chore: review-cleanup fleet (audit + fix + hardening) (#5158)

This commit is contained in:
James Rich
2026-04-16 19:02:59 -05:00
committed by GitHub
parent 872c566ef1
commit 17e69c6d4c
68 changed files with 784 additions and 459 deletions

View File

@@ -44,13 +44,16 @@ jobs:
uses: actions/ai-inference@v2
id: quality
continue-on-error: true
env:
PR_TITLE: ${{ github.event.pull_request.title }}
PR_BODY: ${{ github.event.pull_request.body }}
with:
max-tokens: 20
prompt: |
Is this GitHub pull request spam, AI-generated slop, or low quality?
Title: ${{ github.event.pull_request.title }}
Body: ${{ github.event.pull_request.body }}
Title: ${{ env.PR_TITLE }}
Body: ${{ env.PR_BODY }}
Respond with exactly one of: spam, ai-generated, needs-review, ok
system-prompt: You detect spam and low-quality contributions. Be conservative - only flag obvious spam or AI slop.
@@ -94,6 +97,9 @@ jobs:
uses: actions/ai-inference@v2
id: classify
continue-on-error: true
env:
PR_TITLE: ${{ github.event.pull_request.title }}
PR_BODY: ${{ github.event.pull_request.body }}
with:
max-tokens: 30
prompt: |
@@ -105,8 +111,8 @@ jobs:
Use enhancement if it adds a new feature, improves performance, or adds new functionality.
Use refactor if it restructures code without changing behavior, cleans up code, or improves architecture.
Title: ${{ github.event.pull_request.title }}
Body: ${{ github.event.pull_request.body }}
Title: ${{ env.PR_TITLE }}
Body: ${{ env.PR_BODY }}
system-prompt: You classify pull requests into categories. Be conservative and pick the most appropriate single label.
model: openai/gpt-4o-mini