feat(dreaming): auto-classify memory topics on fact extraction#23
Draft
stackbilt-admin wants to merge 1 commit intomainfrom
Draft
feat(dreaming): auto-classify memory topics on fact extraction#23stackbilt-admin wants to merge 1 commit intomainfrom
stackbilt-admin wants to merge 1 commit intomainfrom
Conversation
Wire recordMemoryWithAutoTopic into the dreaming cycle's fact and preference extraction phases. When tarotscriptFetcher is available, facts are classified via the memory-topic-classify spread against the 15-topic canonical taxonomy (v1 memory-topics deck). This produces real observation data against the 70% synthetic accuracy baseline from tarotscript#165. Classification metadata (topic, confidence, source) is logged in existing [dreaming] log lines for live accuracy observation. Fallback behavior: - Classifier failure / low confidence → falls through to 'general' topic safely (existing recordMemoryWithAutoTopic semantics) - No tarotscriptFetcher → original recordMemory path with LLM- provided or hardcoded topics (existing behavior preserved) - Blocked topic prefixes (synthesis_*) still rejected even when auto-topic is active Call sites swapped (2): - processFacts: fact writes (LLM-provided topics → classifier) - processFacts: preference writes (hardcoded 'operator_preferences' → classifier) Call sites deliberately left alone (3): - persona.ts: 'operator_persona' (deliberate phase-specific topic) - pattern-synthesis.ts: 'meta_insight' (deliberate PRISM categorization) - symbolic.ts: 'symbolic_reflection' (deliberate phase-specific topic) Co-Authored-By: Claude Opus 4.6 (1M context) <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.
Summary
recordMemoryWithAutoTopic()into the dreaming cycle's fact and preference extraction phasestarotscriptFetcheris available, facts are classified via the TarotScript memory-topic-classify spread against the 15-topic canonical taxonomyChanges
Swapped (2 call sites):
processFactsfact writes: LLM-provided topics → classifierprocessFactspreference writes: hardcodedoperator_preferences→ classifierDeliberately left alone (3 call sites):
persona.ts:operator_persona— deliberate phase-specific topicpattern-synthesis.ts:meta_insight— deliberate PRISM categorizationsymbolic.ts:symbolic_reflection— deliberate phase-specific topicBehavior
[dreaming]linestarotscriptFetcher→ graceful fallback to originalrecordMemorypathgeneralsafelysynthesis_*) still rejected even with auto-topic activeTest plan
🤖 Generated with Claude Code