scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-11 22:51:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 123

fix(realtime): set guardrail turn_detection flag only after successful send

Browse source 
Previously the _guardrail_turn_detection_update_sent flag was set inline
during message rewriting in client_ack_messages, before the modified
session.update was forwarded to the backend. If _send_to_backend raised
(e.g. backend WebSocket disconnect), the exception was caught and the
loop continued, but the flag remained True — permanently disabling the
guardrail create_response=False injection for the rest of the session.
Neither the client_ack_messages path nor the
_maybe_send_guardrail_turn_detection_update backup path would retry.

Track the injection locally and only set the flag after _send_to_backend
returns a truthy sent result, matching the pattern used by
_maybe_send_guardrail_turn_detection_update.

Co-authored-by: Yassin Kortam <yassin@berri.ai>
This commit is contained in:
Cursor Agent 2026-05-22 18:49:47 +00:00
parent b721714783
commit 6f45b5df06
No known key found for this signature in database
1 changed files with 10 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
litellm/litellm_core_utils/realtime_streaming.py
View file

@ -848,6 +848,7 @@ class RealTimeStreaming:
message = await self.websocket.receive_text()
## GUARDRAIL: intercept conversation.item.create for text-based injection.
guardrail_turn_detection_injected = False
try:
msg_obj = json.loads(message)
msg_type = msg_obj.get("type")
@ -905,7 +906,7 @@ class RealTimeStreaming:
existing_td["create_response"] = False
session["turn_detection"] = existing_td
message = json.dumps(msg_obj)
self._guardrail_turn_detection_update_sent = True
guardrail_turn_detection_injected = True
verbose_logger.debug(
"Injected turn_detection into first session.update for audio transcription guardrails"
)
@ -933,7 +934,14 @@ class RealTimeStreaming:
self.store_input(message=message)
## FORWARD TO BACKEND
await self._send_to_backend(message)
# Only mark the guardrail turn_detection update as sent after the
# backend actually accepted the message. Setting the flag earlier
# would permanently disable the injection if ``_send_to_backend``
# raised — neither this loop nor
# ``_maybe_send_guardrail_turn_detection_update`` would retry.
sent = await self._send_to_backend(message)
if guardrail_turn_detection_injected and sent:
self._guardrail_turn_detection_update_sent = True
except Exception as e:
verbose_logger.debug(f"Error in client ack messages: {e}")