Technology·Stockholm ·
Aido 1.4.2 restores compatibility with the latest Claude models
A patch release makes the sampling temperature opt-in, so the AI code-review tool's Claude commands work again on Anthropic's newest models, which no longer accept that parameter.
Aido, the open-source multi-provider AI assistant for GitHub code review, has released version 1.4.2. The patch restores compatibility with Anthropic's latest Claude models.
Aido lets a team run review, summary, explanation, documentation, test, and triage commands on pull requests and issues, using Gemini, ChatGPT, or Claude, entirely inside their own GitHub Actions.
Working with the newest Claude models again
Anthropic's most recent Claude models no longer accept a sampling temperature and reject the parameter with an error. Aido previously set a fixed temperature on every Claude request, which caused all of its Claude commands to fail on those models. Version 1.4.2 makes the temperature opt-in, sent only when a team explicitly configures it, matching how Aido already handled the Gemini provider. Aido's Claude commands now work out of the box on the latest models, and older Claude models are unaffected.
Version 1.4.2 is available now on GitHub. Remote installs on the moving version-one tag receive the fix automatically; pinned installs upgrade by bumping the tag.
More press releases
Aido now automatically reviews the pull requests your AI coding agents open, and lands on the GitHub Marketplace
A run of releases makes the open-source, multi-provider tool run automatically on pull requests from agents like Copilot, Claude Code, and Cursor, adds a composite GitHub Action for running it as a step in any workflow, and publishes it to the GitHub Marketplace.
Aido 1.2.1 improves reliability by retrying transient AI provider errors
A patch release, surfaced by the tool's first external adopter, keeps code reviews running when an AI provider returns a temporary error instead of failing the whole command.
Aido 1.2.0 lets teams adopt its AI code review by pinning a single workflow file
The open-source, multi-provider AI reviewer for GitHub can now be installed with one thin workflow instead of copying about 30 files, and upgrades become a one-line tag bump.