feat: add OpenAI-compatible /v1/chat/completions endpoint

app.py

@@ -188,6 +188,52 @@ async def chat_api(request: Request):
     except Exception as e:
         return JSONResponse(status_code=500, content={"error": str(e), "status": "error"})
 
+@app.post("/v1/chat/completions")
+async def chat_completions(request: Request):
+    import time
+    try:
+        body = await request.json()
+        messages = body.get("messages", [])
+        model = body.get("model", PRIMARY_MODEL)
+        max_tokens = int(body.get("max_tokens", 512))
+        temperature = float(body.get("temperature", 0.7))
+
+        user_msg = ""
+        history = []
+        for m in messages:
+            if m.get("role") == "user":
+                user_msg = m.get("content", "")
+            elif m.get("role") == "assistant":
+                history.append((user_msg, m.get("content", "")))
+
+        full_text = ""
+        for chunk in predict(user_msg, history, model, max_tokens, temperature):
+            full_text = chunk
+
+        return JSONResponse(content={
+            "id": f"chatcmpl-{int(time.time())}",
+            "object": "chat.completion",
+            "created": int(time.time()),
+            "model": model,
+            "choices": [
+                {
+                    "index": 0,
+                    "message": {
+                        "role": "assistant",
+                        "content": full_text
+                    },
+                    "finish_reason": "stop"
+                }
+            ],
+            "usage": {
+                "prompt_tokens": len(user_msg.split()),
+                "completion_tokens": len(full_text.split()),
+                "total_tokens": len(user_msg.split()) + len(full_text.split())
+            }
+        })
+    except Exception as e:
+        return JSONResponse(status_code=500, content={"error": str(e)})
+
 @app.get("/api/health")
 async def health_check():
     return JSONResponse(content={