chore(ai-reviews): bump ai-workflows to v3.1.5 + switch auto-review to DeepSeek V3.2 (gpt-5.5 down on mantle)
Nobody has claimed this yet.
- Dominant language
- Java
- Stars
- 970
- Forks
- 486
- Avg merge
- 3d 33m
- Merged PRs (30d)
- 170
Description
Bump dotCMS/ai-workflows pin v3.1.4 → v3.1.5 in the AI review workflows.
v3.1.5 (ai-workflows#40) surfaces the actual failure reason when the mantle Responses API returns response.failed (it was discarded before — the sticky just said "failed before producing output"). Now the ❌ sticky + job log show response.error (e.g. server_error), notes it's typically an AWS/mantle-side issue, and retries once on transient failures.
Motivated by a real gpt-5.5 mantle outage (server_error on every request, both regions) that produced opaque failure stickies on core PRs.
ai_claude-orchestrator.yml: v3.1.4 → v3.1.5 (both jobs)ai_claude-backend-reviewer.yml: v3.1.4 → v3.1.5
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with ai_claude-orchestrator.yml and ai_claude-backend-reviewer.yml, then inspect the pinned dotCMS/ai-workflows versions in both orchestrator jobs. Update the pins from v3.1.4 to v3.1.5 and verify that all three specified workflow references use the new version.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- github-actions
- Domain
- ci-cd
- Issue type
- Refactor
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Active
- Clarity
- Clearly specified
- Newbie friendliness
- 86/100