|
Some checks failed
Test / frontend-tests (pull_request) Successful in 1m41s
Test / frontend-typecheck (pull_request) Successful in 1m58s
PR Review Automation / review (pull_request) Successful in 10m22s
Test / rust-fmt-check (pull_request) Failing after 12m51s
Test / rust-clippy (pull_request) Successful in 14m40s
Test / rust-tests (pull_request) Successful in 16m29s
Replaces the single monolithic LLM call (which timed out on PRs >~150KB) with a batching strategy: - Changed files are grouped into batches capped at 2500 lines each, always respecting file boundaries (no file is split across batches) - Each batch is sent as an independent LLM call (max-time 600s) - Verdicts are aggregated: harshest verdict across all batches wins - Single-batch PRs produce identical output to the old workflow - Multi-batch PRs get a combined review with per-batch sections and an Overall Verdict line at the end - Partial failures are tolerated: if some batches succeed, the review is posted with a note about any failed batches - Cleanup removes /tmp/pr_batch_*.txt alongside existing temp files |
||
|---|---|---|
| .. | ||
| workflows | ||