agentbench / tests /test_tools.py

Commit History

docs(eval): Fix 2 SearchTool query expansion β€” attempted and reverted
27c2e17

Nomearod Claude Opus 4.6 (1M context) commited on

feat: expose reranker scores through retrieval pipeline
c5573d3

Nomearod Claude Opus 4.6 (1M context) commited on

feat: add grounded refusal gate based on retrieval score threshold
c410788

Nomearod Claude Opus 4.6 (1M context) commited on

fix: wire top_k/strategy through orchestrator to SearchTool, add RAG integration test
3fc43ec

Nomearod Claude Opus 4.6 (1M context) commited on

fix: handle malformed top_k in SearchTool, add registry dispatch test
8766b82

Nomearod Claude Opus 4.6 (1M context) commited on

feat: Day 2 β€” tool system with registry, calculator, and search
36a9ab7

Nomearod Claude Opus 4.6 (1M context) commited on