From 5b866056ab2c9ed0165c73a4f2e31af345c2f818 Mon Sep 17 00:00:00 2001 From: Diptesh Roy Date: Tue, 30 Jun 2026 16:49:14 +0530 Subject: [PATCH] feat: add per_page=100 to contributor breadth events API call The GitHub events API defaults to 30 results per page. Adding per_page=100 reduces the number of API calls needed by ~3x when fetching contributor events, making the contributor breadth model more efficient. The paginate_resource method follows GitHub's Link header for pagination, so the per_page param is safely preserved across all pages. Fixes #426 Signed-off-by: Diptesh Roy --- .../contributor_breadth_worker/contributor_breadth_worker.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/collectoss/tasks/data_analysis/contributor_breadth_worker/contributor_breadth_worker.py b/collectoss/tasks/data_analysis/contributor_breadth_worker/contributor_breadth_worker.py index 4c8aec067..5f5aff767 100644 --- a/collectoss/tasks/data_analysis/contributor_breadth_worker/contributor_breadth_worker.py +++ b/collectoss/tasks/data_analysis/contributor_breadth_worker/contributor_breadth_worker.py @@ -92,7 +92,7 @@ def contributor_breadth_model(self) -> None: logger.info(f"Processing cntrb {index} of {total}") index += 1 - repo_cntrb_url = f"https://api.github.com/users/{cntrb['gh_login']}/events" + repo_cntrb_url = f"https://api.github.com/users/{cntrb['gh_login']}/events?per_page=100" newest_event_in_db = datetime(1970, 1, 1) if cntrb["gh_login"] in cntrb_newest_events_map: