lingo.dev@0.138.8

FiloSottile/mkcertlingo.dev@0.138.8Sep 11, 2026by github-actions[bot]

Upgrading?

AI Summary

A patch release addressing npm audit advisories by updating `csv-parse` and AI SDK packages to latest major versions.

Key Highlights

  • Updated `csv-parse` to 7.0.2 to fix prototype replacement vulnerabilities.
  • Updated AI SDK packages (e.g., `ai` to 6.0.280) to fix uncontrolled resource consumption.
  • Changed system prompt handling from `messages` object to `system` option.
  • Basic translator now passes raw prompt text to the provider instead of JSON-wrapped text.

Breaking Changes

  • System prompt structure changed: moved from `{ role: 'system' }` in messages to the `system` option on `generateText`.
  • Basic translator prompt format changed: provider now receives raw text instead of a serialized JSON envelope.

Full Release Notes

### Patch Changes

- [#2208](https://github.com/lingodotdev/lingo.dev/pull/2208) [`8dfdf49`](https://github.com/lingodotdev/lingo.dev/commit/8dfdf49b75cab1887376979c1ffd7093b11f9a75) Thanks [@cherkanovart](https://github.com/cherkanovart)! - Clear two `npm audit` advisories that surfaced through transitive dependencies.

  `csv-parse` moves from 5.6.0 to 7.0.2, which patches GHSA-8cw4-87c7-c6xx (prototype replacement reachable through the `columns` option). None of the options renamed in csv-parse 6.0.0 were in use, so the CSV loaders are unchanged.

  The AI SDK packages move to the latest release of the major they were already on, so that `@ai-sdk/provider-utils` resolves at or above 4.0.33 and clears GHSA-866g-f22w-33x8 (uncontrolled resource consumption). The SDK packages pin `@ai-sdk/provider-utils` to an exact version, so bumping them is the only way to reach it: `ai` goes to 6.0.280 and `@ai-sdk/anthropic`, `@ai-sdk/google`, `@ai-sdk/groq`, `@ai-sdk/mistral` and `@ai-sdk/openai` follow on their 3.x line.

  The system prompt moves from a `{ role: "system" }` entry in `messages` to the `system` option on `generateText`. Since `ai` 6.0.170 the former makes the SDK print a prompt-injection warning on every BYOK run.

  The basic translator also stops wrapping its system prompt in a serialized `{ role, content }` envelope before handing it over, so the provider now receives the prompt text on its own rather than a line of JSON quoting it. This is the one change here that alters what reaches the model.

Related Repositories