Repository navigation
Conversation
The dotted-identifier scan over user text turned "e.g", "i.e" and "it.Then" into subjects. Require 2+ char parts with no capital after a dot (snake_case always counts).
Contributor
Author
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Salvage of #48 (port of NousResearch/hermes-memory-wiki#3 by @tillstriegel), rebased onto current
mainwith authorship kept, plus one fix on top.What #48 does: topics come from user turns and the title, not from tool/system/preview noise. Assistant text can only add context to an existing topic, never create one. User-supported topics rank first in Subjects and Daily logs. Tool-name rows are dropped from work items. This also stops cron prompt text and tool names (
terminal,exit code) from flooding the index, which is the noise #379 describes; #424 fixes that by source.Fix on top (e7c2016): #48 runs the dotted-identifier regex over free user text, so ordinary prose became subjects:
"Use a cache, e.g. redis, i.e. fast. Fix it.Then…"producede.g,i.eandit.Then. Matches now need parts of 2+ characters with no capital after a dot; snake_case always counts.tools.lookupandsearch_filesare still extracted. The new test fails on #48's head and passes here.Verification: full
memory-wiki/tests44 passed (main 26). The cherry-pick onto main had no conflicts.Merge order: this textually conflicts with #250 (Han extraction in the same
extract_subject_candidateshunks), #262 and #318 (memory_wiki_core.py). Land it after those; I'll rebase it.Supersedes #48.
Co-authored-by: Till Striegel till.striegel@gmail.com