, 10)
 
 		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
@@ -307,10 +310,13 @@ data: [DONE]
 		assert.NoError(t, err)
 
 		metrics := mm.getMetrics()
-		assert.Equal(t, 0, len(metrics))
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 0, metrics[0].InputTokens)
+		assert.Equal(t, 0, metrics[0].OutputTokens)
 	})
 
-	t.Run("invalid JSON does not record metrics", func(t *testing.T) {
+	t.Run("invalid JSON records minimal metrics", func(t *testing.T) {
 		mm := newMetricsMonitor(testLogger, 10)
 
 		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
@@ -328,7 +334,10 @@ data: [DONE]
 		assert.NoError(t, err) // Errors after response is sent are logged, not returned
 
 		metrics := mm.getMetrics()
-		assert.Equal(t, 0, len(metrics))
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 0, metrics[0].InputTokens)
+		assert.Equal(t, 0, metrics[0].OutputTokens)
 	})
 
 	t.Run("next handler error is propagated", func(t *testing.T) {
@@ -350,7 +359,7 @@ data: [DONE]
 		assert.Equal(t, 0, len(metrics))
 	})
 
-	t.Run("response without usage or timings does not record metrics", func(t *testing.T) {
+	t.Run("response without usage or timings records minimal metrics", func(t *testing.T) {
 		mm := newMetricsMonitor(testLogger, 10)
 
 		responseBody := `{"result": "ok"}`
@@ -367,10 +376,13 @@ data: [DONE]
 		ginCtx, _ := gin.CreateTestContext(rec)
 
 		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
-		assert.NoError(t, err) // Errors after response is sent are logged, not returned
+		assert.NoError(t, err)
 
 		metrics := mm.getMetrics()
-		assert.Equal(t, 0, len(metrics))
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 0, metrics[0].InputTokens)
+		assert.Equal(t, 0, metrics[0].OutputTokens)
 	})
 }
 
@@ -598,7 +610,7 @@ data: [DONE]
 		assert.Equal(t, 50, metrics[0].OutputTokens)
 	})
 
-	t.Run("handles streaming with no valid JSON", func(t *testing.T) {
+	t.Run("handles streaming with no valid JSON records minimal metrics", func(t *testing.T) {
 		mm := newMetricsMonitor(testLogger, 10)
 
 		responseBody := `data: not json
@@ -619,13 +631,16 @@ data: [DONE]
 		ginCtx, _ := gin.CreateTestContext(rec)
 
 		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
-		assert.NoError(t, err) // Errors after response is sent are logged, not returned
+		assert.NoError(t, err)
 
 		metrics := mm.getMetrics()
-		assert.Equal(t, 0, len(metrics))
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 0, metrics[0].InputTokens)
+		assert.Equal(t, 0, metrics[0].OutputTokens)
 	})
 
-	t.Run("handles empty streaming response", func(t *testing.T) {
+	t.Run("handles empty streaming response records minimal metrics", func(t *testing.T) {
 		mm := newMetricsMonitor(testLogger, 10)
 
 		responseBody := ``
@@ -642,11 +657,13 @@ data: [DONE]
 		ginCtx, _ := gin.CreateTestContext(rec)
 
 		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
-		// Empty body should not trigger WrapHandler processing
 		assert.NoError(t, err)
 
 		metrics := mm.getMetrics()
-		assert.Equal(t, 0, len(metrics))
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 0, metrics[0].InputTokens)
+		assert.Equal(t, 0, metrics[0].OutputTokens)
 	})
 }
 
@@ -691,3 +708,127 @@ func BenchmarkMetricsMonitor_AddMetrics_SmallBuffer(b *testing.B) {
 		mm.addMetrics(metric)
 	}
 }
+
+func TestMetricsMonitor_WrapHandler_Compression(t *testing.T) {
+	t.Run("gzip encoded response", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		responseBody := `{"usage": {"prompt_tokens": 100, "completion_tokens": 50}}`
+
+		// Compress with gzip
+		var buf bytes.Buffer
+		gzWriter := gzip.NewWriter(&buf)
+		gzWriter.Write([]byte(responseBody))
+		gzWriter.Close()
+		compressedBody := buf.Bytes()
+
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			w.Header().Set("Content-Type", "application/json")
+			w.Header().Set("Content-Encoding", "gzip")
+			w.WriteHeader(http.StatusOK)
+			w.Write(compressedBody)
+			return nil
+		}
+
+		req := httptest.NewRequest("POST", "/test", nil)
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+
+		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
+		assert.NoError(t, err)
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 100, metrics[0].InputTokens)
+		assert.Equal(t, 50, metrics[0].OutputTokens)
+	})
+
+	t.Run("deflate encoded response", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		responseBody := `{"usage": {"prompt_tokens": 200, "completion_tokens": 75}}`
+
+		// Compress with deflate
+		var buf bytes.Buffer
+		flateWriter, _ := flate.NewWriter(&buf, flate.DefaultCompression)
+		flateWriter.Write([]byte(responseBody))
+		flateWriter.Close()
+		compressedBody := buf.Bytes()
+
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			w.Header().Set("Content-Type", "application/json")
+			w.Header().Set("Content-Encoding", "deflate")
+			w.WriteHeader(http.StatusOK)
+			w.Write(compressedBody)
+			return nil
+		}
+
+		req := httptest.NewRequest("POST", "/test", nil)
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+
+		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
+		assert.NoError(t, err)
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 200, metrics[0].InputTokens)
+		assert.Equal(t, 75, metrics[0].OutputTokens)
+	})
+
+	t.Run("invalid gzip data records minimal metrics", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		// Invalid compressed data
+		invalidData := []byte("this is not gzip data")
+
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			w.Header().Set("Content-Type", "application/json")
+			w.Header().Set("Content-Encoding", "gzip")
+			w.WriteHeader(http.StatusOK)
+			w.Write(invalidData)
+			return nil
+		}
+
+		req := httptest.NewRequest("POST", "/test", nil)
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+
+		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
+		assert.NoError(t, err) // Should not return error, just log warning
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, "test-model", metrics[0].Model)
+		assert.Equal(t, 0, metrics[0].InputTokens)
+		assert.Equal(t, 0, metrics[0].OutputTokens)
+	})
+
+	t.Run("unknown encoding treated as uncompressed", func(t *testing.T) {
+		mm := newMetricsMonitor(testLogger, 10)
+
+		responseBody := `{"usage": {"prompt_tokens": 300, "completion_tokens": 100}}`
+
+		nextHandler := func(modelID string, w http.ResponseWriter, r *http.Request) error {
+			w.Header().Set("Content-Type", "application/json")
+			w.Header().Set("Content-Encoding", "unknown-encoding")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte(responseBody))
+			return nil
+		}
+
+		req := httptest.NewRequest("POST", "/test", nil)
+		rec := httptest.NewRecorder()
+		ginCtx, _ := gin.CreateTestContext(rec)
+
+		err := mm.wrapHandler("test-model", ginCtx.Writer, req, nextHandler)
+		assert.NoError(t, err)
+
+		metrics := mm.getMetrics()
+		assert.Equal(t, 1, len(metrics))
+		assert.Equal(t, 300, metrics[0].InputTokens)
+		assert.Equal(t, 100, metrics[0].OutputTokens)
+	})
+}

proxy/peerproxy.go

@@ -0,0 +1,127 @@
+package proxy
+
+import (
+	"fmt"
+	"net"
+	"net/http"
+	"net/http/httputil"
+	"runtime"
+	"sort"
+	"strings"
+	"time"
+
+	"github.com/mostlygeek/llama-swap/proxy/config"
+)
+
+type peerProxyMember struct {
+	peerID       string
+	reverseProxy *httputil.ReverseProxy
+	apiKey       string
+}
+
+type PeerProxy struct {
+	peers    config.PeerDictionaryConfig
+	proxyMap map[string]*peerProxyMember
+}
+
+func NewPeerProxy(peers config.PeerDictionaryConfig, proxyLogger *LogMonitor) (*PeerProxy, error) {
+	proxyMap := make(map[string]*peerProxyMember)
+
+	// Sort peer IDs for consistent iteration order
+	peerIDs := make([]string, 0, len(peers))
+	for peerID := range peers {
+		peerIDs = append(peerIDs, peerID)
+	}
+	sort.Strings(peerIDs)
+
+	// Create a shared transport with reasonable timeouts for peer connections
+	// these can be tuned with feedback later
+	peerTransport := &http.Transport{
+		DialContext: (&net.Dialer{
+			Timeout:   30 * time.Second, // Connection timeout
+			KeepAlive: 30 * time.Second,
+		}).DialContext,
+		TLSHandshakeTimeout:   10 * time.Second,
+		ResponseHeaderTimeout: 60 * time.Second, // Time to wait for response headers
+		ExpectContinueTimeout: 1 * time.Second,
+		MaxIdleConns:          100,
+		MaxIdleConnsPerHost:   10,
+		IdleConnTimeout:       90 * time.Second,
+	}
+
+	for _, peerID := range peerIDs {
+		peer := peers[peerID]
+		// Create reverse proxy for this peer
+		reverseProxy := httputil.NewSingleHostReverseProxy(peer.ProxyURL)
+		reverseProxy.Transport = peerTransport
+
+		// Wrap Director to set Host header for remote hosts (not localhost)
+		originalDirector := reverseProxy.Director
+		reverseProxy.Director = func(req *http.Request) {
+			originalDirector(req)
+			// Ensure Host header matches target URL for remote proxying
+			req.Host = req.URL.Host
+		}
+
+		reverseProxy.ModifyResponse = func(resp *http.Response) error {
+			if strings.Contains(strings.ToLower(resp.Header.Get("Content-Type")), "text/event-stream") {
+				resp.Header.Set("X-Accel-Buffering", "no")
+			}
+			return nil
+		}
+
+		reverseProxy.ErrorHandler = func(w http.ResponseWriter, r *http.Request, err error) {
+			proxyLogger.Warnf("peer %s: proxy error: %v", peerID, err)
+			errMsg := fmt.Sprintf("peer proxy error: %v", err)
+			if runtime.GOOS == "darwin" && strings.Contains(err.Error(), "connect: no route to host") {
+				errMsg += " (hint: on macOS, check System Settings > Privacy & Security > Local Network permissions)"
+			}
+			http.Error(w, errMsg, http.StatusBadGateway)
+		}
+
+		pp := &peerProxyMember{
+			peerID:       peerID,
+			reverseProxy: reverseProxy,
+			apiKey:       peer.ApiKey,
+		}
+
+		// Map each model to this peer's proxy
+		for _, modelID := range peer.Models {
+			if _, found := proxyMap[modelID]; found {
+				proxyLogger.Warnf("peer %s: model %s already mapped to another peer, skipping", peerID, modelID)
+				continue
+			}
+			proxyMap[modelID] = pp
+		}
+	}
+
+	return &PeerProxy{
+		peers:    peers,
+		proxyMap: proxyMap,
+	}, nil
+}
+
+func (p *PeerProxy) HasPeerModel(modelID string) bool {
+	_, found := p.proxyMap[modelID]
+	return found
+}
+
+func (p *PeerProxy) ListPeers() config.PeerDictionaryConfig {
+	return p.peers
+}
+
+func (p *PeerProxy) ProxyRequest(model_id string, writer http.ResponseWriter, request *http.Request) error {
+	pp, found := p.proxyMap[model_id]
+	if !found {
+		return fmt.Errorf("no peer proxy found for model %s", model_id)
+	}
+
+	// Inject API key if configured for this peer
+	if pp.apiKey != "" {
+		request.Header.Set("Authorization", "Bearer "+pp.apiKey)
+		request.Header.Set("x-api-key", pp.apiKey)
+	}
+
+	pp.reverseProxy.ServeHTTP(writer, request)
+	return nil
+}

proxy/peerproxy_test.go

@@ -0,0 +1,268 @@
+package proxy
+
+import (
+	"net/http"
+	"net/http/httptest"
+	"net/url"
+	"strings"
+	"testing"
+
+	"github.com/mostlygeek/llama-swap/proxy/config"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestNewPeerProxy_EmptyPeers(t *testing.T) {
+	peers := config.PeerDictionaryConfig{}
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+	assert.NotNil(t, pm)
+	assert.Empty(t, pm.proxyMap)
+}
+
+func TestNewPeerProxy_SinglePeer(t *testing.T) {
+	proxyURL, _ := url.Parse("http://peer1.example.com:8080")
+	peers := config.PeerDictionaryConfig{
+		"peer1": config.PeerConfig{
+			Proxy:    "http://peer1.example.com:8080",
+			ProxyURL: proxyURL,
+			ApiKey:   "test-key",
+			Models:   []string{"model-a", "model-b"},
+		},
+	}
+
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+	assert.Len(t, pm.proxyMap, 2)
+	assert.True(t, pm.HasPeerModel("model-a"))
+	assert.True(t, pm.HasPeerModel("model-b"))
+	assert.False(t, pm.HasPeerModel("model-c"))
+}
+
+func TestNewPeerProxy_MultiplePeers(t *testing.T) {
+	proxyURL1, _ := url.Parse("http://peer1.example.com:8080")
+	proxyURL2, _ := url.Parse("http://peer2.example.com:8080")
+	peers := config.PeerDictionaryConfig{
+		"peer1": config.PeerConfig{
+			Proxy:    "http://peer1.example.com:8080",
+			ProxyURL: proxyURL1,
+			Models:   []string{"model-a", "model-b"},
+		},
+		"peer2": config.PeerConfig{
+			Proxy:    "http://peer2.example.com:8080",
+			ProxyURL: proxyURL2,
+			Models:   []string{"model-c", "model-d"},
+		},
+	}
+
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+	assert.Len(t, pm.proxyMap, 4)
+	assert.True(t, pm.HasPeerModel("model-a"))
+	assert.True(t, pm.HasPeerModel("model-b"))
+	assert.True(t, pm.HasPeerModel("model-c"))
+	assert.True(t, pm.HasPeerModel("model-d"))
+}
+
+func TestNewPeerProxy_DuplicateModelWarning(t *testing.T) {
+	// When the same model is in multiple peers, only the first (lexicographically by peer ID)
+	// should be mapped, and a warning should be logged
+	proxyURL1, _ := url.Parse("http://peer1.example.com:8080")
+	proxyURL2, _ := url.Parse("http://peer2.example.com:8080")
+	peers := config.PeerDictionaryConfig{
+		"alpha-peer": config.PeerConfig{
+			Proxy:    "http://peer1.example.com:8080",
+			ProxyURL: proxyURL1,
+			Models:   []string{"duplicate-model"},
+		},
+		"beta-peer": config.PeerConfig{
+			Proxy:    "http://peer2.example.com:8080",
+			ProxyURL: proxyURL2,
+			Models:   []string{"duplicate-model"},
+		},
+	}
+
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+	// Should only have one entry for the duplicate model
+	assert.Len(t, pm.proxyMap, 1)
+	assert.True(t, pm.HasPeerModel("duplicate-model"))
+}
+
+func TestHasPeerModel(t *testing.T) {
+	proxyURL, _ := url.Parse("http://peer1.example.com:8080")
+	peers := config.PeerDictionaryConfig{
+		"peer1": config.PeerConfig{
+			Proxy:    "http://peer1.example.com:8080",
+			ProxyURL: proxyURL,
+			Models:   []string{"existing-model"},
+		},
+	}
+
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+
+	assert.True(t, pm.HasPeerModel("existing-model"))
+	assert.False(t, pm.HasPeerModel("non-existing-model"))
+}
+
+func TestProxyRequest_ModelNotFound(t *testing.T) {
+	peers := config.PeerDictionaryConfig{}
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+
+	req := httptest.NewRequest("POST", "/v1/chat/completions", nil)
+	w := httptest.NewRecorder()
+
+	err = pm.ProxyRequest("non-existing-model", w, req)
+	assert.Error(t, err)
+	assert.Contains(t, err.Error(), "no peer proxy found for model non-existing-model")
+}
+
+func TestProxyRequest_Success(t *testing.T) {
+	// Create a test server to act as the peer
+	testServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.WriteHeader(http.StatusOK)
+		w.Write([]byte("response from peer"))
+	}))
+	defer testServer.Close()
+
+	proxyURL, _ := url.Parse(testServer.URL)
+	peers := config.PeerDictionaryConfig{
+		"peer1": config.PeerConfig{
+			Proxy:    testServer.URL,
+			ProxyURL: proxyURL,
+			Models:   []string{"test-model"},
+		},
+	}
+
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+
+	req := httptest.NewRequest("POST", "/v1/chat/completions", nil)
+	w := httptest.NewRecorder()
+
+	err = pm.ProxyRequest("test-model", w, req)
+	assert.NoError(t, err)
+	assert.Equal(t, http.StatusOK, w.Code)
+	assert.Equal(t, "response from peer", w.Body.String())
+}
+
+func TestProxyRequest_ApiKeyInjection(t *testing.T) {
+	// Create a test server that checks for the Authorization header
+	var receivedAuthHeader string
+	testServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		receivedAuthHeader = r.Header.Get("Authorization")
+		w.WriteHeader(http.StatusOK)
+	}))
+	defer testServer.Close()
+
+	proxyURL, _ := url.Parse(testServer.URL)
+	peers := config.PeerDictionaryConfig{
+		"peer1": config.PeerConfig{
+			Proxy:    testServer.URL,
+			ProxyURL: proxyURL,
+			ApiKey:   "secret-api-key",
+			Models:   []string{"test-model"},
+		},
+	}
+
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+
+	req := httptest.NewRequest("POST", "/v1/chat/completions", nil)
+	w := httptest.NewRecorder()
+
+	err = pm.ProxyRequest("test-model", w, req)
+	assert.NoError(t, err)
+	assert.Equal(t, "Bearer secret-api-key", receivedAuthHeader)
+}
+
+func TestProxyRequest_NoApiKey(t *testing.T) {
+	// Create a test server that checks for the Authorization header
+	var receivedAuthHeader string
+	testServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		receivedAuthHeader = r.Header.Get("Authorization")
+		w.WriteHeader(http.StatusOK)
+	}))
+	defer testServer.Close()
+
+	proxyURL, _ := url.Parse(testServer.URL)
+	peers := config.PeerDictionaryConfig{
+		"peer1": config.PeerConfig{
+			Proxy:    testServer.URL,
+			ProxyURL: proxyURL,
+			ApiKey:   "", // No API key
+			Models:   []string{"test-model"},
+		},
+	}
+
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+
+	req := httptest.NewRequest("POST", "/v1/chat/completions", nil)
+	w := httptest.NewRecorder()
+
+	err = pm.ProxyRequest("test-model", w, req)
+	assert.NoError(t, err)
+	assert.Empty(t, receivedAuthHeader)
+}
+
+func TestProxyRequest_HostHeaderSet(t *testing.T) {
+	// Create a test server that checks the Host header
+	var receivedHost string
+	testServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		receivedHost = r.Host
+		w.WriteHeader(http.StatusOK)
+	}))
+	defer testServer.Close()
+
+	proxyURL, _ := url.Parse(testServer.URL)
+	peers := config.PeerDictionaryConfig{
+		"peer1": config.PeerConfig{
+			Proxy:    testServer.URL,
+			ProxyURL: proxyURL,
+			Models:   []string{"test-model"},
+		},
+	}
+
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+
+	req := httptest.NewRequest("POST", "/v1/chat/completions", nil)
+	w := httptest.NewRecorder()
+
+	err = pm.ProxyRequest("test-model", w, req)
+	assert.NoError(t, err)
+	// The Host header should be set to the target URL's host
+	assert.True(t, strings.HasPrefix(receivedHost, "127.0.0.1:"))
+}
+
+func TestProxyRequest_SSEHeaderModification(t *testing.T) {
+	// Create a test server that returns SSE content type
+	testServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "text/event-stream")
+		w.WriteHeader(http.StatusOK)
+	}))
+	defer testServer.Close()
+
+	proxyURL, _ := url.Parse(testServer.URL)
+	peers := config.PeerDictionaryConfig{
+		"peer1": config.PeerConfig{
+			Proxy:    testServer.URL,
+			ProxyURL: proxyURL,
+			Models:   []string{"test-model"},
+		},
+	}
+
+	pm, err := NewPeerProxy(peers, testLogger)
+	require.NoError(t, err)
+
+	req := httptest.NewRequest("POST", "/v1/chat/completions", nil)
+	w := httptest.NewRecorder()
+
+	err = pm.ProxyRequest("test-model", w, req)
+	assert.NoError(t, err)
+	// The X-Accel-Buffering header should be set to "no" for SSE
+	assert.Equal(t, "no", w.Header().Get("X-Accel-Buffering"))
+}

proxy/process.go

@@ -2,8 +2,10 @@ package proxy
 
 import (
 	"context"
+	"encoding/json"
 	"errors"
 	"fmt"
+	"math/rand"
 	"net"
 	"net/http"
 	"net/http/httputil"
@@ -254,6 +256,7 @@ func (p *Process) start() error {
 	p.cmd.Env = append(p.cmd.Environ(), p.config.Env...)
 	p.cmd.Cancel = p.cmdStopUpstreamProcess
 	p.cmd.WaitDelay = p.gracefulStopTimeout
+	setProcAttributes(p.cmd)
 
 	p.cmdMutex.Lock()
 	p.cancelUpstream = ctxCancelUpstream
@@ -411,6 +414,9 @@ func (p *Process) stopCommand() {
 	stopStartTime := time.Now()
 	defer func() {
 		p.proxyLogger.Debugf("<%s> stopCommand took %v", p.ID, time.Since(stopStartTime))
+
+		// free the buffer in processLogger so the memory can be recovered
+		p.processLogger.Clear()
 	}()
 
 	p.cmdMutex.RLock()
@@ -462,6 +468,12 @@ func (p *Process) checkHealthEndpoint(healthURL string) error {
 }
 
 func (p *Process) ProxyRequest(w http.ResponseWriter, r *http.Request) {
+
+	if p.reverseProxy == nil {
+		http.Error(w, fmt.Sprintf("No reverse proxy available for %s", p.ID), http.StatusInternalServerError)
+		return
+	}
+
 	requestBeginTime := time.Now()
 	var startDuration time.Duration
 
@@ -488,17 +500,47 @@ func (p *Process) ProxyRequest(w http.ResponseWriter, r *http.Request) {
 		p.inFlightRequests.Done()
 	}()
 
+	// for #366
+	// - extract streaming param from request context, should have been set by proxymanager
+	var srw *statusResponseWriter
+	swapCtx, cancelLoadCtx := context.WithCancel(r.Context())
 	// start the process on demand
 	if p.CurrentState() != StateReady {
+		// start a goroutine to stream loading status messages into the response writer
+		// add a sync so the streaming client only runs when the goroutine has exited
+
+		isStreaming, _ := r.Context().Value(proxyCtxKey("streaming")).(bool)
+
+		// PR #417 (no support for anthropic v1/messages yet)
+		isChatCompletions := strings.HasPrefix(r.URL.Path, "/v1/chat/completions")
+		if p.config.SendLoadingState != nil && *p.config.SendLoadingState && isStreaming && isChatCompletions {
+			srw = newStatusResponseWriter(p, w)
+			go srw.statusUpdates(swapCtx)
+		} else {
+			p.proxyLogger.Debugf("<%s> SendLoadingState is nil or false, not streaming loading state", p.ID)
+		}
+
 		beginStartTime := time.Now()
 		if err := p.start(); err != nil {
 			errstr := fmt.Sprintf("unable to start process: %s", err)
-			http.Error(w, errstr, http.StatusBadGateway)
+			cancelLoadCtx()
+			if srw != nil {
+				srw.sendData(fmt.Sprintf("Unable to swap model err: %s\n", errstr))
+				// Wait for statusUpdates goroutine to finish writing its deferred "Done!" messages
+				// before closing the connection. Without this, the connection would close before
+				// the goroutine can write its cleanup messages, causing incomplete SSE output.
+				srw.waitForCompletion(100 * time.Millisecond)
+			} else {
+				http.Error(w, errstr, http.StatusBadGateway)
+			}
 			return
 		}
 		startDuration = time.Since(beginStartTime)
 	}
 
+	// should trigger srw to stop sending loading events ...
+	cancelLoadCtx()
+
 	// recover from http.ErrAbortHandler panics that can occur when the client
 	// disconnects before the response is sent
 	defer func() {
@@ -511,10 +553,15 @@ func (p *Process) ProxyRequest(w http.ResponseWriter, r *http.Request) {
 		}
 	}()
 
