代码提交

This commit is contained in:
董宏凯 committed 2026-08-15 12:51:58 +08:00
1 parent 500dab29ab
commit 70da7c5649
59 files changed
+12108 -148

No files matched your search

@@ -0,0 +1,33 @@
"""Deep-research follow-up message persistence."""
from __future__ import annotations
from deerflow.persistence.deep_research_messages.model import DeepResearchMessageRow
from deerflow.persistence.deep_research_messages.sql import DeepResearchMessageRepository
def make_deep_research_message_store(session_factory) -> DeepResearchMessageRepository | None:
if session_factory is None:
return None
return DeepResearchMessageRepository(session_factory)
_default_store: DeepResearchMessageRepository | None = None
def register_default_store(store: DeepResearchMessageRepository | None) -> None:
global _default_store
_default_store = store
def get_default_store() -> DeepResearchMessageRepository | None:
return _default_store
__all__ = [
"DeepResearchMessageRepository",
"DeepResearchMessageRow",
"get_default_store",
"make_deep_research_message_store",
"register_default_store",
]
@@ -0,0 +1,35 @@
"""ORM model for deep-research follow-up messages.
After a report is complete, the user can ask follow-up questions that are
answered against the session's report + sources only (``allow_new_research=false``
default; §13.5 / §16.6). This table persists that conversation.
"""
from __future__ import annotations
from datetime import UTC, datetime
from sqlalchemy import Integer, String
from sqlalchemy.orm import Mapped, mapped_column
from deerflow.persistence.base import Base
from deerflow.persistence.types import BeijingDateTime, PortableLongText
class DeepResearchMessageRow(Base):
__tablename__ = "deep_research_messages"
id: Mapped[str] = mapped_column(String(64), primary_key=True)
session_id: Mapped[str] = mapped_column(String(64), nullable=False, index=True)
user_id: Mapped[str | None] = mapped_column(String(64), nullable=True, index=True)
role: Mapped[str] = mapped_column(String(16), nullable=False) # user / assistant
content: Mapped[str] = mapped_column(PortableLongText, nullable=False, default="")
# Source ids cited in an assistant reply.
citation_source_ids: Mapped[str | None] = mapped_column(PortableLongText, nullable=True)
# Token/cost usage for this message (JSON).
usage_snapshot: Mapped[str | None] = mapped_column(PortableLongText, nullable=True)
seq: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
created_at: Mapped[datetime] = mapped_column(
BeijingDateTime(), nullable=False, default=lambda: datetime.now(UTC)
)
@@ -0,0 +1,105 @@
"""SQLAlchemy repository for deep-research follow-up messages."""
from __future__ import annotations
import json
import logging
from typing import Any
from sqlalchemy import func, select
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker
from deerflow.persistence.deep_research_messages.model import DeepResearchMessageRow
from deerflow.runtime.user_context import AUTO, _AutoSentinel, resolve_user_id
logger = logging.getLogger(__name__)
def _dumps(value: Any) -> str | None:
if value is None:
return None
return json.dumps(value, ensure_ascii=False)
def _loads(value: Any) -> Any:
if not isinstance(value, str) or not value:
return None
try:
return json.loads(value)
except Exception:
return None
class DeepResearchMessageRepository:
def __init__(self, session_factory: async_sessionmaker[AsyncSession]) -> None:
self._sf = session_factory
@staticmethod
def _row_to_dict(row: DeepResearchMessageRow) -> dict[str, Any]:
d = row.to_dict()
if "citation_source_ids" in d:
d["citation_source_ids"] = _loads(d["citation_source_ids"]) or []
if "usage_snapshot" in d:
d["usage_snapshot"] = _loads(d["usage_snapshot"])
return d
async def append(
self,
*,
id: str,
session_id: str,
user_id: str | _AutoSentinel = AUTO,
role: str,
content: str,
citation_source_ids: list[str] | None = None,
usage_snapshot: dict[str, Any] | None = None,
) -> dict[str, Any]:
resolved = resolve_user_id(user_id, method_name="DeepResearchMessageRepository.append")
async with self._sf() as session:
current_max = (
await session.execute(
select(func.max(DeepResearchMessageRow.seq)).where(
DeepResearchMessageRow.session_id == session_id
)
)
).scalar() or 0
row = DeepResearchMessageRow(
id=id,
session_id=session_id,
user_id=resolved,
role=role,
content=content,
citation_source_ids=_dumps(citation_source_ids),
usage_snapshot=_dumps(usage_snapshot),
seq=int(current_max) + 1,
)
session.add(row)
await session.commit()
await session.refresh(row)
return self._row_to_dict(row)
async def list_by_session(
self, session_id: str, *, user_id: str | _AutoSentinel = AUTO, limit: int = 100
) -> list[dict[str, Any]]:
resolved = resolve_user_id(user_id, method_name="DeepResearchMessageRepository.list_by_session")
async with self._sf() as session:
stmt = select(DeepResearchMessageRow).where(
DeepResearchMessageRow.session_id == session_id
)
if resolved is not None:
stmt = stmt.where(DeepResearchMessageRow.user_id == resolved)
stmt = stmt.order_by(DeepResearchMessageRow.seq.asc()).limit(limit)
rows = (await session.execute(stmt)).scalars().all()
return [self._row_to_dict(r) for r in rows]
async def delete_by_session(self, session_id: str) -> int:
from sqlalchemy import delete
async with self._sf() as session:
result = await session.execute(
delete(DeepResearchMessageRow).where(
DeepResearchMessageRow.session_id == session_id
)
)
await session.commit()
return result.rowcount