fix(session): skip messages.jsonl in semantic file summary generation#617
Merged
MaojiaSheng merged 1 commit intovolcengine:mainfrom Mar 15, 2026
Conversation
During session commit, messages.jsonl (the archived session transcript) was unnecessarily summarized by the semantic file summary pipeline, wasting tokens and adding latency. Add messages.jsonl to a skip list in _list_dir() so it never enters the semantic DAG. Closes volcengine#564
MaojiaSheng
approved these changes
Mar 15, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Skip
messages.jsonlfrom the semantic file summary pipeline during session commit. This file is the canonical session transcript archive and should not be re-summarized as a generic document.Why this matters
During
session.commit(), the session temp directory is enqueued intoSemanticQueuewithrecursive=True.SemanticDagExecutorprocesses all files uniformly, somessages.jsonlgoes through VLM-based file summary generation and vectorization - wasting tokens, adding latency, and providing no retrieval value.SemanticDagExecutor._file_summary_task()insemantic_dag.pyChanges
_SKIP_FILENAMESfrozenset insemantic_dag.pycontainingmessages.jsonl_list_dir()to exclude these files from the DAG before they reach_file_summary_task()Testing
tests/storage/test_semantic_dag_skip_files.pywith 2 test cases:messages.jsonlexcluded at root level while other files are still processedmessages.jsonlexcluded in nested subdirectoriesFixes #564
This contribution was developed with AI assistance (Claude Code).