ui: fix node-tar vulnerability

Trying out svelte for the UI. The port was done by Claude Code on the iOS app w/ Opus 4.5. 

---

* ui: add Svelte port of React UI

Port the React-based UI to Svelte 5 with the following changes:

- Create new ui-svelte directory with complete Svelte 5 implementation
- Use Svelte stores instead of React contexts for state management
- Implement custom ResizablePanels component to replace react-resizable-panels
- Port all pages: LogViewer, Models, Activity
- Port all components: Header, ConnectionStatus, LogPanel, ModelsPanel, etc.
- Use svelte-spa-router for client-side routing
- Same build output directory (proxy/ui_dist) and base path (/ui/)
- Tailwind CSS 4 with same theme configuration

https://claude.ai/code/session_01F3xXLYsd62gePVSFv7aboP

* ui-svelte: simplify state management

- Remove redundant state syncing pattern in LogPanel and ModelsPanel
- Use store values directly with $ syntax instead of manual subscriptions
- Consolidate duplicate title sync logic in App.svelte
- Use existing syncTitleToDocument() from theme.ts

https://claude.ai/code/session_01F3xXLYsd62gePVSFv7aboP

* ui-svelte: use idiomatic Svelte 5 patterns

- Use $effect for document side effects (theme, title) instead of
  store subscriptions
- Use class: directive for active nav links in Header
- Remove SSR guards (unnecessary for client-only SPA)
- Remove leaked subscription in syncThemeToDocument
- Simplify theme.ts by removing sync functions

https://claude.ai/code/session_01F3xXLYsd62gePVSFv7aboP

* ui-svelte: fix build warnings and improve accessibility

Fix Svelte build warnings and add proper accessibility support
to interactive components.

- add aria-labels to buttons for screen readers
- implement keyboard navigation for resizable separator
- suppress intentional state initialization warnings
- update Makefile to use ui-svelte build directory
- add peer:true to package-lock.json dependencies

* ui-svelte: reorganize navigation and add log view toggle

Make Models the default landing page and add view mode toggle
to the Logs page with persistent state.

- set Models as default route at /
- move Logs to /logs route
- reorder navigation: Models, Activity, Logs
- add view toggle with three modes: Panels, Proxy only, Upstream only
- fix horizontal overflow with width constraints

.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/containers.yml

@@ -10,17 +10,36 @@ on:
   # Allows manual triggering of the workflow
   workflow_dispatch:
 
+  # Run on workflow file changes (without pushing)
+  push:
+    paths:
+      - '.github/workflows/containers.yml'
+      - 'docker/build-container.sh'
+
 jobs:
   build-and-push:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        platform: [intel, cuda, vulkan, cpu, musa]
+        platform: [intel, cuda, vulkan, cpu, musa, rocm]
       fail-fast: false
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
 
+      - name: Free up disk space
+        if: matrix.platform == 'rocm'
+        run: |
+          echo "Before cleanup:"
+          df -h
+          sudo rm -rf /usr/share/dotnet
+          sudo rm -rf /usr/local/lib/android
+          sudo rm -rf /opt/ghc
+          sudo rm -rf /opt/hostedtoolcache/CodeQL
+          sudo docker system prune -af
+          echo "After cleanup:"
+          df -h
+
       - name: Log in to GitHub Container Registry
         uses: docker/login-action@v2
         with:
@@ -31,7 +50,7 @@ jobs:
       - name: Run build-container
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: ./docker/build-container.sh ${{ matrix.platform }} true
+        run: ./docker/build-container.sh ${{ matrix.platform }} ${{ github.event_name != 'push' }}
 
   # note make sure mostlygeek/llama-swap has admin rights to the llama-swap package
   # see: https://github.com/actions/delete-package-versions/issues/74

.github/workflows/release.yml

@@ -3,13 +3,13 @@ name: goreleaser
 on:
   push:
     tags:
-      - '*'
+      - "*"
 
   # Allows manual triggering of the workflow
   workflow_dispatch:
     inputs:
       tag:
-        description: 'Tag version to release (e.g. v144)'
+        description: "Tag version to release (e.g. v144)"
         required: true
 
 permissions:
@@ -19,35 +19,30 @@ jobs:
   goreleaser:
     runs-on: ubuntu-latest
     steps:
-      -
+      - name: Checkout
-        name: Checkout
         uses: actions/checkout@v4
         with:
           fetch-depth: 0
           ref: ${{ github.event.inputs.tag || github.ref }}
-      -
+      - name: Set up Go
-        name: Set up Go
         uses: actions/setup-go@v5
-      -
+      - name: Set up Node.js
-        name: Set up Node.js
         uses: actions/setup-node@v4
         with:
-          node-version: '23'
+          node-version: "23"
-      -
+      - name: Install dependencies and build UI
-        name: Install dependencies and build UI
         run: |
-          cd ui
+          cd ui-svelte
           npm ci
           npm run build
 
-      -
+      - name: Run GoReleaser
-        name: Run GoReleaser
         uses: goreleaser/goreleaser-action@v6
         with:
           # either 'goreleaser' (default) or 'goreleaser-pro'
           distribution: goreleaser
           # 'latest', 'nightly', or a semver
-          version: '~> v2'
+          version: "~> v2"
           args: release --clean
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@@ -76,4 +71,4 @@ jobs:
               "release": {
                 "tag_name": "${{ steps.tag.outputs.tag }}"
               }
-            }
+            }

CLAUDE.md

@@ -1,5 +1,3 @@
-# Project: llama-swap
-
 ## Project Description:
 
 llama-swap is a light weight, transparent proxy server that provides automatic model swapping to llama.cpp's server.
@@ -7,37 +5,45 @@ llama-swap is a light weight, transparent proxy server that provides automatic m
 ## Tech stack
 
 - golang
-- typescript, vite and react for UI (ui/)
+- typescript, vite and react for UI (located in ui/)
-
-## Testing
-
-- `make test-dev` - Use this when making iterative changes. Runs `go test` and `staticcheck`. Fix any static checking errors. Use this only when changes are made to any code under the `proxy/` directory
-- `make test-all` - runs at the end before completing work. Includes long running concurrency tests.
 
 ## Workflow Tasks
 
-### Plan Improvements
+- when summarizing changes only include details that require further action
+- just say "Done." when there is no further action
+- use `gh` to create PRs and load issues
+- do include Co-Authored-By or created by when committing changes or creating PRs
+- keep PR descriptions short and focused on changes.
+  - never include a test plan
 
-Work plans are located in ai-plans/. Plans written by the user may be incomplete, contain inconsistencies or errors.
+## Testing
 
-When the user asks to improve a plan follow these guidelines for expanding and improving it.
+- 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.
 
-- Identify any inconsistencies.
+### Commit message example format:
-- Expand plans out to be detailed specification of requirements and changes to be made.
-- Plans should have at least these sections:
-  - Title - very short, describes changes
-  - Overview: A more detailed summary of goal and outcomes desired
-  - Design Requirements: Detailed descriptions of what needs to be done
-  - Testing Plan: Tests to be implemented
-  - Checklist: A detailed list of changes to be made
 
-Look for "plan expansion" as explicit instructions to improve a plan.
+```
+proxy: add new feature
 
-### Implementation of plans
+Add new feature that implements functionality X and Y.
 
-When the user says "paint it", respond with "commencing automated assembly". Then implement the changes as described by the plan. Update the checklist as you complete items.
+- key change 1
+- key change 2
+- key change 3
 
-## General Rules
+fixes #123
+```
 
-- when summarizing changes only include details that require further action (action items)
+## Code Reviews
-- when there are no action items, just say "Done."
+
+- use three levels High, Medium, Low severity
+- label each discovered issue with a label like H1, M2, L3 respectively
+- High severity are must fix issues (security, race conditions, critical bugs)
+- Medium severity are recommended improvements (coding style, missing functionality, inconsistencies)
+- Low severity are nice to have changes and nits
+- Include a suggestion with each discovered item
+- Limit your code review to three items with the highest priority first
+- Double check your discovered items and recommended remediations

Makefile

@@ -36,11 +36,11 @@ test-all: proxy/ui_dist/placeholder.txt
 	go test -race -count=1 ./proxy/...
 
 ui/node_modules:
-	cd ui && npm install
+	cd ui-svelte && npm install
 
 # build react UI
 ui: ui/node_modules
-	cd ui && npm run build
+	cd ui-svelte && npm run build
 
 # Build OSX binary
 mac: ui

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 +13,21 @@ 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`
+  - `v1/messages/count_tokens`
 - ✅ llama-server (llama.cpp) supported endpoints
   - `v1/rerank`, `v1/reranking`, `/rerank`
   - `/infill` - for code infilling
@@ -32,6 +39,7 @@ 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`
@@ -44,7 +52,6 @@ llama-swap includes a real time web interface for monitoring logs and controllin
 
 <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:
 
 <img width="1360" height="963" alt="image" src="https://github.com/user-attachments/assets/5f3edee6-d03a-4ae5-ae06-b20ac1f135bd" />
@@ -61,7 +68,7 @@ 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
@@ -71,6 +78,14 @@ $ 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>
@@ -89,6 +104,9 @@ 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>
@@ -191,23 +209,26 @@ 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
+# stream llama-swap's proxy status logs
-curl -Ns 'http://host/logs/stream/proxy'
+curl -Ns http://host/logs/stream/proxy
 
-# just upstream's logs
+# stream logs from upstream processes that llama-swap loads
-curl -Ns 'http://host/logs/stream/upstream'
+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

config-schema.json

@@ -188,11 +188,17 @@
                                 "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."
+                            },
+                            "setParams": {
+                                "type": "object",
+                                "additionalProperties": true,
+                                "default": {},
+                                "description": "Dictionary of parameters to set/override in requests. Useful for enforcing specific parameter values. Protected params like 'model' cannot be overridden. Values can be strings, numbers, booleans, arrays, or objects."
                             }
                         },
                         "additionalProperties": false,
                         "default": {},
-                        "description": "Dictionary of filter settings. Only stripParams is supported."
+                        "description": "Dictionary of filter settings. Supports stripParams and setParams."
                     },
                     "metadata": {
                         "type": "object",
@@ -273,6 +279,78 @@
             },
             "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."
+                    },
+                    "filters": {
+                        "type": "object",
+                        "properties": {
+                            "stripParams": {
+                                "type": "string",
+                                "default": "",
+                                "pattern": "^[a-zA-Z0-9_, ]*$",
+                                "description": "Comma separated list of parameters to remove from the request. Useful for removing parameters that the peer doesn't support."
+                            },
+                            "setParams": {
+                                "type": "object",
+                                "additionalProperties": true,
+                                "default": {},
+                                "description": "Dictionary of parameters to set/override in requests to this peer. Useful for injecting provider-specific settings. Protected params like 'model' cannot be overridden. Values can be strings, numbers, booleans, arrays, or objects."
+                            }
+                        },
+                        "additionalProperties": false,
+                        "default": {},
+                        "description": "Dictionary of filter settings for peer requests. Supports stripParams and setParams."
+                    }
+                }
+            },
+            "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

@@ -34,6 +34,16 @@ logLevel: info
 # - 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
@@ -70,6 +80,9 @@ includeAliasesInList: false
 # - macro names must not be a reserved name: PORT or MODEL_ID
 # - macro values can be numbers, bools, or strings
 # - macros can contain other macros, but they must be defined before they are used
+# - environment variables can be referenced with ${env.VAR_NAME} syntax
+#   - env macros are substituted first, before regular macros
+#   - if the env var is not set, config loading will fail with an error
 macros:
   # Example of a multi-line macro
   "latest-llama": >
@@ -82,6 +95,24 @@ macros:
   # but they must be previously declared.
   "default_args": "--ctx-size ${default_ctx}"
 
+  # Example of environment variable macros
+  # - ${env.VAR_NAME} pulls the value from the system environment
+  # - useful for paths, secrets, or machine-specific configuration
+  "models_dir": "${env.HOME}/models"
+
+# 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"
+  # tip, one liner: printf "sk-%s\n" "$(head -c 48 /dev/urandom | base64 )"
+  - "sk-gyCPiKUcIfPlaM4OSMZekkprgijPx6+OsmQs8Rsg0xZ9qpy6gKWsIKqHOk+cgXVx"
+
+  # use environment variable macros to keep secrets out of the config
+  - "${env.API_KEY_1}"
+  - "${env.API_KEY_2}"
+
 # models: a dictionary of model configurations
 # - required
 # - each key is the model's ID, used in API requests
@@ -165,7 +196,7 @@ models:
 
     # filters: a dictionary of filter settings
     # - optional, default: empty dictionary
-    # - only stripParams is currently supported
+    # - same capabilities as peer filters (stripParams, setParams)
     filters:
       # stripParams: a comma separated list of parameters to remove from the request
       # - optional, default: ""
@@ -175,6 +206,16 @@ models:
       # - recommended to stick to sampling parameters
       stripParams: "temperature, top_p, top_k"
 
+      # setParams: a dictionary of parameters to set/override in requests
+      # - optional, default: empty dictionary
+      # - useful for enforcing specific parameter values
+      # - protected params like "model" cannot be overridden
+      # - values can be strings, numbers, booleans, arrays, or objects
+      setParams:
+        # Example: enforce specific sampling parameters
+        temperature: 0.7
+        top_p: 0.9
+
     # metadata: a dictionary of arbitrary values that are included in /v1/models
     # - optional, default: empty dictionary
     # - while metadata can contains complex types it is recommended to keep it simple
@@ -321,3 +362,56 @@ 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>
+    # - can be a string or a macro
+    apiKey: ${env.OPENROUTER_API_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
+    # filters: a dictionary of filter settings for peer requests
+    # - optional, default: empty dictionary
+    # - same capabilities as model filters (stripParams, setParams)
+    filters:
+      # stripParams: a comma separated list of parameters to remove from the request
+      # - optional, default: ""
+      # - useful for removing parameters that the peer doesn't support
+      # - the `model` parameter can never be removed
+      stripParams: "temperature, top_p"
+
+      # setParams: a dictionary of parameters to set/override in requests to this peer
+      # - optional, default: empty dictionary
+      # - useful for injecting provider-specific settings like data retention policies
+      # - protected params like "model" cannot be overridden
+      # - values can be strings, numbers, booleans, arrays, or objects
+      setParams:
+        # Example: enforce zero-data-retention for OpenRouter
+        provider:
+          data_collection: "deny"
+          zdr: true

docker/build-container.sh

@@ -2,21 +2,37 @@
 
 cd $(dirname "$0")
 
+# use this to test locally, example:
+# GITHUB_TOKEN=$(gh auth token) LOG_DEBUG=1 DEBUG_ABORT_BUILD=1 ./docker/build-container.sh rocm
+# you need read:package scope on the token. Generate a personal access token with
+# the scopes: gist, read:org, repo, write:packages
+# then: gh auth login (and copy/paste the new token)
+
+log_debug() {
+    if [ "$LOG_DEBUG" = "1" ]; then
+        echo "[DEBUG] $*"
+    fi
+}
+
+log_info() {
+    echo "[INFO] $*"
+}
+
 ARCH=$1
 PUSH_IMAGES=${2:-false}
 
 # List of allowed architectures
-ALLOWED_ARCHS=("intel" "vulkan" "musa" "cuda" "cpu")
+ALLOWED_ARCHS=("intel" "vulkan" "musa" "cuda" "cpu" "rocm")
 
 # Check if ARCH is in the allowed list
 if [[ ! " ${ALLOWED_ARCHS[@]} " =~ " ${ARCH} " ]]; then
-  echo "Error: ARCH must be one of the following: ${ALLOWED_ARCHS[@]}"
+  log_info "Error: ARCH must be one of the following: ${ALLOWED_ARCHS[@]}"
   exit 1
 fi
 
 # Check if GITHUB_TOKEN is set and not empty
 if [[ -z "$GITHUB_TOKEN" ]]; then
-  echo "Error: GITHUB_TOKEN is not set or is empty."
+  log_info "Error: GITHUB_TOKEN is not set or is empty."
   exit 1
 fi
 
@@ -32,25 +48,74 @@ LS_REPO=${GITHUB_REPOSITORY:-mostlygeek/llama-swap}
 # have to strip out the 'v' due to .tar.gz file naming
 LS_VER=$(curl -s https://api.github.com/repos/${LS_REPO}/releases/latest | jq -r .tag_name | sed 's/v//')
 
+# Fetches the most recent llama.cpp tag matching the given prefix
+# Handles pagination to search beyond the first 100 results
+# $1 - tag_prefix (e.g., "server" or "server-vulkan")
+# Returns: the version number extracted from the tag
+fetch_llama_tag() {
+    local tag_prefix=$1
+    local page=1
+    local per_page=100
+
+    while true; do
+        log_debug "Fetching page $page for tag prefix: $tag_prefix"
+
+        local response=$(curl -s -H "Authorization: Bearer $GITHUB_TOKEN" \
+            "https://api.github.com/users/ggml-org/packages/container/llama.cpp/versions?per_page=${per_page}&page=${page}")
+
+        # Check for API errors
+        if echo "$response" | jq -e '.message' > /dev/null 2>&1; then
+            local error_msg=$(echo "$response" | jq -r '.message')
+            log_info "GitHub API error: $error_msg"
+            return 1
+        fi
+
+        # Check if response is empty array (no more pages)
+        if [ "$(echo "$response" | jq 'length')" -eq 0 ]; then
+            log_debug "No more pages (empty response)"
+            return 1
+        fi
+
+        # Extract matching tag from this page
+        local found_tag=$(echo "$response" | jq -r \
+            ".[] | select(.metadata.container.tags[]? | startswith(\"$tag_prefix\")) | .metadata.container.tags[] | select(startswith(\"$tag_prefix\"))" \
+            | sort -r | head -n1)
+
+        if [ -n "$found_tag" ]; then
+            log_debug "Found tag: $found_tag on page $page"
+            echo "$found_tag" | awk -F '-' '{print $NF}'
+            return 0
+        fi
+
+        page=$((page + 1))
+
+        # Safety limit to prevent infinite loops
+        if [ $page -gt 50 ]; then
+            log_info "Reached pagination safety limit (50 pages)"
+            return 1
+        fi
+    done
+}
+
 if [ "$ARCH" == "cpu" ]; then
-    # cpu only containers just use the server tag
+    LCPP_TAG=$(fetch_llama_tag "server")
-    LCPP_TAG=$(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 $GITHUB_TOKEN" \
+    LCPP_TAG=$(fetch_llama_tag "server-${ARCH}")
-        "https://api.github.com/users/ggml-org/packages/container/llama.cpp/versions" \
-        | jq -r --arg arch "$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"
+    log_info "Abort: Could not find llama-server container for arch: $ARCH"
     exit 1
+else
+    log_info "LCPP_TAG: $LCPP_TAG"
+fi
+
+if [[ ! -z "$DEBUG_ABORT_BUILD" ]]; then
+    log_info "Abort: DEBUG_ABORT_BUILD set"
+    exit 0
 fi
 
 for CONTAINER_TYPE in non-root root; do
@@ -68,7 +133,7 @@ for CONTAINER_TYPE in non-root root; do
     USER_HOME=/app
   fi
 
-  echo "Building $CONTAINER_TYPE $CONTAINER_TAG $LS_VER"
+  log_info "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} .

docker/llama-swap.Containerfile

@@ -29,6 +29,10 @@ RUN chown --recursive $UID:$GID $HOME /app
 USER $UID:$GID
 
 WORKDIR /app
+
+# 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" && \

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.

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
@@ -81,6 +87,7 @@ type GroupConfig struct {
 var (
 	macroNameRegex    = regexp.MustCompile(`^[a-zA-Z0-9_-]+$`)
 	macroPatternRegex = regexp.MustCompile(`\$\{([a-zA-Z0-9_-]+)\}`)
+	envMacroRegex     = regexp.MustCompile(`\$\{env\.([a-zA-Z_][a-zA-Z0-9_]*)\}`)
 )
 
 // set default values for GroupConfig
@@ -114,6 +121,7 @@ type Config struct {
 	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"`
@@ -136,6 +144,12 @@ type Config struct {
 
 	// 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) {
@@ -170,22 +184,29 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 	if err != nil {
 		return Config{}, err
 	}
+	yamlStr := string(data)
 
-	// default configuration values
+	// Phase 1: Substitute all ${env.VAR} macros at string level
+	// This is safe because env values are simple strings without YAML formatting
+	yamlStr, err = substituteEnvMacros(yamlStr)
+	if err != nil {
+		return Config{}, err
+	}
+
+	// Unmarshal into full Config with defaults
 	config := Config{
 		HealthCheckTimeout: 120,
 		StartPort:          5800,
 		LogLevel:           "info",
 		LogTimeFormat:      "",
+		LogToStdout:        LogToStdoutProxy,
 		MetricsMaxInMemory: 1000,
 	}
-	err = yaml.Unmarshal(data, &config)
+	if err = yaml.Unmarshal([]byte(yamlStr), &config); err != nil {
-	if err != nil {
 		return Config{}, err
 	}
 
 	if config.HealthCheckTimeout < 15 {
-		// set a minimum of 15 seconds
 		config.HealthCheckTimeout = 15
 	}
 
@@ -193,6 +214,12 @@ 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 {
@@ -204,55 +231,46 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		}
 	}
 
-	/* check macro constraint rules:
+	// Validate global macros
-
-	- name must fit the regex ^[a-zA-Z0-9_-]+$
-	- names must be less than 64 characters (no reason, just cause)
-	- name can not be any reserved macros: PORT, MODEL_ID
-	- macro values must be less than 1024 characters
-	*/
 	for _, macro := range config.Macros {
 		if err = validateMacro(macro.Name, macro.Value); err != nil {
 			return Config{}, err
 		}
 	}
 
-	// Get and sort all model IDs first, makes testing more consistent
+	// Get and sort all model IDs for consistent port assignment
 	modelIds := make([]string, 0, len(config.Models))
 	for modelId := range config.Models {
 		modelIds = append(modelIds, modelId)
 	}
-	sort.Strings(modelIds) // This guarantees stable iteration order
+	sort.Strings(modelIds)
 
 	nextPort := config.StartPort
 	for _, modelId := range modelIds {
 		modelConfig := config.Models[modelId]
 
-		// Strip comments from command fields before macro expansion
+		// Strip comments from command fields
 		modelConfig.Cmd = StripComments(modelConfig.Cmd)
 		modelConfig.CmdStop = StripComments(modelConfig.CmdStop)
 
-		// validate model macros
+		// Validate model macros
 		for _, macro := range modelConfig.Macros {
 			if err = validateMacro(macro.Name, macro.Value); err != nil {
 				return Config{}, fmt.Errorf("model %s: %s", modelId, err.Error())
 			}
 		}
 
-		// Merge global config and model macros. Model macros take precedence
+		// Build merged macro list: MODEL_ID + global macros + model macros (model overrides global)
-		mergedMacros := make(MacroList, 0, len(config.Macros)+len(modelConfig.Macros))
+		mergedMacros := make(MacroList, 0, len(config.Macros)+len(modelConfig.Macros)+1)
 		mergedMacros = append(mergedMacros, MacroEntry{Name: "MODEL_ID", Value: modelId})
-
-		// Add global macros first
 		mergedMacros = append(mergedMacros, config.Macros...)
 
