Conversation
Bump version to 3.4.5.dev0 and add release process docs
The SQL queries used ORDER BY priority DESC which selected higher numbers first, but the priority scale defines lower numbers as more urgent (1=urgent, 5=minimal). This caused minimal priority tasks to be processed before urgent ones. Changed priority ordering from DESC to ASC in: - get_next_work() query - get_pending_work() query - Priority index definition Updated tests to use correct priority values matching the scale.
Fix task priority ordering - urgent tasks now processed first
Bump version to 3.4.5.dev2
- Add sugar/memory module with store, embedder, retriever, types - Add CLI commands: remember, recall, memories, forget, export-context, memory-stats - Add MCP memory server for Claude Code integration - Support semantic search with sentence-transformers (optional) - Fallback to FTS5 keyword search when embeddings unavailable - Add optional dependencies: memory, all extras in pyproject.toml - Add 24 comprehensive tests for memory functionality - Update README, CHANGELOG, and CLI reference documentation
Add Memory System for persistent semantic memory (v3.5)
- Remove phrase-matching quotes that broke multi-word searches - Add OR between terms for better recall - Add simple English stemming (trademarks → trademark) - Add prefix matching (*) for partial word matches Fixes searches like "trademarks" and "trademark worksignal" that previously returned 0 results due to exact phrase matching.
Applied consistent import ordering: - stdlib imports first - third-party imports second - local imports last - alphabetical within each group
Shows users how Sugar memory reduces token usage: - Compression ratio analysis (typically 90%+ reduction) - Per-session savings projection - Cumulative cost savings over time - Works with real project memory data Run: python examples/token_savings_demo.py
fix: Improve FTS5 memory search for stemming and multi-word queries
- Add Token Savings section to memory.md with real metrics - Update README Memory System section with savings highlight - Bump version to 3.5.0.dev1 Memory system provides ~89% token reduction per session through: - Compressed summaries (90%+ smaller than full content) - Targeted retrieval (only fetch what's relevant) - Persistent storage (store once, retrieve many times)
Memory System improvements: - fix: FTS5 search now handles stemming and multi-word queries - docs: Added token savings documentation and demo script - style: Sorted imports across codebase Token savings: ~89% reduction per session through compressed summaries and targeted retrieval.
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
Release 3.5.0 brings significant improvements to the Memory System, including better search functionality and documentation of token savings.
Highlights
Memory Search Fix
trademarks→trademark)trademark worksignal)trade*)Token Savings
examples/token_savings_demo.pyfor users to measure their own savingsChanges
Test Results
After Merge
git tag v3.5.0 && git push origin v3.5.03.5.1.dev0