-	if p.reverseProxy != nil {
-		p.reverseProxy.ServeHTTP(w, r)
+	if srw != nil {
+		// Wait for the goroutine to finish writing its final messages
+		const completionTimeout = 1 * time.Second
+		if !srw.waitForCompletion(completionTimeout) {
+			p.proxyLogger.Warnf("<%s> status updates goroutine did not complete within %v, proceeding with proxy request", p.ID, completionTimeout)
+		}
+		p.reverseProxy.ServeHTTP(srw, r)
 	} else {
-		http.Error(w, fmt.Sprintf("No reverse proxy available for %s", p.ID), http.StatusInternalServerError)
+		p.reverseProxy.ServeHTTP(w, r)
 	}
 
 	totalTime := time.Since(requestBeginTime)
@@ -585,6 +632,7 @@ 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 {
@@ -600,3 +648,232 @@ func (p *Process) cmdStopUpstreamProcess() error {
 
 	return nil
 }
+
+// Logger returns the logger for this process.
+func (p *Process) Logger() *LogMonitor {
+	return p.processLogger
+}
+
+var loadingRemarks = []string{
+	"Still faster than your last standup meeting...",
+	"Reticulating splines...",
+	"Waking up the hamsters...",
+	"Teaching the model manners...",
+	"Convincing the GPU to participate...",
+	"Loading weights (they're heavy)...",
+	"Herding electrons...",
+	"Compiling excuses for the delay...",
+	"Downloading more RAM...",
+	"Asking the model nicely to boot up...",
+	"Bribing CUDA with cookies...",
+	"Still loading (blame VRAM)...",
+	"The model is fashionably late...",
+	"Warming up those tensors...",
+	"Making the neural net do push-ups...",
+	"Your patience is appreciated (really)...",
+	"Almost there (probably)...",
+	"Loading like it's 1999...",
+	"The model forgot where it put its keys...",
+	"Quantum tunneling through layers...",
+	"Negotiating with the PCIe bus...",
+	"Defrosting frozen parameters...",
+	"Teaching attention heads to focus...",
+	"Running the matrix (slowly)...",
+	"Untangling transformer blocks...",
+	"Calibrating the flux capacitor...",
+	"Spinning up the probability wheels...",
+	"Waiting for the GPU to wake from its nap...",
+	"Converting caffeine to compute...",
+	"Allocating virtual patience...",
+	"Performing arcane CUDA rituals...",
+	"The model is stuck in traffic...",
+	"Inflating embeddings...",
+	"Summoning computational demons...",
+	"Pleading with the OOM killer...",
+	"Calculating the meaning of life (still at 42)...",
+	"Training the training wheels...",
+	"Optimizing the optimizer...",
+	"Bootstrapping the bootstrapper...",
+	"Loading loading screen...",
+	"Processing processing logs...",
+	"Buffering buffer overflow jokes...",
+	"The model hit snooze...",
+	"Debugging the debugger...",
+	"Compiling the compiler...",
+	"Parsing the parser (meta)...",
+	"Tokenizing tokens...",
+	"Encoding the encoder...",
+	"Hashing hash browns...",
+	"Forking spoons (not forks)...",
+	"The model is contemplating existence...",
+	"Transcending dimensional barriers...",
+	"Invoking elder tensor gods...",
+	"Unfurling probability clouds...",
+	"Synchronizing parallel universes...",
+	"The GPU is having second thoughts...",
+	"Recalibrating reality matrices...",
+	"Time is an illusion, loading doubly so...",
+	"Convincing bits to flip themselves...",
+	"The model is reading its own documentation...",
+}
+
+type statusResponseWriter struct {
+	hasWritten bool
+	writer     http.ResponseWriter
+	process    *Process
+	wg         sync.WaitGroup // Track goroutine completion
+	start      time.Time
+}
+
+func newStatusResponseWriter(p *Process, w http.ResponseWriter) *statusResponseWriter {
+	s := &statusResponseWriter{
+		writer:  w,
+		process: p,
+		start:   time.Now(),
+	}
+
+	s.Header().Set("Content-Type", "text/event-stream") // SSE
+	s.Header().Set("Cache-Control", "no-cache")         // no-cache
+	s.Header().Set("Connection", "keep-alive")          // keep-alive
+	s.WriteHeader(http.StatusOK)                        // send status code 200
+	s.sendLine("━━━━━")
+	s.sendLine(fmt.Sprintf("llama-swap loading model: %s", p.ID))
+	return s
+}
+
+// statusUpdates sends status updates to the client while the model is loading
+func (s *statusResponseWriter) statusUpdates(ctx context.Context) {
+	s.wg.Add(1)
+	defer s.wg.Done()
+
+	// Recover from panics caused by client disconnection
+	// Note: recover() only works within the same goroutine, so we need it here
+	defer func() {
+		if r := recover(); r != nil {
+			s.process.proxyLogger.Debugf("<%s> statusUpdates recovered from panic (likely client disconnect): %v", s.process.ID, r)
+		}
+	}()
+
+	defer func() {
+		duration := time.Since(s.start)
+		s.sendLine(fmt.Sprintf("\nDone! (%.2fs)", duration.Seconds()))
+		s.sendLine("━━━━━")
+		s.sendLine(" ")
+	}()
+
+	// Create a shuffled copy of loadingRemarks
+	remarks := make([]string, len(loadingRemarks))
+	copy(remarks, loadingRemarks)
+	rand.Shuffle(len(remarks), func(i, j int) {
+		remarks[i], remarks[j] = remarks[j], remarks[i]
+	})
+	ri := 0
+
+	// Pick a random duration to send a remark
+	nextRemarkIn := time.Duration(2+rand.Intn(4)) * time.Second
+	lastRemarkTime := time.Now()
+
+	ticker := time.NewTicker(time.Second)
+	defer ticker.Stop() // Ensure ticker is stopped to prevent resource leak
+	for {
+		select {
+		case <-ctx.Done():
+			return
+		case <-ticker.C:
+			if s.process.CurrentState() == StateReady {
+				return
+			}
+
+			// Check if it's time for a snarky remark
+			if time.Since(lastRemarkTime) >= nextRemarkIn {
+				remark := remarks[ri%len(remarks)]
+				ri++
+				s.sendLine(fmt.Sprintf("\n%s", remark))
+				lastRemarkTime = time.Now()
+				// Pick a new random duration for the next remark
+				nextRemarkIn = time.Duration(5+rand.Intn(5)) * time.Second
+			} else {
+				s.sendData(".")
+			}
+		}
+	}
+}
+
+// waitForCompletion waits for the statusUpdates goroutine to finish
+func (s *statusResponseWriter) waitForCompletion(timeout time.Duration) bool {
+	done := make(chan struct{})
+	go func() {
+		s.wg.Wait()
+		close(done)
+	}()
+
+	select {
+	case <-done:
+		return true
+	case <-time.After(timeout):
+		return false
+	}
+}
+
+func (s *statusResponseWriter) sendLine(line string) {
+	s.sendData(line + "\n")
+}
+
+func (s *statusResponseWriter) sendData(data string) {
+	// Create the proper SSE JSON structure
+	type Delta struct {
+		ReasoningContent string `json:"reasoning_content"`
+	}
+	type Choice struct {
+		Delta Delta `json:"delta"`
+	}
+	type SSEMessage struct {
+		Choices []Choice `json:"choices"`
+	}
+
+	msg := SSEMessage{
+		Choices: []Choice{
+			{
+				Delta: Delta{
+					ReasoningContent: data,
+				},
+			},
+		},
+	}
+
+	jsonData, err := json.Marshal(msg)
+	if err != nil {
+		s.process.proxyLogger.Errorf("<%s> Failed to marshal SSE message: %v", s.process.ID, err)
+		return
+	}
+
+	// Write SSE formatted data, panic if not able to write
+	_, err = fmt.Fprintf(s.writer, "data: %s\n\n", jsonData)
+	if err != nil {
+		panic(fmt.Sprintf("<%s> Failed to write SSE data: %v", s.process.ID, err))
+	}
+	s.Flush()
+}
+
+func (s *statusResponseWriter) Header() http.Header {
+	return s.writer.Header()
+}
+
+func (s *statusResponseWriter) Write(data []byte) (int, error) {
+	return s.writer.Write(data)
+}
+
+func (s *statusResponseWriter) WriteHeader(statusCode int) {
+	if s.hasWritten {
+		return
+	}
+	s.hasWritten = true
+	s.writer.WriteHeader(statusCode)
+	s.Flush()
+}
+
+func (s *statusResponseWriter) Flush() {
+	if flusher, ok := s.writer.(http.Flusher); ok {
+		flusher.Flush()
+	}
+}

proxy/process_test.go

@@ -395,6 +395,10 @@ func TestProcess_StopImmediately(t *testing.T) {
 // Test that SIGKILL is sent when gracefulStopTimeout is reached and properly terminates
 // the upstream command
 func TestProcess_ForceStopWithKill(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping slow test")
+	}
+
 	if runtime.GOOS == "windows" {
 		t.Skip("skipping SIGTERM test on Windows ")
 	}

proxy/process_unix.go

@@ -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
+}

proxy/process_windows.go

@@ -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
+	}
+}

proxy/processgroup.go

@@ -46,7 +46,8 @@ func NewProcessGroup(id string, config config.Config, proxyLogger *LogMonitor, u
 	// 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)
+		processLogger := NewLogMonitorWriter(upstreamLogger)
+		process := NewProcess(modelID, pg.config.HealthCheckTimeout, modelConfig, processLogger, pg.proxyLogger)
 		pg.processes[modelID] = process
 	}
 
@@ -88,6 +89,13 @@ func (pg *ProcessGroup) HasMember(modelName string) bool {
 	return slices.Contains(pg.config.Groups[pg.id].Members, modelName)
 }
 
+func (pg *ProcessGroup) GetMember(modelName string) (*Process, bool) {
+	if pg.HasMember(modelName) {
+		return pg.processes[modelName], true
+	}
+	return nil, false
+}
+
 func (pg *ProcessGroup) StopProcess(modelID string, strategy StopStrategy) error {
 	pg.Lock()
 

proxy/processgroup_test.go

@@ -49,6 +49,10 @@ func TestProcessGroup_HasMember(t *testing.T) {
 // TestProcessGroup_ProxyRequestSwapIsTrueParallel tests that when swap is true
 // and multiple requests are made in parallel, only one process is running at a time.
 func TestProcessGroup_ProxyRequestSwapIsTrueParallel(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping slow test")
+	}
+
 	var processGroupTestConfig = config.AddDefaultGroupToConfig(config.Config{
 		HealthCheckTimeout: 15,
 		Models: map[string]config.ModelConfig{

proxy/proxymanager.go

@@ -3,6 +3,7 @@ package proxy
 import (
 	"bytes"
 	"context"
+	"encoding/base64"
 	"fmt"
 	"io"
 	"mime/multipart"
@@ -25,6 +26,8 @@ const (
 	PROFILE_SPLIT_CHAR = ":"
 )
 
+type proxyCtxKey string
+
 type ProxyManager struct {
 	sync.Mutex
 
@@ -43,19 +46,47 @@ type ProxyManager struct {
 	// shutdown signaling
 	shutdownCtx    context.Context
 	shutdownCancel context.CancelFunc
+
+	// version info
+	buildDate string
+	commit    string
+	version   string
+
+	// peer proxy see: #296, #433
+	peerProxy *PeerProxy
 }
 
-func New(config config.Config) *ProxyManager {
+func New(proxyConfig config.Config) *ProxyManager {
 	// set up loggers
-	stdoutLogger := NewLogMonitorWriter(os.Stdout)
-	upstreamLogger := NewLogMonitorWriter(stdoutLogger)
-	proxyLogger := NewLogMonitorWriter(stdoutLogger)
 
-	if config.LogRequests {
+	var muxLogger, upstreamLogger, proxyLogger *LogMonitor
+	switch proxyConfig.LogToStdout {
+	case config.LogToStdoutNone:
+		muxLogger = NewLogMonitorWriter(io.Discard)
+		upstreamLogger = NewLogMonitorWriter(io.Discard)
+		proxyLogger = NewLogMonitorWriter(io.Discard)
+	case config.LogToStdoutBoth:
+		muxLogger = NewLogMonitorWriter(os.Stdout)
+		upstreamLogger = NewLogMonitorWriter(muxLogger)
+		proxyLogger = NewLogMonitorWriter(muxLogger)
+	case config.LogToStdoutUpstream:
+		muxLogger = NewLogMonitorWriter(os.Stdout)
+		upstreamLogger = NewLogMonitorWriter(muxLogger)
+		proxyLogger = NewLogMonitorWriter(io.Discard)
+	default:
+		// same as config.LogToStdoutProxy
+		// helpful because some old tests create a config.Config directly and it
+		// may not have LogToStdout set explicitly
+		muxLogger = NewLogMonitorWriter(os.Stdout)
+		upstreamLogger = NewLogMonitorWriter(io.Discard)
+		proxyLogger = NewLogMonitorWriter(muxLogger)
+	}
+
+	if proxyConfig.LogRequests {
 		proxyLogger.Warn("LogRequests configuration is deprecated. Use logLevel instead.")
 	}
 
