Make request execution overrides presence-aware
This commit is contained in:
@@ -65,7 +65,7 @@ type RunRequest struct {
|
||||
ProfileID string
|
||||
Inputs map[string]ArtifactRef
|
||||
Vars map[string]string
|
||||
Execution *ExecutionTarget
|
||||
Execution *ExecutionTargetOverride
|
||||
Validation *OutputContract
|
||||
Metadata map[string]string
|
||||
}
|
||||
@@ -159,31 +159,45 @@ type PromptMessageTemplate struct {
|
||||
|
||||
// ExecutionProfile describes how and where to execute a model.
|
||||
type ExecutionProfile struct {
|
||||
ID string `yaml:"id"`
|
||||
Endpoint string `yaml:"endpoint"`
|
||||
Model string `yaml:"model"`
|
||||
Temperature float64 `yaml:"temperature"`
|
||||
MaxTokens int `yaml:"max_tokens"`
|
||||
TopP float64 `yaml:"top_p"`
|
||||
TimeoutSeconds int `yaml:"timeout_seconds"`
|
||||
ServiceTier string `yaml:"service_tier"`
|
||||
ReasoningEffort string `yaml:"reasoning_effort"`
|
||||
APIKeyEnv string `yaml:"api_key_env"`
|
||||
ExtraParams map[string]string `yaml:"extra_params"`
|
||||
ID string `yaml:"id"`
|
||||
Endpoint string `yaml:"endpoint"`
|
||||
Model string `yaml:"model"`
|
||||
Temperature float64 `yaml:"temperature"`
|
||||
MaxTokens int `yaml:"max_tokens"`
|
||||
TopP float64 `yaml:"top_p"`
|
||||
TimeoutSeconds int `yaml:"timeout_seconds"`
|
||||
ServiceTier string `yaml:"service_tier"`
|
||||
ReasoningEffort string `yaml:"reasoning_effort"`
|
||||
APIKeyEnv string `yaml:"api_key_env"`
|
||||
ExtraParams map[string]any `yaml:"extra_params"`
|
||||
}
|
||||
|
||||
// ExecutionTargetOverride represents per-request runtime setting overrides.
|
||||
type ExecutionTargetOverride struct {
|
||||
Endpoint string `json:"endpoint,omitempty"`
|
||||
Model string `json:"model,omitempty"`
|
||||
Temperature *float64 `json:"temperature,omitempty"`
|
||||
MaxTokens *int `json:"max_tokens,omitempty"`
|
||||
TopP *float64 `json:"top_p,omitempty"`
|
||||
TimeoutSeconds *int `json:"timeout_seconds,omitempty"`
|
||||
ServiceTier string `json:"service_tier,omitempty"`
|
||||
ReasoningEffort string `json:"reasoning_effort,omitempty"`
|
||||
APIKeyEnv string `json:"api_key_env,omitempty"`
|
||||
ExtraParams map[string]any `json:"extra_params,omitempty"`
|
||||
}
|
||||
|
||||
// ExecutionTarget represents effective model runtime settings for a run.
|
||||
type ExecutionTarget struct {
|
||||
Endpoint string `yaml:"endpoint" json:"endpoint"`
|
||||
Model string `yaml:"model" json:"model"`
|
||||
Temperature float64 `yaml:"temperature" json:"temperature"`
|
||||
MaxTokens int `yaml:"max_tokens" json:"max_tokens"`
|
||||
TopP float64 `yaml:"top_p" json:"top_p"`
|
||||
TimeoutSeconds int `yaml:"timeout_seconds" json:"timeout_seconds"`
|
||||
ServiceTier string `yaml:"service_tier" json:"service_tier"`
|
||||
ReasoningEffort string `yaml:"reasoning_effort" json:"reasoning_effort"`
|
||||
APIKeyEnv string `yaml:"api_key_env" json:"api_key_env"`
|
||||
ExtraParams map[string]string `yaml:"extra_params" json:"extra_params"`
|
||||
Endpoint string `yaml:"endpoint" json:"endpoint"`
|
||||
Model string `yaml:"model" json:"model"`
|
||||
Temperature float64 `yaml:"temperature" json:"temperature"`
|
||||
MaxTokens int `yaml:"max_tokens" json:"max_tokens"`
|
||||
TopP float64 `yaml:"top_p" json:"top_p"`
|
||||
TimeoutSeconds int `yaml:"timeout_seconds" json:"timeout_seconds"`
|
||||
ServiceTier string `yaml:"service_tier" json:"service_tier"`
|
||||
ReasoningEffort string `yaml:"reasoning_effort" json:"reasoning_effort"`
|
||||
APIKeyEnv string `yaml:"api_key_env" json:"api_key_env"`
|
||||
ExtraParams map[string]any `yaml:"extra_params" json:"extra_params"`
|
||||
}
|
||||
|
||||
// OutputContract defines the requirements for the output artifact.
|
||||
|
||||
Reference in New Issue
Block a user