tapir/internal/config/uploads.go

package config

import (
	"fmt"
	"os"
	"strconv"
	"time"
)

// UploadConfig holds the settings for audio upload and private transcription
// (ADR-033). It is embedded in Config, so its fields read as c.UploadsEnabled etc.
type UploadConfig struct {
	// UploadsEnabled mounts the /uploads routes and starts the worker. Off by
	// default: the runtime image must contain ffmpeg and ffprobe first (ADR-033).
	UploadsEnabled bool
	// UploadMaxBytes caps one upload. UploadMaxDuration caps one recording; 90
	// minutes is the longest length MEASURED, not a ceiling that was found, so
	// raising it is a measurement, not an edit.
	UploadMaxBytes    int64
	UploadMaxDuration time.Duration
	// TranscribeModel is the primary gateway alias; TranscribeFallbackModel is the
	// fallback, tried on ANY primary failure. The fallback is a cloud endpoint
	// (berget): set it EMPTY to keep private audio on the homelab.
	TranscribeModel         string
	TranscribeFallbackModel string
	// TranscribeTimeout bounds one job (conversion + transcription); a 90 minute
	// recording took ~7.5 minutes on iguana.
	TranscribeTimeout time.Duration
	// UploadTmpDir is where uploads are spooled and converted. Audio is deleted
	// after transcription, so this holds at most the in-flight files.
	UploadTmpDir string
	FFmpegBin    string
	FFprobeBin   string
	// MaxUploadedTranscriptChars bounds the transcript sent to a chat model for an
	// UPLOADED recording. The 18,000-char default for captions is ~22 minutes of
	// speech; an hour of meeting is ~50,000 chars. A guess until measured against
	// the models chat offers.
	MaxUploadedTranscriptChars int
}

const (
	defaultUploadMaxMB             = 200
	defaultUploadMaxMinutes        = 90
	defaultTranscribeModel         = "iguana/kb-whisper"
	defaultTranscribeFallbackModel = "berget/kb-whisper"
	defaultTranscribeTimeout       = 30 * time.Minute
	defaultMaxUploadedChars        = 120000
)

func loadUploadConfig() (UploadConfig, error) {
	u := UploadConfig{
		TranscribeModel:         envOr("TAPIR_TRANSCRIBE_MODEL", defaultTranscribeModel),
		TranscribeFallbackModel: lookupOr("TAPIR_TRANSCRIBE_FALLBACK_MODEL", defaultTranscribeFallbackModel),
		UploadTmpDir:            envOr("TAPIR_UPLOAD_TMP_DIR", os.TempDir()),
		FFmpegBin:               envOr("TAPIR_FFMPEG_BIN", "ffmpeg"),
		FFprobeBin:              envOr("TAPIR_FFPROBE_BIN", "ffprobe"),
	}

	if v := os.Getenv("TAPIR_UPLOADS_ENABLED"); v != "" {
		on, err := strconv.ParseBool(v)
		if err != nil {
			return UploadConfig{}, fmt.Errorf("config: TAPIR_UPLOADS_ENABLED=%q: %w", v, err)
		}
		u.UploadsEnabled = on
	}

	mb, err := positiveInt("TAPIR_UPLOAD_MAX_MB", defaultUploadMaxMB)
	if err != nil {
		return UploadConfig{}, err
	}
	u.UploadMaxBytes = int64(mb) << 20

	mins, err := positiveInt("TAPIR_UPLOAD_MAX_MINUTES", defaultUploadMaxMinutes)
	if err != nil {
		return UploadConfig{}, err
	}
	u.UploadMaxDuration = time.Duration(mins) * time.Minute

	timeout, err := durationOr("TAPIR_TRANSCRIBE_TIMEOUT", defaultTranscribeTimeout)
	if err != nil {
		return UploadConfig{}, err
	}
	if timeout <= 0 {
		return UploadConfig{}, fmt.Errorf("config: TAPIR_TRANSCRIBE_TIMEOUT must be positive, got %v", timeout)
	}
	u.TranscribeTimeout = timeout

	chars, err := intOr("TAPIR_MAX_UPLOADED_TRANSCRIPT_CHARS", defaultMaxUploadedChars)
	if err != nil {
		return UploadConfig{}, err
	}
	if chars < 0 {
		chars = 0
	}
	u.MaxUploadedTranscriptChars = chars
	return u, nil
}

// positiveInt is intOr that refuses zero and negatives: a zero upload limit would
// reject every file, which is a misconfiguration to fail on, not to run with.
func positiveInt(key string, fallback int) (int, error) {
	n, err := intOr(key, fallback)
	if err != nil {
		return 0, err
	}
	if n <= 0 {
		return 0, fmt.Errorf("config: %s must be positive, got %d", key, n)
	}
	return n, nil
}