- Fix the histogram calculation to use server provided generation
tokens/second.
- Move histogram to Activities page where it can exist with the rest of
the token metrics
Fixes#681
The fsnotify-based config watcher does not work reliably when the config
file is bind-mounted into a Docker container as an individual file, and
mishandles k8s ConfigMap projections (atomically swapped symlinks).
Replace it with a small os.Stat-polling watcher and add SIGHUP as an
explicit reload signal.
- new proxy/configwatcher package: 2s os.Stat poller, follows symlinks,
fires on mtime/size change and on missing -> present transitions
- SIGHUP triggers reload unconditionally (works without --watch-config)
via the same ConfigFileChangedEvent pipeline so the UI sees identical
state transitions
- watcher goroutine now exits cleanly on shutdown via a context
- drop github.com/fsnotify/fsnotify dependency
fixes#682
Install uv after the cpp tool binaries are copied and before the
llama-swap binary, enabling `uv run` usage for Python-based inference
backends like vLLM.
- add python3-pip to runtime apt installs
- add `pip install uv --break-system-packages` after cpp installs
fixes#628
Co-authored-by: Claude <[email protected]>
- matrix.go change logic to consider any proxy.Process not in
StateStopped or StateShutdown
- process.StopImmediately, and Stop() which called it had a subtle bug
where it only handled state transitions from StateReady to
StateStopping. StateStarting -> StateStopping was ignored completely.
fix: #670
The previous captures were saved uncompressed in memory. In agentic
workflows there can be many turns with each request containing the
previous context in the body with a lot of redundant data. Use zstd to
compress the request and response data before keeping a copy of memory.
Results:
- Average Percentage Saved: 73.19%
- Average Compression Factor: ~6.77:1
I pointed Opus 4.7 (high effort) at proxy.ProcessGroup to identify any
race conditions in the swapping code. It found a race condition where
there is a small window in the fast path for routing a request to a
loaded model. There is a very small window where:
- model M1 is loaded and ready for requests
- a request, R1, for M1 comes in
- a request, R2, for M2 comes in almost immediately after
- R1 acquires the lock, sees M1 is loaded (fast path), releases the lock
`[race window]` and the request is ready to be forwarded
- the race window occurs between the release of the lock and the request
being forwarded
- the lock is released so requests can be handled concurrently
- R2 comes in within the `[race window]`, acquires the lock, triggers a
model swap to M2. stopping M1
- R1 is forwarded to a model that is unloaded or in the process of
shutting down creating an error response
In deployed systems the race window is very small and doesn't happen
often. However with #635 and PR #656 I though this deserved a bit more
attention. It is not concluded that this race is the cause of #635 but
the race is likely to happen more often under sustained or high load.
AI Note: Opus 4.7 x-high effort took about an hour to write the original
patch. With the pattern discovered the fix to matrix.go was very quick.
GLM 5.1 using the previous established patterns was able to easily write
the fix for ProcessGroup.StopProcesses().
Supersedes: #656
Updates: #277, #635
Add a new swap matrix to supersede groups for running concurrent models.
The matrix uses a solver that picks the lowest cost evictions to make a
requested model available. This simple approach along with a very basic
DSL grammar can enable very complex swapping scenarios.
- add DSL parser for set expressions with & (AND), | (OR), (), +ref
- add MatrixConfig structs, validation, and topological sort for +ref
- add MatrixSolver with cost-minimizing swap decisions
- add Matrix runtime integrating solver with Process lifecycle
- integrate matrix into ProxyManager with if-branches at all endpoints
- update config.example.yaml and config-schema.json with matrix schema
- config enforces groups XOR matrix (cannot use both)
fixes#643
Build the root image once, then derive the rootless variant from it
using a small inline Dockerfile that adds the non-root user and chowns
the writable directories. This halves the number of CI jobs (4 → 2) and
eliminates the redundant full CUDA compilation for the rootless variant.
- remove RUN_UID build arg from build-image.sh
- derive rootless image inline after root build completes
- collapse variant matrix out of unified-docker.yml
- push both root and rootless tags in a single CI job
Co-authored-by: Claude Sonnet 4.6 <[email protected]>
Extend the existing config-schema workflow to also validate
config.example.yaml against config-schema.json using check-jsonschema.
- add config.example.yaml to PR and push path triggers
- install check-jsonschema via pip
- run validation of config.example.yaml against schema
https://claude.ai/code/session_01Y1oqwE6mwNs9UTJgZRgXtG
---------
Co-authored-by: Claude <[email protected]>
Expose CMAKE_CUDA_ARCHITECTURES as a Docker build ARG so users can
customize CUDA architectures via --build-arg without editing the
Dockerfile.
