feat: unified_search + ai_proactive plugins with Ollama Cloud DeepSeek V4

- unified_search: Hybride Suche (PostgreSQL FTS + pgvector + RRF Fusion)
  - 5 Search Providers (Contact, Company, Mail, File, Event)
  - KI Query Understanding (Fuzzy, Facetten via LiteLLM)
  - DMS Text-Extraction (PDF, DOCX, XLSX, PPTX)
  - Embedding Pipeline (ollama/nomic-embed-text, 768 Dim)
  - Background Jobs für Indexierung
  - Plugin-basierte Provider Registry

- ai_proactive: Proaktiver KI-Agent
  - Context-Tracking (Frontend → Backend → Event Bus)
  - Proactive Engine mit LLM Suggestion-Generierung
  - SSE Real-time Push an Frontend
  - 6 AI Tools für Tool Registry
  - Rate-Limiting + User Settings
  - Deep Analysis Background Jobs

- Frontend Integration:
  - useAIContext Hook, SuggestionSidebar, SuggestionBadge
  - ProactiveAISettings Page, Search API Client
  - Globale Suche auf neue API umgestellt

- Tests: test_unified_search.py + test_ai_proactive.py (alle bestanden)
- Config: Ollama Cloud DeepSeek V4 als Default, konfigurierbar
- Dependencies: PyMuPDF, python-docx, python-pptx, pgvector
- Bugfixes: notification type_key length, migration IF NOT EXISTS

app/plugins/builtins/unified_search/migrations/0002_embeddings.sql

@@ -0,0 +1,24 @@
+-- Unified Search: Embedding columns and HNSW indexes
+
+-- ─── Mails ───
+ALTER TABLE mails ADD COLUMN IF NOT EXISTS embedding vector(768);
+CREATE INDEX IF NOT EXISTS ix_mails_embedding ON mails USING hnsw(embedding vector_cosine_ops);
+
+-- ─── Contacts ───
+ALTER TABLE contacts ADD COLUMN IF NOT EXISTS embedding vector(768);
+CREATE INDEX IF NOT EXISTS ix_contacts_embedding ON contacts USING hnsw(embedding vector_cosine_ops);
+
+-- ─── Companies ───
+ALTER TABLE companies ADD COLUMN IF NOT EXISTS embedding vector(768);
+CREATE INDEX IF NOT EXISTS ix_companies_embedding ON companies USING hnsw(embedding vector_cosine_ops);
+
+-- ─── Files (content_text already added in 0001) ───
+ALTER TABLE files ADD COLUMN IF NOT EXISTS embedding vector(768);
+CREATE INDEX IF NOT EXISTS ix_files_embedding ON files USING hnsw(embedding vector_cosine_ops);
+
+-- ─── Calendar Entries ───
+ALTER TABLE calendar_entries ADD COLUMN IF NOT EXISTS embedding vector(768);
+CREATE INDEX IF NOT EXISTS ix_cal_embedding ON calendar_entries USING hnsw(embedding vector_cosine_ops);
+
+-- ─── Tags (shorter dimension for short text) ───
+ALTER TABLE tags ADD COLUMN IF NOT EXISTS embedding vector(384);