-	switch strings.ToLower(strings.TrimSpace(config.LogLevel)) {
+	switch strings.ToLower(strings.TrimSpace(proxyConfig.LogLevel)) {
 	case "debug":
 		proxyLogger.SetLogLevel(LevelDebug)
 		upstreamLogger.SetLogLevel(LevelDebug)
@@ -73,21 +104,51 @@ 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(proxyConfig.LogTimeFormat))]; ok {
+		proxyLogger.SetLogTimeFormat(timeFormat)
+		upstreamLogger.SetLogTimeFormat(timeFormat)
+	}
+
 	shutdownCtx, shutdownCancel := context.WithCancel(context.Background())
 
 	var maxMetrics int
-	if config.MetricsMaxInMemory <= 0 {
+	if proxyConfig.MetricsMaxInMemory <= 0 {
 		maxMetrics = 1000 // Default fallback
 	} else {
-		maxMetrics = config.MetricsMaxInMemory
+		maxMetrics = proxyConfig.MetricsMaxInMemory
+	}
+
+	peerProxy, err := NewPeerProxy(proxyConfig.Peers, proxyLogger)
+	if err != nil {
+		proxyLogger.Errorf("Disabling Peering. Failed to create proxy peers: %v", err)
+		peerProxy = nil
 	}
 
 	pm := &ProxyManager{
-		config:    config,
+		config:    proxyConfig,
 		ginEngine: gin.New(),
 
 		proxyLogger:    proxyLogger,
-		muxLogger:      stdoutLogger,
+		muxLogger:      muxLogger,
 		upstreamLogger: upstreamLogger,
 
 		metricsMonitor: newMetricsMonitor(proxyLogger, maxMetrics),
@@ -96,37 +157,50 @@ func New(config config.Config) *ProxyManager {
 
 		shutdownCtx:    shutdownCtx,
 		shutdownCancel: shutdownCancel,
+
+		buildDate: "unknown",
+		commit:    "abcd1234",
+		version:   "0",
+
+		peerProxy: peerProxy,
 	}
 
 	// create the process groups
-	for groupID := range config.Groups {
-		processGroup := NewProcessGroup(groupID, config, proxyLogger, upstreamLogger)
+	for groupID := range proxyConfig.Groups {
+		processGroup := NewProcessGroup(groupID, proxyConfig, proxyLogger, upstreamLogger)
 		pm.processGroups[groupID] = processGroup
 	}
 
 	pm.setupGinEngine()
 
 	// run any startup hooks
-	if len(config.Hooks.OnStartup.Preload) > 0 {
+	if len(proxyConfig.Hooks.OnStartup.Preload) > 0 {
 		// do it in the background, don't block startup -- not sure if good idea yet
 		go func() {
 			discardWriter := &DiscardWriter{}
-			for _, realModelName := range config.Hooks.OnStartup.Preload {
-				proxyLogger.Infof("Preloading model: %s", realModelName)
-				processGroup, _, err := pm.swapProcessGroup(realModelName)
+			for _, preloadModelName := range proxyConfig.Hooks.OnStartup.Preload {
+				modelID, ok := proxyConfig.RealModelName(preloadModelName)
+
+				if !ok {
+					proxyLogger.Warnf("Preload model %s not found in config", preloadModelName)
+					continue
+				}
+
+				proxyLogger.Infof("Preloading model: %s", modelID)
+				processGroup, err := pm.swapProcessGroup(modelID)
 
 				if err != nil {
 					event.Emit(ModelPreloadedEvent{
-						ModelName: realModelName,
+						ModelName: modelID,
 						Success:   false,
 					})
-					proxyLogger.Errorf("Failed to preload model %s: %v", realModelName, err)
+					proxyLogger.Errorf("Failed to preload model %s: %v", modelID, err)
 					continue
 				} else {
 					req, _ := http.NewRequest("GET", "/", nil)
-					processGroup.ProxyRequest(realModelName, discardWriter, req)
+					processGroup.ProxyRequest(modelID, discardWriter, req)
 					event.Emit(ModelPreloadedEvent{
-						ModelName: realModelName,
+						ModelName: modelID,
 						Success:   true,
 					})
 				}
@@ -201,35 +275,41 @@ func (pm *ProxyManager) setupGinEngine() {
 	})
 
 	// Set up routes using the Gin engine
-	pm.ginEngine.POST("/v1/chat/completions", pm.proxyOAIHandler)
+	// Protected routes use pm.apiKeyAuth() middleware
+	pm.ginEngine.POST("/v1/chat/completions", pm.apiKeyAuth(), pm.proxyInferenceHandler)
 	// Support legacy /v1/completions api, see issue #12
-	pm.ginEngine.POST("/v1/completions", pm.proxyOAIHandler)
+	pm.ginEngine.POST("/v1/completions", pm.apiKeyAuth(), pm.proxyInferenceHandler)
+	// Support anthropic /v1/messages (added https://github.com/ggml-org/llama.cpp/pull/17570)
+	pm.ginEngine.POST("/v1/messages", pm.apiKeyAuth(), pm.proxyInferenceHandler)
 
 	// Support embeddings and reranking
-	pm.ginEngine.POST("/v1/embeddings", pm.proxyOAIHandler)
+	pm.ginEngine.POST("/v1/embeddings", pm.apiKeyAuth(), pm.proxyInferenceHandler)
 
 	// llama-server's /reranking endpoint + aliases
-	pm.ginEngine.POST("/reranking", pm.proxyOAIHandler)
-	pm.ginEngine.POST("/rerank", pm.proxyOAIHandler)
-	pm.ginEngine.POST("/v1/rerank", pm.proxyOAIHandler)
-	pm.ginEngine.POST("/v1/reranking", pm.proxyOAIHandler)
+	pm.ginEngine.POST("/reranking", pm.apiKeyAuth(), pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/rerank", pm.apiKeyAuth(), pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/rerank", pm.apiKeyAuth(), pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/reranking", pm.apiKeyAuth(), pm.proxyInferenceHandler)
 
 	// llama-server's /infill endpoint for code infilling
-	pm.ginEngine.POST("/infill", pm.proxyOAIHandler)
+	pm.ginEngine.POST("/infill", pm.apiKeyAuth(), pm.proxyInferenceHandler)
 
 	// llama-server's /completion endpoint
-	pm.ginEngine.POST("/completion", pm.proxyOAIHandler)
+	pm.ginEngine.POST("/completion", pm.apiKeyAuth(), pm.proxyInferenceHandler)
 
 	// Support audio/speech endpoint
-	pm.ginEngine.POST("/v1/audio/speech", pm.proxyOAIHandler)
-	pm.ginEngine.POST("/v1/audio/transcriptions", pm.proxyOAIPostFormHandler)
+	pm.ginEngine.POST("/v1/audio/speech", pm.apiKeyAuth(), pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/audio/voices", pm.apiKeyAuth(), pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/audio/transcriptions", pm.apiKeyAuth(), pm.proxyOAIPostFormHandler)
+	pm.ginEngine.POST("/v1/images/generations", pm.apiKeyAuth(), pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/images/edits", pm.apiKeyAuth(), pm.proxyOAIPostFormHandler)
 
-	pm.ginEngine.GET("/v1/models", pm.listModelsHandler)
+	pm.ginEngine.GET("/v1/models", pm.apiKeyAuth(), pm.listModelsHandler)
 
 	// in proxymanager_loghandlers.go
-	pm.ginEngine.GET("/logs", pm.sendLogsHandlers)
-	pm.ginEngine.GET("/logs/stream", pm.streamLogsHandler)
-	pm.ginEngine.GET("/logs/stream/:logMonitorID", pm.streamLogsHandler)
+	pm.ginEngine.GET("/logs", pm.apiKeyAuth(), pm.sendLogsHandlers)
+	pm.ginEngine.GET("/logs/stream", pm.apiKeyAuth(), pm.streamLogsHandler)
+	pm.ginEngine.GET("/logs/stream/*logMonitorID", pm.apiKeyAuth(), pm.streamLogsHandler)
 
 	/**
 	 * User Interface Endpoints
@@ -241,9 +321,9 @@ func (pm *ProxyManager) setupGinEngine() {
 	pm.ginEngine.GET("/upstream", func(c *gin.Context) {
 		c.Redirect(http.StatusFound, "/ui/models")
 	})
-	pm.ginEngine.Any("/upstream/*upstreamPath", pm.proxyToUpstream)
-	pm.ginEngine.GET("/unload", pm.unloadAllModelsHandler)
-	pm.ginEngine.GET("/running", pm.listRunningProcessesHandler)
+	pm.ginEngine.Any("/upstream/*upstreamPath", pm.apiKeyAuth(), pm.proxyToUpstream)
+	pm.ginEngine.GET("/unload", pm.apiKeyAuth(), pm.unloadAllModelsHandler)
+	pm.ginEngine.GET("/running", pm.apiKeyAuth(), pm.listRunningProcessesHandler)
 	pm.ginEngine.GET("/health", func(c *gin.Context) {
 		c.String(http.StatusOK, "OK")
 	})
@@ -341,16 +421,10 @@ func (pm *ProxyManager) Shutdown() {
 	pm.shutdownCancel()
 }
 
-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)
-	}
-
+func (pm *ProxyManager) swapProcessGroup(realModelName string) (*ProcessGroup, error) {
 	processGroup := pm.findGroupByModelName(realModelName)
 	if processGroup == nil {
-		return nil, realModelName, fmt.Errorf("could not find process group for model %s", requestedModel)
+		return nil, fmt.Errorf("could not find process group for model %s", realModelName)
 	}
 
 	if processGroup.exclusive {
@@ -362,20 +436,16 @@ func (pm *ProxyManager) swapProcessGroup(requestedModel string) (*ProcessGroup,
 		}
 	}
 
-	return processGroup, realModelName, nil
+	return processGroup, nil
 }
 
 func (pm *ProxyManager) listModelsHandler(c *gin.Context) {
 	data := make([]gin.H, 0, len(pm.config.Models))
 	createdTime := time.Now().Unix()
 
-	for id, modelConfig := range pm.config.Models {
-		if modelConfig.Unlisted {
-			continue
-		}
-
+	newRecord := func(modelId string, modelConfig config.ModelConfig) gin.H {
 		record := gin.H{
-			"id":       id,
+			"id":       modelId,
 			"object":   "model",
 			"created":  createdTime,
 			"owned_by": "llama-swap",
@@ -394,8 +464,41 @@ func (pm *ProxyManager) listModelsHandler(c *gin.Context) {
 				"llamaswap": modelConfig.Metadata,
 			}
 		}
+		return record
+	}
 
-		data = append(data, record)
+	for id, modelConfig := range pm.config.Models {
+		if modelConfig.Unlisted {
+			continue
+		}
+
+		data = append(data, newRecord(id, modelConfig))
+
+		// Include aliases
+		if pm.config.IncludeAliasesInList {
+			for _, alias := range modelConfig.Aliases {
+				if alias := strings.TrimSpace(alias); alias != "" {
+					data = append(data, newRecord(alias, modelConfig))
+				}
+			}
+		}
+	}
+
+	if pm.peerProxy != nil {
+		for peerID, peer := range pm.peerProxy.ListPeers() {
+			// add peer models
+			for _, modelID := range peer.Models {
+				// Skip unlisted models if not showing them
+				record := newRecord(modelID, config.ModelConfig{
+					Name: fmt.Sprintf("%s: %s", peerID, modelID),
+					Metadata: map[string]any{
+						"peerID": peerID,
+					},
+				})
+
+				data = append(data, record)
+			}
+		}
 	}
 
 	// Sort by the "id" key
@@ -417,62 +520,61 @@ func (pm *ProxyManager) listModelsHandler(c *gin.Context) {
 	})
 }
 
-func (pm *ProxyManager) proxyToUpstream(c *gin.Context) {
-	upstreamPath := c.Param("upstreamPath")
-
-	// split the upstream path by / and search for the model name
-	parts := strings.Split(strings.TrimSpace(upstreamPath), "/")
-	if len(parts) == 0 {
-		pm.sendErrorResponse(c, http.StatusBadRequest, "model id required in path")
-		return
-	}
-
-	modelFound := false
+// findModelInPath searches for a valid model name in a path with slashes.
+// It iteratively builds up path segments until it finds a matching model.
+// Returns: (searchModelName, realModelName, remainingPath, found)
+// Example: "/author/model/endpoint" with model "author/model" -> ("author/model", "author/model", "/endpoint", true)
+func (pm *ProxyManager) findModelInPath(path string) (searchName string, realName string, remainingPath string, found bool) {
+	parts := strings.Split(strings.TrimSpace(path), "/")
 	searchModelName := ""
-	var modelName, remainingPath string
+
 	for i, part := range parts {
-		if parts[i] == "" {
+		if part == "" {
 			continue
 		}
 
 		if searchModelName == "" {
 			searchModelName = part
 		} else {
-			searchModelName = searchModelName + "/" + parts[i]
+			searchModelName = searchModelName + "/" + part
 		}
 
