mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-08 13:12:08 +00:00
cb6d6d46ab
The FactRetriever's _fts_candidates passed the raw query string directly to FTS5's MATCH operator. FTS5 defaults to AND-between-tokens, which means any multi-word prose query like 'what happened with the deployment rollback' required every single token to co-occur in a fact — dropping recall to zero on the kind of queries agents actually issue via prefetch(). Fix: add _sanitize_fts_query() that: - tokenizes the query and drops English stopwords - strips FTS5 operator characters per token - OR-joins the remaining content tokens as phrase literals For pathological inputs (all stopwords, empty), falls back to the raw query so the caller sees zero results instead of a SQL error. This is a pure-retrieval-quality fix — the HRR + Jaccard reranking stages still keep precision high. Ships with 10 tests covering the sanitizer and retrieval integration. |
||
|---|---|---|
| .. | ||
| browser | ||
| context_engine | ||
| cron_providers | ||
| dashboard_auth | ||
| disk-cleanup | ||
| google_meet | ||
| hermes-achievements | ||
| image_gen | ||
| kanban | ||
| memory | ||
| model-providers | ||
| observability | ||
| platforms | ||
| security-guidance | ||
| spotify | ||
| teams_pipeline | ||
| video_gen | ||
| web | ||
| __init__.py | ||
| plugin_utils.py | ||