-		// Add model macros (can override global)
+		// Add model macros (override globals with same name)
 		for _, entry := range modelConfig.Macros {
-			// Remove any existing global macro with same name
 			found := false
 			for i, existing := range mergedMacros {
 				if existing.Name == entry.Name {
-					mergedMacros[i] = entry // Override
+					mergedMacros[i] = entry
 					found = true
 					break
 				}
@@ -262,23 +280,20 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 			}
 		}
 
-		// First pass: Substitute user-defined macros in reverse order (LIFO - last defined first)
+		// Substitute remaining macros in model fields (LIFO order)
-		// This allows later macros to reference earlier ones
 		for i := len(mergedMacros) - 1; i >= 0; i-- {
 			entry := mergedMacros[i]
 			macroSlug := fmt.Sprintf("${%s}", entry.Name)
 			macroStr := fmt.Sprintf("%v", entry.Value)
 
-			// Substitute in command fields
 			modelConfig.Cmd = strings.ReplaceAll(modelConfig.Cmd, macroSlug, macroStr)
 			modelConfig.CmdStop = strings.ReplaceAll(modelConfig.CmdStop, macroSlug, macroStr)
 			modelConfig.Proxy = strings.ReplaceAll(modelConfig.Proxy, macroSlug, macroStr)
 			modelConfig.CheckEndpoint = strings.ReplaceAll(modelConfig.CheckEndpoint, macroSlug, macroStr)
 			modelConfig.Filters.StripParams = strings.ReplaceAll(modelConfig.Filters.StripParams, macroSlug, macroStr)
 
-			// Substitute in metadata (recursive)
+			// Substitute in metadata (type-preserving)
 			if len(modelConfig.Metadata) > 0 {
-				var err error
 				result, err := substituteMacroInValue(modelConfig.Metadata, entry.Name, entry.Value)
 				if err != nil {
 					return Config{}, fmt.Errorf("model %s metadata: %s", modelId, err.Error())
@@ -287,18 +302,14 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 			}
 		}
 
-		// Final pass: check if PORT macro is needed after macro expansion
+		// Handle PORT macro - only allocate if cmd uses it
-		// ${PORT} is a resource on the local machine so a new port is only allocated
-		// if it is required in either cmd or proxy keys
 		cmdHasPort := strings.Contains(modelConfig.Cmd, "${PORT}")
 		proxyHasPort := strings.Contains(modelConfig.Proxy, "${PORT}")
-		if cmdHasPort || proxyHasPort { // either has it
+		if cmdHasPort || proxyHasPort {
-			if !cmdHasPort && proxyHasPort { // but both don't have it
+			if !cmdHasPort && proxyHasPort {
 				return Config{}, fmt.Errorf("model %s: proxy uses ${PORT} but cmd does not - ${PORT} is only available when used in cmd", modelId)
 			}
 
-			// Add PORT macro and substitute it
-			portEntry := MacroEntry{Name: "PORT", Value: nextPort}
 			macroSlug := "${PORT}"
 			macroStr := fmt.Sprintf("%v", nextPort)
 
@@ -306,10 +317,8 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 			modelConfig.CmdStop = strings.ReplaceAll(modelConfig.CmdStop, macroSlug, macroStr)
 			modelConfig.Proxy = strings.ReplaceAll(modelConfig.Proxy, macroSlug, macroStr)
 
-			// Substitute PORT in metadata
 			if len(modelConfig.Metadata) > 0 {
-				var err error
+				result, err := substituteMacroInValue(modelConfig.Metadata, "PORT", nextPort)
-				result, err := substituteMacroInValue(modelConfig.Metadata, portEntry.Name, portEntry.Value)
 				if err != nil {
 					return Config{}, fmt.Errorf("model %s metadata: %s", modelId, err.Error())
 				}
@@ -319,7 +328,7 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 			nextPort++
 		}
 
-		// make sure there are no unknown macros that have not been replaced
+		// Validate no unknown macros remain
 		fieldMap := map[string]string{
 			"cmd":                 modelConfig.Cmd,
 			"cmdStop":             modelConfig.CmdStop,
@@ -333,35 +342,27 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 			for _, match := range matches {
 				macroName := match[1]
 				if macroName == "PID" && fieldName == "cmdStop" {
-					continue // this is ok, has to be replaced by process later
+					continue // replaced at runtime
 				}
-				// Reserved macros are always valid (they should have been substituted already)
 				if macroName == "PORT" || macroName == "MODEL_ID" {
 					return Config{}, fmt.Errorf("macro '${%s}' should have been substituted in %s.%s", macroName, modelId, fieldName)
 				}
-				// Any other macro is unknown
 				return Config{}, fmt.Errorf("unknown macro '${%s}' found in %s.%s", macroName, modelId, fieldName)
 			}
 		}
 
-		// Check for unknown macros in metadata
 		if len(modelConfig.Metadata) > 0 {
-			if err := validateMetadataForUnknownMacros(modelConfig.Metadata, modelId); err != nil {
+			if err := validateNestedForUnknownMacros(modelConfig.Metadata, fmt.Sprintf("model %s metadata", modelId)); err != nil {
 				return Config{}, err
 			}
 		}
 
-		// Validate the proxy URL.
 		if _, err := url.Parse(modelConfig.Proxy); err != nil {
-			return Config{}, fmt.Errorf(
+			return Config{}, fmt.Errorf("model %s: invalid proxy URL: %w", modelId, err)
-				"model %s: invalid proxy URL: %w", modelId, err,
-			)
 		}
 
-		// if sendLoadingState is nil, set it to the global config value
-		// see #366
 		if modelConfig.SendLoadingState == nil {
-			v := config.SendLoadingState // copy it
+			v := config.SendLoadingState
 			modelConfig.SendLoadingState = &v
 		}
 
@@ -369,18 +370,17 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 	}
 
 	config = AddDefaultGroupToConfig(config)
-	// check that members are all unique in the groups
+
-	memberUsage := make(map[string]string) // maps member to group it appears in
+	// Validate group members
+	memberUsage := make(map[string]string)
 	for groupID, groupConfig := range config.Groups {
 		prevSet := make(map[string]bool)
 		for _, member := range groupConfig.Members {
-			// Check for duplicates within this group
 			if _, found := prevSet[member]; found {
 				return Config{}, fmt.Errorf("duplicate model member %s found in group: %s", member, groupID)
 			}
 			prevSet[member] = true
 
-			// Check if member is used in another group
 			if existingGroup, exists := memberUsage[member]; exists {
 				return Config{}, fmt.Errorf("model member %s is used in multiple groups: %s and %s", member, existingGroup, groupID)
 			}
@@ -388,7 +388,7 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 		}
 	}
 
-	// clean up hooks preload
+	// Clean up hooks preload
 	if len(config.Hooks.OnStartup.Preload) > 0 {
 		var toPreload []string
 		for _, modelID := range config.Hooks.OnStartup.Preload {
@@ -400,10 +400,56 @@ func LoadConfigFromReader(r io.Reader) (Config, error) {
 				toPreload = append(toPreload, real)
 			}
 		}
-
 		config.Hooks.OnStartup.Preload = toPreload
 	}
 
+	// Validate API keys (env macros already substituted at string level)
+	for i, 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)
+		}
+		config.RequiredAPIKeys[i] = apikey
+	}
+
+	// Process peers with global macro substitution
+	for peerName, peerConfig := range config.Peers {
+		// Substitute global macros (LIFO order)
+		for i := len(config.Macros) - 1; i >= 0; i-- {
+			entry := config.Macros[i]
+			macroSlug := fmt.Sprintf("${%s}", entry.Name)
+			macroStr := fmt.Sprintf("%v", entry.Value)
+
+			peerConfig.ApiKey = strings.ReplaceAll(peerConfig.ApiKey, macroSlug, macroStr)
+			peerConfig.Filters.StripParams = strings.ReplaceAll(peerConfig.Filters.StripParams, macroSlug, macroStr)
+
+			// Substitute in setParams (type-preserving)
+			if len(peerConfig.Filters.SetParams) > 0 {
+				result, err := substituteMacroInValue(peerConfig.Filters.SetParams, entry.Name, entry.Value)
+				if err != nil {
+					return Config{}, fmt.Errorf("peers.%s.filters.setParams: %w", peerName, err)
+				}
+				peerConfig.Filters.SetParams = result.(map[string]any)
+			}
+		}
+
+		// Validate no unknown macros remain
+		if matches := macroPatternRegex.FindAllStringSubmatch(peerConfig.ApiKey, -1); len(matches) > 0 {
+			return Config{}, fmt.Errorf("peers.%s.apiKey: unknown macro '${%s}'", peerName, matches[0][1])
+		}
+		if matches := macroPatternRegex.FindAllStringSubmatch(peerConfig.Filters.StripParams, -1); len(matches) > 0 {
+			return Config{}, fmt.Errorf("peers.%s.filters.stripParams: unknown macro '${%s}'", peerName, matches[0][1])
+		}
+		if len(peerConfig.Filters.SetParams) > 0 {
+			if err := validateNestedForUnknownMacros(peerConfig.Filters.SetParams, fmt.Sprintf("peers.%s.filters.setParams", peerName)); err != nil {
+				return Config{}, err
+			}
+		}
+		config.Peers[peerName] = peerConfig
+	}
+
 	return config, nil
 }
 
@@ -534,20 +580,26 @@ func validateMacro(name string, value any) error {
 	return nil
 }
 
-// validateMetadataForUnknownMacros recursively checks for any remaining macro references in metadata
+// validateNestedForUnknownMacros recursively checks for any remaining macro references in nested structures
-func validateMetadataForUnknownMacros(value any, modelId string) error {
+func validateNestedForUnknownMacros(value any, context string) error {
 	switch v := value.(type) {
 	case string:
 		matches := macroPatternRegex.FindAllStringSubmatch(v, -1)
 		for _, match := range matches {
 			macroName := match[1]
-			return fmt.Errorf("model %s metadata: unknown macro '${%s}'", modelId, macroName)
+			return fmt.Errorf("%s: unknown macro '${%s}'", context, macroName)
+		}
+		// Check for unsubstituted env macros
+		envMatches := envMacroRegex.FindAllStringSubmatch(v, -1)
+		for _, match := range envMatches {
+			varName := match[1]
+			return fmt.Errorf("%s: environment variable '%s' not set", context, varName)
 		}
 		return nil
 
 	case map[string]any:
 		for _, val := range v {
-			if err := validateMetadataForUnknownMacros(val, modelId); err != nil {
+			if err := validateNestedForUnknownMacros(val, context); err != nil {
 				return err
 			}
 		}
@@ -555,7 +607,7 @@ func validateMetadataForUnknownMacros(value any, modelId string) error {
 
 	case []any:
 		for _, val := range v {
-			if err := validateMetadataForUnknownMacros(val, modelId); err != nil {
+			if err := validateNestedForUnknownMacros(val, context); err != nil {
 				return err
 			}
 		}
@@ -614,3 +666,46 @@ func substituteMacroInValue(value any, macroName string, macroValue any) (any, e
 		return value, nil
 	}
 }
+
+// substituteEnvMacros replaces ${env.VAR_NAME} with environment variable values
+// Returns error if any env var is not set or contains invalid characters
+func substituteEnvMacros(s string) (string, error) {
+	result := s
+	matches := envMacroRegex.FindAllStringSubmatch(s, -1)
+	for _, match := range matches {
+		fullMatch := match[0] // ${env.VAR_NAME}
+		varName := match[1]   // VAR_NAME
+
+		value, exists := os.LookupEnv(varName)
+		if !exists {
+			return "", fmt.Errorf("environment variable '%s' is not set", varName)
+		}
+
+		// Sanitize the value for safe YAML substitution
+		value, err := sanitizeEnvValueForYAML(value, varName)
+		if err != nil {
+			return "", err
+		}
+
+		result = strings.ReplaceAll(result, fullMatch, value)
+	}
+	return result, nil
+}
+
+// sanitizeEnvValueForYAML ensures an environment variable value is safe for YAML substitution.
+// It rejects values with characters that break YAML structure and escapes quotes/backslashes
+// for compatibility with double-quoted YAML strings.
+func sanitizeEnvValueForYAML(value, varName string) (string, error) {
+	// Reject values that would break YAML structure regardless of quoting context
+	if strings.ContainsAny(value, "\n\r\x00") {
+		return "", fmt.Errorf("environment variable '%s' contains newlines or null bytes which are not allowed in YAML substitution", varName)
+	}
+
+	// Escape backslashes and double quotes for safe use in double-quoted YAML strings.
+	// In unquoted contexts, these escapes appear literally (harmless for most use cases).
+	// In double-quoted contexts, they are interpreted correctly.
+	value = strings.ReplaceAll(value, `\`, `\\`)
+	value = strings.ReplaceAll(value, `"`, `\"`)
+
+	return value, nil
+}

proxy/config/config_posix_test.go

@@ -166,6 +166,7 @@ groups:
 	expected := Config{
 		LogLevel:      "info",
 		LogTimeFormat: "",
+		LogToStdout:   LogToStdoutProxy,
 		StartPort:     5800,
 		Macros: MacroList{
 			{"svr-path", "path/to/server"},

proxy/config/config_test.go

@@ -761,3 +761,551 @@ 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())
+			}
+		})
+	}
+}
+
+func TestConfig_APIKeys_EnvMacros(t *testing.T) {
+	t.Run("env substitution in apiKeys", func(t *testing.T) {
+		t.Setenv("TEST_API_KEY", "secret-key-123")
+
+		content := `apiKeys: ["${env.TEST_API_KEY}"]`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, []string{"secret-key-123"}, config.RequiredAPIKeys)
+	})
+
+	t.Run("multiple env substitutions in apiKeys", func(t *testing.T) {
+		t.Setenv("TEST_API_KEY_1", "key-one")
+		t.Setenv("TEST_API_KEY_2", "key-two")
+
+		content := `apiKeys: ["${env.TEST_API_KEY_1}", "${env.TEST_API_KEY_2}", "static-key"]`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, []string{"key-one", "key-two", "static-key"}, config.RequiredAPIKeys)
+	})
+
+	t.Run("missing env var in apiKeys", func(t *testing.T) {
+		content := `apiKeys: ["${env.NONEXISTENT_API_KEY}"]`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.Error(t, err)
+		// With string-level env substitution, error only includes var name
+		assert.Contains(t, err.Error(), "NONEXISTENT_API_KEY")
+	})
+
+	t.Run("env substitution results in empty key", func(t *testing.T) {
+		t.Setenv("TEST_EMPTY_KEY", "")
+
+		content := `apiKeys: ["${env.TEST_EMPTY_KEY}"]`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.Error(t, err)
+		assert.Equal(t, "empty api key found in apiKeys", err.Error())
+	})
+}
+
+func TestConfig_EnvMacros(t *testing.T) {
+	t.Run("basic env substitution in cmd", func(t *testing.T) {
+		t.Setenv("TEST_MODEL_PATH", "/opt/models")
+
+		content := `
+models:
+  test:
+    cmd: "${env.TEST_MODEL_PATH}/llama-server"
+    proxy: "http://localhost:8080"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "/opt/models/llama-server", config.Models["test"].Cmd)
+	})
+
+	t.Run("env substitution in multiple fields", func(t *testing.T) {
+		t.Setenv("TEST_HOST", "myserver")
+		t.Setenv("TEST_PORT", "9999")
+
+		content := `
+models:
+  test:
+    cmd: "server --host ${env.TEST_HOST}"
+    proxy: "http://${env.TEST_HOST}:${env.TEST_PORT}"
+    checkEndpoint: "http://${env.TEST_HOST}/health"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "server --host myserver", config.Models["test"].Cmd)
+		assert.Equal(t, "http://myserver:9999", config.Models["test"].Proxy)
+		assert.Equal(t, "http://myserver/health", config.Models["test"].CheckEndpoint)
+	})
+
+	t.Run("env in global macro value", func(t *testing.T) {
+		t.Setenv("TEST_BASE_PATH", "/usr/local")
+
+		content := `
+macros:
+  SERVER_PATH: "${env.TEST_BASE_PATH}/bin/server"
+models:
+  test:
+    cmd: "${SERVER_PATH} --port 8080"
+    proxy: "http://localhost:8080"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "/usr/local/bin/server --port 8080", config.Models["test"].Cmd)
+	})
+
+	t.Run("env in model-level macro value", func(t *testing.T) {
+		t.Setenv("TEST_MODEL_DIR", "/models/llama")
+
+		content := `
+models:
+  test:
+    macros:
+      MODEL_FILE: "${env.TEST_MODEL_DIR}/model.gguf"
+    cmd: "server --model ${MODEL_FILE}"
+    proxy: "http://localhost:8080"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "server --model /models/llama/model.gguf", config.Models["test"].Cmd)
+	})
+
+	t.Run("env in metadata", func(t *testing.T) {
+		t.Setenv("TEST_API_KEY", "secret123")
+
+		content := `
+models:
+  test:
+    cmd: "server"
+    proxy: "http://localhost:8080"
+    metadata:
+      api_key: "${env.TEST_API_KEY}"
+      nested:
+        key: "${env.TEST_API_KEY}"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "secret123", config.Models["test"].Metadata["api_key"])
+		nested := config.Models["test"].Metadata["nested"].(map[string]any)
+		assert.Equal(t, "secret123", nested["key"])
+	})
+
+	t.Run("env in filters.stripParams", func(t *testing.T) {
+		t.Setenv("TEST_STRIP_PARAMS", "temperature,top_p")
+
+		content := `
+models:
+  test:
+    cmd: "server"
+    proxy: "http://localhost:8080"
+    filters:
+      stripParams: "${env.TEST_STRIP_PARAMS}"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "temperature,top_p", config.Models["test"].Filters.StripParams)
+	})
+
+	t.Run("env in cmdStop", func(t *testing.T) {
+		t.Setenv("TEST_KILL_SIGNAL", "SIGTERM")
+
+		content := `
+models:
+  test:
+    cmd: "server --port ${PORT}"
+    cmdStop: "kill -${env.TEST_KILL_SIGNAL} ${PID}"
+    proxy: "http://localhost:${PORT}"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Contains(t, config.Models["test"].CmdStop, "-SIGTERM")
+	})
+
+	t.Run("missing env var returns error", func(t *testing.T) {
+		content := `
+models:
+  test:
+    cmd: "${env.UNDEFINED_VAR_12345}/server"
+    proxy: "http://localhost:8080"
+`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		if assert.Error(t, err) {
+			assert.Contains(t, err.Error(), "UNDEFINED_VAR_12345")
+			assert.Contains(t, err.Error(), "not set")
+		}
+	})
+
+	t.Run("missing env var in global macro", func(t *testing.T) {
+		content := `
+macros:
+  PATH: "${env.UNDEFINED_GLOBAL_VAR}"
+models:
+  test:
+    cmd: "server"
+    proxy: "http://localhost:8080"
+`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		if assert.Error(t, err) {
+			assert.Contains(t, err.Error(), "UNDEFINED_GLOBAL_VAR")
+			assert.Contains(t, err.Error(), "not set")
+		}
+	})
+
+	t.Run("missing env var in model macro", func(t *testing.T) {
+		content := `
+models:
+  test:
+    macros:
+      MY_PATH: "${env.UNDEFINED_MODEL_VAR}"
+    cmd: "server"
+    proxy: "http://localhost:8080"
+`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		if assert.Error(t, err) {
+			assert.Contains(t, err.Error(), "UNDEFINED_MODEL_VAR")
+			assert.Contains(t, err.Error(), "not set")
+		}
+	})
+
+	t.Run("missing env var in metadata", func(t *testing.T) {
+		content := `
+models:
+  test:
+    cmd: "server"
+    proxy: "http://localhost:8080"
+    metadata:
+      key: "${env.UNDEFINED_META_VAR}"
+`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		if assert.Error(t, err) {
+			assert.Contains(t, err.Error(), "UNDEFINED_META_VAR")
+			assert.Contains(t, err.Error(), "not set")
+		}
+	})
+
+	t.Run("env combined with regular macros", func(t *testing.T) {
+		t.Setenv("TEST_ROOT", "/data")
+
+		content := `
+macros:
+  MODEL_BASE: "${env.TEST_ROOT}/models"
+models:
+  test:
+    cmd: "server --model ${MODEL_BASE}/${MODEL_ID}.gguf"
+    proxy: "http://localhost:8080"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "server --model /data/models/test.gguf", config.Models["test"].Cmd)
+	})
+
+	t.Run("multiple env vars in same string", func(t *testing.T) {
+		t.Setenv("TEST_USER", "admin")
+		t.Setenv("TEST_PASS", "secret")
+
+		content := `
+models:
+  test:
+    cmd: "server --auth ${env.TEST_USER}:${env.TEST_PASS}"
+    proxy: "http://localhost:8080"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "server --auth admin:secret", config.Models["test"].Cmd)
+	})
+
+	t.Run("env value with newline is rejected", func(t *testing.T) {
+		t.Setenv("TEST_MULTILINE", "line1\nline2")
+
+		content := `
+models:
+  test:
+    cmd: "server --config ${env.TEST_MULTILINE}"
+    proxy: "http://localhost:8080"
+`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		if assert.Error(t, err) {
+			assert.Contains(t, err.Error(), "TEST_MULTILINE")
+			assert.Contains(t, err.Error(), "newlines")
+		}
+	})
+
+	t.Run("env value with carriage return is rejected", func(t *testing.T) {
+		t.Setenv("TEST_CR", "line1\rline2")
+
+		content := `
+models:
+  test:
+    cmd: "server --config ${env.TEST_CR}"
+    proxy: "http://localhost:8080"
+`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		if assert.Error(t, err) {
+			assert.Contains(t, err.Error(), "TEST_CR")
+			assert.Contains(t, err.Error(), "newlines")
+		}
+	})
+
+	t.Run("env value with quotes is escaped for YAML", func(t *testing.T) {
+		t.Setenv("TEST_QUOTED", `value with "quotes"`)
+
+		content := `
+models:
+  test:
+    cmd: "server --arg \"${env.TEST_QUOTED}\""
+    proxy: "http://localhost:8080"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		// Quotes are escaped before YAML parsing, then YAML unescapes them
+		// Final result preserves the original value with quotes
+		assert.Contains(t, config.Models["test"].Cmd, `"quotes"`)
+	})
+
+	t.Run("env value with backslash is escaped for YAML", func(t *testing.T) {
+		t.Setenv("TEST_BACKSLASH", `path\to\file`)
+
+		content := `
+models:
+  test:
+    cmd: "server --path \"${env.TEST_BACKSLASH}\""
+    proxy: "http://localhost:8080"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		// Backslashes are escaped before YAML parsing, then YAML unescapes them
+		// Final result preserves the original value with backslashes
+		assert.Contains(t, config.Models["test"].Cmd, `path\to\file`)
+	})
+}
+
+func TestConfig_PeerApiKey_EnvMacros(t *testing.T) {
+	t.Run("env substitution in peer apiKey", func(t *testing.T) {
+		t.Setenv("TEST_PEER_API_KEY", "sk-peer-secret-123")
+
+		content := `
+peers:
+  openrouter:
+    proxy: https://openrouter.ai/api
+    apiKey: "${env.TEST_PEER_API_KEY}"
+    models:
+      - llama-3.1-8b
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "sk-peer-secret-123", config.Peers["openrouter"].ApiKey)
+	})
+
+	t.Run("missing env var in peer apiKey", func(t *testing.T) {
+		content := `
+peers:
+  openrouter:
+    proxy: https://openrouter.ai/api
+    apiKey: "${env.NONEXISTENT_PEER_KEY}"
+    models:
+      - llama-3.1-8b
+`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.Error(t, err)
+		// With string-level env substitution, error only includes var name
+		assert.Contains(t, err.Error(), "NONEXISTENT_PEER_KEY")
+	})
+
+	t.Run("static apiKey unchanged", func(t *testing.T) {
+		content := `
+peers:
+  openrouter:
+    proxy: https://openrouter.ai/api
+    apiKey: sk-static-key
+    models:
+      - llama-3.1-8b
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "sk-static-key", config.Peers["openrouter"].ApiKey)
+	})
+
+	t.Run("multiple peers with env apiKeys", func(t *testing.T) {
+		t.Setenv("TEST_PEER_KEY_1", "key-one")
+		t.Setenv("TEST_PEER_KEY_2", "key-two")
+
+		content := `
+peers:
+  peer1:
+    proxy: https://peer1.example.com
+    apiKey: "${env.TEST_PEER_KEY_1}"
+    models:
+      - model-a
+  peer2:
+    proxy: https://peer2.example.com
+    apiKey: "${env.TEST_PEER_KEY_2}"
+    models:
+      - model-b
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "key-one", config.Peers["peer1"].ApiKey)
+		assert.Equal(t, "key-two", config.Peers["peer2"].ApiKey)
+	})
+
+	t.Run("global macro substitution in peer apiKey", func(t *testing.T) {
+		content := `
+macros:
+  API_KEY: sk-from-global-macro
+peers:
+  openrouter:
+    proxy: https://openrouter.ai/api
+    apiKey: "${API_KEY}"
+    models:
+      - llama-3.1-8b
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "sk-from-global-macro", config.Peers["openrouter"].ApiKey)
+	})
+
+	t.Run("global macro in peer filters.stripParams", func(t *testing.T) {
+		content := `
+macros:
+  STRIP_LIST: "temperature, top_p"
+peers:
+  openrouter:
+    proxy: https://openrouter.ai/api
+    models:
+      - llama-3.1-8b
+    filters:
+      stripParams: "${STRIP_LIST}"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "temperature, top_p", config.Peers["openrouter"].Filters.StripParams)
+	})
+
+	t.Run("global macro in peer filters.setParams", func(t *testing.T) {
+		content := `
+macros:
+  MAX_TOKENS: 4096
+peers:
+  openrouter:
+    proxy: https://openrouter.ai/api
+    models:
+      - llama-3.1-8b
+    filters:
+      setParams:
+        max_tokens: "${MAX_TOKENS}"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, 4096, config.Peers["openrouter"].Filters.SetParams["max_tokens"])
+	})
+
+	t.Run("env macro in peer filters.setParams", func(t *testing.T) {
+		t.Setenv("TEST_RETENTION_POLICY", "deny")
+
+		content := `
+peers:
+  openrouter:
+    proxy: https://openrouter.ai/api
+    models:
+      - llama-3.1-8b
+    filters:
+      setParams:
+        data_collection: "${env.TEST_RETENTION_POLICY}"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "deny", config.Peers["openrouter"].Filters.SetParams["data_collection"])
+	})
+
+	t.Run("env macro in peer filters.stripParams", func(t *testing.T) {
+		t.Setenv("TEST_STRIP_PARAMS", "frequency_penalty, presence_penalty")
+
+		content := `
+peers:
+  openrouter:
+    proxy: https://openrouter.ai/api
+    models:
+      - llama-3.1-8b
+    filters:
+      stripParams: "${env.TEST_STRIP_PARAMS}"
+`
+		config, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.NoError(t, err)
+		assert.Equal(t, "frequency_penalty, presence_penalty", config.Peers["openrouter"].Filters.StripParams)
+	})
+
+	t.Run("unknown macro in peer apiKey fails", func(t *testing.T) {
+		content := `
+peers:
+  openrouter:
+    proxy: https://openrouter.ai/api
+    apiKey: "${UNDEFINED_MACRO}"
+    models:
+      - llama-3.1-8b
+`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.Error(t, err)
+		assert.Contains(t, err.Error(), "peers.openrouter.apiKey")
+		assert.Contains(t, err.Error(), "unknown macro")
+	})
+
+	t.Run("unknown macro in peer filters.setParams fails", func(t *testing.T) {
+		content := `
+peers:
+  openrouter:
+    proxy: https://openrouter.ai/api
+    models:
+      - llama-3.1-8b
+    filters:
+      setParams:
+        value: "${UNDEFINED_MACRO}"
+`
+		_, err := LoadConfigFromReader(strings.NewReader(content))
+		assert.Error(t, err)
+		assert.Contains(t, err.Error(), "peers.openrouter.filters.setParams")
+		assert.Contains(t, err.Error(), "unknown macro")
+	})
+}

proxy/config/config_windows_test.go

@@ -158,6 +158,7 @@ groups:
 	expected := Config{
 		LogLevel:      "info",
 		LogTimeFormat: "",
+		LogToStdout:   LogToStdoutProxy,
 		StartPort:     5800,
 		Macros: MacroList{
 			{"svr-path", "path/to/server"},

proxy/config/filters.go

@@ -0,0 +1,81 @@
+package config
+
+import (
+	"slices"
+	"sort"
+	"strings"
+)
+
+// ProtectedParams is a list of parameters that cannot be set or stripped via filters
+// These are protected to prevent breaking the proxy's ability to route requests correctly
+var ProtectedParams = []string{"model"}
+
+// Filters contains filter settings for modifying request parameters
+// Used by both models and peers
+type Filters struct {
+	// StripParams is a comma-separated list of parameters to remove from requests
+	// The "model" parameter can never be removed
+	StripParams string `yaml:"stripParams"`
+
+	// SetParams is a dictionary of parameters to set/override in requests
+	// Protected params (like "model") cannot be set
+	SetParams map[string]any `yaml:"setParams"`
+}
+
+// SanitizedStripParams returns a sorted list of parameters to strip,
+// with duplicates, empty strings, and protected params removed
+func (f Filters) SanitizedStripParams() []string {
+	if f.StripParams == "" {
+		return nil
+	}
+
+	params := strings.Split(f.StripParams, ",")
+	cleaned := make([]string, 0, len(params))
+	seen := make(map[string]bool)
+
+	for _, param := range params {
+		trimmed := strings.TrimSpace(param)
+		// Skip protected params, empty strings, and duplicates
+		if slices.Contains(ProtectedParams, trimmed) || trimmed == "" || seen[trimmed] {
+			continue
+		}
+		seen[trimmed] = true
+		cleaned = append(cleaned, trimmed)
+	}
+
+	if len(cleaned) == 0 {
+		return nil
+	}
+
+	slices.Sort(cleaned)
+	return cleaned
+}
+
+// SanitizedSetParams returns a copy of SetParams with protected params removed
+// and keys sorted for consistent iteration order
+func (f Filters) SanitizedSetParams() (map[string]any, []string) {
+	if len(f.SetParams) == 0 {
+		return nil, nil
+	}
+
+	result := make(map[string]any, len(f.SetParams))
+	keys := make([]string, 0, len(f.SetParams))
+
+	for key, value := range f.SetParams {
+		// Skip protected params
+		if slices.Contains(ProtectedParams, key) {
+			continue
+		}
+		result[key] = value
+		keys = append(keys, key)
+	}
+
+	// Sort keys for consistent ordering
+	sort.Strings(keys)
+
+	if len(result) == 0 {
+		return nil, nil
+	}
+
+	return result, keys
+}

proxy/config/filters_test.go

@@ -0,0 +1,168 @@
+package config
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestFilters_SanitizedStripParams(t *testing.T) {
+	tests := []struct {
+		name        string
+		stripParams string
+		want        []string
+	}{
+		{
+			name:        "empty string",
+			stripParams: "",
+			want:        nil,
+		},
+		{
+			name:        "single param",
+			stripParams: "temperature",
+			want:        []string{"temperature"},
+		},
+		{
+			name:        "multiple params",
+			stripParams: "temperature, top_p, top_k",
+			want:        []string{"temperature", "top_k", "top_p"}, // sorted
+		},
+		{
+			name:        "model param filtered",
+			stripParams: "model, temperature, top_p",
+			want:        []string{"temperature", "top_p"},
+		},
+		{
+			name:        "only model param",
+			stripParams: "model",
+			want:        nil,
+		},
+		{
+			name:        "duplicates removed",
+			stripParams: "temperature, top_p, temperature",
+			want:        []string{"temperature", "top_p"},
+		},
+		{
+			name:        "extra whitespace",
+			stripParams: "  temperature  ,  top_p  ",
+			want:        []string{"temperature", "top_p"},
+		},
+		{
+			name:        "empty values filtered",
+			stripParams: "temperature,,top_p,",
+			want:        []string{"temperature", "top_p"},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			f := Filters{StripParams: tt.stripParams}
+			got := f.SanitizedStripParams()
+			assert.Equal(t, tt.want, got)
+		})
+	}
+}
+
+func TestFilters_SanitizedSetParams(t *testing.T) {
+	tests := []struct {
+		name       string
+		setParams  map[string]any
+		wantParams map[string]any
+		wantKeys   []string
+	}{
+		{
+			name:       "empty setParams",
+			setParams:  nil,
+			wantParams: nil,
+			wantKeys:   nil,
+		},
+		{
+			name:       "empty map",
+			setParams:  map[string]any{},
+			wantParams: nil,
+			wantKeys:   nil,
+		},
+		{
+			name: "normal params",
+			setParams: map[string]any{
+				"temperature": 0.7,
+				"top_p":       0.9,
+			},
+			wantParams: map[string]any{
+				"temperature": 0.7,
+				"top_p":       0.9,
+			},
+			wantKeys: []string{"temperature", "top_p"},
+		},
+		{
+			name: "protected model param filtered",
+			setParams: map[string]any{
+				"model":       "should-be-filtered",
+				"temperature": 0.7,
+			},
+			wantParams: map[string]any{
+				"temperature": 0.7,
+			},
+			wantKeys: []string{"temperature"},
+		},
+		{
+			name: "only protected param",
+			setParams: map[string]any{
+				"model": "should-be-filtered",
+			},
+			wantParams: nil,
+			wantKeys:   nil,
+		},
+		{
+			name: "complex nested values",
+			setParams: map[string]any{
+				"provider": map[string]any{
+					"data_collection": "deny",
+					"allow_fallbacks": false,
+				},
+				"transforms": []string{"middle-out"},
+			},
+			wantParams: map[string]any{
+				"provider": map[string]any{
+					"data_collection": "deny",
+					"allow_fallbacks": false,
+				},
+				"transforms": []string{"middle-out"},
+			},
+			wantKeys: []string{"provider", "transforms"},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			f := Filters{SetParams: tt.setParams}
+			gotParams, gotKeys := f.SanitizedSetParams()
+
+			assert.Equal(t, len(tt.wantKeys), len(gotKeys), "keys length mismatch")
+			for i, key := range gotKeys {
+				assert.Equal(t, tt.wantKeys[i], key, "key mismatch at %d", i)
+			}
+
+			if tt.wantParams == nil {
+				assert.Nil(t, gotParams, "expected nil params")
+				return
+			}
+
+			assert.Equal(t, len(tt.wantParams), len(gotParams), "params length mismatch")
+			for key, wantValue := range tt.wantParams {
+				gotValue, exists := gotParams[key]
+				assert.True(t, exists, "missing key: %s", key)
+				// Simple comparison for basic types
+				switch v := wantValue.(type) {
+				case string, int, float64, bool:
+					assert.Equal(t, v, gotValue, "value mismatch for key %s", key)
+				}
+			}
+		})
+	}
+}
+
+func TestProtectedParams(t *testing.T) {
+	// Verify that "model" is protected
+	assert.Contains(t, ProtectedParams, "model")
+}

proxy/config/model_config.go

@@ -3,8 +3,6 @@ package config
 import (
 	"errors"
 	"runtime"
-	"slices"
-	"strings"
 )
 
 type ModelConfig struct {
@@ -74,16 +72,15 @@ func (m *ModelConfig) SanitizedCommand() ([]string, error) {
 	return SanitizeCommand(m.Cmd)
 }
 
-// ModelFilters see issue #174
+// ModelFilters embeds Filters and adds legacy support for strip_params field
+// See issue #174
 type ModelFilters struct {
-	StripParams string `yaml:"stripParams"`
+	Filters `yaml:",inline"`
 }
 
 func (m *ModelFilters) UnmarshalYAML(unmarshal func(interface{}) error) error {
 	type rawModelFilters ModelFilters
-	defaults := rawModelFilters{
+	defaults := rawModelFilters{}
-		StripParams: "",
-	}
 
 	if err := unmarshal(&defaults); err != nil {
 		return err
@@ -104,25 +101,8 @@ func (m *ModelFilters) UnmarshalYAML(unmarshal func(interface{}) error) error {
 	return nil
 }
 
+// SanitizedStripParams wraps Filters.SanitizedStripParams for backwards compatibility
+// Returns ([]string, error) to match existing API
 func (f ModelFilters) SanitizedStripParams() ([]string, error) {
-	if f.StripParams == "" {
+	return f.Filters.SanitizedStripParams(), nil
-		return nil, nil
-	}
-
-	params := strings.Split(f.StripParams, ",")
-	cleaned := make([]string, 0, len(params))
-	seen := make(map[string]bool)
-
-	for _, param := range params {
-		trimmed := strings.TrimSpace(param)
-		if trimmed == "model" || trimmed == "" || seen[trimmed] {
-			continue
-		}
-		seen[trimmed] = true
-		cleaned = append(cleaned, trimmed)
-	}
-
-	// sort cleaned
-	slices.Sort(cleaned)
-	return cleaned, nil
 }

proxy/config/model_config_test.go

@@ -72,3 +72,35 @@ models:
 		assert.True(t, *config.Models["model2"].SendLoadingState)
 	}
 }
+
+func TestConfig_ModelFiltersWithSetParams(t *testing.T) {
+	content := `
+models:
+  model1:
+    cmd: path/to/cmd --port ${PORT}
+    filters:
+      stripParams: "top_k"
+      setParams:
+        temperature: 0.7
+        top_p: 0.9
+        stop:
+          - "<|end|>"
+          - "<|stop|>"
+`
+	config, err := LoadConfigFromReader(strings.NewReader(content))
+	assert.NoError(t, err)
+
+	modelConfig := config.Models["model1"]
+
+	// Check stripParams
+	stripParams, err := modelConfig.Filters.SanitizedStripParams()
+	assert.NoError(t, err)
+	assert.Equal(t, []string{"top_k"}, stripParams)
+
+	// Check setParams
+	setParams, keys := modelConfig.Filters.SanitizedSetParams()
+	assert.NotNil(t, setParams)
+	assert.Equal(t, []string{"stop", "temperature", "top_p"}, keys)
+	assert.Equal(t, 0.7, setParams["temperature"])
+	assert.Equal(t, 0.9, setParams["top_p"])
+}

proxy/config/peer.go

@@ -0,0 +1,49 @@
+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"`
+	Filters  Filters  `yaml:"filters"`
+}
+
+func (c *PeerConfig) UnmarshalYAML(unmarshal func(interface{}) error) error {
+	type rawPeerConfig PeerConfig
+	defaults := rawPeerConfig{
+		Proxy:   "",
+		ApiKey:  "",
+		Models:  []string{},
+		Filters: Filters{},
+	}
+
+	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 +1,209 @@
+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
+}
+
+func TestPeerConfig_WithFilters(t *testing.T) {
+	yamlData := `
+proxy: https://openrouter.ai/api
+apiKey: sk-test
+models:
+  - model_a
+filters:
+  setParams:
+    temperature: 0.7
+    provider:
+      data_collection: deny
+`
+	var config PeerConfig
+	err := yaml.Unmarshal([]byte(yamlData), &config)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+
+	if config.Filters.SetParams == nil {
+		t.Fatal("Filters.SetParams should not be nil")
+	}
+
+	if config.Filters.SetParams["temperature"] != 0.7 {
+		t.Errorf("expected temperature 0.7, got %v", config.Filters.SetParams["temperature"])
+	}
+
+	provider, ok := config.Filters.SetParams["provider"].(map[string]any)
+	if !ok {
+		t.Fatal("provider should be a map")
+	}
+	if provider["data_collection"] != "deny" {
+		t.Errorf("expected data_collection deny, got %v", provider["data_collection"])
+	}
+}
+
+func TestPeerConfig_WithBothFilters(t *testing.T) {
+	yamlData := `
+proxy: https://openrouter.ai/api
+apiKey: sk-test
+models:
+  - model_a
+filters:
+  stripParams: "temperature, top_p"
+  setParams:
+    max_tokens: 1000
+`
+	var config PeerConfig
+	err := yaml.Unmarshal([]byte(yamlData), &config)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+
+	// Check stripParams
+	stripParams := config.Filters.SanitizedStripParams()
+	if len(stripParams) != 2 {
+		t.Errorf("expected 2 strip params, got %d", len(stripParams))
+	}
+	if stripParams[0] != "temperature" || stripParams[1] != "top_p" {
+		t.Errorf("unexpected strip params: %v", stripParams)
+	}
+
+	// Check setParams
+	if config.Filters.SetParams == nil {
+		t.Fatal("Filters.SetParams should not be nil")
+	}
+	if config.Filters.SetParams["max_tokens"] != 1000 {
+		t.Errorf("expected max_tokens 1000, got %v", config.Filters.SetParams["max_tokens"])
+	}
+}

proxy/logMonitor.go

@@ -1,7 +1,6 @@
 package proxy
 
 import (
-	"container/ring"
 	"context"
 	"fmt"
 	"io"
@@ -12,6 +11,85 @@ import (
 	"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 (
@@ -19,12 +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
@@ -45,7 +125,7 @@ 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
+		buffer:     nil, // lazy initialized on first Write
 		stdout:     stdout,
 		level:      LevelInfo,
 		prefix:     "",
@@ -64,12 +144,15 @@ func (w *LogMonitor) Write(p []byte) (n int, err error) {
 	}
 
 	w.bufferMu.Lock()
-	bufferCopy := make([]byte, len(p))
+	if w.buffer == nil {
-	copy(bufferCopy, p)
+		w.buffer = newCircularBuffer(LogBufferSize)
-	w.buffer.Value = bufferCopy
+	}
-	w.buffer = w.buffer.Next()
+	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
 }
@@ -77,16 +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
+// Clear releases the buffer memory, making it eligible for GC.
-	w.buffer.Do(func(p any) {
+// The buffer will be lazily re-allocated on the next Write.
-		if p != nil {
+func (w *LogMonitor) Clear() {
-			if content, ok := p.([]byte); ok {
+	w.bufferMu.Lock()
-				history = append(history, content...)
+	w.buffer = nil
-			}
+	w.bufferMu.Unlock()
-		}
-	})
-	return history
 }
 
 func (w *LogMonitor) OnLogData(callback func(data []byte)) context.CancelFunc {

proxy/logMonitor_test.go

@@ -113,3 +113,204 @@ func TestWrite_LogTimeFormat(t *testing.T) {
 		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
 	}
@@ -108,17 +116,36 @@ 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") {
+	// Decompress if needed
-		if tm, err := processStreamingResponse(modelID, recorder.StartTime(), body); err != nil {
+	if encoding := recorder.Header().Get("Content-Encoding"); encoding != "" {
-			mp.logger.Warnf("error processing streaming response: %v, path=%s", err, request.URL.Path)
+		var err error
-		} else {
+		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)
+			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) {
@@ -127,18 +154,18 @@ func (mp *metricsMonitor) wrapHandler(
 			timings := parsed.Get("timings")
 
 			if usage.Exists() || timings.Exists() {
-				if tm, err := parseMetrics(modelID, recorder.StartTime(), usage, timings); err != nil {
+				if parsedMetrics, err := parseMetrics(modelID, recorder.StartTime(), usage, timings); err != nil {
-					mp.logger.Warnf("error parsing metrics: %v, path=%s", err, request.URL.Path)
+					mp.logger.Warnf("error parsing metrics: %v, path=%s, recording minimal metrics", err, request.URL.Path)
 				} else {
-					mp.addMetrics(tm)
+					tm = parsedMetrics
 				}
 			}
-
 		} else {
-			mp.logger.Warnf("metrics skipped, invalid JSON in response body path=%s", request.URL.Path)
+			mp.logger.Warnf("metrics: invalid JSON in response body path=%s, recording minimal metrics", request.URL.Path)
 		}
 	}
 
+	mp.addMetrics(tm)
 	return nil
 }
 
@@ -251,6 +278,25 @@ func parseMetrics(modelID string, start time.Time, usage, timings gjson.Result)
 	}, 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 {
@@ -289,3 +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 +1,141 @@
+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
+}
+
+// GetPeerFilters returns the filters for a peer model, or empty filters if not found
+func (p *PeerProxy) GetPeerFilters(modelID string) config.Filters {
+	pp, found := p.proxyMap[modelID]
+	if !found {
+		return config.Filters{}
+	}
+	// Get the peer config using the peerID
+	peer, found := p.peers[pp.peerID]
+	if !found {
+		return config.Filters{}
+	}
+	return peer.Filters
+}
+
+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

@@ -414,6 +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()
@@ -646,6 +649,11 @@ 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...",
@@ -864,7 +872,6 @@ func (s *statusResponseWriter) WriteHeader(statusCode int) {
 	s.Flush()
 }
 
-// Add Flush method
 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/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"
@@ -50,19 +51,42 @@ type ProxyManager struct {
 	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)
@@ -99,7 +123,7 @@ func New(config config.Config) *ProxyManager {
 		"stampnano":   time.StampNano,
 	}
 
-	if timeFormat, ok := timeFormats[strings.ToLower(strings.TrimSpace(config.LogTimeFormat))]; ok {
+	if timeFormat, ok := timeFormats[strings.ToLower(strings.TrimSpace(proxyConfig.LogTimeFormat))]; ok {
 		proxyLogger.SetLogTimeFormat(timeFormat)
 		upstreamLogger.SetLogTimeFormat(timeFormat)
 	}
@@ -107,18 +131,24 @@ func New(config config.Config) *ProxyManager {
 	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),
@@ -131,37 +161,46 @@ func New(config config.Config) *ProxyManager {
 		buildDate: "unknown",
 		commit:    "abcd1234",
 		version:   "0",
+
+		peerProxy: peerProxy,
 	}
 
 	// create the process groups
-	for groupID := range config.Groups {
+	for groupID := range proxyConfig.Groups {
-		processGroup := NewProcessGroup(groupID, config, proxyLogger, upstreamLogger)
+		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 {
+			for _, preloadModelName := range proxyConfig.Hooks.OnStartup.Preload {
-				proxyLogger.Infof("Preloading model: %s", realModelName)
+				modelID, ok := proxyConfig.RealModelName(preloadModelName)
-				processGroup, _, err := pm.swapProcessGroup(realModelName)
+
+				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,
 					})
 				}
@@ -236,37 +275,44 @@ func (pm *ProxyManager) setupGinEngine() {
 	})
 
 	// Set up routes using the Gin engine
-	pm.ginEngine.POST("/v1/chat/completions", pm.proxyInferenceHandler)
+	// Protected routes use pm.apiKeyAuth() middleware
+	pm.ginEngine.POST("/v1/chat/completions", pm.apiKeyAuth(), pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/responses", pm.apiKeyAuth(), pm.proxyInferenceHandler)
 	// Support legacy /v1/completions api, see issue #12
-	pm.ginEngine.POST("/v1/completions", pm.proxyInferenceHandler)
+	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.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/messages", pm.apiKeyAuth(), pm.proxyInferenceHandler)
+	// Support anthropic count_tokens API (Also added in the above PR)
+	pm.ginEngine.POST("/v1/messages/count_tokens", pm.apiKeyAuth(), pm.proxyInferenceHandler)
 
 	// Support embeddings and reranking
-	pm.ginEngine.POST("/v1/embeddings", pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/embeddings", pm.apiKeyAuth(), pm.proxyInferenceHandler)
 
 	// llama-server's /reranking endpoint + aliases
-	pm.ginEngine.POST("/reranking", pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/reranking", pm.apiKeyAuth(), pm.proxyInferenceHandler)
-	pm.ginEngine.POST("/rerank", pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/rerank", pm.apiKeyAuth(), pm.proxyInferenceHandler)
-	pm.ginEngine.POST("/v1/rerank", pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/rerank", pm.apiKeyAuth(), pm.proxyInferenceHandler)
-	pm.ginEngine.POST("/v1/reranking", pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/reranking", pm.apiKeyAuth(), pm.proxyInferenceHandler)
 
 	// llama-server's /infill endpoint for code infilling
-	pm.ginEngine.POST("/infill", pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/infill", pm.apiKeyAuth(), pm.proxyInferenceHandler)
 
 	// llama-server's /completion endpoint
-	pm.ginEngine.POST("/completion", pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/completion", pm.apiKeyAuth(), pm.proxyInferenceHandler)
 
 	// Support audio/speech endpoint
-	pm.ginEngine.POST("/v1/audio/speech", pm.proxyInferenceHandler)
+	pm.ginEngine.POST("/v1/audio/speech", pm.apiKeyAuth(), pm.proxyInferenceHandler)
-	pm.ginEngine.POST("/v1/audio/transcriptions", pm.proxyOAIPostFormHandler)
+	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", pm.apiKeyAuth(), pm.sendLogsHandlers)
-	pm.ginEngine.GET("/logs/stream", pm.streamLogsHandler)
+	pm.ginEngine.GET("/logs/stream", pm.apiKeyAuth(), pm.streamLogsHandler)
-	pm.ginEngine.GET("/logs/stream/:logMonitorID", pm.streamLogsHandler)
+	pm.ginEngine.GET("/logs/stream/*logMonitorID", pm.apiKeyAuth(), pm.streamLogsHandler)
 
 	/**
 	 * User Interface Endpoints
@@ -278,9 +324,9 @@ 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.Any("/upstream/*upstreamPath", pm.apiKeyAuth(), pm.proxyToUpstream)
-	pm.ginEngine.GET("/unload", pm.unloadAllModelsHandler)
+	pm.ginEngine.GET("/unload", pm.apiKeyAuth(), pm.unloadAllModelsHandler)
-	pm.ginEngine.GET("/running", pm.listRunningProcessesHandler)
+	pm.ginEngine.GET("/running", pm.apiKeyAuth(), pm.listRunningProcessesHandler)
 	pm.ginEngine.GET("/health", func(c *gin.Context) {
 		c.String(http.StatusOK, "OK")
 	})
@@ -378,16 +424,10 @@ func (pm *ProxyManager) Shutdown() {
 	pm.shutdownCancel()
 }
 
-func (pm *ProxyManager) swapProcessGroup(requestedModel string) (*ProcessGroup, string, error) {
+func (pm *ProxyManager) swapProcessGroup(realModelName string) (*ProcessGroup, error) {
-	// de-alias the real model name and get a real one
-	realModelName, found := pm.config.RealModelName(requestedModel)
-	if !found {
-		return nil, realModelName, fmt.Errorf("could not find real modelID for %s", requestedModel)
-	}
-
 	processGroup := pm.findGroupByModelName(realModelName)
 	if processGroup == nil {
-		return nil, realModelName, fmt.Errorf("could not find process group for model %s", requestedModel)
+		return nil, fmt.Errorf("could not find process group for model %s", realModelName)
 	}
 
 	if processGroup.exclusive {
@@ -399,54 +439,71 @@ 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()
 
+	newRecord := func(modelId string, modelConfig config.ModelConfig) gin.H {
+		record := gin.H{
+			"id":       modelId,
+			"object":   "model",
+			"created":  createdTime,
+			"owned_by": "llama-swap",
+		}
+
+		if name := strings.TrimSpace(modelConfig.Name); name != "" {
+			record["name"] = name
+		}
+		if desc := strings.TrimSpace(modelConfig.Description); desc != "" {
+			record["description"] = desc
+		}
+
+		// Add metadata if present
+		if len(modelConfig.Metadata) > 0 {
+			record["meta"] = gin.H{
+				"llamaswap": modelConfig.Metadata,
+			}
+		}
+		return record
+	}
+
 	for id, modelConfig := range pm.config.Models {
 		if modelConfig.Unlisted {
 			continue
 		}
 
-		newRecord := func(modelId string) gin.H {
+		data = append(data, newRecord(id, modelConfig))
-			record := gin.H{
-				"id":       modelId,
-				"object":   "model",
-				"created":  createdTime,
-				"owned_by": "llama-swap",
-			}
-
-			if name := strings.TrimSpace(modelConfig.Name); name != "" {
-				record["name"] = name
-			}
-			if desc := strings.TrimSpace(modelConfig.Description); desc != "" {
-				record["description"] = desc
-			}
-
-			// Add metadata if present
-			if len(modelConfig.Metadata) > 0 {
-				record["meta"] = gin.H{
-					"llamaswap": modelConfig.Metadata,
-				}
-			}
-			return record
-		}
-
-		data = append(data, newRecord(id))
 
 		// Include aliases
 		if pm.config.IncludeAliasesInList {
 			for _, alias := range modelConfig.Aliases {
 				if alias := strings.TrimSpace(alias); alias != "" {
-					data = append(data, newRecord(alias))
+					data = append(data, 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
 	sort.Slice(data, func(i, j int) bool {
 		si, _ := data[i]["id"].(string)
@@ -466,62 +523,61 @@ func (pm *ProxyManager) listModelsHandler(c *gin.Context) {
 	})
 }
 
-func (pm *ProxyManager) proxyToUpstream(c *gin.Context) {
+// findModelInPath searches for a valid model name in a path with slashes.
-	upstreamPath := c.Param("upstreamPath")
+// It iteratively builds up path segments until it finds a matching model.
-
+// Returns: (searchModelName, realModelName, remainingPath, found)
-	// split the upstream path by / and search for the model name
+// Example: "/author/model/endpoint" with model "author/model" -> ("author/model", "author/model", "/endpoint", true)
-	parts := strings.Split(strings.TrimSpace(upstreamPath), "/")
+func (pm *ProxyManager) findModelInPath(path string) (searchName string, realName string, remainingPath string, found bool) {
-	if len(parts) == 0 {
+	parts := strings.Split(strings.TrimSpace(path), "/")
-		pm.sendErrorResponse(c, http.StatusBadRequest, "model id required in path")
-		return
-	}
-
-	modelFound := false
 	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 {
+		if modelID, ok := pm.config.RealModelName(searchModelName); ok {
-			modelName = real
+			return searchModelName, modelID, "/" + strings.Join(parts[i+1:], "/"), true
-			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
 		}
 	}
 
+	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
@@ -533,15 +589,15 @@ 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
 		}
 	}
@@ -560,41 +616,90 @@ func (pm *ProxyManager) proxyInferenceHandler(c *gin.Context) {
 		return
 	}
 
-	realModelName, found := pm.config.RealModelName(requestedModel)
+	// Look for a matching local model first
-	if !found {
+	var nextHandler func(modelID string, w http.ResponseWriter, r *http.Request) error
-		pm.sendErrorResponse(c, http.StatusBadRequest, fmt.Sprintf("could not find real modelID for %s", requestedModel))
-		return
-	}
 
-	processGroup, _, err := pm.swapProcessGroup(realModelName)
+	modelID, found := pm.config.RealModelName(requestedModel)
-	if err != nil {
+	if found {
-		pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error swapping process group: %s", err.Error()))
+		processGroup, err := pm.swapProcessGroup(modelID)
-		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)
 		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
+		// issue #69 allow custom model names to be sent to upstream
-	stripParams, err := pm.config.Models[realModelName].Filters.SanitizedStripParams()
+		useModelName := pm.config.Models[modelID].UseModelName
-	if err != nil { // just log it and continue
+		if useModelName != "" {
-		pm.proxyLogger.Errorf("Error sanitizing strip params string: %s, %s", pm.config.Models[realModelName].Filters.StripParams, err.Error())
+			bodyBytes, err = sjson.SetBytes(bodyBytes, "model", useModelName)
-	} else {
-		for _, param := range stripParams {
-			pm.proxyLogger.Debugf("<%s> stripping param: %s", realModelName, param)
-			bodyBytes, err = sjson.DeleteBytes(bodyBytes, param)
 			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
+				}
+			}
+		}
+
+		// issue #453 set/override parameters in the JSON body
+		setParams, setParamKeys := pm.config.Models[modelID].Filters.SanitizedSetParams()
+		for _, key := range setParamKeys {
+			pm.proxyLogger.Debugf("<%s> setting param: %s", modelID, key)
+			bodyBytes, err = sjson.SetBytes(bodyBytes, key, setParams[key])
+			if err != nil {
+				pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error setting parameter %s in request", key))
+				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
+
+		// issue #453 apply filters for peer requests
+		peerFilters := pm.peerProxy.GetPeerFilters(requestedModel)
+
+		// Apply stripParams - remove specified parameters from request
+		stripParams := peerFilters.SanitizedStripParams()
+		for _, param := range stripParams {
+			pm.proxyLogger.Debugf("<%s> stripping param: %s", requestedModel, param)
+			bodyBytes, err = sjson.DeleteBytes(bodyBytes, param)
+			if err != nil {
+				pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error stripping parameter %s from request", param))
+				return
+			}
+		}
+
+		// Apply setParams - set/override specified parameters in request
+		setParams, setParamKeys := peerFilters.SanitizedSetParams()
+		for _, key := range setParamKeys {
+			pm.proxyLogger.Debugf("<%s> setting param: %s", requestedModel, key)
+			bodyBytes, err = sjson.SetBytes(bodyBytes, key, setParams[key])
+			if err != nil {
+				pm.sendErrorResponse(c, http.StatusInternalServerError, fmt.Sprintf("error setting parameter %s in request", key))
+				return
+			}
+		}
+
+		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))
@@ -607,19 +712,19 @@ func (pm *ProxyManager) proxyInferenceHandler(c *gin.Context) {
 	// 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"), realModelName)
+	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
 		}
 	}
@@ -639,7 +744,13 @@ 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
@@ -657,7 +768,7 @@ 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
@@ -728,9 +839,9 @@ 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
 	}
 }
@@ -745,6 +856,67 @@ 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")
@@ -758,8 +930,13 @@ func (pm *ProxyManager) listRunningProcessesHandler(context *gin.Context) {
 		for _, process := range processGroup.processes {
 			if process.CurrentState() == StateReady {
 				runningProcesses = append(runningProcesses, gin.H{
-					"model": process.ID,
+					"model":       process.ID,
-					"state": process.state,
+					"state":       process.state,
+					"cmd":         process.config.Cmd,
+					"proxy":       process.config.Proxy,
+					"ttl":         process.config.UnloadAfter,
+					"name":        process.config.Name,
+					"description": process.config.Description,
 				})
 			}
 		}

proxy/proxymanager_api.go

@@ -18,11 +18,13 @@ 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)
@@ -82,6 +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
 }
 

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
+	switch logMonitorId {
-
+	case "":
-	if logMonitorId == "" {
 		// maintain the default
-		logger = pm.muxLogger
+		return pm.muxLogger, nil
-	} else if logMonitorId == "proxy" {
+	case "proxy":
-		logger = pm.proxyLogger
+		return pm.proxyLogger, nil
-	} else if logMonitorId == "upstream" {
+	case "upstream":
-		logger = pm.upstreamLogger
+		return pm.upstreamLogger, nil
-	} else {
+	default:
-		return nil, fmt.Errorf("invalid logger. Use 'proxy' or 'upstream'")
+		// 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
+	// Check the number of models returned (3 local + 2 peer models)
-	assert.Len(t, response.Data, 3)
+	assert.Len(t, response.Data, 5)
 
 	// Check the details of each model
 	expectedModels := map[string]struct{}{
-		"model1": {},
+		"model1":       {},
-		"model2": {},
+		"model2":       {},
-		"model3": {},
+		"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)
@@ -502,6 +520,10 @@ func TestProxyManager_ListModelsHandler_IncludeAliasesInList(t *testing.T) {
 }
 
 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/"
@@ -650,8 +672,13 @@ func TestProxyManager_RunningEndpoint(t *testing.T) {
 	// Define a helper struct to parse the JSON response.
 	type RunningResponse struct {
 		Running []struct {
-			Model string `json:"model"`
+			Model       string `json:"model"`
-			State string `json:"state"`
+			State       string `json:"state"`
+			Cmd         string `json:"cmd"`
+			Proxy       string `json:"proxy"`
+			TTL         int    `json:"ttl"`
+			Name        string `json:"name"`
+			Description string `json:"description"`
 		} `json:"running"`
 	}
 
@@ -699,6 +726,11 @@ func TestProxyManager_RunningEndpoint(t *testing.T) {
 
 		// Is the model loaded?
 		assert.Equal(t, "ready", response.Running[0].State)
+
+		// Verify extended fields are present
+		assert.NotEmpty(t, response.Running[0].Cmd, "cmd should be populated")
+		assert.NotEmpty(t, response.Running[0].Proxy, "proxy should be populated")
+		assert.Equal(t, 0, response.Running[0].TTL, "ttl should default to 0")
 	})
 }
 
@@ -944,7 +976,9 @@ func TestProxyManager_ChatContentLength(t *testing.T) {
 func TestProxyManager_FiltersStripParams(t *testing.T) {
 	modelConfig := getTestSimpleResponderConfig("model1")
 	modelConfig.Filters = config.ModelFilters{
-		StripParams: "temperature, model, stream",
+		Filters: config.Filters{
+			StripParams: "temperature, model, stream",
+		},
 	}
 
 	config := config.AddDefaultGroupToConfig(config.Config{
@@ -1078,7 +1112,8 @@ 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",
 	})
@@ -1091,6 +1126,7 @@ func TestProxyManager_StreamingEndpointsReturnNoBufferingHeader(t *testing.T) {
 		"/logs/stream",
 		"/logs/stream/proxy",
 		"/logs/stream/upstream",
+		"/logs/stream/author/model",
 	}
 
 	for _, endpoint := range endpoints {
@@ -1185,3 +1221,349 @@ func TestProxyManager_ApiGetVersion(t *testing.T) {
 		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-svelte/.gitignore

@@ -0,0 +1,2 @@
+node_modules
+.vite

ui-svelte/index.html

@@ -0,0 +1,17 @@
+<!doctype html>
+<html lang="en">
+  <head>
+    <meta charset="UTF-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <link rel="icon" type="image/png" href="/favicon-96x96.png" sizes="96x96" />
+    <link rel="icon" type="image/svg+xml" href="/favicon.svg" />
+    <link rel="shortcut icon" href="/favicon.ico" />
+    <link rel="apple-touch-icon" sizes="180x180" href="/apple-touch-icon.png" />
+    <link rel="manifest" href="/site.webmanifest" />
+    <title>llama-swap</title>
+  </head>
+  <body>
+    <div id="app"></div>
+    <script type="module" src="/src/main.ts"></script>
+  </body>
+</html>

ui-svelte/package.json

@@ -0,0 +1,25 @@
+{
+  "name": "ui-svelte",
+  "private": true,
+  "version": "0.0.0",
+  "type": "module",
+  "scripts": {
+    "start": "vite",
+    "build": "vite build --emptyOutDir",
+    "preview": "vite preview",
+    "check": "svelte-check --tsconfig ./tsconfig.json"
+  },
+  "devDependencies": {
+    "@sveltejs/vite-plugin-svelte": "^5.0.3",
+    "@tailwindcss/vite": "^4.1.8",
+    "@tsconfig/svelte": "^5.0.4",
+    "svelte": "^5.19.0",
+    "svelte-check": "^4.1.4",
+    "tailwindcss": "^4.1.8",
+    "typescript": "~5.8.3",
+    "vite": "^6.3.5"
+  },
+  "dependencies": {
+    "svelte-spa-router": "^4.0.1"
+  }
+}

ui-svelte/public/site.webmanifest

@@ -0,0 +1,21 @@
+{
+  "name": "llama-swap",
+  "short_name": "llama-swap",
+  "icons": [
+    {
+      "src": "/web-app-manifest-192x192.png",
+      "sizes": "192x192",
+      "type": "image/png",
+      "purpose": "maskable"
+    },
+    {
+      "src": "/web-app-manifest-512x512.png",
+      "sizes": "512x512",
+      "type": "image/png",
+      "purpose": "maskable"
+    }
+  ],
+  "theme_color": "#ffffff",
+  "background_color": "#ffffff",
+  "display": "standalone"
+}

ui-svelte/src/App.svelte

@@ -0,0 +1,46 @@
+<script lang="ts">
+  import { onMount } from "svelte";
+  import Router from "svelte-spa-router";
+  import Header from "./components/Header.svelte";
+  import LogViewer from "./routes/LogViewer.svelte";
+  import Models from "./routes/Models.svelte";
+  import Activity from "./routes/Activity.svelte";
+  import { enableAPIEvents } from "./stores/api";
+  import { initScreenWidth, isDarkMode, appTitle, connectionState } from "./stores/theme";
+
+  const routes = {
+    "/": Models,
+    "/logs": LogViewer,
+    "/activity": Activity,
+    "*": Models,
+  };
+
+  // Sync theme to document attribute
+  $effect(() => {
+    document.documentElement.setAttribute("data-theme", $isDarkMode ? "dark" : "light");
+  });
+
+  // Sync title to document
+  $effect(() => {
+    const icon = $connectionState === "connecting" ? "\u{1F7E1}" : $connectionState === "connected" ? "\u{1F7E2}" : "\u{1F534}";
+    document.title = `${icon} ${$appTitle}`;
+  });
+
+  onMount(() => {
+    const cleanupScreenWidth = initScreenWidth();
+    enableAPIEvents(true);
+
+    return () => {
+      cleanupScreenWidth();
+      enableAPIEvents(false);
+    };
+  });
+</script>
+
+<div class="flex flex-col h-screen">
+  <Header />
+
+  <main class="flex-1 overflow-auto p-4">
+    <Router {routes} />
+  </main>
+</div>

ui-svelte/src/assets/react.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" class="iconify iconify--logos" width="35.93" height="32" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 228"><path fill="#00D8FF" d="M210.483 73.824a171.49 171.49 0 0 0-8.24-2.597c.465-1.9.893-3.777 1.273-5.621c6.238-30.281 2.16-54.676-11.769-62.708c-13.355-7.7-35.196.329-57.254 19.526a171.23 171.23 0 0 0-6.375 5.848a155.866 155.866 0 0 0-4.241-3.917C100.759 3.829 77.587-4.822 63.673 3.233C50.33 10.957 46.379 33.89 51.995 62.588a170.974 170.974 0 0 0 1.892 8.48c-3.28.932-6.445 1.924-9.474 2.98C17.309 83.498 0 98.307 0 113.668c0 15.865 18.582 31.778 46.812 41.427a145.52 145.52 0 0 0 6.921 2.165a167.467 167.467 0 0 0-2.01 9.138c-5.354 28.2-1.173 50.591 12.134 58.266c13.744 7.926 36.812-.22 59.273-19.855a145.567 145.567 0 0 0 5.342-4.923a168.064 168.064 0 0 0 6.92 6.314c21.758 18.722 43.246 26.282 56.54 18.586c13.731-7.949 18.194-32.003 12.4-61.268a145.016 145.016 0 0 0-1.535-6.842c1.62-.48 3.21-.974 4.76-1.488c29.348-9.723 48.443-25.443 48.443-41.52c0-15.417-17.868-30.326-45.517-39.844Zm-6.365 70.984c-1.4.463-2.836.91-4.3 1.345c-3.24-10.257-7.612-21.163-12.963-32.432c5.106-11 9.31-21.767 12.459-31.957c2.619.758 5.16 1.557 7.61 2.4c23.69 8.156 38.14 20.213 38.14 29.504c0 9.896-15.606 22.743-40.946 31.14Zm-10.514 20.834c2.562 12.94 2.927 24.64 1.23 33.787c-1.524 8.219-4.59 13.698-8.382 15.893c-8.067 4.67-25.32-1.4-43.927-17.412a156.726 156.726 0 0 1-6.437-5.87c7.214-7.889 14.423-17.06 21.459-27.246c12.376-1.098 24.068-2.894 34.671-5.345a134.17 134.17 0 0 1 1.386 6.193ZM87.276 214.515c-7.882 2.783-14.16 2.863-17.955.675c-8.075-4.657-11.432-22.636-6.853-46.752a156.923 156.923 0 0 1 1.869-8.499c10.486 2.32 22.093 3.988 34.498 4.994c7.084 9.967 14.501 19.128 21.976 27.15a134.668 134.668 0 0 1-4.877 4.492c-9.933 8.682-19.886 14.842-28.658 17.94ZM50.35 144.747c-12.483-4.267-22.792-9.812-29.858-15.863c-6.35-5.437-9.555-10.836-9.555-15.216c0-9.322 13.897-21.212 37.076-29.293c2.813-.98 5.757-1.905 8.812-2.773c3.204 10.42 7.406 21.315 12.477 32.332c-5.137 11.18-9.399 22.249-12.634 32.792a134.718 134.718 0 0 1-6.318-1.979Zm12.378-84.26c-4.811-24.587-1.616-43.134 6.425-47.789c8.564-4.958 27.502 2.111 47.463 19.835a144.318 144.318 0 0 1 3.841 3.545c-7.438 7.987-14.787 17.08-21.808 26.988c-12.04 1.116-23.565 2.908-34.161 5.309a160.342 160.342 0 0 1-1.76-7.887Zm110.427 27.268a347.8 347.8 0 0 0-7.785-12.803c8.168 1.033 15.994 2.404 23.343 4.08c-2.206 7.072-4.956 14.465-8.193 22.045a381.151 381.151 0 0 0-7.365-13.322Zm-45.032-43.861c5.044 5.465 10.096 11.566 15.065 18.186a322.04 322.04 0 0 0-30.257-.006c4.974-6.559 10.069-12.652 15.192-18.18ZM82.802 87.83a323.167 323.167 0 0 0-7.227 13.238c-3.184-7.553-5.909-14.98-8.134-22.152c7.304-1.634 15.093-2.97 23.209-3.984a321.524 321.524 0 0 0-7.848 12.897Zm8.081 65.352c-8.385-.936-16.291-2.203-23.593-3.793c2.26-7.3 5.045-14.885 8.298-22.6a321.187 321.187 0 0 0 7.257 13.246c2.594 4.48 5.28 8.868 8.038 13.147Zm37.542 31.03c-5.184-5.592-10.354-11.779-15.403-18.433c4.902.192 9.899.29 14.978.29c5.218 0 10.376-.117 15.453-.343c-4.985 6.774-10.018 12.97-15.028 18.486Zm52.198-57.817c3.422 7.8 6.306 15.345 8.596 22.52c-7.422 1.694-15.436 3.058-23.88 4.071a382.417 382.417 0 0 0 7.859-13.026a347.403 347.403 0 0 0 7.425-13.565Zm-16.898 8.101a358.557 358.557 0 0 1-12.281 19.815a329.4 329.4 0 0 1-23.444.823c-7.967 0-15.716-.248-23.178-.732a310.202 310.202 0 0 1-12.513-19.846h.001a307.41 307.41 0 0 1-10.923-20.627a310.278 310.278 0 0 1 10.89-20.637l-.001.001a307.318 307.318 0 0 1 12.413-19.761c7.613-.576 15.42-.876 23.31-.876H128c7.926 0 15.743.303 23.354.883a329.357 329.357 0 0 1 12.335 19.695a358.489 358.489 0 0 1 11.036 20.54a329.472 329.472 0 0 1-11 20.722Zm22.56-122.124c8.572 4.944 11.906 24.881 6.52 51.026c-.344 1.668-.73 3.367-1.15 5.09c-10.622-2.452-22.155-4.275-34.23-5.408c-7.034-10.017-14.323-19.124-21.64-27.008a160.789 160.789 0 0 1 5.888-5.4c18.9-16.447 36.564-22.941 44.612-18.3ZM128 90.808c12.625 0 22.86 10.235 22.86 22.86s-10.235 22.86-22.86 22.86s-22.86-10.235-22.86-22.86s10.235-22.86 22.86-22.86Z"></path></svg>

ui-svelte/src/components/ConnectionStatus.svelte

@@ -0,0 +1,24 @@
+<script lang="ts">
+  import { connectionState } from "../stores/theme";
+  import { versionInfo } from "../stores/api";
+
+  let eventStatusColor = $derived.by(() => {
+    switch ($connectionState) {
+      case "connected":
+        return "bg-emerald-500";
+      case "connecting":
+        return "bg-amber-500";
+      case "disconnected":
+      default:
+        return "bg-red-500";
+    }
+  });
+
+  let tooltipText = $derived(
+    `Event Stream: ${$connectionState ?? "unknown"}\nAPI Version: ${$versionInfo?.version ?? "unknown"}\nCommit Hash: ${$versionInfo?.commit?.substring(0, 7) ?? "unknown"}\nBuild Date: ${$versionInfo?.build_date ?? "unknown"}`
+  );
+</script>
+
+<div class="flex items-center" title={tooltipText}>
+  <span class="inline-block w-3 h-3 rounded-full {eventStatusColor} mr-2"></span>
+</div>

ui-svelte/src/components/Header.svelte

@@ -0,0 +1,90 @@
+<script lang="ts">
+  import { link, location } from "svelte-spa-router";
+  import { screenWidth, toggleTheme, isDarkMode, appTitle, isNarrow } from "../stores/theme";
+  import ConnectionStatus from "./ConnectionStatus.svelte";
+
+  function handleTitleChange(newTitle: string): void {
+    const sanitized = newTitle.replace(/\n/g, "").trim().substring(0, 64) || "llama-swap";
+    appTitle.set(sanitized);
+  }
+
+  function handleKeyDown(e: KeyboardEvent): void {
+    if (e.key === "Enter") {
+      e.preventDefault();
+      const target = e.currentTarget as HTMLElement;
+      handleTitleChange(target.textContent || "(set title)");
+      target.blur();
+    }
+  }
+
+  function handleBlur(e: FocusEvent): void {
+    const target = e.currentTarget as HTMLElement;
+    handleTitleChange(target.textContent || "(set title)");
+  }
+
+  function isActive(path: string, currentLocation: string): boolean {
+    return path === "/" ? currentLocation === "/" : currentLocation.startsWith(path);
+  }
+</script>
+
+<header
+  class="flex items-center justify-between bg-surface border-b border-border px-4 {$isNarrow
+    ? 'py-1 h-[60px]'
+    : 'p-2 h-[75px]'}"
+>
+  {#if $screenWidth !== "xs" && $screenWidth !== "sm"}
+    <h1
+      contenteditable="true"
+      class="p-0 outline-none hover:bg-gray-100 dark:hover:bg-gray-700 rounded"
+      onblur={handleBlur}
+      onkeydown={handleKeyDown}
+    >
+      {$appTitle}
+    </h1>
+  {/if}
+
+  <menu class="flex items-center gap-4">
+    <a
+      href="/"
+      use:link
+      class="text-gray-600 hover:text-black dark:text-gray-300 dark:hover:text-gray-100 p-1"
+      class:font-semibold={isActive("/", $location)}
+    >
+      Models
+    </a>
+    <a
+      href="/activity"
+      use:link
+      class="text-gray-600 hover:text-black dark:text-gray-300 dark:hover:text-gray-100 p-1"
+      class:font-semibold={isActive("/activity", $location)}
+    >
+      Activity
+    </a>
+    <a
+      href="/logs"
+      use:link
+      class="text-gray-600 hover:text-black dark:text-gray-300 dark:hover:text-gray-100 p-1"
+      class:font-semibold={isActive("/logs", $location)}
+    >
+      Logs
+    </a>
+    <button onclick={toggleTheme} title="Toggle theme">
+      {#if $isDarkMode}
+        <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor" class="w-5 h-5">
+          <path
+            fill-rule="evenodd"
+            d="M9.528 1.718a.75.75 0 0 1 .162.819A8.97 8.97 0 0 0 9 6a9 9 0 0 0 9 9 8.97 8.97 0 0 0 3.463-.69.75.75 0 0 1 .981.98 10.503 10.503 0 0 1-9.694 6.46c-5.799 0-10.5-4.7-10.5-10.5 0-4.368 2.667-8.112 6.46-9.694a.75.75 0 0 1 .818.162Z"
+            clip-rule="evenodd"
+          />
+        </svg>
+      {:else}
+        <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor" class="w-5 h-5">
+          <path
+            d="M12 2.25a.75.75 0 0 1 .75.75v2.25a.75.75 0 0 1-1.5 0V3a.75.75 0 0 1 .75-.75ZM7.5 12a4.5 4.5 0 1 1 9 0 4.5 4.5 0 0 1-9 0ZM18.894 6.166a.75.75 0 0 0-1.06-1.06l-1.591 1.59a.75.75 0 1 0 1.06 1.061l1.591-1.59ZM21.75 12a.75.75 0 0 1-.75.75h-2.25a.75.75 0 0 1 0-1.5H21a.75.75 0 0 1 .75.75ZM17.834 18.894a.75.75 0 0 0 1.06-1.06l-1.59-1.591a.75.75 0 1 0-1.061 1.06l1.591 1.591ZM12 18a.75.75 0 0 1 .75.75V21a.75.75 0 0 1-1.5 0v-2.25A.75.75 0 0 1 12 18ZM7.758 17.303a.75.75 0 0 0-1.061-1.06l-1.591 1.59a.75.75 0 0 0 1.06 1.061l1.591-1.59ZM6 12a.75.75 0 0 1-.75.75H3a.75.75 0 0 1 0-1.5h2.25A.75.75 0 0 1 6 12ZM6.697 7.757a.75.75 0 0 0 1.06-1.06l-1.59-1.591a.75.75 0 0 0-1.061 1.06l1.59 1.591Z"
+          />
+        </svg>
+      {/if}
+    </button>
+    <ConnectionStatus />
+  </menu>
+</header>

ui-svelte/src/components/LogPanel.svelte

@@ -0,0 +1,132 @@
+<script lang="ts">
+  import { persistentStore } from "../stores/persistent";
+
+  interface Props {
+    id: string;
+    title: string;
+    logData: string;
+  }
+
+  let { id, title, logData }: Props = $props();
+
+  let filterRegex = $state("");
+
+  // Create persistent stores for this panel (id is intentionally captured at init time)
+  // svelte-ignore state_referenced_locally
+  const fontSizeStore = persistentStore<"xxs" | "xs" | "small" | "normal">(`logPanel-${id}-fontSize`, "normal");
+  // svelte-ignore state_referenced_locally
+  const wrapTextStore = persistentStore<boolean>(`logPanel-${id}-wrapText`, false);
+  // svelte-ignore state_referenced_locally
+  const showFilterStore = persistentStore<boolean>(`logPanel-${id}-showFilter`, false);
+
+  let textWrapClass = $derived($wrapTextStore ? "whitespace-pre-wrap" : "whitespace-pre");
+
+  function toggleFontSize(): void {
+    fontSizeStore.update((prev) => {
+      switch (prev) {
+        case "xxs": return "xs";
+        case "xs": return "small";
+        case "small": return "normal";
+        case "normal": return "xxs";
+      }
+    });
+  }
+
+  function toggleWrapText(): void {
+    wrapTextStore.update((prev) => !prev);
+  }
+
+  function toggleFilter(): void {
+    if ($showFilterStore) {
+      showFilterStore.set(false);
+      filterRegex = "";
+    } else {
+      showFilterStore.set(true);
+    }
+  }
+
+  let fontSizeClass = $derived.by(() => {
+    switch ($fontSizeStore) {
+      case "xxs": return "text-[0.5rem]";
+      case "xs": return "text-[0.75rem]";
+      case "small": return "text-[0.875rem]";
+      case "normal": return "text-base";
+    }
+  });
+
+  let filteredLogs = $derived.by(() => {
+    if (!filterRegex) return logData;
+    try {
+      const regex = new RegExp(filterRegex, "i");
+      return logData.split("\n").filter((line) => regex.test(line)).join("\n");
+    } catch {
+      return logData;
+    }
+  });
+
+  let preElement: HTMLPreElement;
+
+  // Auto scroll to bottom when logs change
+  $effect(() => {
+    if (preElement && filteredLogs) {
+      preElement.scrollTop = preElement.scrollHeight;
+    }
+  });
+</script>
+
+<div class="rounded-lg overflow-hidden flex flex-col bg-gray-950/5 dark:bg-white/10 h-full w-full p-1">
+  <div class="p-4">
+    <div class="flex items-center justify-between">
+      <h3 class="m-0 text-lg p-0">{title}</h3>
+
+      <div class="flex gap-2 items-center">
+        <button class="btn border-0" onclick={toggleFontSize} title="Change font size">
+          <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor" class="w-4 h-4">
+            <path fill-rule="evenodd" d="M10.5 3.75a6 6 0 0 0-5.98 6.496A5.25 5.25 0 0 0 6.75 20.25H18a4.5 4.5 0 0 0 2.206-8.423 3.75 3.75 0 0 0-4.133-4.303A6.001 6.001 0 0 0 10.5 3.75Zm2.25 6a.75.75 0 0 0-1.5 0v4.94l-1.72-1.72a.75.75 0 0 0-1.06 1.06l3 3a.75.75 0 0 0 1.06 0l3-3a.75.75 0 1 0-1.06-1.06l-1.72 1.72V9.75Z" clip-rule="evenodd" />
+          </svg>
+        </button>
+        <button class="btn border-0" onclick={toggleWrapText} title="Toggle text wrap">
+          {#if $wrapTextStore}
+            <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor" class="w-4 h-4">
+              <path fill-rule="evenodd" d="M3 6.75A.75.75 0 0 1 3.75 6h16.5a.75.75 0 0 1 0 1.5H3.75A.75.75 0 0 1 3 6.75ZM3 12a.75.75 0 0 1 .75-.75h16.5a.75.75 0 0 1 0 1.5H3.75A.75.75 0 0 1 3 12Zm0 5.25a.75.75 0 0 1 .75-.75h16.5a.75.75 0 0 1 0 1.5H3.75a.75.75 0 0 1-.75-.75Z" clip-rule="evenodd" />
+            </svg>
+          {:else}
+            <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor" class="w-4 h-4">
+              <path fill-rule="evenodd" d="M3 6.75A.75.75 0 0 1 3.75 6h16.5a.75.75 0 0 1 0 1.5H3.75A.75.75 0 0 1 3 6.75ZM3 12a.75.75 0 0 1 .75-.75h10.5a.75.75 0 0 1 0 1.5H3.75A.75.75 0 0 1 3 12Zm0 5.25a.75.75 0 0 1 .75-.75h16.5a.75.75 0 0 1 0 1.5H3.75a.75.75 0 0 1-.75-.75Z" clip-rule="evenodd" />
+            </svg>
+          {/if}
+        </button>
+        <button class="btn border-0" onclick={toggleFilter} title="Toggle filter">
+          {#if $showFilterStore}
+            <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor" class="w-4 h-4">
+              <path fill-rule="evenodd" d="M10.5 3.75a6.75 6.75 0 1 0 0 13.5 6.75 6.75 0 0 0 0-13.5ZM2.25 10.5a8.25 8.25 0 1 1 14.59 5.28l4.69 4.69a.75.75 0 1 1-1.06 1.06l-4.69-4.69A8.25 8.25 0 0 1 2.25 10.5Z" clip-rule="evenodd" />
+            </svg>
+          {:else}
+            <svg xmlns="http://www.w3.org/2000/svg" fill="none" viewBox="0 0 24 24" stroke-width="1.5" stroke="currentColor" class="w-4 h-4">
+              <path stroke-linecap="round" stroke-linejoin="round" d="m21 21-5.197-5.197m0 0A7.5 7.5 0 1 0 5.196 5.196a7.5 7.5 0 0 0 10.607 10.607Z" />
+            </svg>
+          {/if}
+        </button>
+      </div>
+    </div>
+
+    {#if $showFilterStore}
+      <div class="mt-2 flex gap-2 items-center w-full">
+        <input
+          type="text"
+          class="w-full text-sm border border-gray-950/10 dark:border-white/5 p-2 rounded outline-none"
+          placeholder="Filter logs (regex)..."
+          bind:value={filterRegex}
+        />
+        <button class="pl-2" onclick={() => (filterRegex = "")} aria-label="Clear filter">
+          <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor" class="w-6 h-6">
+            <path fill-rule="evenodd" d="M12 2.25c-5.385 0-9.75 4.365-9.75 9.75s4.365 9.75 9.75 9.75 9.75-4.365 9.75-9.75S17.385 2.25 12 2.25Zm-1.72 6.97a.75.75 0 1 0-1.06 1.06L10.94 12l-1.72 1.72a.75.75 0 1 0 1.06 1.06L12 13.06l1.72 1.72a.75.75 0 1 0 1.06-1.06L13.06 12l1.72-1.72a.75.75 0 1 0-1.06-1.06L12 10.94l-1.72-1.72Z" clip-rule="evenodd" />
+          </svg>
+        </button>
+      </div>
+    {/if}
+  </div>
+  <div class="rounded-lg bg-background font-mono text-sm flex-1 overflow-hidden">
+    <pre bind:this={preElement} class="{textWrapClass} {fontSizeClass} h-full overflow-auto p-4">{filteredLogs}</pre>
+  </div>
+</div>

ui-svelte/src/components/ModelsPanel.svelte

@@ -0,0 +1,208 @@
+<script lang="ts">
+  import { models, loadModel, unloadAllModels, unloadSingleModel } from "../stores/api";
+  import { isNarrow } from "../stores/theme";
+  import { persistentStore } from "../stores/persistent";
+  import type { Model } from "../lib/types";
+
+  let isUnloading = $state(false);
+  let menuOpen = $state(false);
+
+  const showUnlistedStore = persistentStore<boolean>("showUnlisted", true);
+  const showIdorNameStore = persistentStore<"id" | "name">("showIdorName", "id");
+
+  let filteredModels = $derived.by(() => {
+    const filtered = $models.filter((model) => $showUnlistedStore || !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, Model[]>
+    );
+
+    return {
+      regularModels: filtered.filter((m) => !m.peerID),
+      peerModelsByPeerId: grouped,
+    };
+  });
+
+  async function handleUnloadAllModels(): Promise<void> {
+    isUnloading = true;
+    try {
+      await unloadAllModels();
+    } catch (e) {
+      console.error(e);
+    } finally {
+      setTimeout(() => (isUnloading = false), 1000);
+    }
+  }
+
+  function toggleIdorName(): void {
+    showIdorNameStore.update((prev) => (prev === "name" ? "id" : "name"));
+  }
+
+  function toggleShowUnlisted(): void {
+    showUnlistedStore.update((prev) => !prev);
+  }
+
+  function getModelDisplay(model: Model): string {
+    return $showIdorNameStore === "id" ? model.id : (model.name || model.id);
+  }
+</script>
+
+<div class="card h-full flex flex-col">
+  <div class="shrink-0">
+    <div class="flex justify-between items-baseline">
+      <h2 class={$isNarrow ? "text-xl" : ""}>Models</h2>
+      {#if $isNarrow}
+        <div class="relative">
+          <button class="btn text-base flex items-center gap-2 py-1" onclick={() => (menuOpen = !menuOpen)} aria-label="Toggle menu">
+            <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor" class="w-5 h-5">
+              <path fill-rule="evenodd" d="M3 6.75A.75.75 0 0 1 3.75 6h16.5a.75.75 0 0 1 0 1.5H3.75A.75.75 0 0 1 3 6.75ZM3 12a.75.75 0 0 1 .75-.75h16.5a.75.75 0 0 1 0 1.5H3.75A.75.75 0 0 1 3 12Zm0 5.25a.75.75 0 0 1 .75-.75h16.5a.75.75 0 0 1 0 1.5H3.75a.75.75 0 0 1-.75-.75Z" clip-rule="evenodd" />
+            </svg>
+          </button>
+          {#if menuOpen}
+            <div class="absolute right-0 mt-2 w-48 bg-surface border border-gray-200 dark:border-white/10 rounded shadow-lg z-20">
+              <button
+                class="w-full text-left px-4 py-2 hover:bg-secondary-hover flex items-center gap-2"
+                onclick={() => { toggleIdorName(); menuOpen = false; }}
+              >
+                <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor" class="w-5 h-5">
+                  <path fill-rule="evenodd" d="M15.97 2.47a.75.75 0 0 1 1.06 0l4.5 4.5a.75.75 0 0 1 0 1.06l-4.5 4.5a.75.75 0 1 1-1.06-1.06l3.22-3.22H7.5a.75.75 0 0 1 0-1.5h11.69l-3.22-3.22a.75.75 0 0 1 0-1.06Zm-7.94 9a.75.75 0 0 1 0 1.06l-3.22 3.22H16.5a.75.75 0 0 1 0 1.5H4.81l3.22 3.22a.75.75 0 1 1-1.06 1.06l-4.5-4.5a.75.75 0 0 1 0-1.06l4.5-4.5a.75.75 0 0 1 1.06 0Z" clip-rule="evenodd" />
+                </svg>
+                {$showIdorNameStore === "id" ? "Show Name" : "Show ID"}
+              </button>
+              <button
+                class="w-full text-left px-4 py-2 hover:bg-secondary-hover flex items-center gap-2"
+                onclick={() => { toggleShowUnlisted(); menuOpen = false; }}
+              >
+                {#if $showUnlistedStore}
+                  <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor" class="w-5 h-5">
+                    <path d="M3.53 2.47a.75.75 0 0 0-1.06 1.06l18 18a.75.75 0 1 0 1.06-1.06l-18-18ZM22.676 12.553a11.249 11.249 0 0 1-2.631 4.31l-3.099-3.099a5.25 5.25 0 0 0-6.71-6.71L7.759 4.577a11.217 11.217 0 0 1 4.242-.827c4.97 0 9.185 3.223 10.675 7.69.12.362.12.752 0 1.113Z" />
+                    <path d="M15.75 12c0 .18-.013.357-.037.53l-4.244-4.243A3.75 3.75 0 0 1 15.75 12ZM12.53 15.713l-4.243-4.244a3.75 3.75 0 0 0 4.244 4.243Z" />
+                    <path d="M6.75 12c0-.619.107-1.213.304-1.764l-3.1-3.1a11.25 11.25 0 0 0-2.63 4.31c-.12.362-.12.752 0 1.114 1.489 4.467 5.704 7.69 10.675 7.69 1.5 0 2.933-.294 4.242-.827l-2.477-2.477A5.25 5.25 0 0 1 6.75 12Z" />
+                  </svg>
+                {:else}
+                  <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor" class="w-5 h-5">
+                    <path d="M12 15a3 3 0 1 0 0-6 3 3 0 0 0 0 6Z" />
+                    <path fill-rule="evenodd" d="M1.323 11.447C2.811 6.976 7.028 3.75 12.001 3.75c4.97 0 9.185 3.223 10.675 7.69.12.362.12.752 0 1.113-1.487 4.471-5.705 7.697-10.677 7.697-4.97 0-9.186-3.223-10.675-7.69a1.762 1.762 0 0 1 0-1.113ZM17.25 12a5.25 5.25 0 1 1-10.5 0 5.25 5.25 0 0 1 10.5 0Z" clip-rule="evenodd" />
+                  </svg>
+                {/if}
+                {$showUnlistedStore ? "Hide Unlisted" : "Show Unlisted"}
+              </button>
+              <button
+                class="w-full text-left px-4 py-2 hover:bg-secondary-hover flex items-center gap-2"
+                onclick={() => { handleUnloadAllModels(); menuOpen = false; }}
+                disabled={isUnloading}
+              >
+                <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor" class="w-6 h-6">
+                  <path fill-rule="evenodd" d="M12 2.25c-5.385 0-9.75 4.365-9.75 9.75s4.365 9.75 9.75 9.75 9.75-4.365 9.75-9.75S17.385 2.25 12 2.25Zm.53 5.47a.75.75 0 0 0-1.06 0l-3 3a.75.75 0 1 0 1.06 1.06l1.72-1.72v5.69a.75.75 0 0 0 1.5 0v-5.69l1.72 1.72a.75.75 0 1 0 1.06-1.06l-3-3Z" clip-rule="evenodd" />
+                </svg>
+                {isUnloading ? "Unloading..." : "Unload All"}
+              </button>
+            </div>
+          {/if}
+        </div>
+      {/if}
+    </div>
+    {#if !$isNarrow}
+      <div class="flex justify-between">
+        <div class="flex gap-2">
+          <button class="btn text-base flex items-center gap-2" onclick={toggleIdorName} style="line-height: 1.2">
+            <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor" class="w-5 h-5">
+              <path fill-rule="evenodd" d="M15.97 2.47a.75.75 0 0 1 1.06 0l4.5 4.5a.75.75 0 0 1 0 1.06l-4.5 4.5a.75.75 0 1 1-1.06-1.06l3.22-3.22H7.5a.75.75 0 0 1 0-1.5h11.69l-3.22-3.22a.75.75 0 0 1 0-1.06Zm-7.94 9a.75.75 0 0 1 0 1.06l-3.22 3.22H16.5a.75.75 0 0 1 0 1.5H4.81l3.22 3.22a.75.75 0 1 1-1.06 1.06l-4.5-4.5a.75.75 0 0 1 0-1.06l4.5-4.5a.75.75 0 0 1 1.06 0Z" clip-rule="evenodd" />
+            </svg>
+            {$showIdorNameStore === "id" ? "ID" : "Name"}
+          </button>
+
+          <button class="btn text-base flex items-center gap-2" onclick={toggleShowUnlisted} style="line-height: 1.2">
+            {#if $showUnlistedStore}
+              <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor" class="w-5 h-5">
+                <path d="M12 15a3 3 0 1 0 0-6 3 3 0 0 0 0 6Z" />
+                <path fill-rule="evenodd" d="M1.323 11.447C2.811 6.976 7.028 3.75 12.001 3.75c4.97 0 9.185 3.223 10.675 7.69.12.362.12.752 0 1.113-1.487 4.471-5.705 7.697-10.677 7.697-4.97 0-9.186-3.223-10.675-7.69a1.762 1.762 0 0 1 0-1.113ZM17.25 12a5.25 5.25 0 1 1-10.5 0 5.25 5.25 0 0 1 10.5 0Z" clip-rule="evenodd" />
+              </svg>
+            {:else}
+              <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor" class="w-5 h-5">
+                <path d="M3.53 2.47a.75.75 0 0 0-1.06 1.06l18 18a.75.75 0 1 0 1.06-1.06l-18-18ZM22.676 12.553a11.249 11.249 0 0 1-2.631 4.31l-3.099-3.099a5.25 5.25 0 0 0-6.71-6.71L7.759 4.577a11.217 11.217 0 0 1 4.242-.827c4.97 0 9.185 3.223 10.675 7.69.12.362.12.752 0 1.113Z" />
+                <path d="M15.75 12c0 .18-.013.357-.037.53l-4.244-4.243A3.75 3.75 0 0 1 15.75 12ZM12.53 15.713l-4.243-4.244a3.75 3.75 0 0 0 4.244 4.243Z" />
+                <path d="M6.75 12c0-.619.107-1.213.304-1.764l-3.1-3.1a11.25 11.25 0 0 0-2.63 4.31c-.12.362-.12.752 0 1.114 1.489 4.467 5.704 7.69 10.675 7.69 1.5 0 2.933-.294 4.242-.827l-2.477-2.477A5.25 5.25 0 0 1 6.75 12Z" />
+              </svg>
+            {/if}
+            unlisted
+          </button>
+        </div>
+        <button class="btn text-base flex items-center gap-2" onclick={handleUnloadAllModels} disabled={isUnloading}>
+          <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor" class="w-6 h-6">
+            <path fill-rule="evenodd" d="M12 2.25c-5.385 0-9.75 4.365-9.75 9.75s4.365 9.75 9.75 9.75 9.75-4.365 9.75-9.75S17.385 2.25 12 2.25Zm.53 5.47a.75.75 0 0 0-1.06 0l-3 3a.75.75 0 1 0 1.06 1.06l1.72-1.72v5.69a.75.75 0 0 0 1.5 0v-5.69l1.72 1.72a.75.75 0 1 0 1.06-1.06l-3-3Z" clip-rule="evenodd" />
+          </svg>
+          {isUnloading ? "Unloading..." : "Unload All"}
+        </button>
+      </div>
+    {/if}
+  </div>
+
+  <div class="flex-1 overflow-y-auto">
+    <table class="w-full">
+      <thead class="sticky top-0 bg-card z-10">
+        <tr class="text-left border-b border-gray-200 dark:border-white/10 bg-surface">
+          <th>{$showIdorNameStore === "id" ? "Model ID" : "Name"}</th>
+          <th></th>
+          <th>State</th>
+        </tr>
+      </thead>
+      <tbody>
+        {#each filteredModels.regularModels as model (model.id)}
+          <tr class="border-b hover:bg-secondary-hover border-gray-200">
+            <td class={model.unlisted ? "text-txtsecondary" : ""}>
+              <a href="/upstream/{model.id}/" class="font-semibold" target="_blank">
+                {getModelDisplay(model)}
+              </a>
+              {#if model.description}
+                <p class={model.unlisted ? "text-opacity-70" : ""}><em>{model.description}</em></p>
+              {/if}
+            </td>
+            <td class="w-12">
+              {#if model.state === "stopped"}
+                <button class="btn btn--sm" onclick={() => loadModel(model.id)}>Load</button>
+              {:else}
+                <button class="btn btn--sm" onclick={() => unloadSingleModel(model.id)} disabled={model.state !== "ready"}>Unload</button>
+              {/if}
+            </td>
+            <td class="w-20">
+              <span class="w-16 text-center status status--{model.state}">{model.state}</span>
+            </td>
+          </tr>
+        {/each}
+      </tbody>
+    </table>
+
+    {#if Object.keys(filteredModels.peerModelsByPeerId).length > 0}
+      <h3 class="mt-8 mb-2">Peer Models</h3>
+      {#each Object.entries(filteredModels.peerModelsByPeerId).sort(([a], [b]) => a.localeCompare(b)) as [peerId, peerModels] (peerId)}
+        <div class="mb-4">
+          <table class="w-full">
+            <thead class="sticky top-0 bg-card z-10">
+              <tr class="text-left border-b border-gray-200 dark:border-white/10 bg-surface">
+                <th class="font-semibold">{peerId}</th>
+              </tr>
+            </thead>
+            <tbody>
+              {#each peerModels as model (model.id)}
+                <tr class="border-b hover:bg-secondary-hover border-gray-200">
+                  <td class="pl-8 {model.unlisted ? 'text-txtsecondary' : ''}">
+                    <span>{model.id}</span>
+                  </td>
+                </tr>
+              {/each}
+            </tbody>
+          </table>
+        </div>
+      {/each}
+    {/if}
+  </div>
+</div>

ui-svelte/src/components/ResizablePanels.svelte

@@ -0,0 +1,152 @@
+<script lang="ts">
+  import type { Snippet } from "svelte";
+  import { onMount } from "svelte";
+
+  interface Props {
+    direction: "horizontal" | "vertical";
+    storageKey: string;
+    leftPanel: Snippet;
+    rightPanel: Snippet;
+    defaultSize?: number;
+    minSize?: number;
+  }
+
+  let { direction, storageKey, leftPanel, rightPanel, defaultSize = 50, minSize = 5 }: Props = $props();
+
+  let containerRef: HTMLDivElement;
+  let isDragging = $state(false);
+  // svelte-ignore state_referenced_locally
+  let leftSize = $state(defaultSize);
+
+  // Load saved size from localStorage
+  onMount(() => {
+    const saved = localStorage.getItem(`panel-size-${storageKey}`);
+    if (saved) {
+      const parsed = parseFloat(saved);
+      if (!isNaN(parsed) && parsed >= minSize && parsed <= 100 - minSize) {
+        leftSize = parsed;
+      }
+    }
+  });
+
+  function saveSize(): void {
+    localStorage.setItem(`panel-size-${storageKey}`, String(leftSize));
+  }
+
+  function handleMouseDown(e: MouseEvent): void {
+    e.preventDefault();
+    isDragging = true;
+    document.addEventListener("mousemove", handleMouseMove);
+    document.addEventListener("mouseup", handleMouseUp);
+  }
+
+  function handleTouchStart(_e: TouchEvent): void {
+    isDragging = true;
+    document.addEventListener("touchmove", handleTouchMove);
+    document.addEventListener("touchend", handleTouchEnd);
+  }
+
+  function handleMouseMove(e: MouseEvent): void {
+    if (!isDragging || !containerRef) return;
+    updateSize(e.clientX, e.clientY);
+  }
+
+  function handleTouchMove(e: TouchEvent): void {
+    if (!isDragging || !containerRef || e.touches.length === 0) return;
+    updateSize(e.touches[0].clientX, e.touches[0].clientY);
+  }
+
+  function updateSize(clientX: number, clientY: number): void {
+    const rect = containerRef.getBoundingClientRect();
+
+    let newSize: number;
+    if (direction === "horizontal") {
+      newSize = ((clientX - rect.left) / rect.width) * 100;
+    } else {
+      newSize = ((clientY - rect.top) / rect.height) * 100;
+    }
+
+    // Clamp size
+    newSize = Math.max(minSize, Math.min(100 - minSize, newSize));
+    leftSize = newSize;
+  }
+
+  function handleMouseUp(): void {
+    isDragging = false;
+    saveSize();
+    document.removeEventListener("mousemove", handleMouseMove);
+    document.removeEventListener("mouseup", handleMouseUp);
+  }
+
+  function handleTouchEnd(): void {
+    isDragging = false;
+    saveSize();
+    document.removeEventListener("touchmove", handleTouchMove);
+    document.removeEventListener("touchend", handleTouchEnd);
+  }
+
+  function handleKeyDown(e: KeyboardEvent): void {
+    const step = 2; // 2% increment for keyboard navigation
+    const key = e.key;
+
+    if (direction === "horizontal" && (key === "ArrowLeft" || key === "ArrowRight")) {
+      e.preventDefault();
+      const delta = key === "ArrowLeft" ? -step : step;
+      const newSize = Math.max(minSize, Math.min(100 - minSize, leftSize + delta));
+      leftSize = newSize;
+      saveSize();
+    } else if (direction === "vertical" && (key === "ArrowUp" || key === "ArrowDown")) {
+      e.preventDefault();
+      const delta = key === "ArrowUp" ? -step : step;
+      const newSize = Math.max(minSize, Math.min(100 - minSize, leftSize + delta));
+      leftSize = newSize;
+      saveSize();
+    }
+  }
+
+  let containerClass = $derived(direction === "horizontal" ? "flex-row" : "flex-col");
+
+  let handleClass = $derived(
+    direction === "horizontal"
+      ? "w-2 h-full cursor-col-resize"
+      : "w-full h-2 cursor-row-resize"
+  );
+
+  let leftStyle = $derived(
+    direction === "horizontal"
+      ? `width: ${leftSize}%; min-width: ${minSize}%`
+      : `height: ${leftSize}%; min-height: ${minSize}%`
+  );
+
+  let rightStyle = $derived(
+    direction === "horizontal"
+      ? `width: ${100 - leftSize}%; min-width: ${minSize}%`
+      : `height: ${100 - leftSize}%; min-height: ${minSize}%`
+  );
+</script>
+
+<div bind:this={containerRef} class="flex {containerClass} h-full w-full gap-2">
+  <div style={leftStyle} class="overflow-hidden">
+    {@render leftPanel()}
+  </div>
+
+  <!-- svelte-ignore a11y_no_noninteractive_tabindex -->
+  <!-- svelte-ignore a11y_no_noninteractive_element_interactions -->
+  <div
+    role="separator"
+    tabindex="0"
+    class="{handleClass} bg-primary hover:bg-success transition-colors rounded flex-shrink-0"
+    onmousedown={handleMouseDown}
+    ontouchstart={handleTouchStart}
+    onkeydown={handleKeyDown}
+    aria-label="Resize panels"
+    aria-orientation={direction}
+    aria-valuenow={Math.round(leftSize)}
+    aria-valuemin={minSize}
+    aria-valuemax={100 - minSize}
+  ></div>
+
+  <div style={rightStyle} class="overflow-hidden">
+    {@render rightPanel()}
+  </div>
+</div>

ui-svelte/src/components/StatsPanel.svelte

@@ -0,0 +1,147 @@
+<script lang="ts">
+  import { metrics } from "../stores/api";
+  import TokenHistogram from "./TokenHistogram.svelte";
+
+  interface HistogramData {
+    bins: number[];
+    min: number;
+    max: number;
+    binSize: number;
+    p99: number;
+    p95: number;
+    p50: number;
+  }
+
+  let stats = $derived.by(() => {
+    const totalRequests = $metrics.length;
+    if (totalRequests === 0) {
+      return { totalRequests: 0, totalInputTokens: 0, totalOutputTokens: 0, tokenStats: { p99: "0", p95: "0", p50: "0" }, histogramData: null };
+    }
+
+    const totalInputTokens = $metrics.reduce((sum, m) => sum + m.input_tokens, 0);
+    const totalOutputTokens = $metrics.reduce((sum, m) => sum + m.output_tokens, 0);
+
+    // Calculate token statistics using output_tokens and duration_ms
+    const validMetrics = $metrics.filter((m) => m.duration_ms > 0 && m.output_tokens > 0);
+    if (validMetrics.length === 0) {
+      return { totalRequests, totalInputTokens, totalOutputTokens, tokenStats: { p99: "0", p95: "0", p50: "0" }, histogramData: null };
+    }
+
+    // Calculate tokens/second for each valid metric
+    const tokensPerSecond = validMetrics.map((m) => m.output_tokens / (m.duration_ms / 1000));
+
+    // Sort for percentile calculation
+    const sortedTokensPerSecond = [...tokensPerSecond].sort((a, b) => a - b);
+
+    const p99 = sortedTokensPerSecond[Math.floor(sortedTokensPerSecond.length * 0.99)];
+    const p95 = sortedTokensPerSecond[Math.floor(sortedTokensPerSecond.length * 0.95)];
+    const p50 = sortedTokensPerSecond[Math.floor(sortedTokensPerSecond.length * 0.5)];
+
+    // Create histogram data
+    const min = Math.min(...tokensPerSecond);
+    const max = Math.max(...tokensPerSecond);
+    const binCount = Math.min(30, Math.max(10, Math.floor(tokensPerSecond.length / 5)));
+    const binSize = (max - min) / binCount;
+
+    const bins = Array(binCount).fill(0);
+    tokensPerSecond.forEach((value) => {
+      const binIndex = Math.min(Math.floor((value - min) / binSize), binCount - 1);
+      bins[binIndex]++;
+    });
+
+    const histogramData: HistogramData = {
+      bins,
+      min,
+      max,
+      binSize,
+      p99,
+      p95,
+      p50,
+    };
+
+    return {
+      totalRequests,
+      totalInputTokens,
+      totalOutputTokens,
+      tokenStats: {
+        p99: p99.toFixed(2),
+        p95: p95.toFixed(2),
+        p50: p50.toFixed(2),
+      },
+      histogramData,
+    };
+  });
+
+  const nf = new Intl.NumberFormat();
+</script>
+
+<div class="card">
+  <div class="rounded-lg overflow-hidden border border-card-border-inner">
+    <table class="min-w-full divide-y divide-card-border-inner">
+      <thead class="bg-secondary">
+        <tr>
+          <th class="px-4 py-3 text-left text-xs font-semibold uppercase tracking-wider text-txtmain">Requests</th>
+          <th class="px-4 py-3 text-left text-xs font-semibold uppercase tracking-wider text-txtmain border-l border-card-border-inner">
+            Processed
+          </th>
+          <th class="px-4 py-3 text-left text-xs font-semibold uppercase tracking-wider text-txtmain border-l border-card-border-inner">
+            Generated
+          </th>
+          <th class="px-4 py-3 text-left text-xs font-semibold uppercase tracking-wider text-txtmain border-l border-card-border-inner">
+            Token Stats (tokens/sec)
+          </th>
+        </tr>
+      </thead>
+
+      <tbody class="bg-surface divide-y divide-card-border-inner">
+        <tr class="hover:bg-secondary">
+          <td class="px-4 py-4 text-sm font-semibold text-gray-900 dark:text-white">{stats.totalRequests}</td>
+
+          <td class="px-4 py-4 text-sm text-gray-700 dark:text-gray-300 border-l border-gray-200 dark:border-white/10">
+            <div class="flex items-center gap-2">
+              <span class="text-sm font-medium">{nf.format(stats.totalInputTokens)}</span>
+              <span class="text-xs text-gray-500 dark:text-gray-400">tokens</span>
+            </div>
+          </td>
+
+          <td class="px-4 py-4 text-sm text-gray-700 dark:text-gray-300 border-l border-gray-200 dark:border-white/10">
+            <div class="flex items-center gap-2">
+              <span class="text-sm font-medium">{nf.format(stats.totalOutputTokens)}</span>
+              <span class="text-xs text-gray-500 dark:text-gray-400">tokens</span>
+            </div>
+          </td>
+
+          <td class="px-4 py-4 border-l border-gray-200 dark:border-white/10">
+            <div class="space-y-3">
+              <div class="grid grid-cols-3 gap-2 items-center">
+                <div class="text-center">
+                  <div class="text-xs text-gray-500 dark:text-gray-400">P50</div>
+                  <div class="mt-1 inline-block rounded-full bg-gray-100 dark:bg-white/5 px-3 py-1 text-sm font-semibold text-gray-800 dark:text-white">
+                    {stats.tokenStats.p50}
+                  </div>
+                </div>
+
+                <div class="text-center">
+                  <div class="text-xs text-gray-500 dark:text-gray-400">P95</div>
+                  <div class="mt-1 inline-block rounded-full bg-gray-100 dark:bg-white/5 px-3 py-1 text-sm font-semibold text-gray-800 dark:text-white">
+                    {stats.tokenStats.p95}
+                  </div>
+                </div>
+
+                <div class="text-center">
+                  <div class="text-xs text-gray-500 dark:text-gray-400">P99</div>
+                  <div class="mt-1 inline-block rounded-full bg-gray-100 dark:bg-white/5 px-3 py-1 text-sm font-semibold text-gray-800 dark:text-white">
+                    {stats.tokenStats.p99}
+                  </div>
+                </div>
+              </div>
+              {#if stats.histogramData}
+                <TokenHistogram data={stats.histogramData} />
+              {/if}
+            </div>
+          </td>
+        </tr>
+      </tbody>
+    </table>
+  </div>
+</div>

ui-svelte/src/components/TokenHistogram.svelte

@@ -0,0 +1,129 @@
+<script lang="ts">
+  interface HistogramData {
+    bins: number[];
+    min: number;
+    max: number;
+    binSize: number;
+    p99: number;
+    p95: number;
+    p50: number;
+  }
+
+  interface Props {
+    data: HistogramData;
+  }
+
+  let { data }: Props = $props();
+
+  const height = 120;
+  const padding = { top: 10, right: 15, bottom: 25, left: 45 };
+  const viewBoxWidth = 600;
+  const chartWidth = viewBoxWidth - padding.left - padding.right;
+  const chartHeight = height - padding.top - padding.bottom;
+
+  let maxCount = $derived(Math.max(...data.bins));
+  let barWidth = $derived(chartWidth / data.bins.length);
+  let range = $derived(data.max - data.min);
+
+  function getXPosition(value: number): number {
+    return padding.left + ((value - data.min) / range) * chartWidth;
+  }
+</script>
+
+<div class="mt-2 w-full">
+  <svg viewBox="0 0 {viewBoxWidth} {height}" class="w-full h-auto" preserveAspectRatio="xMidYMid meet">
+    <!-- Y-axis -->
+    <line
+      x1={padding.left}
+      y1={padding.top}
+      x2={padding.left}
+      y2={height - padding.bottom}
+      stroke="currentColor"
+      stroke-width="1"
+      opacity="0.3"
+    />
+
+    <!-- X-axis -->
+    <line
+      x1={padding.left}
+      y1={height - padding.bottom}
+      x2={viewBoxWidth - padding.right}
+      y2={height - padding.bottom}
+      stroke="currentColor"
+      stroke-width="1"
+      opacity="0.3"
+    />
+
+    <!-- Histogram bars -->
+    {#each data.bins as count, i}
+      {@const barHeight = maxCount > 0 ? (count / maxCount) * chartHeight : 0}
+      {@const x = padding.left + i * barWidth}
+      {@const y = height - padding.bottom - barHeight}
+      {@const binStart = data.min + i * data.binSize}
+      {@const binEnd = binStart + data.binSize}
+      <g>
+        <rect
+          {x}
+          {y}
+          width={Math.max(barWidth - 1, 1)}
+          height={barHeight}
+          fill="currentColor"
+          opacity="0.6"
+          class="text-blue-500 dark:text-blue-400 hover:opacity-90 transition-opacity cursor-pointer"
+        />
+        <title>{`${binStart.toFixed(1)} - ${binEnd.toFixed(1)} tokens/sec\nCount: ${count}`}</title>
+      </g>
+    {/each}
+
+    <!-- Percentile lines -->
+    <line
+      x1={getXPosition(data.p50)}
+      y1={padding.top}
+      x2={getXPosition(data.p50)}
+      y2={height - padding.bottom}
+      stroke="currentColor"
+      stroke-width="2"
+      stroke-dasharray="4 2"
+      opacity="0.7"
+      class="text-gray-600 dark:text-gray-400"
+    />
+
+    <line
+      x1={getXPosition(data.p95)}
+      y1={padding.top}
+      x2={getXPosition(data.p95)}
+      y2={height - padding.bottom}
+      stroke="currentColor"
+      stroke-width="2"
+      stroke-dasharray="4 2"
+      opacity="0.7"
+      class="text-orange-500 dark:text-orange-400"
+    />
+
+    <line
+      x1={getXPosition(data.p99)}
+      y1={padding.top}
+      x2={getXPosition(data.p99)}
+      y2={height - padding.bottom}
+      stroke="currentColor"
+      stroke-width="2"
+      stroke-dasharray="4 2"
+      opacity="0.7"
+      class="text-green-500 dark:text-green-400"
+    />
+
+    <!-- X-axis labels -->
+    <text x={padding.left} y={height - 5} font-size="10" fill="currentColor" opacity="0.6" text-anchor="start">
+      {data.min.toFixed(1)}
+    </text>
+
+    <text x={viewBoxWidth - padding.right} y={height - 5} font-size="10" fill="currentColor" opacity="0.6" text-anchor="end">
+      {data.max.toFixed(1)}
+    </text>
+
+    <!-- X-axis label -->
+    <text x={padding.left + chartWidth / 2} y={height - 2} font-size="10" fill="currentColor" opacity="0.6" text-anchor="middle">
+      Tokens/Second Distribution
+    </text>
+  </svg>
+</div>

ui-svelte/src/components/Tooltip.svelte

@@ -0,0 +1,20 @@
+<script lang="ts">
+  interface Props {
+    content: string;
+  }
+
+  let { content }: Props = $props();
+</script>
+
+<div class="relative group inline-block">
+  <span class="cursor-help">&#9432;</span>
+  <div
+    class="absolute top-full left-1/2 transform -translate-x-1/2 mt-2
+           px-3 py-2 bg-gray-900 text-white text-sm rounded-md
+           opacity-0 group-hover:opacity-100 transition-opacity
+           duration-200 pointer-events-none whitespace-nowrap z-50 normal-case"
+  >
+    {content}
+    <div class="absolute bottom-full left-1/2 transform -translate-x-1/2 border-4 border-transparent border-b-gray-900"></div>
+  </div>
+</div>

ui-svelte/src/index.css

@@ -0,0 +1,176 @@
+@import "tailwindcss";
+@custom-variant dark (&:where([data-theme=dark], [data-theme=dark] *));
+
+@theme {
+  --color-background: rgba(252, 252, 249, 1);
+  --color-surface: rgba(255, 255, 253, 1);
+
+  /* text colors */
+  --color-txtmain: rgba(19, 52, 59, 1);
+  --color-txtsecondary: rgba(98, 108, 113, 1);
+  --color-navlink-active: rgba(245, 245, 245, 1);
+
+  --color-primary: rgba(50, 184, 198, 1);
+
+  --color-primary-hover: rgba(29, 116, 128, 1);
+  --color-primary-active: rgba(26, 104, 115, 1);
+  --color-secondary: rgba(94, 82, 64, 0.12);
+  --color-secondary-hover: rgba(94, 82, 64, 0.2);
+  --color-secondary-active: rgba(94, 82, 64, 0.25);
+  --color-border: rgba(94, 82, 64, 0.3);
+  --color-btn-primary-text: rgba(252, 252, 249, 1);
+  --color-card-border: rgba(94, 82, 64, 0.12);
+  --color-card-border-inner: rgba(94, 82, 64, 0.12);
+  --color-error: rgba(192, 21, 47, 1);
+  --color-success: rgba(33, 128, 141, 1);
+  --color-warning: rgb(244, 155, 0);
+  --color-info: rgba(98, 108, 113, 1);
+  --color-focus-ring: rgba(33, 128, 141, 0.4);
+  --color-select-caret: rgba(19, 52, 59, 0.8);
+  --color-btn-border: rgba(94, 82, 64, 0.7);
+}
+
+@layer theme {
+  /* over ride theme for dark mode */
+  [data-theme="dark"] {
+    --color-background: rgba(31, 33, 33, 1);
+    --color-surface: rgba(38, 40, 40, 1);
+    /* text colors */
+    --color-txtmain: rgba(245, 245, 245, 1);
+    --color-txtsecondary: rgba(167, 169, 169, 0.7);
+
+    --color-navlink-active: rgba(245, 245, 245, 1);
+
+    --color-primary: rgba(33, 128, 141, 1);
+    --color-primary-hover: rgba(45, 166, 178, 1);
+    --color-primary-active: rgba(41, 150, 161, 1);
+    --color-secondary: rgba(119, 124, 124, 0.15);
+    --color-secondary-hover: rgba(119, 124, 124, 0.25);
+    --color-secondary-active: rgba(119, 124, 124, 0.3);
+    --color-border: rgba(119, 124, 124, 0.3);
+    --color-error: rgba(255, 84, 89, 1);
+    --color-success: rgba(50, 184, 198, 1);
+    --color-warning: rgb(244, 155, 0);
+    --color-info: rgba(167, 169, 169, 1);
+    --color-focus-ring: rgba(50, 184, 198, 0.4);
+    --color-btn-primary-text: rgba(19, 52, 59, 1);
+    --color-card-border: rgba(119, 124, 124, 0.2);
+    --color-card-border-inner: rgba(119, 124, 124, 0.15);
+    --shadow-inset-sm: inset 0 1px 0 rgba(255, 255, 255, 0.1), inset 0 -1px 0 rgba(0, 0, 0, 0.15);
+    --button-border-secondary: rgba(119, 124, 124, 0.2);
+  }
+}
+
+@layer base {
+  body {
+    /* example of how colors using theme colors*/
+    @apply bg-background text-txtmain;
+  }
+
+  h1 {
+    @apply text-4xl text-txtmain font-bold pb-4;
+  }
+  h2 {
+    @apply text-3xl text-txtmain font-bold pb-4;
+  }
+  h3 {
+    @apply text-2xl text-txtmain font-bold pb-4;
+  }
+  h4 {
+    @apply text-xl text-txtmain font-bold pb-4;
+  }
+  h5 {
+    @apply text-lg text-txtmain font-bold pb-4;
+  }
+  h6 {
+    @apply text-base text-txtmain font-bold pb-4;
+  }
+}
+
+/* define CSS classes here for specific types of components */
+@layer components {
+  .container {
+    @apply px-4;
+  }
+
+  /* Tables */
+  table th {
+    @apply p-2 font-semibold;
+  }
+  table td {
+    @apply p-2;
+  }
+
+  /* Navigation Header */
+
+  .navlink {
+    @apply text-txtsecondary hover:bg-secondary hover:text-txtmain rounded-lg p-2;
+  }
+  .navlink.active {
+    @apply bg-primary text-navlink-active;
+  }
+
+  /* Card component */
+  .card {
+    @apply bg-surface rounded-lg border border-card-border shadow-sm overflow-hidden p-4;
+  }
+
+  .card:hover {
+    @apply shadow-md;
+  }
+
+  .card__body {
+    @apply p-4;
+  }
+
+  .card__header,
+  .card__footer {
+    @apply p-4 border-b border-card-border-inner;
+  }
+
+  /* Status Badges */
+  .status {
+    @apply inline-block px-2 py-1 text-xs font-medium rounded-lg;
+  }
+
+  .status--ready {
+    @apply bg-success/10 text-success;
+  }
+
+  .status--starting,
+  .status--stopping {
+    @apply bg-warning/10 text-warning;
+  }
+
+  .status--stopped {
+    @apply bg-error/10 text-error;
+  }
+
+  /* Buttons */
+  .btn {
+    @apply bg-surface py-2 px-4 text-sm rounded-md border transition-colors duration-200 border-btn-border;
+  }
+
+  .btn:hover {
+    cursor: pointer;
+  }
+
+  .btn--sm {
+    @apply px-2 py-0.5 text-xs;
+  }
+
+  .btn:disabled {
+    @apply opacity-50 cursor-not-allowed;
+  }
+}
+
+@layer utilities {
+  .ml-2 {
+    margin-left: 0.5rem;
+  }
+
+  .my-8 {
+    margin-top: 2rem;
+    margin-bottom: 2rem;
+  }
+}

ui-svelte/src/lib/types.ts

@@ -0,0 +1,42 @@
+export type ConnectionState = "connected" | "connecting" | "disconnected";
+
+export type ModelStatus = "ready" | "starting" | "stopping" | "stopped" | "shutdown" | "unknown";
+
+export interface Model {
+  id: string;
+  state: ModelStatus;
+  name: string;
+  description: string;
+  unlisted: boolean;
+  peerID: string;
+}
+
+export interface Metrics {
+  id: number;
+  timestamp: string;
+  model: string;
+  cache_tokens: number;
+  input_tokens: number;
+  output_tokens: number;
+  prompt_per_second: number;
+  tokens_per_second: number;
+  duration_ms: number;
+}
+
+export interface LogData {
+  source: "upstream" | "proxy";
+  data: string;
+}
+
+export interface APIEventEnvelope {
+  type: "modelStatus" | "logData" | "metrics";
+  data: string;
+}
+
+export interface VersionInfo {
+  build_date: string;
+  commit: string;
+  version: string;
+}
+
+export type ScreenWidth = "xs" | "sm" | "md" | "lg" | "xl" | "2xl";

ui-svelte/src/main.ts

@@ -0,0 +1,9 @@
+import "./index.css";
+import App from "./App.svelte";
+import { mount } from "svelte";
+
+const app = mount(App, {
+  target: document.getElementById("app")!,
+});
+
+export default app;

ui-svelte/src/routes/Activity.svelte

@@ -0,0 +1,88 @@
+<script lang="ts">
+  import { metrics } from "../stores/api";
+  import Tooltip from "../components/Tooltip.svelte";
+
+  function formatSpeed(speed: number): string {
+    return speed < 0 ? "unknown" : speed.toFixed(2) + " t/s";
+  }
+
+  function formatDuration(ms: number): string {
+    return (ms / 1000).toFixed(2) + "s";
+  }
+
+  function formatRelativeTime(timestamp: string): string {
+    const now = new Date();
+    const date = new Date(timestamp);
+    const diffInSeconds = Math.floor((now.getTime() - date.getTime()) / 1000);
+
+    // Handle future dates by returning "just now"
+    if (diffInSeconds < 5) {
+      return "now";
+    }
+
+    if (diffInSeconds < 60) {
+      return `${diffInSeconds}s ago`;
+    }
+
+    const diffInMinutes = Math.floor(diffInSeconds / 60);
+    if (diffInMinutes < 60) {
+      return `${diffInMinutes}m ago`;
+    }
+
+    const diffInHours = Math.floor(diffInMinutes / 60);
+    if (diffInHours < 24) {
+      return `${diffInHours}h ago`;
+    }
+
+    return "a while ago";
+  }
+
+  let sortedMetrics = $derived([...$metrics].sort((a, b) => b.id - a.id));
+</script>
+
+<div class="p-2">
+  <h1 class="text-2xl font-bold">Activity</h1>
+
+  {#if $metrics.length === 0}
+    <div class="text-center py-8">
+      <p class="text-gray-600">No metrics data available</p>
+    </div>
+  {:else}
+    <div class="card overflow-auto">
+      <table class="min-w-full divide-y">
+        <thead class="border-gray-200 dark:border-white/10">
+          <tr class="text-left text-xs uppercase tracking-wider">
+            <th class="px-6 py-3">ID</th>
+            <th class="px-6 py-3">Time</th>
+            <th class="px-6 py-3">Model</th>
+            <th class="px-6 py-3">
+              Cached <Tooltip content="prompt tokens from cache" />
+            </th>
+            <th class="px-6 py-3">
+              Prompt <Tooltip content="new prompt tokens processed" />
+            </th>
+            <th class="px-6 py-3">Generated</th>
+            <th class="px-6 py-3">Prompt Processing</th>
+            <th class="px-6 py-3">Generation Speed</th>
+            <th class="px-6 py-3">Duration</th>
+          </tr>
+        </thead>
+        <tbody class="divide-y">
+          {#each sortedMetrics as metric (metric.id)}
+            <tr class="whitespace-nowrap text-sm border-gray-200 dark:border-white/10">
+              <td class="px-4 py-4">{metric.id + 1}</td>
+              <td class="px-6 py-4">{formatRelativeTime(metric.timestamp)}</td>
+              <td class="px-6 py-4">{metric.model}</td>
+              <td class="px-6 py-4">{metric.cache_tokens > 0 ? metric.cache_tokens.toLocaleString() : "-"}</td>
+              <td class="px-6 py-4">{metric.input_tokens.toLocaleString()}</td>
+              <td class="px-6 py-4">{metric.output_tokens.toLocaleString()}</td>
+              <td class="px-6 py-4">{formatSpeed(metric.prompt_per_second)}</td>
+              <td class="px-6 py-4">{formatSpeed(metric.tokens_per_second)}</td>
+              <td class="px-6 py-4">{formatDuration(metric.duration_ms)}</td>
+            </tr>
+          {/each}
+        </tbody>
+      </table>
+    </div>
+  {/if}
+</div>

ui-svelte/src/routes/LogViewer.svelte

@@ -0,0 +1,75 @@
+<script lang="ts">
+  import { proxyLogs, upstreamLogs } from "../stores/api";
+  import { screenWidth } from "../stores/theme";
+  import { persistentStore } from "../stores/persistent";
+  import LogPanel from "../components/LogPanel.svelte";
+  import ResizablePanels from "../components/ResizablePanels.svelte";
+
+  type ViewMode = "proxy" | "upstream" | "panels";
+
+  const viewModeStore = persistentStore<ViewMode>("logviewer-view-mode", "panels");
+
+  let direction = $derived<"horizontal" | "vertical">(
+    $screenWidth === "xs" || $screenWidth === "sm" ? "vertical" : "horizontal"
+  );
+
+  function cycleViewMode(): void {
+    const modes: ViewMode[] = ["panels", "proxy", "upstream"];
+    const currentIndex = modes.indexOf($viewModeStore);
+    const nextIndex = (currentIndex + 1) % modes.length;
+    viewModeStore.set(modes[nextIndex]);
+  }
+
+  function getViewModeIcon(mode: ViewMode): string {
+    switch (mode) {
+      case "proxy":
+        return "P";
+      case "upstream":
+        return "U";
+      case "panels":
+        return "⊞";
+    }
+  }
+
+  function getViewModeLabel(mode: ViewMode): string {
+    switch (mode) {
+      case "proxy":
+        return "Proxy";
+      case "upstream":
+        return "Upstream";
+      case "panels":
+        return "Panels";
+    }
+  }
+</script>
+
+<div class="flex flex-col h-full w-full gap-2">
+  <div class="flex items-center gap-2">
+    <button
+      onclick={cycleViewMode}
+      class="btn flex items-center gap-2 text-sm"
+      title="Toggle view mode"
+      aria-label="Toggle view mode: {getViewModeLabel($viewModeStore)}"
+    >
+      <span class="font-mono font-bold">{getViewModeIcon($viewModeStore)}</span>
+      <span>{getViewModeLabel($viewModeStore)}</span>
+    </button>
+  </div>
+
+  <div class="flex-1 w-full overflow-hidden">
+    {#if $viewModeStore === "panels"}
+      <ResizablePanels {direction} storageKey="logviewer-panel-group">
+        {#snippet leftPanel()}
+          <LogPanel id="proxy" title="Proxy Logs" logData={$proxyLogs} />
+        {/snippet}
+        {#snippet rightPanel()}
+          <LogPanel id="upstream" title="Upstream Logs" logData={$upstreamLogs} />
+        {/snippet}
+      </ResizablePanels>
+    {:else if $viewModeStore === "proxy"}
+      <LogPanel id="proxy" title="Proxy Logs" logData={$proxyLogs} />
+    {:else}
+      <LogPanel id="upstream" title="Upstream Logs" logData={$upstreamLogs} />
+    {/if}
+  </div>
+</div>

ui-svelte/src/routes/Models.svelte

@@ -0,0 +1,26 @@
+<script lang="ts">
+  import { isNarrow } from "../stores/theme";
+  import { upstreamLogs } from "../stores/api";
+  import ModelsPanel from "../components/ModelsPanel.svelte";
+  import StatsPanel from "../components/StatsPanel.svelte";
+  import LogPanel from "../components/LogPanel.svelte";
+  import ResizablePanels from "../components/ResizablePanels.svelte";
+
+  let direction = $derived<"horizontal" | "vertical">($isNarrow ? "vertical" : "horizontal");
+</script>
+
+<ResizablePanels {direction} storageKey="models-panel-group">
+  {#snippet leftPanel()}
+    <ModelsPanel />
+  {/snippet}
+  {#snippet rightPanel()}
+    <div class="flex flex-col h-full space-y-4">
+      {#if direction === "horizontal"}
+        <StatsPanel />
+      {/if}
+      <div class="flex-1 min-h-0">
+        <LogPanel id="modelsupstream" title="Upstream Logs" logData={$upstreamLogs} />
+      </div>
+    </div>
+  {/snippet}
+</ResizablePanels>

ui-svelte/src/stores/api.ts

@@ -0,0 +1,174 @@
+import { writable } from "svelte/store";
+import type { Model, Metrics, VersionInfo, LogData, APIEventEnvelope } from "../lib/types";
+import { connectionState } from "./theme";
+
+const LOG_LENGTH_LIMIT = 1024 * 100; /* 100KB of log data */
+
+// Stores
+export const models = writable<Model[]>([]);
+export const proxyLogs = writable<string>("");
+export const upstreamLogs = writable<string>("");
+export const metrics = writable<Metrics[]>([]);
+export const versionInfo = writable<VersionInfo>({
+  build_date: "unknown",
+  commit: "unknown",
+  version: "unknown",
+});
+
+let apiEventSource: EventSource | null = null;
+
+function appendLog(newData: string, store: typeof proxyLogs | typeof upstreamLogs): void {
+  store.update((prev) => {
+    const updatedLog = prev + newData;
+    return updatedLog.length > LOG_LENGTH_LIMIT ? updatedLog.slice(-LOG_LENGTH_LIMIT) : updatedLog;
+  });
+}
+
+export function enableAPIEvents(enabled: boolean): void {
+  if (!enabled) {
+    apiEventSource?.close();
+    apiEventSource = null;
+    metrics.set([]);
+    return;
+  }
+
+  let retryCount = 0;
+  const initialDelay = 1000; // 1 second
+
+  const connect = () => {
+    apiEventSource?.close();
+    apiEventSource = new EventSource("/api/events");
+
+    connectionState.set("connecting");
+
+    apiEventSource.onopen = () => {
+      // Clear everything on connect to keep things in sync
+      proxyLogs.set("");
+      upstreamLogs.set("");
+      metrics.set([]);
+      models.set([]);
+      retryCount = 0;
+      connectionState.set("connected");
+    };
+
+    apiEventSource.onmessage = (e: MessageEvent) => {
+      try {
+        const message = JSON.parse(e.data) as APIEventEnvelope;
+        switch (message.type) {
+          case "modelStatus": {
+            const newModels = JSON.parse(message.data) as Model[];
+            // Sort models by name and id
+            newModels.sort((a, b) => {
+              return (a.name + a.id).localeCompare(b.name + b.id);
+            });
+            models.set(newModels);
+            break;
+          }
+
+          case "logData": {
+            const logData = JSON.parse(message.data) as LogData;
+            switch (logData.source) {
+              case "proxy":
+                appendLog(logData.data, proxyLogs);
+                break;
+              case "upstream":
+                appendLog(logData.data, upstreamLogs);
+                break;
+            }
+            break;
+          }
+
+          case "metrics": {
+            const newMetrics = JSON.parse(message.data) as Metrics[];
+            metrics.update((prevMetrics) => [...newMetrics, ...prevMetrics]);
+            break;
+          }
+        }
+      } catch (err) {
+        console.error(e.data, err);
+      }
+    };
+
+    apiEventSource.onerror = () => {
+      apiEventSource?.close();
+      retryCount++;
+      const delay = Math.min(initialDelay * Math.pow(2, retryCount - 1), 5000);
+      connectionState.set("disconnected");
+      setTimeout(connect, delay);
+    };
+  };
+
+  connect();
+}
+
+// Fetch version info when connected
+connectionState.subscribe(async (status) => {
+  if (status === "connected") {
+    try {
+      const response = await fetch("/api/version");
+      if (!response.ok) {
+        throw new Error(`HTTP error! status: ${response.status}`);
+      }
+      const data: VersionInfo = await response.json();
+      versionInfo.set(data);
+    } catch (error) {
+      console.error(error);
+    }
+  }
+});
+
+export async function listModels(): Promise<Model[]> {
+  try {
+    const response = await fetch("/api/models/");
+    if (!response.ok) {
+      throw new Error(`HTTP error! status: ${response.status}`);
+    }
+    const data = await response.json();
+    return data || [];
+  } catch (error) {
+    console.error("Failed to fetch models:", error);
+    return [];
+  }
+}
+
+export async function unloadAllModels(): Promise<void> {
+  try {
+    const response = await fetch(`/api/models/unload`, {
+      method: "POST",
+    });
+    if (!response.ok) {
+      throw new Error(`Failed to unload models: ${response.status}`);
+    }
+  } catch (error) {
+    console.error("Failed to unload models:", error);
+    throw error;
+  }
+}
+
+export async function unloadSingleModel(model: string): Promise<void> {
+  try {
+    const response = await fetch(`/api/models/unload/${model}`, {
+      method: "POST",
+    });
+    if (!response.ok) {
+      throw new Error(`Failed to unload model: ${response.status}`);
+    }
+  } catch (error) {
+    console.error("Failed to unload model", model, error);
+    throw error;
+  }
+}
+
+export async function loadModel(model: string): Promise<void> {
+  try {
+    const response = await fetch(`/upstream/${model}/`, {
+      method: "GET",
+    });
+    if (!response.ok) {
+      throw new Error(`Failed to load model: ${response.status}`);
+    }
+  } catch (error) {
+    console.error("Failed to load model:", error);
+    throw error;
+  }
+}

ui-svelte/src/stores/persistent.ts

@@ -0,0 +1,31 @@
+import { writable, type Writable } from "svelte/store";
+
+export function persistentStore<T>(key: string, initialValue: T): Writable<T> {
+  // Get initial value from localStorage or use default
+  let storedValue = initialValue;
+  if (typeof window !== "undefined") {
+    try {
+      const saved = localStorage.getItem(key);
+      if (saved !== null) {
+        storedValue = JSON.parse(saved);
+      }
+    } catch (e) {
+      console.error(`Error parsing stored value for ${key}`, e);
+    }
+  }
+
+  const store = writable<T>(storedValue);
+
+  // Subscribe to changes and save to localStorage
+  store.subscribe((value) => {
+    if (typeof window !== "undefined") {
+      try {
+        localStorage.setItem(key, JSON.stringify(value));
+      } catch (e) {
+        console.error(`Error saving value for ${key}`, e);
+      }
+    }
+  });
+
+  return store;
+}

ui-svelte/src/stores/theme.ts

@@ -0,0 +1,53 @@
+import { writable, derived } from "svelte/store";
+import { persistentStore } from "./persistent";
+import type { ScreenWidth } from "../lib/types";
+
+// Persistent stores
+export const isDarkMode = persistentStore<boolean>("theme", false);
+export const appTitle = persistentStore<string>("app-title", "llama-swap");
+
+// Non-persistent stores
+export const screenWidth = writable<ScreenWidth>("md");
+export const connectionState = writable<"connected" | "connecting" | "disconnected">("disconnected");
+
+// Derived store for narrow screens
+export const isNarrow = derived(screenWidth, ($screenWidth) => {
+  return $screenWidth === "xs" || $screenWidth === "sm" || $screenWidth === "md";
+});
+
+// Function to toggle theme
+export function toggleTheme(): void {
+  isDarkMode.update((current) => !current);
+}
+
+// Function to check and update screen width
+export function checkScreenWidth(): void {
+  const innerWidth = window.innerWidth;
+  let newWidth: ScreenWidth;
+
+  if (innerWidth < 640) {
+    newWidth = "xs";
+  } else if (innerWidth < 768) {
+    newWidth = "sm";
+  } else if (innerWidth < 1024) {
+    newWidth = "md";
+  } else if (innerWidth < 1280) {
+    newWidth = "lg";
+  } else if (innerWidth < 1536) {
+    newWidth = "xl";
+  } else {
+    newWidth = "2xl";
+  }
+
+  screenWidth.set(newWidth);
+}
+
+// Initialize screen width and set up resize listener
+export function initScreenWidth(): () => void {
+  checkScreenWidth();
+  window.addEventListener("resize", checkScreenWidth);
+
+  return () => {
+    window.removeEventListener("resize", checkScreenWidth);
+  };
+}

ui-svelte/svelte.config.js

@@ -0,0 +1,5 @@
+import { vitePreprocess } from "@sveltejs/vite-plugin-svelte";
+
+export default {
+  preprocess: vitePreprocess(),
+};

ui-svelte/tsconfig.json

@@ -0,0 +1,20 @@
+{
+  "extends": "@tsconfig/svelte/tsconfig.json",
+  "compilerOptions": {
+    "target": "ESNext",
+    "useDefineForClassFields": true,
+    "module": "ESNext",
+    "resolveJsonModule": true,
+    "allowJs": true,
+    "checkJs": true,
+    "isolatedModules": true,
+    "moduleDetection": "force",
+    "noEmit": true,
+    "strict": true,
+    "noUnusedLocals": true,
+    "noUnusedParameters": true,
+    "noFallthroughCasesInSwitch": true,
+    "verbatimModuleSyntax": true
+  },
+  "include": ["src/**/*.ts", "src/**/*.svelte"]
+}

ui-svelte/vite.config.ts

@@ -0,0 +1,21 @@
+import { defineConfig } from "vite";
+import { svelte } from "@sveltejs/vite-plugin-svelte";
+import tailwindcss from "@tailwindcss/vite";
+
+// https://vite.dev/config/
+export default defineConfig({
+  plugins: [svelte(), tailwindcss()],
+  base: "/ui/",
+  build: {
+    outDir: "../proxy/ui_dist",
+    assetsDir: "assets",
+  },
+  server: {
+    proxy: {
+      "/api": "http://localhost:8080", // Proxy API calls to Go backend during development
+      "/logs": "http://localhost:8080",
+      "/upstream": "http://localhost:8080",
+      "/unload": "http://localhost:8080",
+    },
+  },
+});

ui/package-lock.json

@@ -12,7 +12,7 @@
         "react-dom": "^19.1.0",
         "react-icons": "^5.5.0",
         "react-resizable-panels": "^3.0.4",
-        "react-router-dom": "^7.6.2"
+        "react-router-dom": "^7.12.0"
       },
       "devDependencies": {
         "@eslint/js": "^9.25.0",
@@ -75,6 +75,7 @@
       "integrity": "sha512-bXYxrXFubeYdvB0NhD/NBB3Qi6aZeV20GOWVI47t2dkecCEoneR4NPVcb7abpXDEvejgrUfFtG6vG/zxAKmg+g==",
       "dev": true,
       "license": "MIT",
+      "peer": true,
       "dependencies": {
         "@ampproject/remapping": "^2.2.0",
         "@babel/code-frame": "^7.27.1",
@@ -1593,6 +1594,66 @@
         "node": ">=14.0.0"
       }
     },
+    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@emnapi/core": {
+      "version": "1.4.3",
+      "dev": true,
+      "inBundle": true,
+      "license": "MIT",
+      "optional": true,
+      "dependencies": {
+        "@emnapi/wasi-threads": "1.0.2",
+        "tslib": "^2.4.0"
+      }
+    },
+    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@emnapi/runtime": {
+      "version": "1.4.3",
+      "dev": true,
+      "inBundle": true,
+      "license": "MIT",
+      "optional": true,
+      "dependencies": {
+        "tslib": "^2.4.0"
+      }
+    },
+    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@emnapi/wasi-threads": {
+      "version": "1.0.2",
+      "dev": true,
+      "inBundle": true,
+      "license": "MIT",
+      "optional": true,
+      "dependencies": {
+        "tslib": "^2.4.0"
+      }
+    },
+    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@napi-rs/wasm-runtime": {
+      "version": "0.2.10",
+      "dev": true,
+      "inBundle": true,
+      "license": "MIT",
+      "optional": true,
+      "dependencies": {
+        "@emnapi/core": "^1.4.3",
+        "@emnapi/runtime": "^1.4.3",
+        "@tybys/wasm-util": "^0.9.0"
+      }
+    },
+    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/@tybys/wasm-util": {
+      "version": "0.9.0",
+      "dev": true,
+      "inBundle": true,
+      "license": "MIT",
+      "optional": true,
+      "dependencies": {
+        "tslib": "^2.4.0"
+      }
+    },
+    "node_modules/@tailwindcss/oxide-wasm32-wasi/node_modules/tslib": {
+      "version": "2.8.0",
+      "dev": true,
+      "inBundle": true,
+      "license": "0BSD",
+      "optional": true
+    },
     "node_modules/@tailwindcss/oxide-win32-arm64-msvc": {
       "version": "4.1.8",
       "resolved": "https://registry.npmjs.org/@tailwindcss/oxide-win32-arm64-msvc/-/oxide-win32-arm64-msvc-4.1.8.tgz",
@@ -1707,6 +1768,7 @@
       "integrity": "sha512-JeG0rEWak0N6Itr6QUx+X60uQmN+5t3j9r/OVDtWzFXKaj6kD1BwJzOksD0FF6iWxZlbE1kB0q9vtnU2ekqa1Q==",
       "dev": true,
       "license": "MIT",
+      "peer": true,
       "dependencies": {
         "csstype": "^3.0.2"
       }
@@ -1767,6 +1829,7 @@
       "integrity": "sha512-qwxv6dq682yVvgKKp2qWwLgRbscDAYktPptK4JPojCwwi3R9cwrvIxS4lvBpzmcqzR4bdn54Z0IG1uHFskW4dA==",
       "dev": true,
       "license": "MIT",
+      "peer": true,
       "dependencies": {
         "@typescript-eslint/scope-manager": "8.33.1",
         "@typescript-eslint/types": "8.33.1",
@@ -2018,6 +2081,7 @@
       "integrity": "sha512-NZyJarBfL7nWwIq+FDL6Zp/yHEhePMNnnJ0y3qfieCrmNvYct8uvtiV41UvlSe6apAfk0fY1FbWx+NwfmpvtTg==",
       "dev": true,
       "license": "MIT",
+      "peer": true,
       "bin": {
         "acorn": "bin/acorn"
       },
@@ -2126,6 +2190,7 @@
         }
       ],
       "license": "MIT",
+      "peer": true,
       "dependencies": {
         "caniuse-lite": "^1.0.30001718",
         "electron-to-chromium": "^1.5.160",
@@ -2232,12 +2297,16 @@
       "license": "MIT"
     },
     "node_modules/cookie": {
-      "version": "1.0.2",
+      "version": "1.1.1",
-      "resolved": "https://registry.npmjs.org/cookie/-/cookie-1.0.2.tgz",
+      "resolved": "https://registry.npmjs.org/cookie/-/cookie-1.1.1.tgz",
-      "integrity": "sha512-9Kr/j4O16ISv8zBBhJoi4bXOYNTkFLOqSL3UDB0njXxCXNezjeyVrJyGOWtgfs/q2km1gwBcfH8q1yEGoMYunA==",
+      "integrity": "sha512-ei8Aos7ja0weRpFzJnEA9UHJ/7XQmqglbRwnf2ATjcB9Wq874VKH9kfjjirM6UhU2/E5fFYadylyhFldcqSidQ==",
       "license": "MIT",
       "engines": {
         "node": ">=18"
+      },
+      "funding": {
+        "type": "opencollective",
+        "url": "https://opencollective.com/express"
       }
     },
     "node_modules/cross-spawn": {
@@ -2388,6 +2457,7 @@
       "integrity": "sha512-BhHmn2yNOFA9H9JmmIVKJmd288g9hrVRDkdoIgRCRuSySRUHH7r/DI6aAXW9T1WwUuY3DFgrcaqB+deURBLR5g==",
       "dev": true,
       "license": "MIT",
+      "peer": true,
       "dependencies": {
         "@eslint-community/eslint-utils": "^4.8.0",
         "@eslint-community/regexpp": "^4.12.1",
@@ -3267,9 +3337,9 @@
       }
     },
     "node_modules/minizlib": {
-      "version": "3.0.2",
+      "version": "3.1.0",
-      "resolved": "https://registry.npmjs.org/minizlib/-/minizlib-3.0.2.tgz",
+      "resolved": "https://registry.npmjs.org/minizlib/-/minizlib-3.1.0.tgz",
-      "integrity": "sha512-oG62iEk+CYt5Xj2YqI5Xi9xWUeZhDI8jjQmC5oThVH5JGCTgIjr7ciJDzC7MBzYd//WvR1OTmP5Q38Q8ShQtVA==",
+      "integrity": "sha512-KZxYo1BUkWD2TVFLr0MQoM8vUUigWD3LlD83a/75BqC+4qE0Hb1Vo5v1FgcfaNXvfXzr+5EhQ6ing/CaBijTlw==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -3279,22 +3349,6 @@
         "node": ">= 18"
       }
     },
-    "node_modules/mkdirp": {
-      "version": "3.0.1",
-      "resolved": "https://registry.npmjs.org/mkdirp/-/mkdirp-3.0.1.tgz",
-      "integrity": "sha512-+NsyUUAZDmo6YVHzL/stxSu3t9YS1iljliy3BSDrXJ/dkn1KYdmtZODGGjLcc9XLgVVpH4KshHB8XmZgMhaBXg==",
-      "dev": true,
-      "license": "MIT",
-      "bin": {
-        "mkdirp": "dist/cjs/src/bin.js"
-      },
-      "engines": {
-        "node": ">=10"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/isaacs"
-      }
-    },
     "node_modules/ms": {
       "version": "2.1.3",
       "resolved": "https://registry.npmjs.org/ms/-/ms-2.1.3.tgz",
@@ -3513,6 +3567,7 @@
       "resolved": "https://registry.npmjs.org/react/-/react-19.1.0.tgz",
       "integrity": "sha512-FS+XFBNvn3GTAWq26joslQgWNoFu08F4kl0J4CgdNKADkdSGXQyTCnKteIAJy96Br6YbpEU1LSzV5dYtjMkMDg==",
       "license": "MIT",
+      "peer": true,
       "engines": {
         "node": ">=0.10.0"
       }
@@ -3522,6 +3577,7 @@
       "resolved": "https://registry.npmjs.org/react-dom/-/react-dom-19.1.0.tgz",
       "integrity": "sha512-Xs1hdnE+DyKgeHJeJznQmYMIBG3TKIHJJT95Q58nHLSrElKlGQqDTR2HQ9fx5CN/Gk6Vh/kupBTDLU11/nDk/g==",
       "license": "MIT",
+      "peer": true,
       "dependencies": {
         "scheduler": "^0.26.0"
       },
@@ -3559,9 +3615,9 @@
       }
     },
     "node_modules/react-router": {
-      "version": "7.6.2",
+      "version": "7.12.0",
-      "resolved": "https://registry.npmjs.org/react-router/-/react-router-7.6.2.tgz",
+      "resolved": "https://registry.npmjs.org/react-router/-/react-router-7.12.0.tgz",
-      "integrity": "sha512-U7Nv3y+bMimgWjhlT5CRdzHPu2/KVmqPwKUCChW8en5P3znxUqwlYFlbmyj8Rgp1SF6zs5X4+77kBVknkg6a0w==",
+      "integrity": "sha512-kTPDYPFzDVGIIGNLS5VJykK0HfHLY5MF3b+xj0/tTyNYL1gF1qs7u67Z9jEhQk2sQ98SUaHxlG31g1JtF7IfVw==",
       "license": "MIT",
       "dependencies": {
         "cookie": "^1.0.1",
@@ -3581,12 +3637,12 @@
       }
     },
     "node_modules/react-router-dom": {
-      "version": "7.6.2",
+      "version": "7.12.0",
-      "resolved": "https://registry.npmjs.org/react-router-dom/-/react-router-dom-7.6.2.tgz",
+      "resolved": "https://registry.npmjs.org/react-router-dom/-/react-router-dom-7.12.0.tgz",
-      "integrity": "sha512-Q8zb6VlTbdYKK5JJBLQEN06oTUa/RAbG/oQS1auK1I0TbJOXktqm+QENEVJU6QvWynlXPRBXI3fiOQcSEA78rA==",
+      "integrity": "sha512-pfO9fiBcpEfX4Tx+iTYKDtPbrSLLCbwJ5EqP+SPYQu1VYCXdy79GSj0wttR0U4cikVdlImZuEZ/9ZNCgoaxwBA==",
       "license": "MIT",
       "dependencies": {
-        "react-router": "7.6.2"
+        "react-router": "7.12.0"
       },
       "engines": {
         "node": ">=20.0.0"
@@ -3705,9 +3761,9 @@
       }
     },
     "node_modules/set-cookie-parser": {
-      "version": "2.7.1",
+      "version": "2.7.2",
-      "resolved": "https://registry.npmjs.org/set-cookie-parser/-/set-cookie-parser-2.7.1.tgz",
+      "resolved": "https://registry.npmjs.org/set-cookie-parser/-/set-cookie-parser-2.7.2.tgz",
-      "integrity": "sha512-IOc8uWeOZgnb3ptbCURJWNjWUPcO3ZnTTdzsurqERrP6nPyv+paC55vJM0LpOlT2ne+Ix+9+CRG1MNLlyZ4GjQ==",
+      "integrity": "sha512-oeM1lpU/UvhTxw+g3cIfxXHyJRc/uidd3yK1P242gzHds0udQBYzs3y8j4gCCW+ZJ7ad0yctld8RYO+bdurlvw==",
       "license": "MIT"
     },
     "node_modules/shebang-command": {
@@ -3787,17 +3843,16 @@
       }
     },
     "node_modules/tar": {
-      "version": "7.4.3",
+      "version": "7.5.7",
-      "resolved": "https://registry.npmjs.org/tar/-/tar-7.4.3.tgz",
+      "resolved": "https://registry.npmjs.org/tar/-/tar-7.5.7.tgz",
-      "integrity": "sha512-5S7Va8hKfV7W5U6g3aYxXmlPoZVAwUMy9AOKyF2fVuZa2UD3qZjg578OrLRt8PcNN1PleVaL/5/yYATNL0ICUw==",
+      "integrity": "sha512-fov56fJiRuThVFXD6o6/Q354S7pnWMJIVlDBYijsTNx6jKSE4pvrDTs6lUnmGvNyfJwFQQwWy3owKz1ucIhveQ==",
       "dev": true,
-      "license": "ISC",
+      "license": "BlueOak-1.0.0",
       "dependencies": {
         "@isaacs/fs-minipass": "^4.0.0",
         "chownr": "^3.0.0",
         "minipass": "^7.1.2",
-        "minizlib": "^3.0.1",
+        "minizlib": "^3.1.0",
-        "mkdirp": "^3.0.1",
         "yallist": "^5.0.0"
       },
       "engines": {
@@ -3852,6 +3907,7 @@
       "integrity": "sha512-M7BAV6Rlcy5u+m6oPhAPFgJTzAioX/6B0DxyvDlo9l8+T3nLKbrczg2WLUyzd45L8RqfUMyGPzekbMvX2Ldkwg==",
       "dev": true,
       "license": "MIT",
+      "peer": true,
       "engines": {
         "node": ">=12"
       },
@@ -3904,6 +3960,7 @@
       "integrity": "sha512-p1diW6TqL9L07nNxvRMM7hMMw4c5XOo/1ibL4aAIGmSAt9slTE1Xgw5KWuof2uTOvCg9BY7ZRi+GaF+7sfgPeQ==",
       "dev": true,
       "license": "Apache-2.0",
+      "peer": true,
       "bin": {
         "tsc": "bin/tsc",
         "tsserver": "bin/tsserver"
@@ -3982,6 +4039,7 @@
       "integrity": "sha512-+Oxm7q9hDoLMyJOYfUYBuHQo+dkAloi33apOPP56pzj+vsdJDzr+j1NISE5pyaAuKL4A3UD34qd0lx5+kfKp2g==",
       "dev": true,
       "license": "MIT",
+      "peer": true,
       "dependencies": {
         "esbuild": "^0.25.0",
         "fdir": "^6.4.4",
@@ -4072,6 +4130,7 @@
       "integrity": "sha512-M7BAV6Rlcy5u+m6oPhAPFgJTzAioX/6B0DxyvDlo9l8+T3nLKbrczg2WLUyzd45L8RqfUMyGPzekbMvX2Ldkwg==",
       "dev": true,
       "license": "MIT",
+      "peer": true,
       "engines": {
         "node": ">=12"
       },

ui/package.json

@@ -14,7 +14,7 @@
     "react-dom": "^19.1.0",
     "react-icons": "^5.5.0",
     "react-resizable-panels": "^3.0.4",
-    "react-router-dom": "^7.6.2"
+    "react-router-dom": "^7.12.0"
   },
   "devDependencies": {
     "@eslint/js": "^9.25.0",

ui/src/contexts/APIProvider.tsx

@@ -10,6 +10,7 @@ export interface Model {
   name: string;
   description: string;
   unlisted: boolean;
+  peerID: string;
 }
 
 interface APIProviderType {
@@ -70,7 +71,7 @@ export function APIProvider({ children, autoStartAPIEvents = true }: APIProvider
   const [versionInfo, setVersionInfo] = useState<VersionInfo>({
     build_date: "unknown",
     commit: "unknown",
-    version: "unknown"
+    version: "unknown",
   });
   //const apiEventSource = useRef<EventSource | null>(null);
 
@@ -166,7 +167,7 @@ export function APIProvider({ children, autoStartAPIEvents = true }: APIProvider
   }, []);
 
   useEffect(() => {
-    // fetch version 
+    // fetch version
     const fetchVersion = async () => {
       try {
         const response = await fetch("/api/version");
@@ -180,7 +181,7 @@ export function APIProvider({ children, autoStartAPIEvents = true }: APIProvider
       }
     };
 
-    if (connectionStatus === 'connected') {
+    if (connectionStatus === "connected") {
       fetchVersion();
     }
   }, [connectionStatus]);
@@ -265,7 +266,19 @@ export function APIProvider({ children, autoStartAPIEvents = true }: APIProvider
       connectionStatus,
       versionInfo,
     }),
-    [models, listModels, unloadAllModels, unloadSingleModel, loadModel, enableAPIEvents, proxyLogs, upstreamLogs, metrics, connectionStatus, versionInfo]
+    [
+      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(() => {
+  const { regularModels, peerModelsByPeerId } = useMemo(() => {
-    return models.filter((model) => showUnlisted || !model.unlisted);
+    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
+      <svg viewBox={`0 0 ${viewBoxWidth} ${height}`} className="w-full h-auto" preserveAspectRatio="xMidYMid meet">
-        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
+        <text x={padding.left} y={height - 5} fontSize="10" fill="currentColor" opacity="0.6" textAnchor="start">
-          x={padding.left}
-          y={height - 5}
-          fontSize="10"
-          fill="currentColor"
-          opacity="0.6"
-          textAnchor="start"
-        >
           {min.toFixed(1)}
         </text>