fix: get LLM API key from DB instead of env var

- ai_proactive now reads API key from ai_providers table (like ai_assistant)
- Falls back to API_KEY_OLLAMA_CLOUD env var if no provider found
- Fixes: proactive engine could not generate suggestions because API key was empty

app/plugins/builtins/ai_proactive/jobs.py

@@ -187,23 +187,35 @@ async def deep_analysis(
 
         # Generate extended suggestion with deep analysis prompt
         model = settings.model or "ollama/deepseek-v4"
+
+        # 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)
+        if not api_key:
+            api_key = os.environ.get('API_KEY_OLLAMA_CLOUD', '') or None
+
+        litellm_kwargs: dict[str, Any] = dict(
+            model=model,
+            messages=[
+                {"role": "system", "content": DEEP_SYSTEM_PROMPT},
+                {
+                    "role": "user",
+                    "content": json.dumps(
+                        extended_context, default=str, ensure_ascii=False
+                    ),
+                },
+            ],
+            temperature=0.3,
+            max_tokens=800,
+            response_format={"type": "json_object"},
+        )
+        if api_key:
+            litellm_kwargs["api_key"] = api_key
+        if api_base:
+            litellm_kwargs["api_base"] = api_base
+
         try:
-            response = await litellm.acompletion(
+            response = await litellm.acompletion(**litellm_kwargs)
-                model=model,
-                messages=[
-                    {"role": "system", "content": DEEP_SYSTEM_PROMPT},
-                    {
-                        "role": "user",
-                        "content": json.dumps(
-                            extended_context, default=str, ensure_ascii=False
-                        ),
-                    },
-                ],
-                temperature=0.3,
-                max_tokens=800,
-                response_format={"type": "json_object"},
-                api_key=OLLAMA_API_KEY,
-            )
             content = response.choices[0].message.content
             if not content:
                 return

app/plugins/builtins/ai_proactive/services.py

@@ -33,7 +33,22 @@ logger = logging.getLogger(__name__)
 
 litellm.suppress_debug_info = True
 
-OLLAMA_API_KEY = os.environ.get('API_KEY_OLLAMA_CLOUD', '')
+async def _get_llm_api_key(db: AsyncSession, tenant_id: uuid.UUID) -> tuple[str | None, str | None]:
+    """Get API key and base_url 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).
+    """
+    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
+    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
 
 # ─── SSE Push Infrastructure ───
 
@@ -372,7 +387,8 @@ Antworte mit JSON:
 
 
 async def generate_suggestion(
-    context_data: dict[str, Any], settings: ProactiveSettings
+    context_data: dict[str, Any], settings: ProactiveSettings,
+    db: AsyncSession | None = None, tenant_id: uuid.UUID | None = None,
 ) -> dict[str, Any] | None:
     """LLM generates a suggestion from context data.
 
@@ -380,21 +396,35 @@ async def generate_suggestion(
     or None on failure.
     """
     model = settings.model or "ollama/deepseek-v4"
+
+    # Get API key from DB (like ai_assistant does) or fall back to env
+    api_key = None
+    api_base = None
+    if db and tenant_id:
+        api_key, api_base = await _get_llm_api_key(db, tenant_id)
+    if not api_key:
+        api_key = os.environ.get('API_KEY_OLLAMA_CLOUD', '') or None
+
+    litellm_kwargs: dict[str, Any] = dict(
+        model=model,
+        messages=[
+            {"role": "system", "content": SYSTEM_PROMPT},
+            {
+                "role": "user",
+                "content": json.dumps(context_data, default=str, ensure_ascii=False),
+            },
+        ],
+        temperature=0.3,
+        max_tokens=500,
+        response_format={"type": "json_object"},
+    )
+    if api_key:
+        litellm_kwargs["api_key"] = api_key
+    if api_base:
+        litellm_kwargs["api_base"] = api_base
+
     try:
-        response = await litellm.acompletion(
+        response = await litellm.acompletion(**litellm_kwargs)
-            model=model,
-            messages=[
-                {"role": "system", "content": SYSTEM_PROMPT},
-                {
-                    "role": "user",
-                    "content": json.dumps(context_data, default=str, ensure_ascii=False),
-                },
-            ],
-            temperature=0.3,
-            max_tokens=500,
-            response_format={"type": "json_object"},
-            api_key=OLLAMA_API_KEY,
-        )
         content = response.choices[0].message.content
         if not content:
             return None
@@ -481,7 +511,7 @@ async def handle_context_change(payload: dict[str, Any]) -> None:
         context_data = await gather_context(db, entity_type, entity_id, tenant_id)
 
         # Generate suggestion
-        suggestion_data = await generate_suggestion(context_data, settings)
+        suggestion_data = await generate_suggestion(context_data, settings, db, tenant_id)
         if suggestion_data is None:
             logger.debug("handle_context_change: no suggestion generated")
             return