- convert hardcoded ENV to ARG with default, feeding into ENV
- replace silent fallback defaults (:-) in scripts with :? guards
to fail fast if the env var is missing
- add usage example to Dockerfile header
Follow up to: #624https://claude.ai/code/session_01EWiUe7jNABX7Uz95dUGJqK
Co-authored-by: Claude <[email protected]>
multiple fixes to vulkan build:
- use ubuntu 26.04 to be compatible with AMD 395+ (Strix halo) hardware
- add home directory in container
- fix stable-diffusion install to actually enable vulkan
---------
Co-authored-by: Claude Opus 4.6 <[email protected]>
- set up a GHA scheduled job to build the container nightly
- enabling pushing a llama-swap:unified and a llama-swap:unified-Y-M-D
image to ghcr.io
- tidy up Dockerfile to use a non-root user and llama-swap as an entry
point
Add proxy routes for stable-diffusion.cpp's /sdapi/v1/txt2img,
/sdapi/v1/img2img, and /sdapi/v1/loras endpoints. POST endpoints
use proxyInferenceHandler (model in JSON body), GET /loras uses
proxyGETModelHandler (model in query param).
Update the image playground with a dual-mode UI supporting both
OpenAI and SDAPI backends. In SDAPI mode, loras are fetched first
to prime the server-side cache, and all txt2img parameters are
exposed (negative prompt, steps, cfg_scale, seed, batch_size,
clip_skip, sampler, scheduler, lora selection with multipliers).
- Add 3 sdapi route registrations in proxymanager.go
- Add sdApi.ts client with generateSdImage and fetchSdLoras
- Add SDAPI types (SdApiTxt2ImgRequest, SdApiResponse, etc.)
- Add /sdapi to vite dev proxy config
- Add backend tests for sdapi routing
- Support batch image display in gallery grid
https://claude.ai/code/session_0186MGX6NXdHVBTv2KH45fqn
---------
Co-authored-by: Claude <[email protected]>
Upgrade vite and related dependencies to take advantage of Vite 8's
improved build times via Rolldown and Oxc.
- vite: ^6.3.5 → ^8.0.0
- @sveltejs/vite-plugin-svelte: ^5.0.3 → ^7.0.0
- svelte: ^5.19.0 → ^5.46.4
- vite-plugin-compression2: ^2.4.0 → ^2.5.1
- vitest: ^4.0.18 → ^4.1.0
---------
Co-authored-by: Claude <[email protected]>
Extend macro substitution to the name and description fields of
ModelConfig, matching the behavior already present for cmd, proxy,
checkEndpoint, and filters.
- substitute global/model macros (including MODEL_ID) in name and
description
- substitute PORT macro in name and description when allocated
- validate no unknown macros remain in name and description after
substitution
- add tests for macro substitution, MODEL_ID, and unknown macro error
Add a new configuration parameter globalTTL that all models will
inherit. The default value is 0 which matches the currently
functionality to never automatically unload a model.
The model.ttl's default has changed to -1, which means use the global
TTL value. Any model.ttl >=0 is now value with 0 meaning never unload.
This allows a model to override a globalTTL > 0 and be configured to
never unload.
Fixes#459Closes#512
Add a copy-to-clipboard button that appears on hover for each code block
rendered in the chat interface assistant messages.
- Svelte action `codeBlockCopy` injects a button into every `<pre>`
element
- MutationObserver reattaches buttons as streaming content arrives
- Button shows a check icon for 2 seconds after a successful copy
- Uses clipboard API with execCommand fallback for non-secure contexts
- CSS hides button by default and reveals it on pre:hover
https://claude.ai/code/session_01PTA5ao5YQuFAS6a9juLeZW
---------
Co-authored-by: Claude <[email protected]>
Updated README to enhance the description of the web interface and added details about features like token metrics, request inspection, model management, and real-time log streaming.
Add a new Rerank tab to the playground that lets users test /v1/rerank
endpoints. Supports a visual table editor and a JSON editor mode that
stay in sync when toggling between them.
- add rerankApi.ts with typed wrapper for /v1/rerank
- add RerankInterface.svelte with query input, sortable document table,
color-coded scores, auto-add row, cancel/clear, and token usage
- add rerankLoading store to playgroundActivity derived store
- register Rerank tab in Playground.svelte
Updates #481
Add setParamsByID filter that applies different request parameters based
on the requested model ID, enabling per-alias behaviour for a single
loaded model.
- add SetParamsByID field to Filters struct and SanitizedSetParamsByID
method
- substitute ${MODEL_ID} and other macros in setParamsByID keys and
values
- validate no unknown macros remain in keys or values after substitution
- apply setParamsByID in proxyInferenceHandler after setParams (can
override it)
- update config-schema.json with setParamsByID definition
- update UI to show aliases and make them selectable in the Playground
closes#534
Pause auto-scroll when the user scrolls up to review logs, and resume
when they scroll back to the bottom.
- add `userScrolledUp` state variable
- add `handleScroll` to detect scroll position with 40px threshold
- guard the auto-scroll effect with `!userScrolledUp`
closes#529
- Keep Playground component mounted when navigating away, preserving
streaming/generating state
- Add animated gradient effect on Playground nav link when activity is
in progress
## Summary
- Add `--provenance=false` to docker build commands in
`build-container.sh`
- BuildKit attestation manifests are stored as untagged images in GHCR,
and the `delete-untagged-containers` cleanup job deletes them, breaking
the manifest list and causing `manifest unknown` errors on pull
- ref: https://github.com/actions/delete-package-versions/issues/162
Add saving request and response headers and bodies that go through
llama-swap in memory.
- captureBuffer added to configuration. Captures are enabled by default.
- 5MB of memory is allocated for req/response captures in a ring buffer.
Setting captureBuffer to 0 will disable captures.
- UI elements to view captured data added to Activity page. Includes
some
QOL features like json formatting and recombining SSE chat streams
- capture saving is done at the byte level and has minimal impact on
llama-swap performance
Fixes#464
Ref #503
Reorganizes control placement in the playground interfaces and
improves form interactions for better UX, particularly on mobile
devices.
## Key Changes
- **AudioInterface & ImageInterface**: Moved "Clear" buttons from the
top control bar into the action button group below the form inputs for
better visual hierarchy and logical grouping
- **ImageInterface**:
- Added prompt clearing to the `clearImage()` function so the input
field is reset when clearing generated images
- Updated Clear button disabled state to also check if prompt is empty,
allowing users to clear an empty prompt
- Added responsive flex styling (`flex-1 md:flex-none`) to the Clear
button for better mobile layout
- **ExpandableTextarea**:
- Imported `untrack` from Svelte to properly handle reactive
dependencies
- Wrapped `expandedValue.length` in `untrack()` to prevent unnecessary
reactivity when setting cursor position
- Improved button visibility on mobile by changing opacity from
`opacity-0` to `opacity-60` with `md:opacity-0` breakpoint, making the
expand button more discoverable on touch devices
## Implementation Details
The `untrack()` usage in ExpandableTextarea ensures that reading the
text length doesn't create a reactive dependency, preventing potential
infinite loops while still allowing the effect to run when `isExpanded`
changes.
* .github/workflows: add UI tests and path-filter Go CI
Add ui-tests.yml workflow to run svelte type checking and vitest
on push/PR to main when ui-svelte/ files change.
- Add path filters to go-ci.yml and go-ci-windows.yml to skip
Go tests when only non-backend files change
- Filter on **/*.go, go.mod, go.sum, and Makefile
https://claude.ai/code/session_01E6acq54D8JjuE7pczxPGT7
* ui-svelte: remove unused declarations in SpeechInterface
Remove unused `generatedText` state and `clearAudio` function
that caused svelte-check errors.
https://claude.ai/code/session_01E6acq54D8JjuE7pczxPGT7
* .github/workflows: update Node.js to v24
Node 23 is end-of-life; bump to 24 in ui-tests.yml and release.yml.
https://claude.ai/code/session_01E6acq54D8JjuE7pczxPGT7
---------
Co-authored-by: Claude <[email protected]>
Replace the legacy React UI with the new Svelte-based one. Introduce a Playground in the UI to quickly test out text, image, text to speech and speech to text models behind llama-swap.
Key Changes
New Svelte UI (ui-svelte/)
- Multi-tab Playground with Chat, Image Generation, Audio Transcription, and Speech interfaces
- Chat: message editing/regeneration, markdown rendering with LaTeX math support, image attachments, code syntax highlighting
- Image: size selector, download/fullscreen viewing
- Audio: transcription with peer support
- Speech: voice caching with manual refresh, download button
- Responsive mobile layout with collapsible navigation
- XSS fixes and accessibility improvements
Proxy Improvements
- Add gzip/brotli compression for UI static assets (proxy/ui_compress.go)
- Add GET /v1/audio/voices?model={model} endpoint for voice listing
- Add peer support for /v1/audio/transcriptions
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
Extend the /running endpoint to return more details about running
processes beyond just model and state.
- add cmd field to show the command being executed
- add proxy field to show the proxy URL
- add ttl (UnloadAfter) for automatic unloading configuration
- add name and description for model metadata
- update tests to verify new fields are returned correctly
fixes#471
This commit simplifies substitution of environment variables into the configuration. There was a lot of repetitive code substituting ${env.VAR_NAME} into different fields after the configuration was parsed into a config.Config. This refactor uses a string substitution of env vars into the YAML config before it is fully parsed. This eliminates a lot of logic while maintaining backwards compatibility.