-		if real, ok := pm.config.RealModelName(searchModelName); ok {
-			modelName = real
-			remainingPath = "/" + strings.Join(parts[i+1:], "/")
-			modelFound = true
-
-			// Check if this is exactly a model name with no additional path
-			// and doesn't end with a trailing slash
-			if remainingPath == "/" && !strings.HasSuffix(upstreamPath, "/") {
-				// Build new URL with query parameters preserved
-				newPath := "/upstream/" + searchModelName + "/"
-				if c.Request.URL.RawQuery != "" {
-					newPath += "?" + c.Request.URL.RawQuery
-				}
-
-				// Use 308 for non-GET/HEAD requests to preserve method
-				if c.Request.Method == http.MethodGet || c.Request.Method == http.MethodHead {
-					c.Redirect(http.StatusMovedPermanently, newPath)
-				} else {
-					c.Redirect(http.StatusPermanentRedirect, newPath)
-				}
-				return
-			}
-			break
+		if modelID, ok := pm.config.RealModelName(searchModelName); ok {
+			return searchModelName, modelID, "/" + strings.Join(parts[i+1:], "/"), true
 		}
 	}
 
+	return "", "", "", false
+}
+
+func (pm *ProxyManager) proxyToUpstream(c *gin.Context) {
+	upstreamPath := c.Param("upstreamPath")
+
+	searchModelName, modelID, remainingPath, modelFound := pm.findModelInPath(upstreamPath)
+
 	if !modelFound {
 		pm.sendErrorResponse(c, http.StatusBadRequest, "model id required in path")
 		return
 	}
 
-	processGroup, realModelName, err := pm.swapProcessGroup(modelName)
+	// Redirect /upstream/modelname to /upstream/modelname/ for URL consistency.
+	// This ensures relative URLs in upstream responses resolve correctly and
+	// provides canonical URL form. Uses 308 for POST/PUT/etc to preserve the
+	// HTTP method (301 would downgrade to GET).
+	if remainingPath == "/" && !strings.HasSuffix(upstreamPath, "/") {
+		newPath := "/upstream/" + searchModelName + "/"
+		if c.Request.URL.RawQuery != "" {
+			newPath += "?" + c.Request.URL.RawQuery
+		}
+		if c.Request.Method == http.MethodGet || c.Request.Method == http.MethodHead {
+			c.Redirect(http.StatusMovedPermanently, newPath)
+		} else {
+			c.Redirect(http.StatusPermanentRedirect, newPath)
+		}
+		return
+	}
+
+	processGroup, err := pm.swapProcessGroup(modelID)
 	if err != nil {
 		pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error swapping process group: %s", err.Error()))
 		return
@@ -484,21 +586,21 @@ func (pm *ProxyManager) proxyToUpstream(c *gin.Context) {
 
 	// attempt to record metrics if it is a POST request
 	if pm.metricsMonitor != nil && c.Request.Method == "POST" {
-		if err := pm.metricsMonitor.wrapHandler(realModelName, c.Writer, c.Request, processGroup.ProxyRequest); err != nil {
+		if err := pm.metricsMonitor.wrapHandler(modelID, c.Writer, c.Request, processGroup.ProxyRequest); err != nil {
 			pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error proxying metrics wrapped request: %s", err.Error()))
-			pm.proxyLogger.Errorf("Error proxying wrapped upstream request for model %s, path=%s", realModelName, originalPath)
+			pm.proxyLogger.Errorf("Error proxying wrapped upstream request for model %s, path=%s", modelID, originalPath)
 			return
 		}
 	} else {
-		if err := processGroup.ProxyRequest(realModelName, c.Writer, c.Request); err != nil {
+		if err := processGroup.ProxyRequest(modelID, c.Writer, c.Request); err != nil {
 			pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error proxying request: %s", err.Error()))
-			pm.proxyLogger.Errorf("Error proxying upstream request for model %s, path=%s", realModelName, originalPath)
+			pm.proxyLogger.Errorf("Error proxying upstream request for model %s, path=%s", modelID, originalPath)
 			return
 		}
 	}
 }
 
-func (pm *ProxyManager) proxyOAIHandler(c *gin.Context) {
+func (pm *ProxyManager) proxyInferenceHandler(c *gin.Context) {
 	bodyBytes, err := io.ReadAll(c.Request.Body)
 	if err != nil {
 		pm.sendErrorResponse(c, http.StatusBadRequest, "could not ready request body")
@@ -511,41 +613,54 @@ func (pm *ProxyManager) proxyOAIHandler(c *gin.Context) {
 		return
 	}
 
-	realModelName, found := pm.config.RealModelName(requestedModel)
-	if !found {
-		pm.sendErrorResponse(c, http.StatusBadRequest, fmt.Sprintf("could not find real modelID for %s", requestedModel))
-		return
-	}
+	// Look for a matching local model first
+	var nextHandler func(modelID string, w http.ResponseWriter, r *http.Request) error
 
-	processGroup, _, err := pm.swapProcessGroup(realModelName)
-	if err != nil {
-		pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error swapping process group: %s", err.Error()))
-		return
-	}
-
-	// issue #69 allow custom model names to be sent to upstream
-	useModelName := pm.config.Models[realModelName].UseModelName
-	if useModelName != "" {
-		bodyBytes, err = sjson.SetBytes(bodyBytes, "model", useModelName)
+	modelID, found := pm.config.RealModelName(requestedModel)
+	if found {
+		processGroup, err := pm.swapProcessGroup(modelID)
 		if err != nil {
-			pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error rewriting model name in JSON: %s", err.Error()))
+			pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error swapping process group: %s", err.Error()))
 			return
 		}
-	}
 
-	// issue #174 strip parameters from the JSON body
-	stripParams, err := pm.config.Models[realModelName].Filters.SanitizedStripParams()
-	if err != nil { // just log it and continue
-		pm.proxyLogger.Errorf("Error sanitizing strip params string: %s, %s", pm.config.Models[realModelName].Filters.StripParams, err.Error())
-	} else {
-		for _, param := range stripParams {
-			pm.proxyLogger.Debugf("<%s> stripping param: %s", realModelName, param)
-			bodyBytes, err = sjson.DeleteBytes(bodyBytes, param)
+		// issue #69 allow custom model names to be sent to upstream
+		useModelName := pm.config.Models[modelID].UseModelName
+		if useModelName != "" {
+			bodyBytes, err = sjson.SetBytes(bodyBytes, "model", useModelName)
 			if err != nil {
-				pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error deleting parameter %s from request", param))
+				pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error rewriting model name in JSON: %s", err.Error()))
 				return
 			}
 		}
+
+		// issue #174 strip parameters from the JSON body
+		stripParams, err := pm.config.Models[modelID].Filters.SanitizedStripParams()
+		if err != nil { // just log it and continue
+			pm.proxyLogger.Errorf("Error sanitizing strip params string: %s, %s", pm.config.Models[modelID].Filters.StripParams, err.Error())
+		} else {
+			for _, param := range stripParams {
+				pm.proxyLogger.Debugf("<%s> stripping param: %s", modelID, param)
+				bodyBytes, err = sjson.DeleteBytes(bodyBytes, param)
+				if err != nil {
+					pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error deleting parameter %s from request", param))
+					return
+				}
+			}
+		}
+
+		pm.proxyLogger.Debugf("ProxyManager using local Process for model: %s", requestedModel)
+		nextHandler = processGroup.ProxyRequest
+	} else if pm.peerProxy != nil && pm.peerProxy.HasPeerModel(requestedModel) {
+		pm.proxyLogger.Debugf("ProxyManager using ProxyPeer for model: %s", requestedModel)
+		modelID = requestedModel
+		nextHandler = pm.peerProxy.ProxyRequest
+
+	}
+
+	if nextHandler == nil {
+		pm.sendErrorResponse(c, http.StatusBadRequest, fmt.Sprintf("could not find suitable inference handler for %s", requestedModel))
+		return
 	}
 
 	c.Request.Body = io.NopCloser(bytes.NewBuffer(bodyBytes))
@@ -555,16 +670,22 @@ func (pm *ProxyManager) proxyOAIHandler(c *gin.Context) {
 	c.Request.Header.Set("content-length", strconv.Itoa(len(bodyBytes)))
 	c.Request.ContentLength = int64(len(bodyBytes))
 
+	// issue #366 extract values that downstream handlers may need
+	isStreaming := gjson.GetBytes(bodyBytes, "stream").Bool()
+	ctx := context.WithValue(c.Request.Context(), proxyCtxKey("streaming"), isStreaming)
+	ctx = context.WithValue(ctx, proxyCtxKey("model"), modelID)
+	c.Request = c.Request.WithContext(ctx)
+
 	if pm.metricsMonitor != nil && c.Request.Method == "POST" {
-		if err := pm.metricsMonitor.wrapHandler(realModelName, c.Writer, c.Request, processGroup.ProxyRequest); err != nil {
+		if err := pm.metricsMonitor.wrapHandler(modelID, c.Writer, c.Request, nextHandler); err != nil {
 			pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error proxying metrics wrapped request: %s", err.Error()))
-			pm.proxyLogger.Errorf("Error Proxying Metrics Wrapped Request for processGroup %s and model %s", processGroup.id, realModelName)
+			pm.proxyLogger.Errorf("Error Proxying Metrics Wrapped Request model %s", modelID)
 			return
 		}
 	} else {
-		if err := processGroup.ProxyRequest(realModelName, c.Writer, c.Request); err != nil {
+		if err := nextHandler(modelID, 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)
+			pm.proxyLogger.Errorf("Error Proxying Request for model %s", modelID)
 			return
 		}
 	}
@@ -584,7 +705,13 @@ func (pm *ProxyManager) proxyOAIPostFormHandler(c *gin.Context) {
 		return
 	}
 
-	processGroup, realModelName, err := pm.swapProcessGroup(requestedModel)
+	modelID, found := pm.config.RealModelName(requestedModel)
+	if !found {
+		pm.sendErrorResponse(c, http.StatusBadRequest, fmt.Sprintf("could not find real modelID for %s", requestedModel))
+		return
+	}
+
+	processGroup, err := pm.swapProcessGroup(modelID)
 	if err != nil {
 		pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error swapping process group: %s", err.Error()))
 		return
@@ -602,7 +729,7 @@ func (pm *ProxyManager) proxyOAIPostFormHandler(c *gin.Context) {
 			// If this is the model field and we have a profile, use just the model name
 			if key == "model" {
 				// # issue #69 allow custom model names to be sent to upstream
-				useModelName := pm.config.Models[realModelName].UseModelName
+				useModelName := pm.config.Models[modelID].UseModelName
 
 				if useModelName != "" {
 					fieldValue = useModelName
@@ -673,9 +800,9 @@ func (pm *ProxyManager) proxyOAIPostFormHandler(c *gin.Context) {
 	modifiedReq.ContentLength = int64(requestBuffer.Len())
 
 	// Use the modified request for proxying
-	if err := processGroup.ProxyRequest(realModelName, c.Writer, modifiedReq); err != nil {
+	if err := processGroup.ProxyRequest(modelID, 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)
+		pm.proxyLogger.Errorf("Error Proxying Request for processGroup %s and model %s", processGroup.id, modelID)
 		return
 	}
 }
@@ -690,6 +817,67 @@ func (pm *ProxyManager) sendErrorResponse(c *gin.Context, statusCode int, messag
 	}
 }
 
