feat: Oracle Canvas, Revision History and Canvas Sharing (#33)

Co-authored-by: Sagnik <sagnik7896@gmail.com>
Reviewed-on: #33

backend/services/runtime_llm_service.py

@@ -13,15 +13,17 @@ import httpx
 
 logger = logging.getLogger("velocity.runtime_llm")
 
-OLLAMA_BASE_URL = os.getenv("OLLAMA_BASE_URL", "http://127.0.0.1:11434").rstrip("/")
-OLLAMA_CHAT_URL = os.getenv("OLLAMA_CHAT_URL", f"{OLLAMA_BASE_URL}/v1/chat/completions")
-OLLAMA_TAGS_URL = os.getenv("OLLAMA_TAGS_URL", f"{OLLAMA_BASE_URL}/api/tags")
-OLLAMA_DEFAULT_MODEL = os.getenv("OLLAMA_MODEL", "qwen3.5:27b")
-
-NEMOCLAW_BASE_URL = os.getenv("NEMOCLAW_BASE_URL", "").rstrip("/")
-NEMOCLAW_CHAT_URL = (os.getenv("NEMOCLAW_CHAT_URL") or f"{NEMOCLAW_BASE_URL}/v1/chat/completions").rstrip("/") if NEMOCLAW_BASE_URL else ""
-NEMOCLAW_DEFAULT_MODEL = os.getenv("NEMOCLAW_MODEL", "nvidia/nemotron-3-super-120b-a12b")
-NEMOCLAW_API_TOKEN = os.getenv("NEMOCLAW_API_TOKEN", "")
+SGLANG_BASE_URL = os.getenv(
+    "SGLANG_BASE_URL",
+    os.getenv("LLM_BASE_URL", os.getenv("OLLAMA_BASE_URL", "https://llm.desineuron.in")),
+).rstrip("/")
+SGLANG_CHAT_URL = os.getenv("SGLANG_CHAT_URL", f"{SGLANG_BASE_URL}/v1/chat/completions")
+SGLANG_MODELS_URL = os.getenv("SGLANG_MODELS_URL", f"{SGLANG_BASE_URL}/v1/models")
+SGLANG_DEFAULT_MODEL = os.getenv(
+    "SGLANG_MODEL",
+    os.getenv("OLLAMA_MODEL", "qwen3.6:35b-a3b"),
+)
+SGLANG_API_TOKEN = os.getenv("SGLANG_API_TOKEN", "")
 
 RUNTIME_LLM_TIMEOUT_S = float(os.getenv("RUNTIME_LLM_TIMEOUT_S", "90.0"))
 RUNTIME_LLM_CONCURRENCY = int(os.getenv("RUNTIME_LLM_BATCH_CONCURRENCY", "2"))
@@ -57,40 +59,30 @@ class RuntimeLLMService:
         self._jobs: dict[str, dict[str, Any]] = {}
 
     def _provider_catalog(self) -> list[RuntimeProvider]:
-        providers: list[RuntimeProvider] = []
-        if OLLAMA_CHAT_URL:
-            providers.append(
-                RuntimeProvider(
-                    provider_id="ollama",
-                    base_url=OLLAMA_BASE_URL,
-                    chat_url=OLLAMA_CHAT_URL,
-                    default_model=OLLAMA_DEFAULT_MODEL,
-                )
+        if not SGLANG_CHAT_URL:
+            return []
+        return [
+            RuntimeProvider(
+                provider_id="sglang",
+                base_url=SGLANG_BASE_URL,
+                chat_url=SGLANG_CHAT_URL,
+                default_model=SGLANG_DEFAULT_MODEL,
+                auth_token=SGLANG_API_TOKEN or None,
             )
-        if NEMOCLAW_CHAT_URL:
-            providers.append(
-                RuntimeProvider(
-                    provider_id="nemoclaw",
-                    base_url=NEMOCLAW_BASE_URL,
-                    chat_url=NEMOCLAW_CHAT_URL,
-                    default_model=NEMOCLAW_DEFAULT_MODEL,
-                    auth_token=NEMOCLAW_API_TOKEN or None,
-                )
-            )
-        return providers
+        ]
 
     def get_provider(self, provider_id: str | None) -> RuntimeProvider:
         providers = {provider.provider_id: provider for provider in self._provider_catalog()}
+        if provider_id in {"ollama", "nemoclaw"}:
+            provider_id = "sglang"
         if provider_id:
             provider = providers.get(provider_id)
             if provider is None:
                 raise ValueError(f"Unknown provider '{provider_id}'.")
             return provider
 
-        if "nemoclaw" in providers:
-            return providers["nemoclaw"]
-        if "ollama" in providers:
-            return providers["ollama"]
+        if "sglang" in providers:
+            return providers["sglang"]
         raise ValueError("No runtime LLM providers are configured.")
 
     async def list_providers(self) -> list[dict[str, Any]]:
@@ -101,28 +93,18 @@ class RuntimeLLMService:
             error: str | None = None
 
             try:
-                if provider.provider_id == "ollama":
-                    async with httpx.AsyncClient(timeout=10.0) as client:
-                        response = await client.get(OLLAMA_TAGS_URL)
-                        response.raise_for_status()
-                    payload = response.json()
-                    models = [str(item.get("name", "")).strip() for item in payload.get("models", []) if item.get("name")]
-                    if provider.default_model not in models:
-                        models.insert(0, provider.default_model)
-                    status = "online"
-                else:
-                    async with httpx.AsyncClient(timeout=10.0) as client:
-                        response = await client.post(
-                            provider.chat_url,
-                            json={
-                                "model": provider.default_model,
-                                "messages": [{"role": "user", "content": "ping"}],
-                                "max_tokens": 4,
-                            },
-                            headers=provider.headers,
-                        )
-                        response.raise_for_status()
-                    status = "online"
+                async with httpx.AsyncClient(timeout=10.0) as client:
+                    response = await client.get(SGLANG_MODELS_URL, headers=provider.headers)
+                    response.raise_for_status()
+                payload = response.json()
+                models = [
+                    str(item.get("id", "")).strip()
+                    for item in payload.get("data", [])
+                    if item.get("id")
+                ]
+                if provider.default_model not in models:
+                    models.insert(0, provider.default_model)
+                status = "online"
             except Exception as exc:  # pragma: no cover - network/runtime dependent
                 error = str(exc)