Skip to content

feat(ai-reviews): bump ai-workflows to v3.1.5 + switch auto-review to DeepSeek V3.2 #36182

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
wezell merged 2 commits into from
Jun 16, 2026
+16 −10
Merged

feat(ai-reviews): bump ai-workflows to v3.1.5 + switch auto-review to DeepSeek V3.2 #36182

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8c548f6
chore(ai-reviews): bump ai-workflows pin to v3.1.5
sfreudenthaler Jun 16, 2026
9642ca0
feat(ai-reviews): switch automatic PR review to DeepSeek V3.2
sfreudenthaler Jun 16, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .github/workflows/ai_claude-backend-reviewer.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,7 @@ jobs:
id-token: write
pull-requests: write
issues: write
uses: dotCMS/ai-workflows/.github/workflows/claude-orchestrator.yml@v3.1.4
uses: dotCMS/ai-workflows/.github/workflows/claude-orchestrator.yml@v3.1.5
with:
model_id: ${{ vars.BEDROCK_MODEL_ID }}
bedrock_role_arn: ${{ vars.BEDROCK_ROLE_ARN }}
Expand Down
24 changes: 15 additions & 9 deletions .github/workflows/ai_claude-orchestrator.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,7 +82,7 @@ jobs:
)
)
)
uses: dotCMS/ai-workflows/.github/workflows/claude-orchestrator.yml@v3.1.4
uses: dotCMS/ai-workflows/.github/workflows/claude-orchestrator.yml@v3.1.5
with:
model_id: ${{ vars.BEDROCK_MODEL_ID }}
bedrock_role_arn: ${{ vars.BEDROCK_ROLE_ARN }}
Expand Down Expand Up @@ -127,11 +127,16 @@ jobs:
} >> "$GITHUB_OUTPUT"

# Automatic PR reviews (no @claude mention)
# Uses GPT-5.5 via AWS Bedrock Mantle for model diversity — Claude writes code here,
# GPT reviews it so training/weighting biases from one model family don't carry into
# the review. Interactive @claude sessions remain on Anthropic Claude (job above).
# Prompt lives in .github/prompts/gpt-auto-review.md — edit it there, not here.
gpt-automatic-review:
# Uses DeepSeek V3.2 via AWS Bedrock (Converse API, generic-bedrock route) for model
# diversity — Claude writes code here, a non-Claude model reviews it so training/weighting
# biases from one model family don't carry into the review. Interactive @claude sessions
# remain on Anthropic Claude (job above). Prompt lives in .github/prompts/gpt-auto-review.md.
#
# Was openai.gpt-5.5 (Bedrock Mantle), but as of 2026-06-15 gpt-5.5 is failing on mantle
# in both regions ("Engine not found"; AWS-side — see ext-aws-tam thread). DeepSeek V3.2 is
# healthy on bedrock-runtime and keeps the reviews running. Switch back to a mantle model by
# setting model_id to an openai.* id once AWS restores it.
ai-automatic-review:
needs: [security-check, load-gpt-prompt]
# load-gpt-prompt enforces all the PR/no-mention conditions; if it was skipped
# or failed this job is skipped too.
Expand All @@ -140,12 +145,13 @@ jobs:
concurrency:
group: claude-automatic-${{ github.event.pull_request.number }}
cancel-in-progress: true
uses: dotCMS/ai-workflows/.github/workflows/claude-orchestrator.yml@v3.1.4
uses: dotCMS/ai-workflows/.github/workflows/claude-orchestrator.yml@v3.1.5
with:
model_id: openai.gpt-5.5
# deepseek.* is not anthropic/openai, so the orchestrator routes it to the
# bedrock-generic (Converse) executor. reasoning_effort has no effect on that path.
model_id: deepseek.v3.2
bedrock_role_arn: ${{ vars.BEDROCK_ROLE_ARN }}
trigger_mode: automatic
reasoning_effort: medium
prompt: ${{ needs.load-gpt-prompt.outputs.prompt }}
timeout_minutes: 20
runner: ubuntu-latest
Expand Down
Loading