+// apiKeyAuth returns a middleware that validates API keys if configured.
+// Returns a pass-through handler if no API keys are configured.
+func (pm *ProxyManager) apiKeyAuth() gin.HandlerFunc {
+	if len(pm.config.RequiredAPIKeys) == 0 {
+		return func(c *gin.Context) { c.Next() }
+	}
+
+	return func(c *gin.Context) {
+		xApiKey := c.GetHeader("x-api-key")
+
+		var bearerKey string
+		var basicKey string
+		if auth := c.GetHeader("Authorization"); auth != "" {
+			if strings.HasPrefix(auth, "Bearer ") {
+				bearerKey = strings.TrimPrefix(auth, "Bearer ")
+			} else if strings.HasPrefix(auth, "Basic ") {
+				// Basic Auth: base64(username:password), password is the API key
+				encoded := strings.TrimPrefix(auth, "Basic ")
+				if decoded, err := base64.StdEncoding.DecodeString(encoded); err == nil {
+					parts := strings.SplitN(string(decoded), ":", 2)
+					if len(parts) == 2 {
+						basicKey = parts[1] // password is the API key
+					}
+				}
+			}
+		}
+
+		// Use first key found: Basic, then Bearer, then x-api-key
+		var providedKey string
+		if basicKey != "" {
+			providedKey = basicKey
+		} else if bearerKey != "" {
+			providedKey = bearerKey
+		} else {
+			providedKey = xApiKey
+		}
+
+		// Validate key
+		valid := false
+		for _, key := range pm.config.RequiredAPIKeys {
+			if providedKey == key {
+				valid = true
+				break
+			}
+		}
+
+		if !valid {
+			c.Header("WWW-Authenticate", `Basic realm="llama-swap"`)
+			pm.sendErrorResponse(c, http.StatusUnauthorized, "unauthorized: invalid or missing API key")
+			c.Abort()
+			return
+		}
+
+		// Strip auth headers to prevent leakage to upstream
+		c.Request.Header.Del("Authorization")
+		c.Request.Header.Del("x-api-key")
+
+		c.Next()
+	}
+}
+
 func (pm *ProxyManager) unloadAllModelsHandler(c *gin.Context) {
 	pm.StopProcesses(StopImmediately)
 	c.String(http.StatusOK, "OK")
@@ -726,3 +914,11 @@ 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

@@ -18,16 +18,19 @@ type Model struct {
 	Description string `json:"description"`
 	State       string `json:"state"`
 	Unlisted    bool   `json:"unlisted"`
+	PeerID      string `json:"peerID"`
 }
 
 func addApiHandlers(pm *ProxyManager) {
 	// Add API endpoints for React to consume
-	apiGroup := pm.ginEngine.Group("/api")
+	// Protected with API key authentication
+	apiGroup := pm.ginEngine.Group("/api", pm.apiKeyAuth())
 	{
 		apiGroup.POST("/models/unload", pm.apiUnloadAllModels)
 		apiGroup.POST("/models/unload/*model", pm.apiUnloadSingleModelHandler)
 		apiGroup.GET("/events", pm.apiSendEvents)
 		apiGroup.GET("/metrics", pm.apiGetMetrics)
+		apiGroup.GET("/version", pm.apiGetVersion)
 	}
 }
 
@@ -81,6 +84,18 @@ func (pm *ProxyManager) getModelStatus() []Model {
 		})
 	}
 
+	// Iterate over the peer models
+	if pm.peerProxy != nil {
+		for peerID, peer := range pm.peerProxy.ListPeers() {
+			for _, modelID := range peer.Models {
+				models = append(models, Model{
+					Id:     modelID,
+					PeerID: peerID,
+				})
+			}
+		}
+	}
+
 	return models
 }
 
@@ -227,3 +242,11 @@ 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_loghandlers.go

@@ -31,7 +31,7 @@ func (pm *ProxyManager) streamLogsHandler(c *gin.Context) {
 	// prevent nginx from buffering streamed logs
 	c.Header("X-Accel-Buffering", "no")
 
-	logMonitorId := c.Param("logMonitorID")
+	logMonitorId := strings.TrimPrefix(c.Param("logMonitorID"), "/")
 	logger, err := pm.getLogger(logMonitorId)
 	if err != nil {
 		c.String(http.StatusBadRequest, err.Error())
@@ -83,18 +83,25 @@ func (pm *ProxyManager) streamLogsHandler(c *gin.Context) {
 
 // getLogger searches for the appropriate logger based on the logMonitorId
 func (pm *ProxyManager) getLogger(logMonitorId string) (*LogMonitor, error) {
-	var logger *LogMonitor
-
-	if logMonitorId == "" {
+	switch logMonitorId {
+	case "":
 		// maintain the default
-		logger = pm.muxLogger
-	} else if logMonitorId == "proxy" {
-		logger = pm.proxyLogger
-	} else if logMonitorId == "upstream" {
-		logger = pm.upstreamLogger
-	} else {
-		return nil, fmt.Errorf("invalid logger. Use 'proxy' or 'upstream'")
-	}
+		return pm.muxLogger, nil
+	case "proxy":
+		return pm.proxyLogger, nil
+	case "upstream":
+		return pm.upstreamLogger, nil
+	default:
+		// search for a models specific logger using findModelInPath
+		// to handle model names with slashes (e.g., "author/model")
+		if _, name, _, found := pm.findModelInPath("/" + logMonitorId); found {
+			for _, group := range pm.processGroups {
+				if process, found := group.GetMember(name); found {
+					return process.Logger(), nil
+				}
+			}
+		}
 
-	return logger, nil
+		return nil, fmt.Errorf("invalid logger. Use 'proxy', 'upstream' or a model's ID")
+	}
 }

proxy/proxymanager_test.go

@@ -3,6 +3,7 @@ package proxy
 import (
 	"bytes"
 	"context"
+	"encoding/base64"
 	"encoding/json"
 	"fmt"
 	"math/rand"
@@ -36,10 +37,6 @@ func (r *TestResponseRecorder) CloseNotify() <-chan bool {
 	return r.closeChannel
 }
 
-func (r *TestResponseRecorder) closeClient() {
-	r.closeChannel <- true
-}
-
 func CreateTestResponseRecorder() *TestResponseRecorder {
 	return &TestResponseRecorder{
 		httptest.NewRecorder(),
@@ -223,17 +220,23 @@ func TestProxyManager_ListModelsHandler(t *testing.T) {
 	model2Config.Name = "     " // empty whitespace only strings will get ignored
 	model2Config.Description = "  "
 
-	config := config.Config{
+	cfg := config.Config{
 		HealthCheckTimeout: 15,
 		Models: map[string]config.ModelConfig{
 			"model1": model1Config,
 			"model2": model2Config,
 			"model3": getTestSimpleResponderConfig("model3"),
 		},
+		Peers: map[string]config.PeerConfig{
+			"peer1": {
+				Proxy:  "http://peer1:8080",
+				Models: []string{"peer-model-a", "peer-model-b"},
+			},
+		},
 		LogLevel: "error",
 	}
 
-	proxy := New(config)
+	proxy := New(cfg)
 
 	// Create a test request
 	req := httptest.NewRequest("GET", "/v1/models", nil)
@@ -258,14 +261,16 @@ func TestProxyManager_ListModelsHandler(t *testing.T) {
 		t.Fatalf("Failed to parse JSON response: %v", err)
 	}
 
-	// Check the number of models returned
-	assert.Len(t, response.Data, 3)
+	// Check the number of models returned (3 local + 2 peer models)
+	assert.Len(t, response.Data, 5)
 
 	// Check the details of each model
 	expectedModels := map[string]struct{}{
-		"model1": {},
-		"model2": {},
-		"model3": {},
+		"model1":       {},
+		"model2":       {},
+		"model3":       {},
+		"peer-model-a": {},
+		"peer-model-b": {},
 	}
 
 	// make all models
@@ -296,6 +301,19 @@ func TestProxyManager_ListModelsHandler(t *testing.T) {
 			description, ok := model["description"].(string)
 			assert.True(t, ok, "description should be a string")
 			assert.Equal(t, "Model 1 description is used for testing", description)
+		} else if modelID == "peer-model-a" || modelID == "peer-model-b" {
+			// Peer models should have meta.llamaswap.peerID
+			meta, exists := model["meta"]
+			assert.True(t, exists, "peer model should have meta field")
+			metaMap, ok := meta.(map[string]interface{})
+			assert.True(t, ok, "meta should be a map")
+			llamaswap, exists := metaMap["llamaswap"]
+			assert.True(t, exists, "meta should have llamaswap field")
+			llamaswapMap, ok := llamaswap.(map[string]interface{})
+			assert.True(t, ok, "llamaswap should be a map")
+			peerID, exists := llamaswapMap["peerID"]
+			assert.True(t, exists, "llamaswap should have peerID field")
+			assert.Equal(t, "peer1", peerID)
 		} else {
 			_, exists := model["name"]
 			assert.False(t, exists, "unexpected name field for model: %s", modelID)
@@ -437,7 +455,75 @@ 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) {
+	if testing.Short() {
+		t.Skip("skipping slow test")
+	}
+
 	// make broken model configurations
 	model1Config := getTestSimpleResponderConfigPort("model1", 9991)
 	model1Config.Proxy = "http://localhost:10001/"
@@ -1014,7 +1100,8 @@ func TestProxyManager_StreamingEndpointsReturnNoBufferingHeader(t *testing.T) {
 	config := config.AddDefaultGroupToConfig(config.Config{
 		HealthCheckTimeout: 15,
 		Models: map[string]config.ModelConfig{
-			"model1": getTestSimpleResponderConfig("model1"),
+			"model1":       getTestSimpleResponderConfig("model1"),
+			"author/model": getTestSimpleResponderConfig("author/model"),
 		},
 		LogLevel: "error",
 	})
@@ -1027,6 +1114,7 @@ func TestProxyManager_StreamingEndpointsReturnNoBufferingHeader(t *testing.T) {
 		"/logs/stream",
 		"/logs/stream/proxy",
 		"/logs/stream/upstream",
+		"/logs/stream/author/model",
 	}
 
