dify/api/services/llm_generation_service.py
Yansong Zhang 44491e427c feat(api): enable all sandbox/skill controller routes and resolve dependencies (P0)
Resolve the full dependency chain to enable all previously disabled controllers:

Enabled routes:
- sandbox_files: sandbox file browser API
- sandbox_providers: sandbox provider management API
- app_asset: app asset management API
- skills: skill extraction API
- CLI API blueprint: DifyCli callback endpoints (/cli/api/*)

Dependencies extracted (64 files, ~8000 lines):
- models/sandbox.py, models/app_asset.py: DB models
- core/zip_sandbox/: zip-based sandbox execution
- core/session/: CLI API session management
- core/memory/: base memory + node token buffer
- core/helper/creators.py: helper utilities
- core/llm_generator/: context models, output models, utils
- core/workflow/nodes/command/: command node type
- core/workflow/nodes/file_upload/: file upload node type
- core/app/entities/: app_asset_entities, app_bundle_entities, llm_generation_entities
- services/: asset_content, skill, workflow_collaboration, workflow_comment
- controllers/console/app/error.py: AppAsset error classes
- core/tools/utils/system_encryption.py

Import fixes:
- dify_graph.enums -> graphon.enums in skill_service.py
- get_signed_file_url_for_plugin -> get_signed_file_url in cli_api.py

All 5 controllers verified: import OK, Flask starts successfully.
46 existing tests still pass.

Made-with: Cursor
2026-04-09 09:36:16 +08:00

38 lines
1.4 KiB
Python

"""
LLM Generation Detail Service.
Provides methods to query and attach generation details to workflow node executions
and messages, avoiding N+1 query problems.
"""
from sqlalchemy import select
from sqlalchemy.orm import Session
from core.app.entities.llm_generation_entities import LLMGenerationDetailData
from models import LLMGenerationDetail
class LLMGenerationService:
"""Service for handling LLM generation details."""
def __init__(self, session: Session):
self._session = session
def get_generation_detail_for_message(self, message_id: str) -> LLMGenerationDetailData | None:
"""Query generation detail for a specific message."""
stmt = select(LLMGenerationDetail).where(LLMGenerationDetail.message_id == message_id)
detail = self._session.scalars(stmt).first()
return detail.to_domain_model() if detail else None
def get_generation_details_for_messages(
self,
message_ids: list[str],
) -> dict[str, LLMGenerationDetailData]:
"""Batch query generation details for multiple messages."""
if not message_ids:
return {}
stmt = select(LLMGenerationDetail).where(LLMGenerationDetail.message_id.in_(message_ids))
details = self._session.scalars(stmt).all()
return {detail.message_id: detail.to_domain_model() for detail in details if detail.message_id}