fix: use provider_type for model prefix and base_url for Ollama Cloud

- _get_llm_api_key now returns provider_type
- Model string built with provider_type prefix (openai/deepseek-v4 instead of ollama/deepseek-v4)
- api_base set from provider.base_url (https://ollama.com/v1)
- Fixes: litellm tried localhost:11434 instead of Ollama Cloud

app/plugins/builtins/ai_proactive/jobs.py

@@ -190,10 +190,16 @@ async def deep_analysis(
 
         # Get API key from DB (like ai_assistant does) or fall back to env
         from app.plugins.builtins.ai_proactive.services import _get_llm_api_key
-        api_key, api_base = await _get_llm_api_key(db, tid)
+        api_key, api_base, provider_type = await _get_llm_api_key(db, tid)
         if not api_key:
             api_key = os.environ.get('API_KEY_OLLAMA_CLOUD', '') or None
 
+        # Build model string with provider prefix
+        model = settings.model or "ollama/deepseek-v4"
+        if provider_type:
+            model_parts = model.split("/", 1)
+            model = f"{provider_type}/{model_parts[-1]}"
+
         litellm_kwargs: dict[str, Any] = dict(
             model=model,
             messages=[