KunN-21 7afaecd617 fix(kimchi): strip reasoning_content echo to bound multi-turn input tokens ...

Clients echo full message history each turn including reasoning_content,
which the Kimchi OpenAI gateway counts as input tokens. Multi-turn convos
balloon to 100k+ tokens and the model returns empty content.

KimchiExecutor.transformRequest now strips reasoning_content from assistant
messages when it exceeds an 8-char threshold, preserving the 1-char
placeholder injectReasoningContent sets and keeping content intact.

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-07-03 10:58:31 +07:00

3.8 KiB

Raw Permalink Blame History

View Raw