增强 Deep Research 可靠性,并接入 8BF 任务卡片与会商上下文。

修复 MySQL 读写分离下的持久化与 SSE 重连问题,报告完成前先落库;8BF 嵌入页支持 taskId 任务卡与独立意图 metadata;前端统一 createClientId 并更新 runtime 配置。

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
董宏凯andCursor committed 2026-08-17 18:16:05 +08:00
1 parent 47faa9bcdf
commit 771957429a
36 files changed
+2038 -300

No files matched your search

@@ -48,6 +48,11 @@ class PersistingEventSink:
self._session_id = session_id
self._job_id = job_id
self._on_event = on_event
# A durable event row normally owns the sequence. When the event
# database is temporarily unavailable, use distinct negative sequence
# numbers for the live-only path so clients can render every milestone
# without advancing their durable ``after`` cursor.
self._fallback_seq = 0
async def emit(
self,
@@ -56,26 +61,66 @@ class PersistingEventSink:
phase: ResearchPhase = "initializing",
payload: dict | None = None,
) -> DeepResearchEvent:
row = await self._repo.append(
session_id=self._session_id,
job_id=self._job_id,
event_type=type,
phase=phase,
payload=payload or {},
)
# Reconstruct the envelope from the persisted row (seq is now assigned).
event = DeepResearchEvent(
seq=int(row.get("seq", 0)),
session_id=self._session_id,
job_id=self._job_id,
type=row.get("event_type", type),
phase=row.get("phase", phase),
payload=row.get("payload") or payload or {},
)
if self._on_event is not None:
await self._on_event(event.to_sse_dict())
event_payload = payload or {}
try:
row = await self._repo.append(
session_id=self._session_id,
job_id=self._job_id,
event_type=type,
phase=phase,
payload=event_payload,
)
# Reconstruct the envelope from the persisted row (seq is now assigned).
event = DeepResearchEvent(
seq=int(row.get("seq", 0)),
session_id=self._session_id,
job_id=self._job_id,
type=row.get("event_type", type),
phase=row.get("phase", phase),
payload=row.get("payload") or event_payload,
)
except Exception: # noqa: BLE001
# Progress persistence must not turn a recoverable database blip
# into a failed report. The job/status stores still record terminal
# state; this live-only frame lets an attached UI stay responsive
# until durable replay becomes available again after reconnect.
self._fallback_seq -= 1
logger.exception(
"deep-research event persistence failed; continuing job with a live-only event (job=%s, type=%s, phase=%s)",
self._job_id,
type,
phase,
)
event = DeepResearchEvent(
seq=self._fallback_seq,
session_id=self._session_id,
job_id=self._job_id,
type=type,
phase=phase,
payload={**event_payload, "eventPersistenceDegraded": True},
)
await self._publish_event(event)
return event
async def _publish_event(self, event: DeepResearchEvent) -> None:
"""Push a persisted or live-only event without risking the worker."""
if self._on_event is None:
return
wire = event.to_sse_dict()
if event.seq < 0:
wire["liveId"] = f"event-persistence-fallback:{self._job_id}:{abs(event.seq)}"
try:
await self._on_event(wire)
except Exception: # noqa: BLE001
# A browser disconnect or a live-hub issue must not abort report
# generation; persisted rows will still be replayable on reconnect.
logger.warning(
"deep-research live event publish failed; job continues (job=%s, seq=%s)",
self._job_id,
event.seq,
exc_info=True,
)
async def publish_live(
self,
type: str, # noqa: A002
@@ -85,16 +130,24 @@ class PersistingEventSink:
) -> None:
if self._on_event is None:
return
await self._on_event(
{
"seq": 0,
"sessionId": self._session_id,
"jobId": self._job_id,
"type": type,
"phase": phase,
"payload": payload or {},
}
)
try:
await self._on_event(
{
"seq": 0,
"sessionId": self._session_id,
"jobId": self._job_id,
"type": type,
"phase": phase,
"payload": payload or {},
}
)
except Exception: # noqa: BLE001
logger.warning(
"deep-research live frame publish failed; job continues (job=%s, type=%s)",
self._job_id,
type,
exc_info=True,
)
class NullEventSink:
@@ -27,14 +27,15 @@ from typing import Any, Protocol, override, runtime_checkable
from langchain.agents import AgentState
from langchain.agents.middleware import SummarizationMiddleware
from langchain.agents.middleware.types import ModelCallResult, ModelRequest, ModelResponse
from langchain_core.messages import (
AIMessage,
AnyMessage,
SystemMessage,
ToolMessage,
message_to_dict,
messages_from_dict,
)
from langchain_core.messages import (
AIMessage,
AnyMessage,
HumanMessage,
SystemMessage,
ToolMessage,
message_to_dict,
messages_from_dict,
)
from langgraph.config import get_config
from langgraph.runtime import Runtime
@@ -145,8 +146,8 @@ class _SummaryCacheEntry:
summarized_ids: frozenset[str]
summary_text: str
preserved_ids: frozenset[str] = frozenset()
preserved_messages: tuple[AnyMessage, ...] = ()
preserved_ids: frozenset[str] = frozenset()
preserved_messages: tuple[AnyMessage, ...] = ()
