feat(E): Unified Search — 24 Tasks complete

- SPIKE-E: FTS+Vector+Permission benchmark on 10k records (all <30ms) - E-PROV: supports_fts/vector/rag/graph capability flags on all providers - E-FTS/VEC: All 11 providers refactored to BaseSearchProvider with permission filtering - E-PERM: Over-fetch strategy for vector+permission (15x faster than ANY() filter) - E-FUSE: rrf_fusion_multi() for N-way RRF over FTS+Vector+RAG+Graph - E-LLM: Query understanding cleaned up to use central llm_complete() - E-CHUNK: Document chunking module + document_chunks table with HNSW index - E-EMB: Chunk embedding ARQ jobs (index_file_chunks, reindex_chunks) - E-RAG: RAG retrieval via FileSearchProvider.search_rag() - E-GRAPH: GraphRAG BFS traversal via GraphRAGSearchProvider.search_graph() - E-IX-EVT: Auto-indexing via outbox events + delete/cleanup handlers - E-IX-RE: Batch reindex with progress tracking + reindex_all job - E-DATA-LIFE: Lifecycle module (remove/rebuild/restore/correct) + API endpoints - E-K-MEM: AgentMemorySearchProvider - E-P-AI: AIChatSearchProvider - E-P-WF: WorkflowSearchProvider - E-P-COMM: ConversationSearchProvider verified (already on BaseSearchProvider) - E-API: Filter params (date_from/to, tags, sort) + /facets endpoint - E-TOOL: unified_search AI tool registered in ToolRegistry - E-MCP: Search tool in MCP server with normal RBAC/tenant checks - E-UI-CMD: CommandPalette (Cmd+K) with debounced search + recent searches - E-UI-FAC: SearchFacets, SearchResultCard, SavedSearches components - E-TEST: 40 new tests in test_unified_search_phase_e.py (105 total green) - E-DOC: api-documentation.md, plugin-development-guide.md, test-strategy.md updated 105 tests passing, TypeScript clean.
2026-08-14 01:34:58 +02:00
parent 60f30d021b
commit 3d9b76cea4
45 changed files with 5378 additions and 402 deletions
@@ -0,0 +1,137 @@
+"""AI chat search provider — FTS search on ai_chat_messages table."""
+
+from __future__ import annotations
+
+import logging
+import uuid
+from typing import Any
+
+from sqlalchemy import text
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.plugins.builtins.unified_search.base_provider import BaseSearchProvider
+
+logger = logging.getLogger(__name__)
+
+
+class AIChatSearchProvider(BaseSearchProvider):
+    """Search provider for AI chat messages."""
+
+    entity_type = "ai_chat"
+    supports_fts = True
+    supports_vector = False
+
+    async def _search_fts_filtered(
+        self,
+        db: AsyncSession,
+        tsquery: str,
+        tenant_id: uuid.UUID,
+        limit: int,
+        visible_ids: set[uuid.UUID] | None,
+    ) -> list[dict[str, Any]]:
+        """Full-text search on ai_chat_messages.content, joined with sessions for title."""
+        if visible_ids is not None:
+            sql = text(
+                """
+                SELECT m.id, m.tenant_id, m.session_id, m.role, m.content,
+                       m.model_used, m.tokens,
+                       s.title AS session_title,
+                       ts_rank(to_tsvector('pg_catalog.german', m.content),
+                               to_tsquery('pg_catalog.german', :q)) AS rank
+                FROM ai_chat_messages m
+                JOIN ai_chat_sessions s ON s.id = m.session_id
+                WHERE m.tenant_id = :tid
+                  AND to_tsvector('pg_catalog.german', m.content) @@ to_tsquery('pg_catalog.german', :q)
+                  AND m.id = ANY(:visible_ids)
+                ORDER BY rank DESC
+                LIMIT :lim
+                """
+            )
+            result = await db.execute(
+                sql,
+                {
+                    "q": tsquery,
+                    "tid": tenant_id,
+                    "lim": limit,
+                    "visible_ids": list(visible_ids),
+                },
+            )
+        else:
+            sql = text(
+                """
+                SELECT m.id, m.tenant_id, m.session_id, m.role, m.content,
+                       m.model_used, m.tokens,
+                       s.title AS session_title,
+                       ts_rank(to_tsvector('pg_catalog.german', m.content),
+                               to_tsquery('pg_catalog.german', :q)) AS rank
+                FROM ai_chat_messages m
+                JOIN ai_chat_sessions s ON s.id = m.session_id
+                WHERE m.tenant_id = :tid
+                  AND to_tsvector('pg_catalog.german', m.content) @@ to_tsquery('pg_catalog.german', :q)
+                ORDER BY rank DESC
+                LIMIT :lim
+                """
+            )
+            result = await db.execute(
+                sql,
+                {"q": tsquery, "tid": tenant_id, "lim": limit},
+            )
+        rows = result.mappings().all()
+        return [dict(r) for r in rows]
+
+    async def _search_vector_filtered(
+        self,
+        db: AsyncSession,
+        embedding: list[float],
+        tenant_id: uuid.UUID,
+        limit: int,
+        visible_ids: set[uuid.UUID] | None,
+    ) -> list[dict[str, Any]]:
+        """No vector support for chat messages — return empty list."""
+        return []
+
+    async def get_embedding_text(
+        self, db: AsyncSession, entity_id: uuid.UUID, tenant_id: uuid.UUID
+    ) -> str:
+        """Get text for embedding generation — returns message content."""
+        sql = text(
+            """
+            SELECT content
+            FROM ai_chat_messages
+            WHERE id = :eid AND tenant_id = :tid
+            """
+        )
+        result = await db.execute(sql, {"eid": entity_id, "tid": tenant_id})
+        row = result.mappings().first()
+        if not row:
+            return ""
+        return str(row.get("content", ""))
+
+    def to_search_result(self, entity: object) -> dict[str, Any]:
+        """Convert chat message to search result dict."""
+        if isinstance(entity, dict):
+            entity_id = str(entity.get("id", ""))
+            content = entity.get("content", "")
+            role = entity.get("role", "")
+            session_title = entity.get("session_title", "")
+            session_id = str(entity.get("session_id", ""))
+            score = entity.get("rank", 0.0)
+        else:
+            entity_id = str(getattr(entity, "id", ""))
+            content = getattr(entity, "content", "")
+            role = getattr(entity, "role", "")
+            session_title = getattr(entity, "session_title", "")
+            session_id = str(getattr(entity, "session_id", ""))
+            score = getattr(entity, "rank", 0.0)
+        return {
+            "entity_type": self.entity_type,
+            "entity_id": entity_id,
+            "title": session_title or content[:80] if content else "",
+            "snippet": content,
+            "score": float(score) if score else 0.0,
+            "data": {
+                "role": role,
+                "session_id": session_id,
+                "session_title": session_title,
+            },
+        }