From 21500b1aaa696d98ae30c9f73cd4917196556353 Mon Sep 17 00:00:00 2001
From: Justin Paul <justin@jpaul.me>
Date: Fri, 22 May 2026 13:38:23 -0400
Subject: [PATCH] fix: stop ignoring corpus/ so refresh workflow can commit it
 (#1)

---
 .gitignore | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/.gitignore b/.gitignore
index fbc0883..d592ac8 100644
--- a/.gitignore
+++ b/.gitignore
@@ -2,11 +2,17 @@
 venv/
 .venv/
 
-# Regenerable from corpus + CI
-corpus/
+# Indexes are regenerated from corpus by `python -m rag.index --rebuild`
+# (run in CI before docker build). Don't commit them.
 chroma/
 bm25/
 
+# corpus/ IS committed — the weekly refresh workflow writes scraped
+# pages here and `git add bundles.json corpus`s them. The image-only
+# workflow then rebuilds indexes from the committed corpus without
+# re-scraping. Earlier the .gitignore silently ate `git add corpus`
+# and refresh.yml's commit step would always report "no changes".
+
 # Python detritus
 __pycache__/
 *.py[cod]