 	for _, endpoint := range endpoints {
@@ -1083,3 +1171,387 @@ 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])
+	}
+}
+
+func TestProxyManager_APIKeyAuth(t *testing.T) {
+	testConfig := config.AddDefaultGroupToConfig(config.Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]config.ModelConfig{
+			"model1": getTestSimpleResponderConfig("model1"),
+		},
+		RequiredAPIKeys: []string{"valid-key-1", "valid-key-2"},
+		LogLevel:        "error",
+	})
+
+	proxy := New(testConfig)
+	defer proxy.StopProcesses(StopImmediately)
+
+	t.Run("valid key in x-api-key header", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		req.Header.Set("x-api-key", "valid-key-1")
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+	})
+
+	t.Run("valid key in Authorization Bearer header", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		req.Header.Set("Authorization", "Bearer valid-key-2")
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+	})
+
+	t.Run("both headers with matching keys", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		req.Header.Set("x-api-key", "valid-key-1")
+		req.Header.Set("Authorization", "Bearer valid-key-1")
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+	})
+
+	t.Run("invalid key returns 401", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		req.Header.Set("x-api-key", "invalid-key")
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusUnauthorized, w.Code)
+		assert.Contains(t, w.Body.String(), "unauthorized")
+	})
+
+	t.Run("missing key returns 401", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusUnauthorized, w.Code)
+	})
+
+	t.Run("valid key in Basic Auth header", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		// Basic Auth: base64("anyuser:valid-key-1")
+		credentials := base64.StdEncoding.EncodeToString([]byte("anyuser:valid-key-1"))
+		req.Header.Set("Authorization", "Basic "+credentials)
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+	})
+
+	t.Run("invalid key in Basic Auth header returns 401", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		credentials := base64.StdEncoding.EncodeToString([]byte("anyuser:wrong-key"))
+		req.Header.Set("Authorization", "Basic "+credentials)
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusUnauthorized, w.Code)
+		assert.Contains(t, w.Body.String(), "unauthorized")
+	})
+
+	t.Run("x-api-key and Basic Auth with matching keys", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		req.Header.Set("x-api-key", "valid-key-1")
+		credentials := base64.StdEncoding.EncodeToString([]byte("user:valid-key-1"))
+		req.Header.Set("Authorization", "Basic "+credentials)
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+	})
+
+	t.Run("401 response includes WWW-Authenticate header", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusUnauthorized, w.Code)
+		assert.Equal(t, `Basic realm="llama-swap"`, w.Header().Get("WWW-Authenticate"))
+	})
+}
+
+func TestProxyManager_APIKeyAuth_Disabled(t *testing.T) {
+	// Config without RequiredAPIKeys - auth should be disabled
+	testConfig := config.AddDefaultGroupToConfig(config.Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]config.ModelConfig{
+			"model1": getTestSimpleResponderConfig("model1"),
+		},
+		LogLevel: "error",
+	})
+
+	proxy := New(testConfig)
+	defer proxy.StopProcesses(StopImmediately)
+
+	t.Run("requests pass without API key when not configured", func(t *testing.T) {
+		reqBody := `{"model":"model1"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+	})
+}
+
+// TestProxyManager_PeerProxy_InferenceHandler tests the peerProxy integration
+// in proxyInferenceHandler for issue #433
+func TestProxyManager_PeerProxy_InferenceHandler(t *testing.T) {
+	t.Run("requests to peer models are proxied", func(t *testing.T) {
+		// Create a test server to act as the peer
+		peerServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			w.Header().Set("Content-Type", "application/json")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte(`{"response":"from-peer","model":"peer-model"}`))
+		}))
+		defer peerServer.Close()
+
+		// Create config with peers but no local model for "peer-model"
+		configStr := fmt.Sprintf(`
+logLevel: error
+peers:
+  test-peer:
+    proxy: %s
+    models:
+      - peer-model
+models:
+  local-model:
+    cmd: %s -port ${PORT} -silent -respond local-model
+`, peerServer.URL, getSimpleResponderPath())
+
+		testConfig, err := config.LoadConfigFromReader(strings.NewReader(configStr))
+		assert.NoError(t, err)
+
+		proxy := New(testConfig)
+		defer proxy.StopProcesses(StopImmediately)
+
+		reqBody := `{"model":"peer-model"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+		assert.Contains(t, w.Body.String(), "from-peer")
+	})
+
+	t.Run("local models take precedence over peer models", func(t *testing.T) {
+		// Create a test server to act as the peer - should NOT be called
+		peerCalled := false
+		peerServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			peerCalled = true
+			w.Header().Set("Content-Type", "application/json")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte(`{"response":"from-peer"}`))
+		}))
+		defer peerServer.Close()
+
+		// Create config where "shared-model" exists both locally and on peer
+		configStr := fmt.Sprintf(`
+logLevel: error
+peers:
+  test-peer:
+    proxy: %s
+    models:
+      - shared-model
+models:
+  shared-model:
+    cmd: %s -port ${PORT} -silent -respond local-response
+`, peerServer.URL, getSimpleResponderPath())
+
+		testConfig, err := config.LoadConfigFromReader(strings.NewReader(configStr))
+		assert.NoError(t, err)
+
+		proxy := New(testConfig)
+		defer proxy.StopProcesses(StopImmediately)
+
+		reqBody := `{"model":"shared-model"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+		assert.Contains(t, w.Body.String(), "local-response")
+		assert.False(t, peerCalled, "peer should not be called when local model exists")
+	})
+
+	t.Run("unknown model returns error", func(t *testing.T) {
+		// Create a test server to act as the peer
+		peerServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			w.WriteHeader(http.StatusOK)
+		}))
+		defer peerServer.Close()
+
+		configStr := fmt.Sprintf(`
+logLevel: error
+peers:
+  test-peer:
+    proxy: %s
+    models:
+      - peer-model
+models:
+  local-model:
+    cmd: %s -port ${PORT} -silent -respond local-model
+`, peerServer.URL, getSimpleResponderPath())
+
+		testConfig, err := config.LoadConfigFromReader(strings.NewReader(configStr))
+		assert.NoError(t, err)
+
+		proxy := New(testConfig)
+		defer proxy.StopProcesses(StopImmediately)
+
+		reqBody := `{"model":"unknown-model"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusBadRequest, w.Code)
+		assert.Contains(t, w.Body.String(), "could not find suitable inference handler")
+	})
+
+	t.Run("peer API key is injected into request", func(t *testing.T) {
+		var receivedAuthHeader string
+		peerServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			receivedAuthHeader = r.Header.Get("Authorization")
+			w.Header().Set("Content-Type", "application/json")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte(`{"response":"ok"}`))
+		}))
+		defer peerServer.Close()
+
+		configStr := fmt.Sprintf(`
+logLevel: error
+peers:
+  test-peer:
+    proxy: %s
+    apiKey: secret-peer-key
+    models:
+      - peer-model
+models:
+  local-model:
+    cmd: %s -port ${PORT} -silent -respond local-model
+`, peerServer.URL, getSimpleResponderPath())
+
+		testConfig, err := config.LoadConfigFromReader(strings.NewReader(configStr))
+		assert.NoError(t, err)
+
+		proxy := New(testConfig)
+		defer proxy.StopProcesses(StopImmediately)
+
+		reqBody := `{"model":"peer-model"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+		assert.Equal(t, "Bearer secret-peer-key", receivedAuthHeader)
+	})
+
+	t.Run("no peers configured - unknown model returns error", func(t *testing.T) {
+		testConfig := config.AddDefaultGroupToConfig(config.Config{
+			HealthCheckTimeout: 15,
+			Models: map[string]config.ModelConfig{
+				"local-model": getTestSimpleResponderConfig("local-model"),
+			},
+			LogLevel: "error",
+		})
+
+		proxy := New(testConfig)
+		defer proxy.StopProcesses(StopImmediately)
+
+		// peerProxy exists but has no peer models configured
+		assert.False(t, proxy.peerProxy.HasPeerModel("unknown-model"))
+
+		reqBody := `{"model":"unknown-model"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusBadRequest, w.Code)
+		assert.Contains(t, w.Body.String(), "could not find suitable inference handler")
+	})
+
+	t.Run("peer streaming response sets X-Accel-Buffering header", func(t *testing.T) {
+		peerServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			w.Header().Set("Content-Type", "text/event-stream")
+			w.WriteHeader(http.StatusOK)
+			w.Write([]byte("data: test\n\n"))
+		}))
+		defer peerServer.Close()
+
+		configStr := fmt.Sprintf(`
+logLevel: error
+peers:
+  test-peer:
+    proxy: %s
+    models:
+      - peer-model
+models:
+  local-model:
+    cmd: %s -port ${PORT} -silent -respond local-model
+`, peerServer.URL, getSimpleResponderPath())
+
+		testConfig, err := config.LoadConfigFromReader(strings.NewReader(configStr))
+		assert.NoError(t, err)
+
+		proxy := New(testConfig)
+		defer proxy.StopProcesses(StopImmediately)
+
+		reqBody := `{"model":"peer-model"}`
+		req := httptest.NewRequest("POST", "/v1/chat/completions", bytes.NewBufferString(reqBody))
+		w := CreateTestResponseRecorder()
+
+		proxy.ServeHTTP(w, req)
+		assert.Equal(t, http.StatusOK, w.Code)
+		assert.Equal(t, "no", w.Header().Get("X-Accel-Buffering"))
+	})
+}

