hermes-agent/contributors/emails/liqiping@msh.team at feat/plugin-catalog - mirrors/hermes-agent - Cosmolan Git

mirrors/hermes-agent

mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-07-23 16:36:23 +00:00

liqiping 60811ced37 feat(agent): adaptive thinking for Kimi-family Anthropic endpoints

Kimi's Anthropic-compatible endpoints (api.moonshot.cn/anthropic,
api.kimi.com/coding) implement the adaptive thinking contract — they
accept thinking.type=adaptive + output_config.effort (all of low,
medium, high, xhigh, max verified live) and return thinking blocks, and
the replay-validation 400s that originally motivated dropping the
parameter (#13848) no longer occur.

_supports_adaptive_thinking() now returns True for Kimi-family models,
so they get thinking={type: adaptive, display: summarized} +
output_config.effort via ADAPTIVE_EFFORT_MAP instead of nothing, and
the blanket drop of the thinking parameter for Kimi-family endpoints is
removed. MiniMax and other non-adaptive third parties keep the manual
budget_tokens path; Claude behavior is unchanged.

2026-07-19 12:21:59 -07:00

1 line

8 B

Text

Raw Permalink Blame History

chouqin