add /completion endpoint (#275)

* feat: add /completion endpoint
* chore: reformat using gofmt

proxy/proxymanager.go

@@ -203,6 +203,9 @@ func (pm *ProxyManager) setupGinEngine() {
 	// llama-server's /infill endpoint for code infilling
 	pm.ginEngine.POST("/infill", mm, pm.proxyOAIHandler)
 
+	// llama-server's /completion endpoint
+	pm.ginEngine.POST("/completion", mm, pm.proxyOAIHandler)
+
 	// Support audio/speech endpoint
 	pm.ginEngine.POST("/v1/audio/speech", pm.proxyOAIHandler)
 	pm.ginEngine.POST("/v1/audio/transcriptions", pm.proxyOAIPostFormHandler)

proxy/proxymanager_test.go

@@ -833,6 +833,28 @@ func TestProxyManager_HealthEndpoint(t *testing.T) {
 	assert.Equal(t, "OK", rec.Body.String())
 }
 
+// Ensure the custom llama-server /completion endpoint proxies correctly
+func TestProxyManager_CompletionEndpoint(t *testing.T) {
+	config := AddDefaultGroupToConfig(Config{
+		HealthCheckTimeout: 15,
+		Models: map[string]ModelConfig{
+			"model1": getTestSimpleResponderConfig("model1"),
+		},
+		LogLevel: "error",
+	})
+
+	proxy := New(config)
+	defer proxy.StopProcesses(StopWaitForInflightRequest)
+
+	reqBody := `{"model":"model1"}`
+	req := httptest.NewRequest("POST", "/completion", bytes.NewBufferString(reqBody))
+	w := httptest.NewRecorder()
+
+	proxy.ServeHTTP(w, req)
+	assert.Equal(t, http.StatusOK, w.Code)
+	assert.Contains(t, w.Body.String(), "model1")
+}
+
 func TestProxyManager_StartupHooks(t *testing.T) {
 
 	// using real YAML as the configuration has gotten more complex