Version updated for https://github.com/yuri-val/ai-codereviewer to version v4. This action is used across all versions by 4 repositories. Action Type This is a Node action using Node version 20. Go to the GitHub Marketplace to find the latest changes. What’s Changed What’s new since v3 Default model is now gpt-5.6-luna (was gpt-4o). Any model can still be set via the OPENAI_API_MODEL input. Prompts overhauled for the GPT-5.6 family: strict JSON output contract (response_format: json_object), severity levels (critical/major), line-number-anchored comments with GitHub suggestion blocks. Hardened review pipeline: concurrent per-file reviews, full-file context fetching, retry with exponential backoff on rate limits/5xx, adaptive completion-token budgets for reasoning models, comment batching with 422/403 fallback. OpenAI SDK upgraded to 4.104, Octokit to 21.x, action runtime on node20. Usage - uses: yuri-val/ai-codereviewer@v4 with: GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }} OPENAI_API_MODEL: "gpt-5.6-luna" exclude: "**/*.lock,dist/**,**/*.json,**/*.md"

Version updated for https://github.com/yuri-val/auto-pr-action to version v1.4.0. This action is used across all versions by ? repositories. Action Type This is a Composite action. Go to the GitHub Marketplace to find the latest changes. What’s Changed Changes in this Release: feat: default to gpt-5.6-luna and tune prompt for GPT-5.6 Switch the default model from gpt-5.4-mini to gpt-5.6-luna Rewrite the system prompt per the GPT-5.6 prompting guide: lean instructions, real newlines (previously literal \n sequences), clear output contract (summary + emoji sections, no title/preamble)

Version updated for https://github.com/yuri-val/auto-pr-description-action to version v1.6.0. This action is used across all versions by 2 repositories. Action Type This is a Node action using Node version 20. Go to the GitHub Marketplace to find the latest changes. What’s Changed Changes in this Release: feat: default to gpt-5.6-luna, tune prompt and token budget Switch the default model from gpt-5.4-mini to gpt-5.6-luna Rewrite the prompt per the GPT-5.6 prompting guide: lean system prompt with a clear output contract, diff moved to the user message