deer-flow/backend/app/gateway/history_seed.py
spud 21175ba46f
fix(runtime): persistently fence stale run event producers (#7619)
* fix(runtime): fence revoked run event producers

* fix(runtime): reduce off-mode producer guard locking

* docs: keep inherited guidance within size budget

* chore(runtime): remove development phase labels

* fix(persistence): normalize libpq SSL options for asyncpg connections

* docs(runtime): clarify producer fencing behavior in off mode

* test(persistence): align migration TLS probes with channel-binding rejection

* fix(runtime): authorize fenced Gateway history seeding

* fix(scheduler): preserve takeover identity in recovery publication

* fix(scheduler): report unconfirmed recovery publication

* fix(runtime): preserve history messages before the first human turn

* fix(runtime): clarify run creation failure diagnostic

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-02 15:26:42 +08:00

75 lines
3.2 KiB
Python

"""Host-authorized history copies under durable thread-operation admission."""
from collections.abc import AsyncIterator
from contextlib import asynccontextmanager
from dataclasses import dataclass
from fastapi import Request
from app.gateway.deps import get_run_manager, get_thread_store
from app.gateway.internal_auth import get_trusted_internal_owner_user_id
from deerflow.persistence.run.sql import RunRepository
from deerflow.persistence.thread_meta.sql import ThreadMetaRepository
from deerflow.runtime.events.producer import RunEventProducerRejected, history_seed_authority, producer_scope
from deerflow.runtime.events.store.db import DbRunEventStore
from deerflow.runtime.runs.manager import RunRecord
from deerflow.runtime.runs.schemas import ThreadOperationKind
@dataclass(frozen=True)
class HistorySeedReservation:
record: RunRecord
thread: dict | None
@asynccontextmanager
async def reserve_history_seed(request: Request, thread_id: str) -> AsyncIterator[HistorySeedReservation | None]:
"""Keep snapshot reads and seed writes exclusive with delete and admission."""
events = request.app.state.run_event_store
manager = getattr(request.app.state, "run_manager", None)
runs = getattr(manager, "_store", None)
threads = getattr(request.app.state, "thread_store", None)
if not isinstance(events, DbRunEventStore):
yield None
return
if not isinstance(runs, RunRepository) or not isinstance(threads, ThreadMetaRepository):
if events._producer_fencing == "strict":
raise RunEventProducerRejected("History seeding requires shared SQL lifecycle stores")
yield None
return
if runs._sf.kw.get("bind") is not events._sf.kw.get("bind") or threads._sf.kw.get("bind") is not events._sf.kw.get("bind"):
raise RunEventProducerRejected("History seeding requires shared SQL lifecycle stores")
async with get_run_manager(request).reserve_thread_operation(
thread_id,
kind=ThreadOperationKind.checkpoint_write,
user_id=get_trusted_internal_owner_user_id(request),
) as reservation:
yield HistorySeedReservation(reservation, await threads.get(thread_id, user_id=None))
async def write_history_seed(
request: Request,
events: list[dict],
*,
reservation: HistorySeedReservation | None,
seed_kind: str,
thread: dict | None = None,
assistant_id: str | None = None,
) -> None:
store = request.app.state.run_event_store
if reservation is None:
await store.put_batch(events)
return
if thread is None:
# Only the checkpoint migration may materialize missing legacy metadata.
# The caller read that checkpoint while holding this same reservation.
if seed_kind != "checkpoint":
raise RunEventProducerRejected("Branch seeding requires its original thread identity")
threads = get_thread_store(request)
thread = reservation.thread
if thread is None:
thread = await threads.create(reservation.record.thread_id, assistant_id=assistant_id, user_id=reservation.record.user_id)
authority = history_seed_authority(reservation.record, thread, seed_kind=seed_kind)
with producer_scope(authority):
await store.put_batch(events)