summaryeval

type AhaMoment struct {
	Seq  int    `json:"seq"`
	Type string `json:"type"`
}

type Completer func(ctx context.Context, prompt string) (CompletionResult, error)

type CompletionResult struct {
	Text             string
	ModelUsed        string
	PromptTokens     int
	CompletionTokens int
}

type DimensionScore struct {
	Dimension string  `json:"dimension"`
	Score     float64 `json:"score"`
	Reason    string  `json:"reason,omitempty"`
}

type Gates struct {
	MinOverall    float64            `json:"min_overall,omitempty"`
	MinDimensions map[string]float64 `json:"min_dimensions,omitempty"`
}

type GoldenSession struct {
	// Name identifies the session (matches ledger session dir name).
	Name string `json:"name"`

	// Notes is free-form human context explaining why this session was
	// chosen and what a good summary should capture. Not scored; helps
	// future curators.
	Notes string `json:"notes,omitempty"`

	// Reference is the trusted summary: what a great distillation looks
	// like for this session. Candidates are scored against this.
	Reference Summary `json:"reference"`
}

type Judge interface {
	Score(ctx context.Context, name string, reference *Summary, candidate Summary) (JudgeResult, error)
}

type JudgeOptions struct {
	// ModelHint is a free-form tag the Judge can use to signal the
	// desired model class to the Completer. The Completer may ignore
	// it. Example: "haiku" for cheap/fast; "opus" for deep evaluation.
	// If empty, the Completer picks.
	ModelHint string

	// IncludeSuggestions, when true, asks the judge for up to 5 concrete
	// suggestions for improving the summary. Slight prompt length
	// increase; usually worth it for diagnostic mode.
	IncludeSuggestions bool

	// MaxRationaleChars caps the rationale length the judge is asked
	// to produce. Default: 600. Set lower to reduce completion tokens.
	MaxRationaleChars int
}

type JudgeResult struct {
	// Name identifies the session scored.
	Name string `json:"name"`

	// Dimensions are per-dimension 0.0-1.0 scores (same dimension
	// names as Rubric). Absent dimensions are treated as 0.0 when
	// converting to SessionScore.
	Dimensions []DimensionScore `json:"dimensions"`

	// Overall is the judge's aggregate verdict, 0.0-1.0.
	Overall float64 `json:"overall"`

	// Rationale is a short human-readable explanation of the verdict.
	// Useful for humans debugging "why did this summary score 0.4?"
	Rationale string `json:"rationale,omitempty"`

	// Suggestions is a short list of specific, actionable fixes the
	// judge thinks would improve the summary. Surfaced to the user
	// via diagnostic output; consumed by CI in "hint to the prompt
	// engineer" mode.
	Suggestions []string `json:"suggestions,omitempty"`

	// ModelUsed identifies which model produced the judgment, for
	// reproducibility tracking ("haiku-4-5", "opus-4-7", etc.).
	ModelUsed string `json:"model_used,omitempty"`

	// DurationMs captures end-to-end judge latency including the LLM
	// call. Useful for operational telemetry.
	DurationMs int64 `json:"duration_ms,omitempty"`

	// PromptTokens / CompletionTokens are the raw token counts the
	// LLM reported, when available. Used for cost attribution.
	PromptTokens     int `json:"prompt_tokens,omitempty"`
	CompletionTokens int `json:"completion_tokens,omitempty"`
}

type Report struct {
	ScoredAt       time.Time          `json:"scored_at"`
	CorpusSize     int                `json:"corpus_size"`
	OverallMean    float64            `json:"overall_mean"`
	OverallMin     float64            `json:"overall_min"`
	OverallMax     float64            `json:"overall_max"`
	DimensionMeans map[string]float64 `json:"dimension_means"`
	Sessions       []SessionScore     `json:"sessions"`

	// GatesFailed lists any minimum-threshold gates that didn't pass.
	// Empty = all gates met (or no gates configured).
	GatesFailed []string `json:"gates_failed,omitempty"`
}

type SessionScore struct {
	Name       string           `json:"name"`
	Dimensions []DimensionScore `json:"dimensions"`
	Overall    float64          `json:"overall"`
}

type Summary struct {
	Title       string      `json:"title"`
	Summary     string      `json:"summary"`
	KeyActions  []string    `json:"key_actions"`
	Outcome     string      `json:"outcome"`
	AhaMoments  []AhaMoment `json:"aha_moments,omitempty"`
	TopicsFound []string    `json:"topics_found,omitempty"`
}

type Weights struct {
	Title      float64 `json:"title"`
	Summary    float64 `json:"summary"`
	KeyActions float64 `json:"key_actions"`
	Outcome    float64 `json:"outcome"`
	AhaMoments float64 `json:"aha_moments"`
}