# Process-wide summary cache shared across every middleware instance.
@@ -160,51 +161,99 @@ class _SummaryCacheEntry:
# so only the first threshold crossing (or a genuine re-compaction) pays for an
# LLM call. A lock guards the non-atomic LRU eviction against concurrent
# threads (subagents / parallel conversations share this process).
_GLOBAL_SUMMARY_CACHE: OrderedDict[str, _SummaryCacheEntry] = OrderedDict()
_GLOBAL_SUMMARY_CACHE_LOCK = threading.Lock()
_STATE_CACHE_KEY = "context_summary_cache"
def _clear_global_summary_cache() -> None:
"""Drop every cached summary. Intended for tests/diagnostics only."""
with _GLOBAL_SUMMARY_CACHE_LOCK:
_GLOBAL_SUMMARY_CACHE.clear()
def _serialize_cache_entry(entry: _SummaryCacheEntry) -> dict[str, Any]:
"""Serialize a summary cache entry so it can live in LangGraph state."""
return {
"version": 1,
"summarized_ids": sorted(entry.summarized_ids),
"summary_text": entry.summary_text,
"preserved_ids": sorted(entry.preserved_ids),
"preserved_messages": [message_to_dict(message) for message in entry.preserved_messages],
}
def _deserialize_cache_entry(raw: Any) -> _SummaryCacheEntry | None:
"""Best-effort restore of a state-backed summary cache entry."""
if not isinstance(raw, dict):
return None
try:
summary_text = raw.get("summary_text")
if not isinstance(summary_text, str) or not summary_text:
return None
summarized_ids = raw.get("summarized_ids") or []
preserved_ids = raw.get("preserved_ids") or []
preserved_messages_raw = raw.get("preserved_messages") or []
if not isinstance(summarized_ids, list) or not isinstance(preserved_ids, list) or not isinstance(preserved_messages_raw, list):
return None
preserved_messages = tuple(messages_from_dict(preserved_messages_raw))
return _SummaryCacheEntry(
summarized_ids=frozenset(str(item) for item in summarized_ids if item is not None),
summary_text=summary_text,
preserved_ids=frozenset(str(item) for item in preserved_ids if item is not None),
preserved_messages=preserved_messages,
)
except Exception:
logger.debug("summarization: failed to restore state-backed summary cache", exc_info=True)
return None
_GLOBAL_SUMMARY_CACHE: OrderedDict[str, _SummaryCacheEntry] = OrderedDict()
_GLOBAL_SUMMARY_CACHE_LOCK = threading.Lock()
_STATE_CACHE_KEY = "context_summary_cache"
def _clear_global_summary_cache() -> None:
"""Drop every cached summary. Intended for tests/diagnostics only."""
with _GLOBAL_SUMMARY_CACHE_LOCK:
_GLOBAL_SUMMARY_CACHE.clear()
def _serialize_cache_entry(entry: _SummaryCacheEntry) -> dict[str, Any]:
"""Serialize a summary cache entry so it can live in LangGraph state."""
return {
"version": 1,
"summarized_ids": sorted(entry.summarized_ids),
"summary_text": entry.summary_text,
"preserved_ids": sorted(entry.preserved_ids),
"preserved_messages": [message_to_dict(message) for message in entry.preserved_messages],
}
def _deserialize_cache_entry(raw: Any) -> _SummaryCacheEntry | None:
"""Best-effort restore of a state-backed summary cache entry."""
