mirror of
https://github.com/ruvnet/RuVector.git
synced 2026-05-24 13:54:31 +00:00
Three critical bugs were preventing the intelligence layer from using
learned patterns:
1. State format mismatch: CLI used spaces ("editing rs in project")
but Q-table used underscores ("edit_rs_in_project")
- Fixed in cli.js: all states now use underscore format
2. stateKey() hyphen normalization: Function converted hyphens to
underscores, but Q-table keys had hyphens (e.g. "ruvector-core")
- Fixed regex: /[^a-z0-9-]+/g preserves hyphens
3. A/B testing control group: 10% random sessions ignored learning
- Reduced holdout to 5% with persistent session assignment
- Added INTELLIGENCE_MODE=treatment env override for development
Result: Agent recommendations now show 80% confidence for Rust files
using learned Q-values, instead of 0% with random selection.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
|
||
|---|---|---|
| .. | ||
| v2 | ||
| zero-copy | ||
| operator-quick-reference.md | ||
| parallel-implementation-summary.md | ||
| parallel-query-guide.md | ||
| postgres-memory-implementation-summary.md | ||
| postgres-zero-copy-memory.md | ||
| postgres-zero-copy-quick-reference.md | ||
| SPARSEVEC_IMPLEMENTATION.md | ||
| SPARSEVEC_QUICKSTART.md | ||