leocrm/app/plugins/builtins/unified_search/providers/workflow_provider.py

"""Workflow search provider — FTS search on workflows and workflow_instances tables."""

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 WorkflowSearchProvider(BaseSearchProvider):
    """Search provider for Workflow entities (definitions and instances)."""

    entity_type = "workflow"
    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 workflows name/description and workflow_instances status."""
        if visible_ids is not None:
            sql = text(
                """
                SELECT w.id, w.tenant_id, w.name, w.description, w.trigger_event,
                       w.is_active,
                       ts_rank(
                           to_tsvector('pg_catalog.german',
                               coalesce(w.name, '') || ' ' || coalesce(w.description, '')),
                           to_tsquery('pg_catalog.german', :q)
                       ) AS rank
                FROM workflows w
                WHERE w.tenant_id = :tid
                  AND to_tsvector('pg_catalog.german',
                       coalesce(w.name, '') || ' ' || coalesce(w.description, ''))
                       @@ to_tsquery('pg_catalog.german', :q)
                  AND w.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 w.id, w.tenant_id, w.name, w.description, w.trigger_event,
                       w.is_active,
                       ts_rank(
                           to_tsvector('pg_catalog.german',
                               coalesce(w.name, '') || ' ' || coalesce(w.description, '')),
                           to_tsquery('pg_catalog.german', :q)
                       ) AS rank
                FROM workflows w
                WHERE w.tenant_id = :tid
                  AND to_tsvector('pg_catalog.german',
                       coalesce(w.name, '') || ' ' || coalesce(w.description, ''))
                       @@ 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 workflows — 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 workflow name + description."""
        sql = text(
            """
            SELECT name, description
            FROM workflows
            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 ""
        parts = [row.get("name", ""), row.get("description", "")]
        return " ".join(str(p) for p in parts if p)

    def to_search_result(self, entity: object) -> dict[str, Any]:
        """Convert workflow to search result dict."""
        if isinstance(entity, dict):
            entity_id = str(entity.get("id", ""))
            name = entity.get("name", "")
            description = entity.get("description", "")
            trigger_event = entity.get("trigger_event", "")
            is_active = entity.get("is_active", True)
            score = entity.get("rank", 0.0)
        else:
            entity_id = str(getattr(entity, "id", ""))
            name = getattr(entity, "name", "")
            description = getattr(entity, "description", "")
            trigger_event = getattr(entity, "trigger_event", "")
            is_active = getattr(entity, "is_active", True)
            score = getattr(entity, "rank", 0.0)
        return {
            "entity_type": self.entity_type,
            "entity_id": entity_id,
            "title": name,
            "snippet": description or "",
            "score": float(score) if score else 0.0,
            "data": {
                "trigger_event": trigger_event,
                "is_active": is_active,
            },
        }