centdix 3f5f211a22 add final context size metric to ai_evals harness (#9660) ...

Record finalContextTokens per attempt: the input-token total of the last
model request (input + cache-creation + cache-read), i.e. how full the
context window ended up. Complements the cumulative tokenUsage.prompt,
which conflates context size with loop-iteration count.

Captured generically in the shared frontend runEval via the chat loop's
lastIterationUsage, so it covers all frontend modes (global/flow/script/
app), plus CLI mode via the last assistant turn's usage. Aggregated as
average and max over passed attempts and printed in the run summary.

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-18 23:21:28 +02:00

..

runtime.test.ts

tests: add cli eval behavior checks (#8899)

2026-04-21 16:17:40 +00:00

runtime.ts

add final context size metric to ai_evals harness (#9660)

2026-06-18 23:21:28 +02:00