sift/internal/config/config.go

package config

import (
	"math"
	"os"
	"strconv"
	"strings"
	"time"

	"github.com/pelletier/go-toml/v2"
)

// File is the on-disk /etc/sift/config.toml.
type File struct {
	Listen       string   `toml:"listen"`
	UserAgent    string   `toml:"user_agent"`
	DenyPrefixes []string `toml:"deny_prefixes"`
	SelfIP       SelfIP   `toml:"self_ip"`
	Dixie        Dixie    `toml:"dixie"`
	Digest       Digest   `toml:"digest"`
	Context      Context  `toml:"context"`
	Search       Search   `toml:"search"`
	Batch        Batch    `toml:"batch"`
}

// Batch is the [batch] block. Batch is on by default: no block means the runner runs with its own
// defaults. disabled = true turns it off and the endpoints answer 503.
type Batch struct {
	Disabled      bool   `toml:"disabled"`
	TargetsPerJob int    `toml:"targets_per_job"`
	JobsPerCaller int    `toml:"jobs_per_caller"`
	JobsTotal     int    `toml:"jobs_total"`
	Workers       int    `toml:"workers"`
	TTL           string `toml:"ttl"`
	MaxBytes      string `toml:"max_bytes"`
}

type Dixie struct {
	Chat        string `toml:"chat"`
	Embed       string `toml:"embed"`
	EmbedModel  string `toml:"embed_model"`
	MaxInflight int    `toml:"max_inflight"`
	QueueDepth  int    `toml:"queue_depth"`
	QueueWait   string `toml:"queue_wait"`
}

type Digest struct {
	Model    string `toml:"model"`
	Thinking bool   `toml:"thinking"`
	Cache    string `toml:"cache"`
}

type Context struct {
	Honcho           string   `toml:"honcho"`
	Workspaces       []string `toml:"workspaces"`
	PermitRestricted []string `toml:"permit_restricted"`
}

// Search is the [search] block. Sources default off; bake-off picks defaults.
type Search struct {
	K        int          `toml:"k"`
	Timeout  string       `toml:"timeout"`
	Rerank   *bool        `toml:"rerank"`
	Digest   bool         `toml:"digest"`
	CacheTTL string       `toml:"cache_ttl"`
	SearxNG  SearchSource `toml:"searxng"`
	BraveLLM SearchSource `toml:"brave_llm"`
	Tavily   TavilySource `toml:"tavily"`
}

type SearchSource struct {
	Enabled  bool   `toml:"enabled"`
	URL      string `toml:"url"`
	NoRerank bool   `toml:"no_rerank"`
}

type TavilySource struct {
	Enabled        bool   `toml:"enabled"`
	URL            string `toml:"url"`
	DailyCreditCap int    `toml:"daily_credit_cap"`
	NoRerank       bool   `toml:"no_rerank"`
}

func (s Search) RerankOn() bool {
	if s.Rerank == nil {
		return true
	}
	return *s.Rerank
}

func (s Search) AnyEnabled() bool {
	return s.SearxNG.Enabled || s.BraveLLM.Enabled || s.Tavily.Enabled
}

// SelfIP is the [self_ip] block.
type SelfIP struct {
	Sources      []string `toml:"sources"`
	Interval     string   `toml:"interval"`
	KeepPrevious string   `toml:"keep_previous"`
	Path         string   `toml:"path"`
}

// Load reads path. A missing file returns a zero File and a nil error.
func Load(path string) (File, error) {
	var f File
	b, err := os.ReadFile(path)
	if err != nil {
		if os.IsNotExist(err) {
			return f, nil
		}
		return f, err
	}
	if err := toml.Unmarshal(b, &f); err != nil {
		return File{}, err
	}
	return f, nil
}

func ParseDuration(s string, def time.Duration) time.Duration {
	if s == "" {
		return def
	}
	d, err := time.ParseDuration(s)
	if err != nil {
		return def
	}
	return d
}

// ParseSize parses a positive byte count: a plain integer, or one with a binary suffix KiB, MiB or
// GiB. Anything else, zero or negative returns def.
func ParseSize(s string, def int64) int64 {
	s = strings.TrimSpace(s)
	if s == "" {
		return def
	}
	var mult int64
	switch {
	case strings.HasSuffix(s, "KiB"):
		mult, s = 1<<10, s[:len(s)-3]
	case strings.HasSuffix(s, "MiB"):
		mult, s = 1<<20, s[:len(s)-3]
	case strings.HasSuffix(s, "GiB"):
		mult, s = 1<<30, s[:len(s)-3]
	default:
		mult = 1
	}
	n, err := strconv.ParseInt(s, 10, 64)
	if err != nil || n <= 0 || n > math.MaxInt64/mult { // the last: n*mult would overflow
		return def
	}
	return n * mult
}