furyhawk/deer-flow
1
0
Fork 0
mirror of https://github.com/bytedance/deer-flow.git synced 2026-05-25 01:15:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(persistence): stream hang when run_events.backend=db

Browse Source 
DbRunEventStore._user_id_from_context() returned user.id without
coercing it to str. User.id is a Pydantic UUID, and aiosqlite cannot
bind a raw UUID object to a VARCHAR column, so the INSERT for the
initial human_message event silently rolled back and raised out of
the worker task. Because that put() sat outside the worker's try
block, the finally-clause that publishes end-of-stream never ran
and the SSE stream hung forever.

jsonl mode was unaffected because json.dumps(default=str) coerces
UUID objects transparently.

Fixes:
- db.py: coerce user.id to str at the context-read boundary (matches
  what resolve_user_id already does for the other repositories)
- worker.py: move RunJournal init + human_message put inside the try
  block so any failure flows through the finally/publish_end path
  instead of hanging the subscriber

Defense-in-depth:
- engine.py: add PRAGMA busy_timeout=5000 so checkpointer and event
  store wait for each other on the shared deerflow.db file instead
  of failing immediately under write-lock contention
- journal.py: skip fire-and-forget _flush_sync when a previous flush
  task is still in flight, to avoid piling up concurrent put_batch
  writes on the same SQLAlchemy engine during streaming; flush() now
  waits for pending tasks before draining the buffer
- database_config.py: doc-only update clarifying WAL + busy_timeout
  keep the unified deerflow.db safe for both workloads

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
rayhpeng
2026-04-11 11:16:22 +08:00
parent 20f64bbf4f
commit 10cc651578
5 changed files with 76 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/packages/harness/deerflow/runtime/runs/worker.py
+45 -36
View File
@@ -143,34 +143,7 @@ async def run_agent(
content = human_msg.content
journal.set_first_human_message(content if isinstance(content, str) else str(content))
# Initialize RunJournal for event capture
journal = None
if event_store is not None:
from deerflow.runtime.journal import RunJournal
journal = RunJournal(
run_id=run_id,
thread_id=thread_id,
event_store=event_store,
track_token_usage=getattr(run_events_config, "track_token_usage", True),
)
# Write human_message event (model_dump format, aligned with checkpoint)
human_msg = _extract_human_message(graph_input)
if human_msg is not None:
msg_metadata = {}
if follow_up_to_run_id:
msg_metadata["follow_up_to_run_id"] = follow_up_to_run_id
await event_store.put(
thread_id=thread_id,
run_id=run_id,
event_type="human_message",
category="message",
content=human_msg.model_dump(),
metadata=msg_metadata or None,
)
content = human_msg.content
journal.set_first_human_message(content if isinstance(content, str) else str(content))
# Track whether "events" was requested but skipped
if "events" in requested_modes:
@@ -180,6 +153,38 @@ async def run_agent(
)
try:
# Initialize RunJournal + write human_message event.
# These are inside the try block so any exception (e.g. a DB
# error writing the event) flows through the except/finally
# path that publishes an "end" event to the SSE bridge —
# otherwise a failure here would leave the stream hanging
# with no terminator.
if event_store is not None:
from deerflow.runtime.journal import RunJournal
journal = RunJournal(
run_id=run_id,
thread_id=thread_id,
event_store=event_store,
track_token_usage=getattr(run_events_config, "track_token_usage", True),
)
human_msg = _extract_human_message(graph_input)
if human_msg is not None:
msg_metadata = {}
if follow_up_to_run_id:
msg_metadata["follow_up_to_run_id"] = follow_up_to_run_id
await event_store.put(
thread_id=thread_id,
run_id=run_id,
event_type="human_message",
category="message",
content=human_msg.model_dump(),
metadata=msg_metadata or None,
)
content = human_msg.content
journal.set_first_human_message(content if isinstance(content, str) else str(content))
# 1. Mark running
await run_manager.set_status(run_id, RunStatus.running)
@@ -363,12 +368,15 @@ async def run_agent(
except Exception:
logger.warning("Failed to flush journal for run %s", run_id, exc_info=True)
# Persist token usage + convenience fields to RunStore
completion = journal.get_completion_data()
await run_manager.update_run_completion(run_id, status=record.status.value, **completion)
try:
# Persist token usage + convenience fields to RunStore
completion = journal.get_completion_data()
await run_manager.update_run_completion(run_id, status=record.status.value, **completion)
except Exception:
logger.warning("Failed to persist run completion for %s (non-fatal)", run_id, exc_info=True)
# Sync title from checkpoint to threads_meta.display_name
if checkpointer is not None:
if checkpointer is not None and thread_store is not None:
try:
ckpt_config = {"configurable": {"thread_id": thread_id, "checkpoint_ns": ""}}
ckpt_tuple = await checkpointer.aget_tuple(ckpt_config)
@@ -381,11 +389,12 @@ async def run_agent(
logger.debug("Failed to sync title for thread %s (non-fatal)", thread_id)
# Update threads_meta status based on run outcome
try:
final_status = "idle" if record.status == RunStatus.success else record.status.value
await thread_store.update_status(thread_id, final_status)
except Exception:
logger.debug("Failed to update thread_meta status for %s (non-fatal)", thread_id)
if thread_store is not None:
try:
final_status = "idle" if record.status == RunStatus.success else record.status.value
await thread_store.update_status(thread_id, final_status)
except Exception:
logger.debug("Failed to update thread_meta status for %s (non-fatal)", thread_id)
await bridge.publish_end(run_id)
asyncio.create_task(bridge.cleanup(run_id, delay=60))