ui/package-lock.json

@@ -752,9 +752,9 @@
       }
     },
     "node_modules/@eslint-community/eslint-utils": {
-      "version": "4.7.0",
-      "resolved": "https://registry.npmjs.org/@eslint-community/eslint-utils/-/eslint-utils-4.7.0.tgz",
-      "integrity": "sha512-dyybb3AcajC7uha6CvhdVRJqaKyn7w2YKqKyAN37NKYgZT36w+iRb0Dymmc5qEJ549c/S31cMMSFd75bteCpCw==",
+      "version": "4.9.0",
+      "resolved": "https://registry.npmjs.org/@eslint-community/eslint-utils/-/eslint-utils-4.9.0.tgz",
+      "integrity": "sha512-ayVFHdtZ+hsq1t2Dy24wCmGXGe4q9Gu3smhLYALJrr473ZH27MsnSL+LKUlimp4BWJqMDMLmPpx/Q9R3OAlL4g==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -794,13 +794,13 @@
       }
     },
     "node_modules/@eslint/config-array": {
-      "version": "0.20.0",
-      "resolved": "https://registry.npmjs.org/@eslint/config-array/-/config-array-0.20.0.tgz",
-      "integrity": "sha512-fxlS1kkIjx8+vy2SjuCB94q3htSNrufYTXubwiBFeaQHbH6Ipi43gFJq2zCMt6PHhImH3Xmr0NksKDvchWlpQQ==",
+      "version": "0.21.1",
+      "resolved": "https://registry.npmjs.org/@eslint/config-array/-/config-array-0.21.1.tgz",
+      "integrity": "sha512-aw1gNayWpdI/jSYVgzN5pL0cfzU02GT3NBpeT/DXbx1/1x7ZKxFPd9bwrzygx/qiwIQiJ1sw/zD8qY/kRvlGHA==",
       "dev": true,
       "license": "Apache-2.0",
       "dependencies": {
-        "@eslint/object-schema": "^2.1.6",
+        "@eslint/object-schema": "^2.1.7",
         "debug": "^4.3.1",
         "minimatch": "^3.1.2"
       },
@@ -809,19 +809,22 @@
       }
     },
     "node_modules/@eslint/config-helpers": {
-      "version": "0.2.2",
-      "resolved": "https://registry.npmjs.org/@eslint/config-helpers/-/config-helpers-0.2.2.tgz",
-      "integrity": "sha512-+GPzk8PlG0sPpzdU5ZvIRMPidzAnZDl/s9L+y13iodqvb8leL53bTannOrQ/Im7UkpsmFU5Ily5U60LWixnmLg==",
+      "version": "0.4.2",
+      "resolved": "https://registry.npmjs.org/@eslint/config-helpers/-/config-helpers-0.4.2.tgz",
+      "integrity": "sha512-gBrxN88gOIf3R7ja5K9slwNayVcZgK6SOUORm2uBzTeIEfeVaIhOpCtTox3P6R7o2jLFwLFTLnC7kU/RGcYEgw==",
       "dev": true,
       "license": "Apache-2.0",
+      "dependencies": {
+        "@eslint/core": "^0.17.0"
+      },
       "engines": {
         "node": "^18.18.0 || ^20.9.0 || >=21.1.0"
       }
     },
     "node_modules/@eslint/core": {
-      "version": "0.14.0",
-      "resolved": "https://registry.npmjs.org/@eslint/core/-/core-0.14.0.tgz",
-      "integrity": "sha512-qIbV0/JZr7iSDjqAc60IqbLdsj9GDt16xQtWD+B78d/HAlvysGdZZ6rpJHGAc2T0FQx1X6thsSPdnoiGKdNtdg==",
+      "version": "0.17.0",
+      "resolved": "https://registry.npmjs.org/@eslint/core/-/core-0.17.0.tgz",
+      "integrity": "sha512-yL/sLrpmtDaFEiUj1osRP4TI2MDz1AddJL+jZ7KSqvBuliN4xqYY54IfdN8qD8Toa6g1iloph1fxQNkjOxrrpQ==",
       "dev": true,
       "license": "Apache-2.0",
       "dependencies": {
@@ -869,9 +872,9 @@
       }
     },
     "node_modules/@eslint/js": {
-      "version": "9.28.0",
-      "resolved": "https://registry.npmjs.org/@eslint/js/-/js-9.28.0.tgz",
-      "integrity": "sha512-fnqSjGWd/CoIp4EXIxWVK/sHA6DOHN4+8Ix2cX5ycOY7LG0UY8nHCU5pIp2eaE1Mc7Qd8kHspYNzYXT2ojPLzg==",
+      "version": "9.39.1",
+      "resolved": "https://registry.npmjs.org/@eslint/js/-/js-9.39.1.tgz",
+      "integrity": "sha512-S26Stp4zCy88tH94QbBv3XCuzRQiZ9yXofEILmglYTh/Ug/a9/umqvgFtYBAo3Lp0nsI/5/qH1CCrbdK3AP1Tw==",
       "dev": true,
       "license": "MIT",
       "engines": {
@@ -882,9 +885,9 @@
       }
     },
     "node_modules/@eslint/object-schema": {
-      "version": "2.1.6",
-      "resolved": "https://registry.npmjs.org/@eslint/object-schema/-/object-schema-2.1.6.tgz",
-      "integrity": "sha512-RBMg5FRL0I0gs51M/guSAj5/e14VQ4tpZnQNWwuDT66P14I43ItmPfIZRhO9fUVIPOAQXU47atlywZ/czoqFPA==",
+      "version": "2.1.7",
+      "resolved": "https://registry.npmjs.org/@eslint/object-schema/-/object-schema-2.1.7.tgz",
+      "integrity": "sha512-VtAOaymWVfZcmZbp6E2mympDIHvyjXs/12LqWYjVw6qjrfF+VK+fyG33kChz3nnK+SU5/NeHOqrTEHS8sXO3OA==",
       "dev": true,
       "license": "Apache-2.0",
       "engines": {
@@ -892,13 +895,13 @@
       }
     },
     "node_modules/@eslint/plugin-kit": {
-      "version": "0.3.1",
-      "resolved": "https://registry.npmjs.org/@eslint/plugin-kit/-/plugin-kit-0.3.1.tgz",
-      "integrity": "sha512-0J+zgWxHN+xXONWIyPWKFMgVuJoZuGiIFu8yxk7RJjxkzpGmyja5wRFqZIVtjDVOQpV+Rw0iOAjYPE2eQyjr0w==",
+      "version": "0.4.1",
+      "resolved": "https://registry.npmjs.org/@eslint/plugin-kit/-/plugin-kit-0.4.1.tgz",
+      "integrity": "sha512-43/qtrDUokr7LJqoF2c3+RInu/t4zfrpYdoSDfYyhg52rwLV6TnOvdG4fXm7IkSB3wErkcmJS9iEhjVtOSEjjA==",
       "dev": true,
       "license": "Apache-2.0",
       "dependencies": {
-        "@eslint/core": "^0.14.0",
+        "@eslint/core": "^0.17.0",
         "levn": "^0.4.1"
       },
       "engines": {
@@ -1908,9 +1911,9 @@
       }
     },
     "node_modules/@typescript-eslint/typescript-estree/node_modules/brace-expansion": {
-      "version": "2.0.1",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
-      "integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
+      "version": "2.0.2",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.2.tgz",
+      "integrity": "sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -2010,9 +2013,9 @@
       }
     },
     "node_modules/acorn": {
-      "version": "8.14.1",
-      "resolved": "https://registry.npmjs.org/acorn/-/acorn-8.14.1.tgz",
-      "integrity": "sha512-OvQ/2pUDKmgfCg++xsTX1wGxfTaszcHVcTctW4UJB4hibJx2HXxxO5UmVgyjMa+ZDsiaf5wWLXYpRWMmBI0QHg==",
+      "version": "8.15.0",
+      "resolved": "https://registry.npmjs.org/acorn/-/acorn-8.15.0.tgz",
+      "integrity": "sha512-NZyJarBfL7nWwIq+FDL6Zp/yHEhePMNnnJ0y3qfieCrmNvYct8uvtiV41UvlSe6apAfk0fY1FbWx+NwfmpvtTg==",
       "dev": true,
       "license": "MIT",
       "bin": {
@@ -2080,9 +2083,9 @@
       "license": "MIT"
     },
     "node_modules/brace-expansion": {
-      "version": "1.1.11",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.11.tgz",
-      "integrity": "sha512-iCuPHDFgrHX7H2vEI/5xpz07zSHB00TpugqhmYtVmMO6518mCuRMoOYFldEBl0g187ufozdaHgWKcYFb61qGiA==",
+      "version": "1.1.12",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz",
+      "integrity": "sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -2380,33 +2383,32 @@
       }
     },
     "node_modules/eslint": {
-      "version": "9.28.0",
-      "resolved": "https://registry.npmjs.org/eslint/-/eslint-9.28.0.tgz",
-      "integrity": "sha512-ocgh41VhRlf9+fVpe7QKzwLj9c92fDiqOj8Y3Sd4/ZmVA4Btx4PlUYPq4pp9JDyupkf1upbEXecxL2mwNV7jPQ==",
+      "version": "9.39.1",
+      "resolved": "https://registry.npmjs.org/eslint/-/eslint-9.39.1.tgz",
+      "integrity": "sha512-BhHmn2yNOFA9H9JmmIVKJmd288g9hrVRDkdoIgRCRuSySRUHH7r/DI6aAXW9T1WwUuY3DFgrcaqB+deURBLR5g==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
-        "@eslint-community/eslint-utils": "^4.2.0",
+        "@eslint-community/eslint-utils": "^4.8.0",
         "@eslint-community/regexpp": "^4.12.1",
-        "@eslint/config-array": "^0.20.0",
-        "@eslint/config-helpers": "^0.2.1",
-        "@eslint/core": "^0.14.0",
+        "@eslint/config-array": "^0.21.1",
+        "@eslint/config-helpers": "^0.4.2",
+        "@eslint/core": "^0.17.0",
         "@eslint/eslintrc": "^3.3.1",
-        "@eslint/js": "9.28.0",
-        "@eslint/plugin-kit": "^0.3.1",
+        "@eslint/js": "9.39.1",
+        "@eslint/plugin-kit": "^0.4.1",
         "@humanfs/node": "^0.16.6",
         "@humanwhocodes/module-importer": "^1.0.1",
         "@humanwhocodes/retry": "^0.4.2",
         "@types/estree": "^1.0.6",
-        "@types/json-schema": "^7.0.15",
         "ajv": "^6.12.4",
         "chalk": "^4.0.0",
         "cross-spawn": "^7.0.6",
         "debug": "^4.3.2",
         "escape-string-regexp": "^4.0.0",
-        "eslint-scope": "^8.3.0",
-        "eslint-visitor-keys": "^4.2.0",
-        "espree": "^10.3.0",
+        "eslint-scope": "^8.4.0",
+        "eslint-visitor-keys": "^4.2.1",
+        "espree": "^10.4.0",
         "esquery": "^1.5.0",
         "esutils": "^2.0.2",
         "fast-deep-equal": "^3.1.3",
@@ -2464,9 +2466,9 @@
       }
     },
     "node_modules/eslint-scope": {
-      "version": "8.3.0",
-      "resolved": "https://registry.npmjs.org/eslint-scope/-/eslint-scope-8.3.0.tgz",
-      "integrity": "sha512-pUNxi75F8MJ/GdeKtVLSbYg4ZI34J6C0C7sbL4YOp2exGwen7ZsuBqKzUhXd0qMQ362yET3z+uPwKeg/0C2XCQ==",
+      "version": "8.4.0",
+      "resolved": "https://registry.npmjs.org/eslint-scope/-/eslint-scope-8.4.0.tgz",
+      "integrity": "sha512-sNXOfKCn74rt8RICKMvJS7XKV/Xk9kA7DyJr8mJik3S7Cwgy3qlkkmyS2uQB3jiJg6VNdZd/pDBJu0nvG2NlTg==",
       "dev": true,
       "license": "BSD-2-Clause",
       "dependencies": {
@@ -2481,9 +2483,9 @@
       }
     },
     "node_modules/eslint-visitor-keys": {
-      "version": "4.2.0",
-      "resolved": "https://registry.npmjs.org/eslint-visitor-keys/-/eslint-visitor-keys-4.2.0.tgz",
-      "integrity": "sha512-UyLnSehNt62FFhSwjZlHmeokpRK59rcz29j+F1/aDgbkbRTk7wIc9XzdoasMUbRNKDM0qQt/+BJ4BrpFeABemw==",
+      "version": "4.2.1",
+      "resolved": "https://registry.npmjs.org/eslint-visitor-keys/-/eslint-visitor-keys-4.2.1.tgz",
+      "integrity": "sha512-Uhdk5sfqcee/9H/rCOJikYz67o0a2Tw2hGRPOG2Y1R2dg7brRe1uG0yaNQDHu+TO/uQPF/5eCapvYSmHUjt7JQ==",
       "dev": true,
       "license": "Apache-2.0",
       "engines": {
@@ -2494,15 +2496,15 @@
       }
     },
     "node_modules/espree": {
-      "version": "10.3.0",
-      "resolved": "https://registry.npmjs.org/espree/-/espree-10.3.0.tgz",
-      "integrity": "sha512-0QYC8b24HWY8zjRnDTL6RiHfDbAWn63qb4LMj1Z4b076A4une81+z03Kg7l7mn/48PUTqoLptSXez8oknU8Clg==",
+      "version": "10.4.0",
+      "resolved": "https://registry.npmjs.org/espree/-/espree-10.4.0.tgz",
+      "integrity": "sha512-j6PAQ2uUr79PZhBjP5C5fhl8e39FmRnOjsD5lGnWrFU8i2G776tBK7+nP8KuQUTTyAZUwfQqXAgrVH5MbH9CYQ==",
       "dev": true,
       "license": "BSD-2-Clause",
       "dependencies": {
-        "acorn": "^8.14.0",
+        "acorn": "^8.15.0",
         "acorn-jsx": "^5.3.2",
-        "eslint-visitor-keys": "^4.2.0"
+        "eslint-visitor-keys": "^4.2.1"
       },
       "engines": {
         "node": "^18.18.0 || ^20.9.0 || >=21.1.0"
@@ -2852,9 +2854,9 @@
       "license": "MIT"
     },
     "node_modules/js-yaml": {
-      "version": "4.1.0",
-      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-4.1.0.tgz",
-      "integrity": "sha512-wpxZs9NoxZaJESJGIZTyDEaYpl0FKSA+FB9aJiyemKhMwkxQg63h4T1KJgUGHpTqPDNRcmmYLugrRjJlBtWvRA==",
+      "version": "4.1.1",
+      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-4.1.1.tgz",
+      "integrity": "sha512-qQKT4zQxXl8lLwBtHMWwaTcGfFOZviOJet3Oy/xmGk2gZH677CJM9EvtfdSkgWcATZhj/55JZ0rmy3myCT5lsA==",
       "dev": true,
       "license": "MIT",
       "dependencies": {

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

@@ -10,6 +10,7 @@ export interface Model {
   name: string;
   description: string;
   unlisted: boolean;
+  peerID: string;
 }
 
 interface APIProviderType {
@@ -23,6 +24,7 @@ interface APIProviderType {
   upstreamLogs: string;
   metrics: Metrics[];
   connectionStatus: ConnectionState;
+  versionInfo: VersionInfo;
 }
 
 interface Metrics {
@@ -41,11 +43,18 @@ 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 +68,11 @@ 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 +166,26 @@ 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 +264,21 @@ 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>;

ui/src/pages/Models.tsx

@@ -44,8 +44,24 @@ function ModelsPanel() {
   const [showIdorName, setShowIdorName] = usePersistentState<"id" | "name">("showIdorName", "id"); // true = show ID, false = show name
   const [menuOpen, setMenuOpen] = useState(false);
 
-  const filteredModels = useMemo(() => {
-    return models.filter((model) => showUnlisted || !model.unlisted);
+  const { regularModels, peerModelsByPeerId } = useMemo(() => {
+    const filtered = models.filter((model) => showUnlisted || !model.unlisted);
+    const peerModels = filtered.filter((m) => m.peerID);
+
+    // Group peer models by peerID
+    const grouped = peerModels.reduce((acc, model) => {
+      const peerId = model.peerID || "unknown";
+      if (!acc[peerId]) {
+        acc[peerId] = [];
+      }
+      acc[peerId].push(model);
+      return acc;
+    }, {} as Record<string, typeof peerModels>);
+
+    return {
+      regularModels: filtered.filter((m) => !m.peerID),
+      peerModelsByPeerId: grouped,
+    };
   }, [models, showUnlisted]);
 
   const handleUnloadAllModels = useCallback(async () => {
@@ -151,7 +167,7 @@ function ModelsPanel() {
             </tr>
           </thead>
           <tbody>
-            {filteredModels.map((model) => (
+            {regularModels.map((model) => (
               <tr key={model.id} className="border-b hover:bg-secondary-hover border-gray-200">
                 <td className={`${model.unlisted ? "text-txtsecondary" : ""}`}>
                   <a href={`/upstream/${model.id}/`} className="font-semibold" target="_blank">
@@ -186,6 +202,34 @@ function ModelsPanel() {
             ))}
           </tbody>
         </table>
+
+        {Object.keys(peerModelsByPeerId).length > 0 && (
+          <>
+            <h3 className="mt-8 mb-2">Peer Models</h3>
+            {Object.entries(peerModelsByPeerId)
+              .sort(([a], [b]) => a.localeCompare(b))
+              .map(([peerId, models]) => (
+                <div key={peerId} className="mb-4">
+                  <table className="w-full">
+                    <thead className="sticky top-0 bg-card z-10">
+                      <tr className="text-left border-b border-gray-200 dark:border-white/10 bg-surface">
+                        <th className="font-semibold">{peerId}</th>
+                      </tr>
+                    </thead>
+                    <tbody>
+                      {models.map((model) => (
+                        <tr key={model.id} className="border-b hover:bg-secondary-hover border-gray-200">
+                          <td className={`pl-8 ${model.unlisted ? "text-txtsecondary" : ""}`}>
+                            <span>{model.id}</span>
+                          </td>
+                        </tr>
+                      ))}
+                    </tbody>
+                  </table>
+                </div>
+              ))}
+          </>
+        )}
       </div>
     </div>
   );
@@ -223,11 +267,7 @@ function TokenHistogram({ data }: { data: HistogramData }) {
 
   return (
     <div className="mt-2 w-full">
-      <svg
-        viewBox={`0 0 ${viewBoxWidth} ${height}`}
-        className="w-full h-auto"
-        preserveAspectRatio="xMidYMid meet"
-      >
+      <svg viewBox={`0 0 ${viewBoxWidth} ${height}`} className="w-full h-auto" preserveAspectRatio="xMidYMid meet">
         {/* Y-axis */}
         <line
           x1={padding.left}
@@ -312,14 +352,7 @@ function TokenHistogram({ data }: { data: HistogramData }) {
         />
 
         {/* X-axis labels */}
-        <text
-          x={padding.left}
-          y={height - 5}
-          fontSize="10"
-          fill="currentColor"
-          opacity="0.6"
-          textAnchor="start"
-        >
+        <text x={padding.left} y={height - 5} fontSize="10" fill="currentColor" opacity="0.6" textAnchor="start">
           {min.toFixed(1)}
         </text>