mirror of
https://github.com/QwenLM/qwen-code.git
synced 2026-11-07 06:19:43 -10:00
On the shared agent loop, a tool batch's approvals are asked for before any of its calls runs, and a write that needs approval checks that its file was read when approval is asked for. The two tests that read and write a file in one response therefore failed the write as unread on the nightly unified-loop leg. The fake model now reads in one round and writes in the next, as a real model must, so both loops exercise canUseTool. The design doc lists the consequence with the batch approvals difference.