From d91075912128e5aac338594783bfa282f0b14ff6 Mon Sep 17 00:00:00 2001
From: Roland Tannous <rolandtannous@gravityq.ai>
Date: Fri, 6 Mar 2026 07:48:09 +0000
Subject: [PATCH] feat: add OpenAI-compatible /v1/chat/completions endpoint

---
 studio/backend/main.py                        |  5 +++
 studio/backend/routes/inference.py            | 37 +++++++++++++++++++
 .../src/features/chat/api/chat-api.ts         |  2 +-
 .../src/features/chat/runtime-provider.tsx    |  2 +-
 4 files changed, 44 insertions(+), 2 deletions(-)

diff --git a/studio/backend/main.py b/studio/backend/main.py
index fca8e581d2..696d8a4d10 100644
--- a/studio/backend/main.py
+++ b/studio/backend/main.py
@@ -96,6 +96,11 @@ app.include_router(auth_router, prefix="/api/auth", tags=["auth"])
 app.include_router(training_router, prefix="/api/train", tags=["training"])
 app.include_router(models_router, prefix="/api/models", tags=["models"])
 app.include_router(inference_router, prefix="/api/inference", tags=["inference"])
+
+# OpenAI-compatible endpoints: mount the same inference router at /v1
+# so external tools (Open WebUI, SillyTavern, etc.) can use the
+# standard /v1/chat/completions path.
+app.include_router(inference_router, prefix="/v1", tags=["openai-compat"])
 app.include_router(datasets_router, prefix="/api/datasets", tags=["datasets"])
 app.include_router(data_recipe_router, prefix="/api/data-recipe", tags=["data-recipe"])
 app.include_router(export_router, prefix="/api/export", tags=["export"])
diff --git a/studio/backend/routes/inference.py b/studio/backend/routes/inference.py
index 156b3237a4..aa4b4ed0cd 100644
--- a/studio/backend/routes/inference.py
+++ b/studio/backend/routes/inference.py
@@ -785,3 +785,40 @@ async def openai_chat_completions(
             backend.reset_generation_state()
             logger.error(f"Error during OpenAI completion: {e}", exc_info=True)
             raise HTTPException(status_code=500, detail=str(e))
+
+
+# =====================================================================
+# OpenAI-Compatible Models Listing  (/models → /v1/models)
+# =====================================================================
+
+@router.get("/models")
+async def openai_list_models(
+    current_subject: str = Depends(get_current_subject),
+):
+    """
+    OpenAI-compatible model listing endpoint.
+
+    Returns the currently loaded model in the format expected by
+    OpenAI-compatible clients (``GET /v1/models``).
+    """
+    models = []
+
+    # Check GGUF backend
+    llama_backend = get_llama_cpp_backend()
+    if llama_backend.is_loaded:
+        models.append({
+            "id": llama_backend.model_identifier,
+            "object": "model",
+            "owned_by": "local",
+        })
+
+    # Check Unsloth backend
+    backend = get_inference_backend()
+    if backend.active_model_name:
+        models.append({
+            "id": backend.active_model_name,
+            "object": "model",
+            "owned_by": "local",
+        })
+
+    return {"object": "list", "data": models}
diff --git a/studio/frontend/src/features/chat/api/chat-api.ts b/studio/frontend/src/features/chat/api/chat-api.ts
index 5d5a9551ef..4276e618ed 100644
--- a/studio/frontend/src/features/chat/api/chat-api.ts
+++ b/studio/frontend/src/features/chat/api/chat-api.ts
@@ -99,7 +99,7 @@ export async function* streamChatCompletions(
   payload: OpenAIChatCompletionsRequest,
   signal: AbortSignal,
 ): AsyncGenerator<OpenAIChatChunk> {
-  const response = await authFetch("/api/inference/chat/completions", {
+  const response = await authFetch("/v1/chat/completions", {
     method: "POST",
     headers: { "Content-Type": "application/json" },
     body: JSON.stringify(payload),
diff --git a/studio/frontend/src/features/chat/runtime-provider.tsx b/studio/frontend/src/features/chat/runtime-provider.tsx
index ce553dcdbf..46e3c697ad 100644
--- a/studio/frontend/src/features/chat/runtime-provider.tsx
+++ b/studio/frontend/src/features/chat/runtime-provider.tsx
@@ -202,7 +202,7 @@ async function generateTitleWithModel(payload: {
     return joined.length > 60 ? joined.slice(0, 60).trimEnd() : joined;
   }
 
-  const response = await authFetch("/api/inference/chat/completions", {
+  const response = await authFetch("/v1/chat/completions", {
     method: "POST",
     headers: { "Content-Type": "application/json" },
     body: JSON.stringify({