Make local_files chunking opt-in instead of default - #14
Merged
Conversation
Files were always split at 2000 chars with 200 overlap. Now each file becomes one memory regardless of size unless chunk_size is explicitly passed in the connector config. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0186k3gs6jRSfTtaCjjY9Xj7
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
local_filesconnector no longer chunks by default — each file becomes one memory regardless of size.chunk_size(and optionallyoverlap, default 200) in the connector config to opt back into splitting large files.chunk_sizeis set).Test plan
tests/test_robustness_hardening.py(chunk_size validation) — 8/8 passedtests/test_connector_sync.py— could not run locally, missingfastapi/mcppackages in this environment (unrelated to this change)Generated by Claude Code