cc3ac9a43d
feat: Unified Messaging System — kommunikation plugin, AI/Proactive/System participants, MessageSidebar, Rich Content Renderer
...
Phase 1: Backend plugin kommunikation (13 files, 10 tables, REST API, WebSocket, RBAC, DMS Bridge, Participant Registry, Mini-App Registry, Search Provider)
Phase 2: AI plugins as participants (ai_assistant + ai_proactive dock as participants, heartbeat job)
Phase 3: system_notif plugin (system events → chat messages, pinned System room)
Phase 4: Frontend MessageSidebar (replaces AISidebar, same design, comm API client, WebSocket hook, commStore)
Phase 5: Rich Content Block Renderer (11 components: Markdown, HTML, Image, Audio, Video, File, ActionCard, ContactCard, MiniApp, BlockRenderer)
BasePlugin: added services property + _container in on_activate
2026-07-22 01:22:15 +02:00
cf75680583
Unified contacts model: Rentman-style type field (company/person), inline addresses, ContactPerson 1:N, all Rentman fields except rental-specific
2026-07-19 21:12:49 +02:00
5db7364071
fix: increase max_tokens for LLM suggestions to prevent truncated JSON
2026-07-19 02:32:39 +02:00
5c3fc027bc
fix: strip markdown code fences from LLM responses before json.loads
...
- glm-5.2 returns JSON wrapped in ```json ... ``` code fences
- Added fence stripping in services.py, query_understanding.py, jobs.py
2026-07-19 02:30:07 +02:00
4a43745b50
fix: unified_search + ai_proactive get API key from DB, fix model names for Ollama Cloud
...
- query_understanding.py: get API key/base_url/provider_type from ai_providers DB
- embedding.py: get API key from DB, pass db+tenant_id through call chain
- routes.py: pass db+tenant_id to llm_analyze_query and llm_aggregate_results
- search_engine.py: pass db+tenant_id to generate_embedding
- unified_search/jobs.py: pass db+tenant_id to generate_embedding
- Fix all default model names: ollama/deepseek-v4 -> ollama/deepseek-v4-flash
- Ollama Cloud has no embedding endpoint; embedding calls fail gracefully
2026-07-19 02:22:25 +02:00
ef4f0cc494
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
2026-07-19 01:51:14 +02:00
7f8344bc24
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
2026-07-19 01:36:16 +02:00
b1153e0c54
fix: add updated_at columns to ai_proactive migration
...
- ai_proactive_suggestions: add updated_at TIMESTAMPTZ
- ai_proactive_context_log: add updated_at TIMESTAMPTZ
TenantMixin inherits TimestampMixin which expects both created_at and updated_at.
Missing updated_at caused 500 errors on /ai-proactive/context POST.
2026-07-18 18:22:16 +02:00
df82796023
fix: add deleted_at columns to ai_proactive migration
...
- ai_proactive_suggestions: add deleted_at TIMESTAMPTZ
- ai_proactive_context_log: add deleted_at TIMESTAMPTZ
- ai_proactive_settings: add deleted_at TIMESTAMPTZ
ORM models expect deleted_at for soft-delete support.
2026-07-18 16:18:45 +02:00
8cebb4f4e9
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
2026-07-18 11:21:51 +02:00
Agent Zero