furyhawk/deer-flow
1
0
Fork 0
mirror of https://github.com/bytedance/deer-flow.git synced 2026-05-22 07:56:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(channels): preserve clarification conversation history across follow-up turns (#2444)

Browse Source 
* fix(channels): preserve clarification conversation history across follow-up turns

Pin channel-triggered runs to the root checkpoint namespace and ensure thread_id is always present in configurable run config so follow-up replies resume the same conversation state.

Add regression coverage to channel tests:

assert checkpoint_ns/thread_id are passed in wait and stream paths
add an integration-style clarification flow test that verifies the second user reply continues prior context instead of starting a new session
This addresses history loss after ask_clarification interruptions (issue #2425).

* Apply suggestions from code review

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* fix(channels): copy configurable dict before injecting run-scoped fields

  When configurable was already a plain dict, _resolve_run_params mutated
  it in place, leaking checkpoint_ns and thread_id back into the shared
  session config. Always copy via dict() before mutating to prevent
  cross-user or cross-channel config pollution.

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
Willem Jiang
2026-05-04 16:14:07 +08:00
committed by GitHub
parent af6e48ccaa
commit 8e48b7e85c
2 changed files with 138 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/app/channels/manager.py
+11
View File
@@ -589,6 +589,17 @@ class ChannelManager:
user_layer.get("config"),
)
configurable = run_config.get("configurable")
if isinstance(configurable, Mapping):
configurable = dict(configurable)
else:
configurable = {}
run_config["configurable"] = configurable
# Pin channel-triggered runs to the root graph namespace so follow-up
# turns continue from the same conversation checkpoint.
configurable["checkpoint_ns"] = ""
configurable["thread_id"] = thread_id
run_context = _merge_dicts(
DEFAULT_RUN_CONTEXT,
self._default_session.get("context"),