audita/internal/core/config/config.go

package config

import (
	"fmt"
	"strings"
)

type WorkDirRetention string

const (
	WorkDirRetentionAuto   WorkDirRetention = "auto"
	WorkDirRetentionAlways WorkDirRetention = "always"
	WorkDirRetentionNever  WorkDirRetention = "never"
)

const (
	DefaultModulesCSV                                     = "glossary,homophones,glossary,spoken_word,grammar"
	DefaultOutputSchema                                   = "bare-segments"
	DefaultPrimaryModel                                   = "openrouter/google/gemma-4-31b-it"
	DefaultPrimaryBaseURL                                 = "https://openrouter.ai/api/v1"
	DefaultPrimaryLLMTimeoutSeconds                       = 600
	DefaultMaxRetries                                     = 3
	DefaultLLMConcurrency                                 = 1
	DefaultValidationMaxPromptTokens                      = 2048
	DefaultMaxSectionTokens                               = 8192
	DefaultMinSectionTokens                               = 2048
	DefaultConfidenceThreshold                            = 0.8
	DefaultNormalizeMaxSegmentGap                         = 4.0
	DefaultNormalizeEllipsisGap                           = 3.5
	DefaultNormalizeMaxSegmentDuration                    = 60.0
	DefaultNormalizeMaxSegmentTokens                      = 2048
	DefaultTranscriptDescriptionMaxChars                  = 500
	DefaultWorkDir                                        = "/tmp/audita"
	DefaultWorkDirRetention              WorkDirRetention = WorkDirRetentionAuto
)

type Config struct {
	Modules                   []string
	OutputSchema              string
	PrimaryLLM                LLMConfig
	ValidationLLM             ValidationLLMConfig
	TotalLLMConcurrency       int
	ProposalLLMConcurrency    int
	ValidationLLMConcurrency  *int
	ValidationMaxPromptTokens int
	MaxSectionTokens          int
	MinSectionTokens          int
	TargetSections            *int
	Thresholds                ConfidenceThresholds
	Normalization             NormalizationConfig
	TranscriptDescription     string
	WorkDir                   string
	WorkDirRetention          WorkDirRetention
}

type LLMConfig struct {
	APIKey         string
	Model          string
	BaseURL        string
	TimeoutSeconds int
	MaxRetries     int
	// Concurrency is retained as a backward-compatible alias for
	// TotalLLMConcurrency.
	Concurrency int
}

type ValidationLLMConfig struct {
	APIKey         string
	Model          string
	BaseURL        string
	TimeoutSeconds *int
	MaxRetries     *int
	// Concurrency is retained as a backward-compatible alias for
	// ValidationLLMConcurrency.
	Concurrency *int
}

type ConfidenceThresholds struct {
	Glossary   float64
	Grammar    float64
	Homophones float64
	SpokenWord float64
}

type NormalizationConfig struct {
	MaxSegmentGap      float64
	EllipsisGap        float64
	MaxSegmentDuration float64
	MaxSegmentTokens   int
}

func Default() Config {
	modules, _ := ParseModulesCSV(DefaultModulesCSV)

	return Config{
		Modules:      modules,
		OutputSchema: DefaultOutputSchema,
		PrimaryLLM: LLMConfig{
			Model:          DefaultPrimaryModel,
			BaseURL:        DefaultPrimaryBaseURL,
			TimeoutSeconds: DefaultPrimaryLLMTimeoutSeconds,
			MaxRetries:     DefaultMaxRetries,
			Concurrency:    DefaultLLMConcurrency,
		},
		ValidationLLM:             ValidationLLMConfig{},
		TotalLLMConcurrency:       DefaultLLMConcurrency,
		ProposalLLMConcurrency:    DefaultLLMConcurrency,
		ValidationLLMConcurrency:  nil,
		ValidationMaxPromptTokens: DefaultValidationMaxPromptTokens,
		MaxSectionTokens:          DefaultMaxSectionTokens,
		MinSectionTokens:          DefaultMinSectionTokens,
		TargetSections:            nil,
		Thresholds: ConfidenceThresholds{
			Glossary:   DefaultConfidenceThreshold,
			Grammar:    DefaultConfidenceThreshold,
			Homophones: DefaultConfidenceThreshold,
			SpokenWord: DefaultConfidenceThreshold,
		},
		Normalization: NormalizationConfig{
			MaxSegmentGap:      DefaultNormalizeMaxSegmentGap,
			EllipsisGap:        DefaultNormalizeEllipsisGap,
			MaxSegmentDuration: DefaultNormalizeMaxSegmentDuration,
			MaxSegmentTokens:   DefaultNormalizeMaxSegmentTokens,
		},
		WorkDir:          DefaultWorkDir,
		WorkDirRetention: DefaultWorkDirRetention,
	}
}

func ParseModulesCSV(raw string) ([]string, error) {
	parts := strings.Split(raw, ",")
	modules := make([]string, 0, len(parts))
	for _, part := range parts {
		trimmed := strings.TrimSpace(part)
		if trimmed == "" {
			return nil, fmt.Errorf("modules list contains an empty value")
		}
		modules = append(modules, trimmed)
	}
	if len(modules) == 0 {
		return nil, fmt.Errorf("modules list must not be empty")
	}
	return modules, nil
}

func (c Config) EffectiveValidationLLMConfig() LLMConfig {
	effective := c.PrimaryLLM

	if c.ValidationLLM.APIKey != "" {
		effective.APIKey = c.ValidationLLM.APIKey
	}
	if c.ValidationLLM.Model != "" {
		effective.Model = c.ValidationLLM.Model
	}
	if c.ValidationLLM.BaseURL != "" {
		effective.BaseURL = c.ValidationLLM.BaseURL
	}
	if c.ValidationLLM.TimeoutSeconds != nil {
		effective.TimeoutSeconds = *c.ValidationLLM.TimeoutSeconds
	}
	if c.ValidationLLM.MaxRetries != nil {
		effective.MaxRetries = *c.ValidationLLM.MaxRetries
	}
	effective.Concurrency = c.EffectiveValidationLLMConcurrency()

	return effective
}

func (c Config) EffectiveValidationLLMConcurrency() int {
	if c.ValidationLLMConcurrency != nil {
		return *c.ValidationLLMConcurrency
	}
	return c.TotalLLMConcurrency
}

func (c Config) EffectiveProposalLLMConcurrency() int {
	if c.ProposalLLMConcurrency > 0 {
		return c.ProposalLLMConcurrency
	}
	return c.TotalLLMConcurrency
}

func (c *Config) syncLegacyConcurrencyAliases() {
	if c == nil {
		return
	}
	c.PrimaryLLM.Concurrency = c.TotalLLMConcurrency
	c.ValidationLLM.Concurrency = intPtr(c.ValidationLLMConcurrency)
}

func intPtr(v *int) *int {
	if v == nil {
		return nil
	}
	x := *v
	return &x
}