if not isinstance(raw, dict):
return None
try:
summary_text = raw.get("summary_text")
if not isinstance(summary_text, str) or not summary_text:
return None
summarized_ids = raw.get("summarized_ids") or []
preserved_ids = raw.get("preserved_ids") or []
preserved_messages_raw = raw.get("preserved_messages") or []
if not isinstance(summarized_ids, list) or not isinstance(preserved_ids, list) or not isinstance(preserved_messages_raw, list):
return None
preserved_messages = tuple(messages_from_dict(preserved_messages_raw))
return _SummaryCacheEntry(
summarized_ids=frozenset(str(item) for item in summarized_ids if item is not None),
summary_text=summary_text,
preserved_ids=frozenset(str(item) for item in preserved_ids if item is not None),
preserved_messages=preserved_messages,
)
except Exception:
logger.debug("summarization: failed to restore state-backed summary cache", exc_info=True)
return None
def _has_nonempty_human_message(message: AnyMessage) -> bool:
"""Whether a message is a real, non-empty user turn.
Some OpenAI-compatible gateways reject a completion request that contains
only ``system`` / ``assistant`` / ``tool`` roles. That can legitimately
happen after compaction: the active model call is continuing a tool turn,
while the user request that started the turn has already moved into the
internal summary.
"""
if not isinstance(message, HumanMessage):
return False
content = message.content
if isinstance(content, str):
return bool(content.strip())
if isinstance(content, list):
return any(bool(block.strip()) if isinstance(block, str) else bool((block.get("text") or block.get("content") or "").strip()) if isinstance(block, dict) else False for block in content)
return bool(str(content).strip())
def _ensure_latest_human_message(
source_messages: list[AnyMessage],
compressed_messages: list[AnyMessage],
) -> list[AnyMessage]:
"""Keep the latest real user request visible to strict chat gateways.
The message is inserted after leading system messages, so it neither
exposes the internal summary to the UI nor splits an AI tool-call from its
following ToolMessages. When there was no user turn in the source at all,
do not fabricate one: that is an upstream caller bug and should remain
diagnosable rather than silently changing the task.
"""
if any(_has_nonempty_human_message(message) for message in compressed_messages):
return compressed_messages
latest_human = next(
(message for message in reversed(source_messages) if _has_nonempty_human_message(message)),
None,
)
if latest_human is None:
logger.warning("summarization: compressed model request has no user message and source history contains none; passing it through unchanged")
return compressed_messages
insert_at = 0
while insert_at < len(compressed_messages) and isinstance(compressed_messages[insert_at], SystemMessage):
insert_at += 1
return [*compressed_messages[:insert_at], latest_human, *compressed_messages[insert_at:]]
class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
@@ -231,8 +280,8 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
# Per-thread cache of the most recent summary: thread_id -> (summarized message ids, summary text).
# Points at the *process-wide* cache (not a fresh per-instance dict) so a
# summary survives across runs/turns — see ``_GLOBAL_SUMMARY_CACHE``.
self._summary_cache: OrderedDict[str, _SummaryCacheEntry] = _GLOBAL_SUMMARY_CACHE
self._pending_state_cache_update: dict[str, Any] | None = None
self._summary_cache: OrderedDict[str, _SummaryCacheEntry] = _GLOBAL_SUMMARY_CACHE
self._pending_state_cache_update: dict[str, Any] | None = None
@override
def before_model(self, state: AgentState, runtime: Runtime) -> dict | None:
@@ -248,21 +297,21 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
"""Async counterpart of :meth:`before_model` — also a no-op."""
return None
@override
def after_model(self, state: AgentState, runtime: Runtime) -> dict | None:
"""Persist the latest reusable summary cache into thread state."""
if self._pending_state_cache_update is None:
return None
update = self._pending_state_cache_update
self._pending_state_cache_update = None
return {_STATE_CACHE_KEY: update}
@override
async def aafter_model(self, state: AgentState, runtime: Runtime) -> dict | None:
"""Async counterpart of :meth:`after_model`."""
return self.after_model(state, runtime)
# ---- wrap_model_call: transient, display-preserving compression ----------
@override
def after_model(self, state: AgentState, runtime: Runtime) -> dict | None:
"""Persist the latest reusable summary cache into thread state."""
if self._pending_state_cache_update is None:
return None
update = self._pending_state_cache_update
self._pending_state_cache_update = None
return {_STATE_CACHE_KEY: update}
@override
async def aafter_model(self, state: AgentState, runtime: Runtime) -> dict | None:
"""Async counterpart of :meth:`after_model`."""
