Expand description
The runner: orchestrates a test case into a conversation, drives the provider across turns, scores the transcript with evals, and fans out over the configured platform × model matrix.
Structs§
- Runner
- Runs test cases against a provider using a configuration.
- Stream
Event - One streamed tool event, tagged with the run it belongs to, delivered live to
a
Runner::run_all_streamingsink so a consumer can watch what a skill does and short-circuit.