fix(memory): extract clean declarative facts instead of raw messages in holographic auto_extract (#22907)#39667
Open
dusterbloom wants to merge 1 commit into
Open
Conversation
…in holographic auto_extract (NousResearch#22907) The old regex patterns (I like/love/want/need) matched common phrases and dumped the entire user message verbatim as a fact. 'I like that, sounds good' became a stored fact. Fix: removed noisy 'like/love/want/need' patterns. Remaining patterns extract captured groups into clean declarative statements: 'prefers dark mode over light mode' instead of 'I prefer dark mode over light mode, can you set it up?'. 200 char cap, one fact per message, assistant messages skipped. Closes NousResearch#22907
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #22907
The old regex patterns (I like/love/want/need) matched common phrases and dumped the entire user message verbatim as a fact. "I like that, sounds good" became a stored fact.
Fix: Removed noisy like/love/want/need patterns. Remaining patterns extract captured groups into clean declarative statements: "prefers dark mode over light mode" instead of "I prefer dark mode over light mode, can you set it up?". 200 char cap, one fact per message, assistant messages skipped.
Tests: 8 tests — preference extraction, no raw dumps, decisions, habits, assistant messages ignored, short messages skipped, one fact per message, 200-char length cap.
This was originally part of #23221 — split into focused single-fix PRs for easier review.