Files
hermes-agent/tools
Teknium 62e8126c69 fix(skill_manage): batch failure results carry the failing op's teaching payload (file_preview, hints)
Live A/B eval (old flat vs operations[] on qwen3.8-27b / gpt-5.6-terra /
claude-sonnet-5) caught a real regression: on a fuzzy-match miss the flat
path returns file_preview so the model can self-correct, but the batch
wrapper rebuilt the error dict and dropped every field except error/
failed_index. Sonnet, recovering blind, probed the file by writing and
reverting placeholder patches for 8+ turns (50k tokens vs 15k on the flat
arm). Batch failures now merge through all non-error fields from the
failing op's result.
2026-08-28 19:38:21 -07:00
..