steve/llama-swap
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

proxy: actually add /v1/responses endpoint (#449)

Browse Source 
ref: #448
This commit is contained in:
Benson Wong
2026-01-01 13:35:45 -08:00
committed by GitHub
parent 8df5e8563b
commit 4413881b2d
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
proxy/proxymanager.go
+1
View File
@@ -277,6 +277,7 @@ func (pm *ProxyManager) setupGinEngine() {
// Set up routes using the Gin engine // Set up routes using the Gin engine
// Protected routes use pm.apiKeyAuth() middleware // Protected routes use pm.apiKeyAuth() middleware
pm.ginEngine.POST("/v1/chat/completions", pm.apiKeyAuth(), pm.proxyInferenceHandler) 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 // Support legacy /v1/completions api, see issue #12
pm.ginEngine.POST("/v1/completions", pm.apiKeyAuth(), 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) // Support anthropic /v1/messages (added https://github.com/ggml-org/llama.cpp/pull/17570)