mirror of
https://github.com/deepseek-ai/deepseek-harness.git
synced 2026-09-07 04:10:42 +00:00
The review found the 64 MiB parse cap contradicted the load-time budget bound: maxLogBytes/maxValueBytes could be configured up to ceiling - envelope (~256 MiB), but the receive path silently dropped any frame past the 64 MiB parser cap, so an honest child's budget-internal done frame under such a config would be discarded and the run stranded to the wall clock. The load bound is now parse-cap - envelope, so a configured budget always fits through the parser; the boundary test moves to 64 MiB - 64. The >64 MiB model-constructed binding-argument drop is registered as an accepted residual in the README (en + zh).