@hmharness/evaluation
MIThmharness evaluation: the Evaluator/Judge contract (V2 blueprint M2). Hard evidence outranks LLM judgment - build results, exit codes, exact/regex assertions first; the LLM judge is a last resort and is labeled as such. Evaluations attach to trajectories
100
Security score
0 known advisories in v0.20.2
Weekly downloads
—
Unpacked size
64.7 kB
Dependencies
2
Last publish
1 hour ago
Security advisories
No known vulnerabilities affect v0.20.2.