* config: support environment variable macros in peer apiKeys
Add ${env.VAR_NAME} substitution for peer apiKey fields, consistent
with existing env macro support for model fields and global apiKeys.
- Add env macro substitution for peers.{name}.apiKey in LoadConfigFromReader
- Add tests for peer apiKey env substitution
- Update config.example.yaml to show env macro usage
* config: support macros in peer apiKey and filters
Extend macro substitution to peer configuration fields:
- peers.{name}.apiKey supports both global macros and env macros
- peers.{name}.filters.stripParams supports both macro types
- peers.{name}.filters.setParams supports both macro types
Also renamed validateMetadataForUnknownMacros to validateNestedForUnknownMacros
for reuse across model metadata and peer filters validation.
Add substituteEnvMacros support for apiKeys configuration field,
allowing API keys to be loaded from environment variables using
the ${env.VAR_NAME} syntax.
- Apply env macro substitution before validation
- Add tests for env macro substitution in apiKeys
* config: add environment variable macros
Add support for ${env.VAR_NAME} syntax to pull values from system
environment variables during config loading.
- env macros processed before regular macros (allows macros to reference env vars)
- works in cmd, cmdStop, proxy, checkEndpoint, filters.stripParams, metadata
- returns error if env var is not set
- add comprehensive tests
fixes#462
* docs: add env macro example to config.example.yaml
This unifies the filtering capabilities for models and peers
- stripParams: removes params in the request
- setParams: sets params in the request
fixes#453
* docker: add .env usage in build-container.sh
* .github,docker: add rocm, improve logging
* .github,CLAUDE.md: fix workflow and update guidelines
Update containers workflow to only push images when triggered
manually or on schedule, not on workflow file changes.
- add push trigger for workflow file changes in containers.yml
- update push condition to skip on regular push events
- update CLAUDE.md commit message guidelines
* docker: remove comma in build-container.sh
* .github,docker: improve container build workflow
Add pagination support for fetching llama.cpp tags and improve debugging.
- add build-container.sh to workflow trigger paths
- implement fetch_llama_tag() with pagination support
- replace .env with local testing instructions
- add DEBUG_ABORT_BUILD flag for testing
Fixes#444 where the UI with api keys did not work. The choice to use
http basic authorization is for simple, automatic browser support. No
changes to the UI were necessary. Just use an API key as the password,
no user name is required.
This PR allows a single llama-swap to be the central proxy for models served by other inference servers. The peer servers can be another llama-swap or any API that supports the /v1/* inference endpoint.
Updates: #433, #299Closes: #296
Add configuration support for api keys that are enforced by llama-swap. Keys are stripped before sending them to upstream servers.
Updates: #433, #50 and #251
The new logToStdout option controls what is logged to stdout. The
default has been changed to just the proxy logs, which contain swap and
http request logs.
There are four supported settings: none, proxy, upstream, both. The
"both" setting is the legacy setting where everything was spewed to
stdout.
A {model_id} containing a forward slash trips up gin's path param
parsing. This updates /logs/stream to work like /upstream where the
model_id is built up in parts and searched for in the configuration.
Updates #421
Replace container/ring.Ring with a custom circularBuffer that uses a
single contiguous []byte slice. This fixes the original implementation
which created 10,240 ring elements instead of 10KB of storage.
GetHistory is now 139x faster (145μs → 1μs) and uses 117x less memory
(1.2MB → 10KB). Allocations reduced from 2 to 1 per write operation.
Create a LogMonitor per proxy.Process, replacing the usage
of a shared one. The buffer in LogMonitor is lazy allocated on the first
call to Write and freed when the Process is stopped. This reduces
unnecessary memory usage when a model is not active.
The /logs/stream/{model_id} endpoint was added to stream logs from a
specific process.
When requesting / wol-proxy will show a loading page that polls /status
every second. When the upstream server is ready the loading page will
refresh causing the actual root page to be displayed
Swapping models can take a long time and leave a lot of silence while the model is loading. Rather than silently load the model in the background, this PR allows llama-swap to send status updates in the reasoning_content of a streaming chat response.
Fixes: #366
Switching to use httputil.ReverseProxy in #342 introduced a possible
panic if a client disconnects while streaming the body. Since llama-swap
does not use http.Server the recover() is not automatically there.
- introduce a recover() in Process.ProxyRequest to recover and log the
event
- add TestProcess_ReverseProxyPanicIsHandled to reproduce and test the
fix
fixes: #362
Benson WongandGitHub