return self.after_model(state, runtime)
# ---- wrap_model_call: transient, display-preserving compression ----------
@override
def wrap_model_call(
@@ -376,20 +425,21 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
return None
thread_id = self._resolve_request_thread_id(request)
if thread_id is None:
logger.debug("summarization: thread_id unresolved; cross-turn summary cache disabled for this call")
cached = self._get_cache_entry(thread_id) if thread_id else None
if cached is None:
cached = _deserialize_cache_entry(getattr(request, "state", {}).get(_STATE_CACHE_KEY))
if cached is not None and thread_id:
self._store_cache_entry(thread_id, cached)
present_ids = {m.id for m in messages}
cache_usable = cached is not None and cached.summarized_ids <= present_ids and cached.preserved_ids <= present_ids
if cache_usable:
preserved = list(cached.preserved_messages)
excluded_ids = cached.summarized_ids | cached.preserved_ids
preserved.extend(m for m in messages if m.id not in excluded_ids)
effective = [self._summary_message(cached.summary_text), *preserved]
if thread_id is None:
logger.debug("summarization: thread_id unresolved; cross-turn summary cache disabled for this call")
cached = self._get_cache_entry(thread_id) if thread_id else None
if cached is None:
cached = _deserialize_cache_entry(getattr(request, "state", {}).get(_STATE_CACHE_KEY))
if cached is not None and thread_id:
self._store_cache_entry(thread_id, cached)
present_ids = {m.id for m in messages}
cache_usable = cached is not None and cached.summarized_ids <= present_ids and cached.preserved_ids <= present_ids
if cache_usable:
preserved = list(cached.preserved_messages)
excluded_ids = cached.summarized_ids | cached.preserved_ids
preserved.extend(m for m in messages if m.id not in excluded_ids)
effective = [self._summary_message(cached.summary_text), *preserved]
effective = _ensure_latest_human_message(messages, effective)
# Decide re-summarization on the *counted* size of the compressed
# context only — NOT ``_should_summarize`` — because that folds in the
# last AIMessage's reported ``usage_metadata`` (system prompt + tool
@@ -400,8 +450,7 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
# Refresh LRU recency and reuse without an LLM call.
self._touch_cache_entry(thread_id)
logger.info(
"summarization: 上下文压缩(复用缓存摘要,无 LLM 调用) context compaction reusing cached summary "
"thread=%s full_tokens=%d compressed_tokens=%d preserved_msgs=%d",
"summarization: 上下文压缩(复用缓存摘要,无 LLM 调用) context compaction reusing cached summary thread=%s full_tokens=%d compressed_tokens=%d preserved_msgs=%d",
thread_id,
self.token_counter(messages),
self.token_counter(effective),
@@ -415,7 +464,7 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
# an "it compacts every turn" report is diagnosable straight from the
# backend log: cache=miss → thread_id/key problem; unusable → message-id
# instability; stale → preserved genuinely grew back over the trigger.
cache_state = "miss" if cached is None else "stale"
cache_state = "miss" if cached is None else "stale"
logger.info(
"summarization: compacting thread=%s cache=%s counted_tokens=%d msgs=%d",
thread_id,
@@ -452,22 +501,23 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
) -> list[AnyMessage]:
"""Assemble the compressed message list and update the per-thread cache."""
compressed = [self._summary_message(summary), *preserved]
compressed = _ensure_latest_human_message([*messages_to_summarize, *preserved], compressed)
if thread_id:
summarized_ids = frozenset(m.id for m in messages_to_summarize if m.id is not None)
preserved_ids = {m.id for m in preserved if m.id is not None}
self._store_cache_entry(
thread_id,
entry := _SummaryCacheEntry(
summarized_ids=summarized_ids,
summary_text=summary,
preserved_ids=frozenset(preserved_ids),
preserved_messages=tuple(preserved),
),
)
self._pending_state_cache_update = _serialize_cache_entry(entry)
return compressed
self._store_cache_entry(
thread_id,
entry := _SummaryCacheEntry(
summarized_ids=summarized_ids,
summary_text=summary,
preserved_ids=frozenset(preserved_ids),
preserved_messages=tuple(preserved),
),
)
self._pending_state_cache_update = _serialize_cache_entry(entry)
return compressed
def _get_cache_entry(self, thread_id: str) -> _SummaryCacheEntry | None:
"""Return the cached entry for ``thread_id`` (thread-safe read)."""
