lukaszraczylo ace50757e4 fix: floor token budgets and surface truncation, add live progress ...

Reasoning models burn thousands of completion tokens before the
answer. Small per-test caps caused silent truncation and zero scores.
The runner now floors max_tokens at the config default (12000). The
client parses finish_reason. Reports mark truncated cells and the
JSON format carries response text for debugging. A stderr progress
reporter prints one line per completed request; --quiet disables it.

2026-08-17 01:55:14 +01:00

..

llm.go

fix: floor token budgets and surface truncation, add live progress

2026-08-17 01:55:14 +01:00

openai_test.go

fix: floor token budgets and surface truncation, add live progress

2026-08-17 01:55:14 +01:00

openai.go

fix: floor token budgets and surface truncation, add live progress

2026-08-17 01:55:14 +01:00