feat(personal): opt-in model extraction for the KG (#1, part 2)#66
Merged
Conversation
…part 2) Adds a Settings toggle 'Richer graph (uses the model)' (default OFF) under Personalization. When on, live learning uses the MODEL extractor instead of the offline heuristic, pulling semantic facts + relationships (so related ideas connect across turns, e.g. custard~caramel) at the cost of one extra model call per turn. Wiring: new personalAiExtract setting (+ setter); learnFromTurn takes an optional model-call and uses modelExtractor when the flag is on; acp_backend passes its existing complete() util (the same one the import path already uses); personalStatus exposes aiExtract; bridge + /api/personal/ai-extract route + UI toggle (only shown when the store is unlocked, since that's when learning runs). Off by default → zero cost; the offline cross-turn linker (part 1, #65) still runs underneath either way. Verified: API round-trips the flag false->true->false; tsc clean; 332 desktop + personal tests pass. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
mlcyclops
added a commit
that referenced
this pull request
Jun 24, 2026
…l hygiene) (#70) ADR-0042: records the opt-in personalAiExtract toggle (default OFF) — model-based extraction for richer semantic facts + cross-turn relations at one model call/turn, reusing backend.complete(); offline heuristic + cross-turn linker remain the free baseline (PR #66, ADR-0010). ADR-0043: records the recall-hygiene decision — recall excludes mechanical tool activity (omp:*/subagent:*, PR #50) and rememberActivity stops promoting raw tool I/O as durable facts while keeping provenance ingest (PR #56); subagent-result promotion through the keystone-#2 gate is untouched (ADR-0009, keystone #2). Co-authored-by: mlcyclops <mlcyclops@users.noreply.github.com> Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
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
1 participant
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.
Part 2 of the 'Both' approach. Adds a Settings toggle 'Richer graph (uses the model)' (default OFF) under Personalization.
When on, live learning uses the model extractor instead of the offline heuristic, pulling semantic facts + relationships so related ideas connect across turns (custard~caramel) — at the cost of one extra model call per turn. Off by default → zero cost; the always-on offline cross-turn linker from #65 still runs underneath either way.
Wiring:
personalAiExtractsetting + setter;learnFromTurntakes an optional model-call and usesmodelExtractorwhen the flag is on;acp_backendpasses its existingcomplete()util (same one import uses);personalStatusexposesaiExtract; bridge +/api/personal/ai-extractroute + UI toggle (shown only when the store is unlocked).Verified: API round-trips the flag false→true→false; tsc clean; 332 desktop + personal tests pass.
🤖 Generated with Claude Code