mirror of
https://github.com/MoonshotAI/kimi-code.git
synced 2026-08-01 20:44:53 +00:00
3d5d630c12
An explicit withThinking('off') collapsed to the same internal state as
"never configured" on chat-completions providers, so the history-based
auto reasoning_effort injection (#1616) silently switched reasoning back
on and could leak the field to models that reject it. Store the requested
effort verbatim and derive the wire encoding per request, suppress the
auto-enable for an explicit 'off', and report the accurate current effort
('on'/'off') instead of recording 'off' for both.
|
||
|---|---|---|
| .. | ||
| src | ||
| test | ||
| CHANGELOG.md | ||
| package.json | ||
| README.md | ||
| tsconfig.json | ||
| tsconfig.type-negative.json | ||
| tsdown.config.ts | ||
| vitest.config.ts | ||