feat(bedrock-harness): agentic Converse reviewer — repo tools, inline comments, severity gate #10
Workflow file for this run
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| --- | |
| # Self-review: run the reviewer on ai-workflows' own PRs. | |
| # | |
| # Pinned to the @v3.3.0-beta.1 orchestrator with agentic: true, so this DOGFOODS the | |
| # new agentic bedrock-harness executor (the model reaches for repo context via a shell, | |
| # posts inline comments, and gates on Critical/High) on this repo's own PRs — including | |
| # the PR that introduced it. Same cheap qwen model. Flip back to @v3 (and drop agentic) | |
| # once the harness is validated and released stable. | |
| # Requires the org-level BEDROCK_ROLE_ARN variable and that role's OIDC trust to permit | |
| # this repo. | |
| name: Self Review | |
| on: | |
| pull_request: | |
| types: [opened, synchronize, reopened, ready_for_review] | |
| jobs: | |
| claude-automatic-review: | |
| uses: dotCMS/ai-workflows/.github/workflows/claude-orchestrator.yml@v3.3.0-beta.5 | |
| with: | |
| model_id: qwen.qwen3-next-80b-a3b | |
| bedrock_role_arn: ${{ vars.BEDROCK_ROLE_ARN }} | |
| trigger_mode: automatic | |
| agentic: true | |
| prompt: ${{ vars.AI_REVIEWER_PROMPT }} | |
| use_sticky_comment: false | |
| enable_mention_detection: false | |
| secrets: inherit |