80ca0cbd4f
Rename Process to Instance
2025-10-16 19:38:44 +02:00
964c6345ef
Refactor backend host/port retrieval and remove redundant code for health checks
2025-10-14 22:16:26 +02:00
92a76bc84b
Move proxy to separate struct
2025-10-14 22:01:09 +02:00
02909c5153
Remove redundant instance prefix from logger
2025-10-14 19:46:43 +02:00
ef3478e2a3
Move logging to separate struct
2025-10-14 19:32:15 +02:00
9ee0a184b3
Re-validate instance name in DeleteInstance for improved security
2025-10-09 22:18:53 +02:00
5436c28a1f
Add instance name validation before deletion for security
2025-10-09 22:10:40 +02:00
e7a6a7003e
Skip remote instances in checkAllTimeouts and EvictLRUInstance methods
2025-10-09 21:13:38 +02:00
2b950ee649
Implement updateLocalInstanceFromRemote to preserve Nodes field when syncing remote instance data
2025-10-09 20:39:21 +02:00
b965b77c18
Prevent remote instances from using local proxy in GetProxy method
2025-10-09 20:24:54 +02:00
8a16a195de
Fix getting remote instance logs
2025-10-09 20:22:32 +02:00
9684a8a09b
Enhance instance management to preserve local state for remote instances
2025-10-09 19:34:52 +02:00
e281708b20
Enhance auto-start logic to differentiate between remote and local instances
2025-10-09 18:56:23 +02:00
8d9b0c0621
Initialize timeProvider and logger in UnmarshalJSON for Process
2025-10-09 18:56:12 +02:00
688b815ca7
Add LocalNode configuration
2025-10-08 19:43:53 +02:00
7f6725da96
Refactor NodeConfig handling to use a map
2025-10-08 19:24:24 +02:00
3418735204
Add stripNodesFromOptions function to prevent routing loops in remote requests
2025-10-07 20:27:31 +02:00
2f1cf5acdc
Refactor CreateRemoteInstance and UpdateRemoteInstance to directly use options parameter in API requests
2025-10-07 19:57:21 +02:00
01380e6641
Update instance manager tests to use empty NodeConfig slice
2025-10-07 19:18:13 +02:00
6298b03636
Refactor RemoteOpenAIProxy to use cached proxies and restore request body handling
2025-10-07 18:57:08 +02:00
aae3f84d49
Implement caching for remote instance proxies and enhance proxy request handling
2025-10-07 18:44:23 +02:00
16b28bac05
Merge branch 'main' into feat/multi-host
2025-10-07 18:04:24 +02:00
Anuruth Lertpiya
997bd1b063
Changed status code to StatusBadRequest (400) if requested invalid model name.
2025-10-05 14:53:20 +00:00
Anuruth Lertpiya
fa43f9e967
Added support for proxying llama.cpp native API endpoints via /llama-cpp/{name}/
2025-10-05 14:28:33 +00:00
8ebdb1a183
Fix double read of json response when content-length header is missing
2025-10-04 22:16:28 +02:00
035e184789
Merge branch 'main' into fix/auto-restart
2025-10-04 21:22:50 +02:00
d15976e7aa
Implement auto-stop for instances with auto-restart disabled and add corresponding tests
2025-10-04 21:17:55 +02:00
Anuruth Lertpiya
0e1bc8a352
Added support for configuring CORS headers
2025-10-04 09:13:40 +00:00
670f8ff81b
Split up handlers
2025-10-02 23:11:20 +02:00
da56456504
Add node management endpoints to handle listing and retrieving node details
2025-10-02 22:51:41 +02:00
c30053e51c
Enhance instance loading to support remote instances and handle node configuration
2025-10-01 22:59:45 +02:00
347c58e15f
Enhance instance manager to persist remote instances and update tracking on modifications
2025-10-01 22:58:57 +02:00
2ed67eb672
Add remote instance proxying functionality to handler
2025-10-01 22:17:19 +02:00
0188f82306
Implement remote instance creation and deletion in instance manager
2025-10-01 22:05:18 +02:00
e0f176de10
Enhance instance manager to support remote instance management and update related tests
2025-10-01 20:25:06 +02:00
2759be65a5
Add remote instance management functionality and configuration support
2025-09-30 21:09:05 +02:00
Anuruth Lertpiya
5906d89f8d
Added support for serving behind a reverse proxy
...
- Added support for specifying response headers for each backend
- Allowing users to set `X-Accel-Buffering: no` to disable buffering for streaming responses in nginx
- Updated `configuration.md` to document the new configuration options
- Modified Vite config to build with `base: "./"`, making assets be accessed via relative paths
- Updated API_BASE to use `document.baseURI`, allowing API calls to be made relative to the base path
2025-09-29 12:43:10 +00:00
0ecd55c354
Start with host environment for instances
2025-09-28 21:37:48 +02:00
808092decf
Initialize context in Start method for command execution
2025-09-28 20:51:11 +02:00
fa9335663a
Parse backend env vars from env vars
2025-09-28 15:22:01 +02:00
c984d95723
Add environment variable support to instance options and command building
2025-09-28 14:42:10 +02:00
50e1355205
Add environment field to BackendSettings for improved configuration
2025-09-28 14:42:10 +02:00
Anuruth Lertpiya
f496a28f04
fix: InstancesDir and LogsDir not being relative path to DataDir when not set
2025-09-27 18:14:25 +00:00
Anuruth Lertpiya
3a979da815
fix: llamactl reads config file per documentation
...
- Added logging to track config file reading operations
- llamactl now properly reads config files from the expected locations ("llamactl.yaml" and "config.yaml" under current directory)
2025-09-27 17:03:54 +00:00
2cd9d374a7
Add Docker badge to UI
2025-09-25 23:04:24 +02:00
031d6c7017
Update Docker command arguments for llama-server and vllm with volume mounts
2025-09-25 22:51:51 +02:00
282344af23
Fix docker command args building
2025-09-25 22:51:40 +02:00
bc9e0535c3
Refactor command building and argument handling
2025-09-25 22:05:46 +02:00
ba0f877185
Fix tests
2025-09-24 21:35:44 +02:00
840a7bc650
Add Docker command handling for backend options and refactor command building
2025-09-24 21:34:54 +02:00