fix(langchain_v1): disable summarization when max_tokens_before_summary is None #33796
+12
−5
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
github-actions
bot
added
langchain
…ry is None Fix SummarizationMiddleware to properly disable all summarization when max_tokens_before_summary=None, as documented. Previously, summarization would still occur based on message count when this parameter was None. The fix adds an early return when max_tokens_before_summary is None, ensuring summarization is completely disabled regardless of message count or token count. Adds test case with messages exceeding messages_to_keep to verify the fix.
karamvirsingh1998
force-pushed
the
fix/summarization-middleware-disable-none
branch
from
1a9783f to
341cd45
Compare
karamvirsingh1998
changed the title
1 task
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description:
Fix
SummarizationMiddlewareto properly disable all summarization whenmax_tokens_before_summary=None, as documented in the docstring.Previously, when
max_tokens_before_summary=None, the middleware would still trigger summarization if the number of messages exceededmessages_to_keep(default: 20). This violated the documented behavior that states: "IfNone, summarization is disabled."The fix adds an early return when
max_tokens_before_summaryis None, ensuring summarization is completely disabled regardless of message count or token count.Changes:
before_model()to return early whenmax_tokens_before_summaryis Nonemessages_to_keep=20) to verify summarization remains disabledIssue: N/A
Dependencies: None
Testing:
test_summarization_middleware_no_summarization_caseswith 25 messages