eval

package
v0.3.73 Latest Latest
Warning

This package is not in the latest version of its module.

Go to latest
Published: Jul 1, 2026 License: MIT Imports: 13 Imported by: 0

Documentation

Index

Constants

This section is empty.

Variables

This section is empty.

Functions

func CleanCommandEnv

func CleanCommandEnv(env []string) []string

func WriteJSON

func WriteJSON(path string, result Result) error

Types

type Budgets

type Budgets struct {
	MaxWallTime    time.Duration
	MaxTotalTokens int64
	MaxCostUSD     float64
}

type Case

type Case struct {
	ID       string
	Title    string
	Category string
	Prompt   string
	Budgets  Budgets
	Oracle   Oracle
}

type Comparison

type Comparison struct {
	BaselinePasses  int     `json:"baseline_passes"`
	CandidatePasses int     `json:"candidate_passes"`
	CostDeltaUSD    float64 `json:"cost_delta_usd"`
	Regressed       bool    `json:"regressed"`
}

func Compare

func Compare(baseline, candidate []Result) Comparison

type Oracle

type Oracle struct {
	Commands       []string
	ExpectedFiles  map[string]string
	ForbiddenFiles []string
}

type Result

type Result struct {
	CaseID          string            `json:"case_id"`
	Suite           string            `json:"suite,omitempty"`
	AgentVersion    string            `json:"agent_version,omitempty"`
	Provider        string            `json:"provider,omitempty"`
	Model           string            `json:"model,omitempty"`
	Status          Status            `json:"status"`
	FailureCategory string            `json:"failure_category,omitempty"`
	EngineStatus    engine.Status     `json:"engine_status"`
	EngineError     string            `json:"engine_error,omitempty"`
	Metrics         engine.RunMetrics `json:"metrics"`
	OracleLog       string            `json:"oracle_log,omitempty"`
	Artifacts       map[string]string `json:"artifacts,omitempty"`
}

type Runner

type Runner struct {
	Suite        string
	AgentVersion string
	Provider     string
	Model        string
	Workspace    string
	ArtifactsDir string
	Engine       *engine.Engine
	Trace        *event.Recorder
}

func (Runner) Run

func (r Runner) Run(ctx context.Context, c Case) (Result, error)

type Status

type Status string
const (
	Pass    Status = "pass"
	Fail    Status = "fail"
	Timeout Status = "timeout"
	Error   Status = "error"
)

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL