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
parent 4c9295de21
commit 8cebb4f4e9
52 changed files with 6493 additions and 41 deletions
@@ -0,0 +1,103 @@
+"""Pydantic v2 schemas for the AI Proactive plugin API."""
+
+from __future__ import annotations
+
+from datetime import datetime
+from typing import Any
+
+from pydantic import BaseModel, Field
+
+
+class ContextReport(BaseModel):
+    """Frontend reports the current page/entity context."""
+
+    page: str = Field(..., description="Current page path")
+    entity_type: str | None = Field(None, description="Entity type being viewed")
+    entity_id: str | None = Field(None, description="Entity ID being viewed")
+    entity_data: dict[str, Any] | None = Field(
+        None, description="Additional entity metadata"
+    )
+
+
+class SuggestionAction(BaseModel):
+    """A suggested CRM action."""
+
+    method: str = Field(..., description="HTTP method")
+    path: str = Field(..., description="API path")
+    body: dict[str, Any] | None = Field(None, description="Request body")
+    description: str = Field(..., description="Human-readable description")
+
+
+class SuggestionResponse(BaseModel):
+    """API response for a single suggestion."""
+
+    id: str
+    entity_type: str
+    entity_id: str | None
+    suggestion_type: str
+    title: str
+    content: str
+    confidence: float
+    actions: list[dict[str, Any]]
+    created_at: datetime
+    is_dismissed: bool
+    is_acted_upon: bool = False
+
+
+class SuggestionListResponse(BaseModel):
+    """Paginated list of suggestions."""
+
+    items: list[SuggestionResponse]
+    total: int
+
+
+class ActRequest(BaseModel):
+    """Execute a suggested action by index."""
+
+    action_index: int = Field(..., ge=0, description="Index into actions array")
+
+
+class ActResponse(BaseModel):
+    """Result of executing a suggested action."""
+
+    success: bool
+    data: dict[str, Any] | None = None
+    error: str | None = None
+
+
+class SettingsResponse(BaseModel):
+    """Proactive AI settings for the current user."""
+
+    enabled: bool
+    suggestion_categories: list[str]
+    confidence_threshold: float
+    rate_limit_seconds: int
+    model: str
+    available_models: list[str] = Field(default_factory=lambda: [
+        'ollama/deepseek-v4',
+        'ollama/deepseek-v4-pro',
+        'ollama/llama3.2',
+        'ollama/gpt-4o-mini',
+        'gpt-4o-mini',
+    ])
+
+
+class SettingsUpdate(BaseModel):
+    """Partial update for proactive AI settings."""
+
+    enabled: bool | None = None
+    suggestion_categories: list[str] | None = None
+    confidence_threshold: float | None = None
+    rate_limit_seconds: int | None = None
+    model: str | None = None
+
+
+class StatsResponse(BaseModel):
+    """Proactive AI usage statistics."""
+
+    total_suggestions: int = 0
+    dismissed: int = 0
+    acted_upon: int = 0
+    active: int = 0
+    dismiss_rate: float = 0.0
+    act_rate: float = 0.0