Conversation
Add a Relevance section to the AI summarization prompt that lets the AI flag sessions as "skip" when they contain no useful project knowledge (test chats, meta-conversations, tooling troubleshooting). When flagged, the session is still stored and summarized but: - Decisions, mistakes, and corrections are not ingested into knowledge - A skip_knowledge frontmatter field marks the session for filtering - Knowledge base rebuilds skip these sessions - ghost log shows a (skipped) indicator https://claude.ai/code/session_01FwyHciZ86DLhgvEH5Gi5Uu
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
This PR adds a mechanism to flag sessions as not relevant for knowledge ingestion, allowing the AI to explicitly mark test chats, demos, and other non-productive sessions so they don't pollute the project knowledge base.
Key Changes
skip_knowledge: truefield in their frontmatter for downstream filteringbuildKnowledge()to skip sessions with theskip_knowledgeflag and log how many were excludedaddFrontmatterField()public insession.tsto support frontmatter updates in the background processorImplementation Details
extractSections()function now parses the Relevance section and returns askipKnowledgeboolean flag!sections.skipKnowledgeguard to prevent processinghttps://claude.ai/code/session_01FwyHciZ86DLhgvEH5Gi5Uu