@@ -571,7 +621,7 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
return None
return _resolve_thread_id(runtime)
def _summary_message(self, summary: str) -> SystemMessage:
def _summary_message(self, summary: str) -> SystemMessage:
"""Build the summary message handed to the model.
It is named ``summary`` and flagged ``hide_from_ui`` defensively. Because
@@ -579,21 +629,21 @@ class DeerFlowSummarizationMiddleware(SummarizationMiddleware):
state), the frontend never receives it — the user keeps seeing the
original conversation.
"""
return SystemMessage(
content=(
"Internal conversation summary for continuity only. Use it silently "
"to answer the user's latest request. Never reveal, quote, mention, "
"or describe this summary or the fact that context was compacted.\n\n"
"<internal_context_summary>\n"
f"{summary}\n"
"</internal_context_summary>"
),
return SystemMessage(
content=(
"Internal conversation summary for continuity only. Use it silently "
"to answer the user's latest request. Never reveal, quote, mention, "
"or describe this summary or the fact that context was compacted.\n\n"
"<internal_context_summary>\n"
f"{summary}\n"
"</internal_context_summary>"
),
name="summary",
additional_kwargs={"hide_from_ui": True, "lc_source": "summarization"},
)
@override
def _build_new_messages(self, summary: str) -> list[AnyMessage]:
def _build_new_messages(self, summary: str) -> list[AnyMessage]:
"""Kept for backwards compatibility; delegates to :meth:`_summary_message`."""
return [self._summary_message(summary)]
@@ -68,13 +68,7 @@ class DeepResearchEventRepository:
"""
for attempt in range(max_retries):
async with self._sf() as session:
current_max = (
await session.execute(
select(func.max(DeepResearchEventRow.seq)).where(
DeepResearchEventRow.job_id == job_id
)
)
).scalar() or 0
current_max = (await session.execute(select(func.max(DeepResearchEventRow.seq)).where(DeepResearchEventRow.job_id == job_id))).scalar() or 0
next_seq = int(current_max) + 1
row = DeepResearchEventRow(
job_id=job_id,
@@ -86,49 +80,38 @@ class DeepResearchEventRepository:
)
session.add(row)
try:
# Do not issue ``session.refresh(row)`` after commit. On a
# MySQL read/write-splitting deployment that read can land
# on a lagging replica, which cannot see the just-committed
# event and raises ``Could not refresh instance``. Flush
# assigns generated primary-key/default values on the writer
# connection, so the plain dict is complete before commit.
await session.flush()
result = self._row_to_dict(row)
await session.commit()
await session.refresh(row)
return self._row_to_dict(row)
return result
except IntegrityError:
await session.rollback()
continue # retry with recomputed max
raise RuntimeError(
f"deep_research_events.append: seq collision persisted after {max_retries} retries (job={job_id})"
)
raise RuntimeError(f"deep_research_events.append: seq collision persisted after {max_retries} retries (job={job_id})")
async def list_after(
self, job_id: str, *, after: int = 0, limit: int = 200
) -> list[dict[str, Any]]:
async def list_after(self, job_id: str, *, after: int = 0, limit: int = 200) -> list[dict[str, Any]]:
"""Events with ``seq > after`` in ascending order (SSE replay, §15.3)."""
