Skip to content

Python: honor reducer auto-reduce in chat completion threads #14017

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
pragnyanramtha wants to merge 2 commits into
base: main
Choose a base branch
from
+17 −1
Open

Python: honor reducer auto-reduce in chat completion threads #14017

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
aa4f2c3
Fix chat completion thread auto-reduction
pragnyanramtha May 16, 2026
dd4e1d9
Merge branch 'main' into pragnyan/python-agent-thread-auto-reduce-12303
pragnyanramtha May 18, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion python/semantic_kernel/agents/chat_completion/chat_completion_agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,7 +89,10 @@ async def _on_new_message(self, new_message: str | ChatMessageContent) -> None:
or "thread_id" not in new_message.metadata
or new_message.metadata["thread_id"] != self._id
):
self._chat_history.add_message(new_message)
if isinstance(self._chat_history, ChatHistoryReducer):
await self._chat_history.add_message_async(new_message)
else:
self._chat_history.add_message(new_message)

async def get_messages(self) -> AsyncIterable[ChatMessageContent]:
"""Retrieve the current chat history.
Expand Down
13 changes: 13 additions & 0 deletions python/tests/unit/agents/chat_completion/test_chat_completion_agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -164,6 +164,19 @@ def test_initialize_with_reducer_chat_history():
assert isinstance(thread._chat_history, ChatHistoryTruncationReducer)


async def test_thread_with_reducer_auto_reduces_new_messages():
reducer = ChatHistoryTruncationReducer(target_count=1, auto_reduce=True)
thread = ChatHistoryAgentThread(chat_history=reducer, thread_id="reducer_test_thread")

await thread.on_new_message(ChatMessageContent(role=AuthorRole.USER, content="first"))
await thread.on_new_message(ChatMessageContent(role=AuthorRole.ASSISTANT, content="second"))

messages = [message async for message in thread.get_messages()]

assert len(messages) == 1
assert messages[0].content == "second"


async def test_get_response(kernel_with_ai_service: tuple[Kernel, ChatCompletionClientBase]):
kernel, _ = kernel_with_ai_service
agent = ChatCompletionAgent(
Expand Down
Loading