ci(ai): upgrade auto-PR reviewer to DeepSeek R1 with configurable model variable
Nobody has claimed this yet.
- Dominant language
- Java
- Stars
- 970
- Forks
- 486
- Avg merge
- 3d 33m
- Merged PRs (30d)
- 170
Description
Summary
The automatic PR code reviewer is hardcoded to deepseek.v3.2. This PR upgrades it to DeepSeek R1 (a reasoning model that produces higher-quality review findings) and makes the model configurable via a GitHub repo variable so future changes don't require a code change.
Changes
- Upgrades reviewer from
deepseek.v3.2→deepseek.r1-v1:0(R1 reasons through code logic before responding — better at catching subtle bugs) - Model now driven by
REVIEW_MODEL_IDrepo variable withdeepseek.r1-v1:0as the fallback default
Setup
After merging, set the variable in Settings → Secrets and variables → Actions → Variables:
| Variable | Value |
|---|---|
REVIEW_MODEL_ID |
deepseek.r1-v1:0 |
To switch models in the future, update the variable — no PR needed.
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 by locating the GitHub Actions configuration for the automatic PR reviewer and trace where its model is selected. Verify that REVIEW_MODEL_ID is read from repository variables with deepseek.r1-v1:0 as the fallback, then run the relevant CI validation. Done means the reviewer uses the configured model without requiring future code changes.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- github-actions
- Domain
- ai, ci-cd
- Issue type
- Feature
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 55/100