phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-12 20:12:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

skip emitting deltas

Browse source
This commit is contained in:
Swapna Lekkala 2025-10-15 06:28:06 -07:00
parent eb7dcebb25
commit fc960a35dd
1 changed files with 9 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

16
llama_stack/providers/inline/agents/meta_reference/responses/streaming.py
View file

@ -601,13 +601,15 @@ class StreamingResponseOrchestrator:
sequence_number=self.sequence_number,
)
self.sequence_number += 1
yield OpenAIResponseObjectStreamResponseOutputTextDelta(
content_index=content_index,
delta=chunk_choice.delta.content,
item_id=message_item_id,
output_index=message_output_index,
sequence_number=self.sequence_number,
)
# Skip Emitting text content delta event if guardrails are configured, only emits chunks after guardrails are applied
if not self.guardrail_ids:
yield OpenAIResponseObjectStreamResponseOutputTextDelta(
content_index=content_index,
delta=chunk_choice.delta.content,
item_id=message_item_id,
output_index=message_output_index,
sequence_number=self.sequence_number,
)
# Collect content for final response
chat_response_content.append(chunk_choice.delta.content or "")