descrybe/apps/api/internal/processing/sanitize.go

package processing

import (
	"regexp"
	"strings"
	"unicode"

	"github.com/descrybe/descrybe-v2/apps/api/internal/logredact"
)

const maxPromptFieldRunes = 4000

var controlOrInject = regexp.MustCompile(`(?i)(ignore\s+(all\s+)?(previous|prior|above)|disregard\s+(all\s+)?(previous|prior)|forget\s+(all\s+)?(previous|prior)|system\s*:|assistant\s*:|<\s*/?\s*script)`)

// SanitizeText strips control chars, truncates, and soft-neutralizes prompt-injection phrases.
func SanitizeText(s string) string {
	s = strings.TrimSpace(s)
	if s == "" {
		return ""
	}
	var b strings.Builder
	b.Grow(len(s))
	for _, r := range s {
		if r == '\n' || r == '\t' || unicode.IsPrint(r) {
			b.WriteRune(r)
		}
	}
	out := b.String()
	out = controlOrInject.ReplaceAllString(out, "[filtered]")
	return truncateRunes(out, maxPromptFieldRunes)
}

// SanitizeOutput keeps model text printable and bounded for storage/UI.
func SanitizeOutput(s string) string {
	s = strings.TrimSpace(s)
	if s == "" {
		return ""
	}
	var b strings.Builder
	b.Grow(len(s))
	for _, r := range s {
		if r == '\n' || r == '\t' || unicode.IsPrint(r) {
			b.WriteRune(r)
		}
	}
	return truncateRunes(b.String(), maxPromptFieldRunes)
}

func truncateRunes(s string, max int) string {
	if max <= 0 {
		return ""
	}
	n := 0
	for i := range s {
		if n == max {
			return s[:i]
		}
		n++
	}
	return s
}

// TruncateError returns a safe, short error string for DB storage / API clients.
// Secret-like substrings and logredact matches become an opaque message so
// job step_progress notes and v1 item errors cannot leak keys/JWTs/DSNs/emails.
// Common provider transport failures are rewritten to short user-facing text
// (no dial URLs / Go net strings) while preserving unrelated provider messages.
func TruncateError(err error) string {
	if err == nil {
		return ""
	}
	msg := strings.ReplaceAll(err.Error(), "\n", " ")
	lower := strings.ToLower(msg)
	for _, secretHint := range []string{
		"api-key", "api_key", "authorization", "bearer ",
		"sk-", "sk_live", "sk_test", "whsec_", "password", "passwd",
	} {
		if strings.Contains(lower, secretHint) {
			return "provider error (details redacted)"
		}
	}
	redacted := logredact.String(msg)
	if strings.Contains(redacted, logredact.Redacted) {
		return "provider error (details redacted)"
	}
	if friendly := classifyProviderError(redacted); friendly != "" {
		return friendly
	}
	// Drop retry-exhaustion wrapper when the inner message is already clear.
	cleaned := redacted
	for _, prefix := range []string{
		"openai retries exhausted: ",
		"openai embedding retries exhausted: ",
	} {
		if strings.HasPrefix(strings.ToLower(cleaned), prefix) {
			cleaned = strings.TrimSpace(cleaned[len(prefix):])
			break
		}
	}
	if friendly := classifyProviderError(cleaned); friendly != "" {
		return friendly
	}
	return truncateRunes(cleaned, 500)
}

// classifyProviderError maps common OpenAI-compatible transport/auth failures
// to short operator-facing text. Returns "" when msg should be kept as-is.
func classifyProviderError(msg string) string {
	lower := strings.ToLower(strings.TrimSpace(msg))
	if lower == "" {
		return ""
	}
	switch {
	case strings.Contains(lower, "connection refused"),
		strings.Contains(lower, "connectex"),
		strings.Contains(lower, "no connection could be made"),
		strings.Contains(lower, "actively refused"),
		strings.Contains(lower, "connection reset"),
		strings.Contains(lower, "no such host"),
		strings.Contains(lower, "dial tcp"):
		return "AI provider unreachable — check base URL and that the service is running"
	case strings.Contains(lower, "deadline exceeded"),
		strings.Contains(lower, "client.timeout"),
		strings.Contains(lower, "i/o timeout"),
		strings.Contains(lower, "timed out"):
		return "AI provider timed out — try again or check provider load"
	case lower == "unauthorized",
		strings.Contains(lower, "http 401"),
		strings.Contains(lower, "invalid api key"),
		strings.Contains(lower, "incorrect api key"),
		strings.Contains(lower, "invalid_api_key"):
		return "AI provider rejected the API key"
	case strings.Contains(lower, "http 403"),
		lower == "forbidden":
		return "AI provider forbidden the request"
	case strings.Contains(lower, "http 429"),
		strings.Contains(lower, "too many requests"),
		lower == "rate limited":
		return "AI provider rate limited — retry later"
	case lower == "rate limited or server error":
		return "AI provider temporarily unavailable (rate limited or server error)"
	}
	return ""
}

func stringFromMap(m map[string]any, keys ...string) string {
	if m == nil {
		return ""
	}
	for _, k := range keys {
		if v, ok := m[k]; ok {
			switch t := v.(type) {
			case string:
				if strings.TrimSpace(t) != "" {
					return SanitizeText(t)
				}
			}
		}
	}
	return ""
}