ct run timing-report

Phase-level timing + token/cost report for a finished eval run. Reads a .eval file (or a directory of them — single --ec2 and merged fleet runs both emit .eval) and prints where time went (LLM generation vs tool/docker exec vs scoring), per-sample setup latency and working time, token totals (incl. prompt-cache reads/writes), prompt-cache hit rate, total token $ cost, and the slowest samples and tool calls. Pure analysis over data already in the log — no API calls, no eval spend.

Usage

ct run timing-report [OPTIONS] EVAL_PATH

Arguments

ArgumentTypeRequired
EVAL_PATHpathYes

Options

OptionDescription
--top INTEGERHow many slowest samples / tool calls to list. [default: 5]
--jsonEmit the report as JSON instead of the text table.
--helpShow this message and exit.