Release Notes: v0.1.6¶
Date: 2026-05-12
This release bumps the crate version to 0.1.6.
Highlights¶
- Bumped crate version from
0.1.5to0.1.6.
Post-Release Snapshot¶
Date: 2026-05-15
This section captures the current main-branch work after the 0.1.6 release. The crate is still on 0.1.6; these notes reflect post-release work that should be visible in the docs and benchmark outputs.
Highlights¶
- Added early query routing intent detection for count, sum, and sequence questions.
- Added routed evidence-first reranking signals for numerical and sequence questions.
- Added
recall_any@kto the scoped LongMemEval benchmark so multi-session reporting matches the benchmark's any-hit interpretation. - Added fine-grained query timing fields, including:
evidence_msgroup_build_msgroup_sort_mslexical_merge_msposting_scoring_msrouting_seed_ms- Optimized routing seeding by removing repeated per-doc text parsing and token-set construction.
- Reduced query latency substantially on routed benchmark cases after the sparse scoring path was tightened.
- Hardened persistence paths and the spaCy subprocess script path.
- Refreshed the README and Tier 1 docs to match the current live query path and the latest benchmark results.
- Gated POS-derived time hints so they only affect ranking when the query has an explicit temporal phrase.
- Stopped applying recency bias from verb tense alone to non-temporal queries.
- Improved the benchmark stability slightly by reducing accidental temporal boosting.
Query Path Notes¶
- Query analysis now exposes routing intent for numerical and sequence questions.
- Routed queries use evidence scoring inside the rerank path.
- The benchmark and live query paths now both expose richer timing breakdowns for profiling.
- The current live pipeline remains lexical + sparse + graph based.
- POS-based time hints remain analysis metadata unless the query is explicitly temporal.
Benchmark Notes¶
- Scoped LongMemEval reporting now includes both
recall@kandrecall_any@k. - The current benchmark report used by the README is
benchmark/data/lintai_longmemeval_scoped_results.json.