whale 8c068a1f5c fix(kimi): normalize reasoning_effort to backend enum (#2427) ... Map auto→high, minimal→low, xhigh→max and whitelist low/medium/high/max so Kimi/kimchi SGLang backends no longer receive invalid effort values. Co-authored-by: Cursor <cursoragent@cursor.com>		2026-07-07 11:56:39 +07:00
..
concerns	fix(kimi): normalize reasoning_effort to backend enum (#2427)	2026-07-07 11:56:39 +07:00
formats	fix(claude): reconcile max_tokens vs thinking budget and lift per-model ceiling (#2381)	2026-07-05 17:38:16 +07:00
request	fix(translator): preserve developer instructions in openai-responses conversion (#2434)	2026-07-07 11:54:07 +07:00
response	feat(usage): track cached tokens + correct input/output/cache cost (#2209)	2026-07-03 15:18:27 +07:00
schema	Refactor	2026-06-15 18:18:04 +07:00
formats.js	feat: add CommandCode provider support	2026-05-07 23:01:33 +07:00
index.js	fix(alicode): preserve cache_control for DashScope providers (#2069)	2026-06-29 15:29:49 +07:00