rodin/review-bot
2
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity

fix(ci): use GPT models available via HAI proxy
CI / test (pull_request) Successful in 13s
Details
CI / review (pull_request) Failing after 12s
Details

Browse Source 
HAI proxy serves Anthropic on a different path (/anthropic/v1) than
OpenAI (/openai/v1). Until review-bot supports multiple base URLs,
use GPT-5 and GPT-5-mini for both review slots.
This commit is contained in:
Rodin
2026-05-01 11:02:27 -07:00
parent d62e8ee4f0
commit 99916fe24a
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.gitea/workflows/ci.yml
+2 -2
View File
@@ -36,7 +36,7 @@ jobs:
REVIEWER_TOKEN: ${{ secrets.SONNET_REVIEW_TOKEN }} REVIEWER_TOKEN: ${{ secrets.SONNET_REVIEW_TOKEN }}
LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }} LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
LLM_API_KEY: ${{ secrets.LLM_API_KEY }} LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
LLM_MODEL: "anthropic--claude-4.6-sonnet" LLM_MODEL: "gpt-5"
CONVENTIONS_FILE: "CONVENTIONS.md" CONVENTIONS_FILE: "CONVENTIONS.md"
run: ./review-bot run: ./review-bot
- name: Run GPT Review - name: Run GPT Review
@@ -47,6 +47,6 @@ jobs:
REVIEWER_TOKEN: ${{ secrets.GPT_REVIEW_TOKEN }} REVIEWER_TOKEN: ${{ secrets.GPT_REVIEW_TOKEN }}
LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }} LLM_BASE_URL: ${{ secrets.LLM_BASE_URL }}
LLM_API_KEY: ${{ secrets.LLM_API_KEY }} LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
LLM_MODEL: "sap-ai-opus-latest-openai/gpt-5" LLM_MODEL: "gpt-5-mini"
CONVENTIONS_FILE: "CONVENTIONS.md" CONVENTIONS_FILE: "CONVENTIONS.md"
run: ./review-bot run: ./review-bot