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=[

app/plugins/builtins/ai_proactive/services.py

@@ -33,22 +33,22 @@ logger = logging.getLogger(__name__)
 
 litellm.suppress_debug_info = True
 
-async def _get_llm_api_key(db: AsyncSession, tenant_id: uuid.UUID) -> tuple[str | None, str | None]:
+async def _get_llm_api_key(db: AsyncSession, tenant_id: uuid.UUID) -> tuple[str | None, str | None, str | None]:
-    """Get API key and base_url from the default AI provider in the DB.
+    """Get API key, base_url and provider_type from the default AI provider in the DB.
 
     Falls back to API_KEY_OLLAMA_CLOUD env var if no provider found.
-    Returns (api_key, base_url).
+    Returns (api_key, base_url, provider_type).
     """
     try:
         from app.plugins.builtins.ai_assistant.services import get_default_provider
         provider = await get_default_provider(db, tenant_id)
         if provider and provider.api_key:
-            return provider.api_key, provider.base_url
+            return provider.api_key, provider.base_url, provider.provider_type
     except Exception:
         logger.debug("Failed to get provider from DB, falling back to env")
     # Fallback to env var
     env_key = os.environ.get('API_KEY_OLLAMA_CLOUD', '')
-    return (env_key if env_key else None), None
+    return (env_key if env_key else None), None, None
 
 # ─── SSE Push Infrastructure ───
 
@@ -400,11 +400,18 @@ async def generate_suggestion(
     # Get API key from DB (like ai_assistant does) or fall back to env
     api_key = None
     api_base = None
+    provider_type = None
     if db and tenant_id:
-        api_key, api_base = await _get_llm_api_key(db, tenant_id)
+        api_key, api_base, provider_type = await _get_llm_api_key(db, tenant_id)
     if not api_key:
         api_key = os.environ.get('API_KEY_OLLAMA_CLOUD', '') or None
 
+    # Build model string with provider prefix (like ai_assistant build_litellm_params)
+    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=[