Compare commits

...

1 Commits

Author SHA1 Message Date
Benson Wong 4413881b2d proxy: actually add /v1/responses endpoint (#449)
ref: #448
2026-01-01 13:35:45 -08:00
+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)