feat(B-LLM): Zentraler LLM Client — llm_complete() + llm_embed() + Migration + Tests + Doku

B-LLM: llm_client.py um generische llm_complete() und llm_embed() erweitert
- Provider-Auswahl, API-Key-Auflösung, Error-Handling, Cost-Tracking
- Retry mit Exponential-Backoff für transient errors
- Timeout konfigurierbar
- Helper: get_api_credentials(), build_model(), _classify_error()

B-LLM-MIG: Alle 8 direkten litellm.acompletion() Calls auf llm_complete() umgestellt
- agent_runner.py, query_understanding.py (2x), ai_proactive (3x), ai_assistant (2x)
- 0 verbleibende direkte litellm.acompletion() Calls außerhalb llm_client.py

B-LLM-TEST: 39 Tests in test_llm_client.py — alle grün
- Mock mode, error handling, embed, helpers, backward compat

B-LLM-DOC: Plugin-Dev-Guide Kapitel 7 (LLM Integration) hinzugefügt

app/plugins/builtins/ai_proactive/context_tools.py

@@ -117,8 +117,6 @@ async def search_related_handler(arguments: dict[str, Any], context: dict[str, A
 async def summarize_mail_thread_handler(arguments: dict[str, Any], context: dict[str, Any]) -> str:
     """Summarize a mail thread using LLM."""
     try:
-        import litellm
-
         db, tenant_id, _ = await _get_db_and_tenant(context)
         thread_id = arguments["thread_id"]
         limit = arguments.get("limit", 20)
@@ -139,7 +137,9 @@ async def summarize_mail_thread_handler(arguments: dict[str, Any], context: dict
             for m in mails
         )
 
-        response = await litellm.acompletion(
+        from app.ai.llm_client import llm_complete
+
+        result = await llm_complete(
             model="gpt-4o-mini",
             messages=[
                 {
@@ -151,7 +151,7 @@ async def summarize_mail_thread_handler(arguments: dict[str, Any], context: dict
             temperature=0.3,
             max_tokens=300,
         )
-        summary = response.choices[0].message.content or ""
+        summary = result["content"] or ""
         return json.dumps({"summary": summary, "count": len(mails)}, default=str)
     except Exception as e:
         logger.exception("summarize_mail_thread_handler failed")