-
fix(prompt): add output precision and threshold iteration rules (#9178)
发布于
2026-02-08 17:37:04 +00:00 - fix(prompt): add output precision and threshold iteration rules
Two concise rules proven effective via Terminal-Bench testing:
- Output precision: produce exactly what's specified, no extra columns/fields/debug output
- Threshold iteration: verify results meet numerical criteria before completing
Tested on 6 targeted Terminal-Bench tasks (job 2026-02-07__16-15-00):
- log-summary-date-ranges: FAIL→PASS (output precision rule eliminated extra columns)
- dna-insert: FAIL→PASS (iterate rule helped agent meet Tm threshold)
A third rule (no-cleanup) was tested and deliberately excluded: it failed to
prevent self-sabotage on configure-git-webserver despite STRICTLY FORBIDDEN
language, and caused a side-effect on polyglot-c-py by preventing legitimate
build artifact cleanup. The cleanup behavior is too deeply trained to override
via prompt rules alone.- test: update prompt snapshots for new rules
下载附件