fix(ci): switch PR review to liteLLM + add push trigger to tests #46

sarman · 2026-04-19T23:42:10Z

sarman commented

2026-04-19 23:42:10 +00:00

Summary

Switch PR review workflow from direct Ollama to liteLLM proxy at 172.0.0.29:11434
Use qwen2.5-72b (72B parameter VLLM model) for code review instead of qwen3-coder-next
Increase curl timeouts from 120s to 300s for larger model inference
Add push-to-master trigger on test.yml so merges run the full CI suite

Why CI did not trigger on PR #45

test.yml only had pull_request as trigger — no push event. When PR #45 was merged to master, there was no push trigger to run tests. This PR adds push: branches: [master] to fix that.

Test plan

Open this PR and verify the PR Review action triggers and calls liteLLM
Merge to master and verify test.yml runs on the push event
Verify the review comment is posted with qwen2.5-72b attribution

## Summary - Switch PR review workflow from direct Ollama to liteLLM proxy at 172.0.0.29:11434 - Use qwen2.5-72b (72B parameter VLLM model) for code review instead of qwen3-coder-next - Increase curl timeouts from 120s to 300s for larger model inference - Add push-to-master trigger on test.yml so merges run the full CI suite ## Why CI did not trigger on PR #45 test.yml only had `pull_request` as trigger — no `push` event. When PR #45 was merged to master, there was no push trigger to run tests. This PR adds `push: branches: [master]` to fix that. ## Test plan - [ ] Open this PR and verify the PR Review action triggers and calls liteLLM - [ ] Merge to master and verify test.yml runs on the push event - [ ] Verify the review comment is posted with qwen2.5-72b attribution

sarman added 1 commit 2026-04-19 23:42:11 +00:00

fix(ci): switch PR review from Ollama to liteLLM (qwen2.5-72b)

Test / rust-fmt-check (pull_request) Successful in 1m9s

Details

Test / frontend-typecheck (pull_request) Successful in 1m17s

Details

Test / frontend-tests (pull_request) Successful in 1m22s

Details

Test / rust-clippy (pull_request) Successful in 4m19s

Details

Test / rust-tests (pull_request) Successful in 5m46s

Details

PR Review Automation / review (pull_request) Failing after 1m15s

Details

d066e71eeb

Replace direct Ollama API calls with liteLLM proxy at
172.0.0.29:11434 using qwen2.5-72b (72B VLLM model). Increase
timeouts to 300s for larger model inference. Reuses existing
OLLAMA_API_KEY secret for liteLLM auth.

Also add push-to-master trigger on test.yml so merges to master
run the full CI suite (previously only pull_request events triggered).

sarman reviewed 2026-04-19 23:44:37 +00:00

sarman left a comment

Automated PR Review could not be completed - LLM analysis failed or produced no output.

sarman reviewed 2026-04-19 23:46:23 +00:00

sarman left a comment

Automated PR Review could not be completed - LLM analysis failed or produced no output.

sarman reviewed 2026-04-19 23:48:54 +00:00

sarman left a comment

Automated PR Review could not be completed - LLM analysis failed or produced no output.

sarman reviewed 2026-04-19 23:54:43 +00:00

sarman left a comment

Automated PR Review could not be completed - LLM analysis failed or produced no output.