Documentation
¶
Overview ¶
Package kimi implements thinking configuration for Kimi (Moonshot AI) models.
Kimi models use a native thinking object for both enabled and disabled thinking. The top-level reasoning_effort field is accepted only as a legacy input by the unified extraction layer and is removed from the final Kimi payload.
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Applier ¶
type Applier struct{}
Applier implements thinking.ProviderApplier for Kimi models.
Kimi-specific behavior:
- Enabled thinking: thinking.type="enabled" + thinking.effort=<level>
- Disabled thinking: thinking.type="disabled"
- Supports budget-to-level conversion
- Preserves existing thinking.keep when enabling or changing effort
func (*Applier) Apply ¶
func (a *Applier) Apply(body []byte, config thinking.ThinkingConfig, modelInfo *registry.ModelInfo) ([]byte, error)
Apply applies thinking configuration to Kimi request body.
Expected output format (enabled):
{
"thinking": {
"type": "enabled",
"effort": "high"
}
}
Expected output format (disabled):
{
"thinking": {
"type": "disabled"
}
}
Source Files
Click to show internal directories.
Click to hide internal directories.