fix(ci): use opencode-go plan model for AI review #5

Merged
Noel merged 14 commits from fix/ai_pr_review into main 2026-10-18 16:24:58 +00:00
Showing only changes of commit 8b6bcb6d70 - Show all commits
+6 -4
View File
@@ -204,14 +204,16 @@ jobs:
env:
OPENCODE_API_KEY: ${{ secrets.OPENCODE_API_KEY }}
run: |
# deepseek-v4-pro#max: flagship reasoning model at maximum thinking
# budget. Requires funds on the opencode account.
# Cheaper fallbacks: opencode/deepseek-v4.1-flash, or remove "#max".
# opencode-go/deepseek-v4-pro#max: flagship reasoning model at
# maximum thinking budget - included in the opencode-go $10 plan
# (variants: high, max). NOTE the provider prefix must be
# "opencode-go", NOT "opencode" (Zen is a different, pay-per-call
# provider and fails with 'Insufficient account funds').
# Output is redirected (not piped through tee): if opencode fails,
# the job must fail here so the error log is never posted as a
# "review" comment.
opencode run \
--model opencode/deepseek-v4-pro#max \
--model opencode-go/deepseek-v4-pro#max \
"You are a principal engineer performing a rigorous code review on a
pull request. You have tool access: read repo files for context when
the diff alone is ambiguous, but review ONLY code changed in this PR.