mirror of
https://github.com/openclaw/openclaw.git
synced 2026-06-22 19:28:09 +00:00
Drop assistant replay turns that ended at the token limit with only incomplete hidden reasoning while preserving visible text, tool calls, empty turns, and unknown content shapes. Apply the same classification to embedded replay and public transport transforms, with focused regression, live OpenAI/Anthropic provider proof, docs, autoreview, Testbox, and green CI. Co-authored-by: clawstation <abel@stationzero.ai>