async with self._sf() as session:
stmt = (
select(DeepResearchEventRow)
.where(DeepResearchEventRow.job_id == job_id)
.where(DeepResearchEventRow.seq > after)
.order_by(DeepResearchEventRow.seq.asc())
.limit(limit)
)
stmt = select(DeepResearchEventRow).where(DeepResearchEventRow.job_id == job_id).where(DeepResearchEventRow.seq > after).order_by(DeepResearchEventRow.seq.asc()).limit(limit)
rows = (await session.execute(stmt)).scalars().all()
return [self._row_to_dict(r) for r in rows]
async def last_seq(self, job_id: str) -> int:
async with self._sf() as session:
mx = (
await session.execute(
select(func.max(DeepResearchEventRow.seq)).where(
DeepResearchEventRow.job_id == job_id
)
)
).scalar()
mx = (await session.execute(select(func.max(DeepResearchEventRow.seq)).where(DeepResearchEventRow.job_id == job_id))).scalar()
return int(mx or 0)
async def delete_by_job(self, job_id: str) -> int:
from sqlalchemy import delete
async with self._sf() as session:
result = await session.execute(
delete(DeepResearchEventRow).where(DeepResearchEventRow.job_id == job_id)
)
result = await session.execute(delete(DeepResearchEventRow).where(DeepResearchEventRow.job_id == job_id))
await session.commit()
return result.rowcount
@@ -136,8 +119,6 @@ class DeepResearchEventRepository:
from sqlalchemy import delete
async with self._sf() as session:
result = await session.execute(
delete(DeepResearchEventRow).where(DeepResearchEventRow.session_id == session_id)
)
result = await session.execute(delete(DeepResearchEventRow).where(DeepResearchEventRow.session_id == session_id))
await session.commit()
return result.rowcount
@@ -113,9 +113,18 @@ class DeepResearchJobRepository:
phase=phase,
)
session.add(row)
# Do not issue ``session.refresh(row)`` after commit. A
# MySQL read/write-splitting proxy can route that read to
# a lagging replica, even though the INSERT has already
# committed on the writer. The caller would receive 500
# while an invisible queued job remains in the database.
# ``flush`` materializes ORM defaults on the writer, so we
# can return a complete, durable snapshot without a
# replica-dependent readback.
await session.flush()
result = self._row_to_dict(row)
await session.commit()
await session.refresh(row)
return self._row_to_dict(row), True
return result, True
except IntegrityError:
# Unique-index conflict → an active job already exists.
pass
@@ -230,13 +239,14 @@ class DeepResearchJobRepository:
)
if result.rowcount == 0:
return None
await session.commit()
row = (
await session.execute(
select(DeepResearchJobRow).where(DeepResearchJobRow.id == job_id)
)
).scalar_one_or_none()
return self._row_to_dict(row) if row else None
snapshot = self._row_to_dict(row) if row else None
await session.commit()
return snapshot
# ── heartbeat ───────────────────────────────────────────────────────────
@@ -351,13 +361,14 @@ class DeepResearchJobRepository:
)
if result.rowcount == 0:
return None
await session.commit()
row = (
await session.execute(
select(DeepResearchJobRow).where(DeepResearchJobRow.id == job_id)
)
).scalar_one_or_none()
return self._row_to_dict(row) if row else None
snapshot = self._row_to_dict(row) if row else None
await session.commit()
return snapshot
# ── two-phase cancel ────────────────────────────────────────────────────
@@ -385,13 +396,14 @@ class DeepResearchJobRepository:
)
if result.rowcount == 0:
return None
await session.commit()
row = (
await session.execute(
select(DeepResearchJobRow).where(DeepResearchJobRow.id == job_id)
)
).scalar_one_or_none()
return self._row_to_dict(row) if row else None
snapshot = self._row_to_dict(row) if row else None
await session.commit()
return snapshot
async def finalize_cancel(
self, job_id: str, *, lease_owner: str | None = None
@@ -419,13 +431,14 @@ class DeepResearchJobRepository:
)
if result.rowcount == 0:
return None
await session.commit()
row = (
await session.execute(
select(DeepResearchJobRow).where(DeepResearchJobRow.id == job_id)
)
).scalar_one_or_none()
return self._row_to_dict(row) if row else None
snapshot = self._row_to_dict(row) if row else None
await session.commit()
return snapshot
# ── resume after human-review interrupt ─────────────────────────────────
@@ -460,13 +473,14 @@ class DeepResearchJobRepository:
)
if result.rowcount == 0:
return None
await session.commit()
row = (
await session.execute(
select(DeepResearchJobRow).where(DeepResearchJobRow.id == job_id)
)
).scalar_one_or_none()
return self._row_to_dict(row) if row else None
snapshot = self._row_to_dict(row) if row else None
await session.commit()
return snapshot
# ── cleanup ─────────────────────────────────────────────────────────────
@@ -74,9 +74,13 @@ class DeepResearchMessageRepository:
seq=int(current_max) + 1,
)
session.add(row)
# Keep the successful append independent of a later replica read.
# The explicit id/seq and Python-side defaults are available after
# flush, before the transaction releases its writer connection.
await session.flush()
snapshot = self._row_to_dict(row)
await session.commit()
await session.refresh(row)
return self._row_to_dict(row)
return snapshot
async def list_by_session(
self, session_id: str, *, user_id: str | _AutoSentinel = AUTO, limit: int = 100
@@ -139,10 +143,11 @@ class DeepResearchMessageRepository:
if not result.rowcount:
await session.rollback()
return None
await session.commit()
stmt = select(DeepResearchMessageRow).where(*where)
row = (await session.execute(stmt)).scalar_one_or_none()
return self._row_to_dict(row) if row is not None else None
snapshot = self._row_to_dict(row) if row is not None else None
await session.commit()
return snapshot
async def delete_by_session(self, session_id: str) -> int:
from sqlalchemy import delete
@@ -85,9 +85,13 @@ class DeepResearchSessionRepository:
runtime_thread_id=runtime_thread_id,
)
session.add(row)
# New sessions are a control-plane write. Avoid a post-commit
# refresh because MySQL read/write-splitting can make a just
# created session look absent on a lagging replica.
await session.flush()
snapshot = self._row_to_dict(row)
await session.commit()
await session.refresh(row)
return self._row_to_dict(row)
return snapshot
# ── read ────────────────────────────────────────────────────────────────
@@ -187,13 +191,14 @@ class DeepResearchSessionRepository:
)
if result.rowcount == 0:
return None
await session.commit()
row = (
await session.execute(
select(DeepResearchSessionRow).where(DeepResearchSessionRow.id == session_id)
)
).scalar_one_or_none()
return self._row_to_dict(row) if row else None
snapshot = self._row_to_dict(row) if row else None
await session.commit()
return snapshot
async def replace_report_if_unchanged(
self,
@@ -231,13 +236,14 @@ class DeepResearchSessionRepository:
)
if result.rowcount == 0:
return None
await session.commit()
row = (
await session.execute(
select(DeepResearchSessionRow).where(DeepResearchSessionRow.id == session_id)
)
).scalar_one_or_none()
return self._row_to_dict(row) if row else None
snapshot = self._row_to_dict(row) if row else None
await session.commit()
return snapshot
# ── delete ──────────────────────────────────────────────────────────────
@@ -23,6 +23,13 @@ from deerflow.persistence.types import BeijingDateTime, PortableLongText
class DeepResearchSourceRow(Base):
__tablename__ = "deep_research_sources"
__table_args__ = (
# MySQL requires a prefix length when indexing TEXT columns. The
# column remains unbounded so long URLs are preserved; the prefix is
# only an index implementation detail and equality filters still
# compare the complete URL value.
sa.Index("ix_deep_research_sources_url", "url", mysql_length=512),
)
id: Mapped[str] = mapped_column(String(64), primary_key=True)
session_id: Mapped[str] = mapped_column(String(64), nullable=False, index=True)
@@ -32,7 +39,7 @@ class DeepResearchSourceRow(Base):
# The query that first surfaced this material.
first_seen_query: Mapped[str | None] = mapped_column(Text, nullable=True)
title: Mapped[str] = mapped_column(Text, nullable=False, default="")
url: Mapped[str | None] = mapped_column(Text, nullable=True, index=True)
url: Mapped[str | None] = mapped_column(Text, nullable=True)
raw_content: Mapped[str] = mapped_column(PortableLongText, nullable=False, default="")
snippet: Mapped[str | None] = mapped_column(Text, nullable=True)
source: Mapped[str] = mapped_column(String(256), nullable=False, default="")
@@ -37,9 +37,14 @@ class DeepResearchSourceRepository:
row = DeepResearchSourceRow(session_id=session_id, job_id=job_id, **fields)
session.add(row)
try:
# The source was produced on the worker's write path. Build
# its response on that same connection so a replica-lag read
# cannot turn a successfully collected source into a failed
# research run.
await session.flush()
snapshot = self._row_to_dict(row)
await session.commit()
await session.refresh(row)
return self._row_to_dict(row)
return snapshot
except Exception:
await session.rollback()
# Fallback: find existing by rec_uuid or url.
@@ -147,13 +152,14 @@ class DeepResearchSourceRepository:
)
if result.rowcount == 0:
return None
await session.commit()
row = (
await session.execute(
select(DeepResearchSourceRow).where(DeepResearchSourceRow.id == source_id)
)
).scalar_one_or_none()
return self._row_to_dict(row) if row else None
snapshot = self._row_to_dict(row) if row else None
await session.commit()
return snapshot
async def delete_by_session(self, session_id: str) -> int:
from sqlalchemy import delete