Documentation
¶
Overview ¶
Package iflow implements thinking configuration for iFlow models.
iFlow models use boolean toggle semantics:
- Models using chat_template_kwargs.enable_thinking (boolean toggle)
- MiniMax models: reasoning_split (boolean)
Level values are converted to boolean: none=false, all others=true See: _bmad-output/planning-artifacts/architecture.md#Epic-9
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 iFlow models.
iFlow-specific behavior:
- enable_thinking toggle models: enable_thinking boolean
- GLM models: enable_thinking boolean + clear_thinking=false
- MiniMax models: reasoning_split boolean
- Level to boolean: none=false, others=true
- No quantized support (only on/off)
func (*Applier) Apply ¶
func (a *Applier) Apply(body []byte, config thinking.ThinkingConfig, modelInfo *registry.ModelInfo) ([]byte, error)
Apply applies thinking configuration to iFlow request body.
Expected output format (GLM):
{
"chat_template_kwargs": {
"enable_thinking": true,
"clear_thinking": false
}
}
Expected output format (MiniMax):
{
"reasoning_split": true
}
Click to show internal directories.
Click to hide internal directories.