From 5d41a03b40341995dc6f99ceb292fc87ee582412 Mon Sep 17 00:00:00 2001
From: Daniel Han <danielhanchen@gmail.com>
Date: Sun, 5 Jul 2026 14:09:48 +0000
Subject: [PATCH] docker: categorize AMD/domain notebooks and wire the feature
 validation into CI

unsloth_nb_view.parse_readme only reset the folder section on level-3
(###) headings. The notebooks README carries level-1 domain headers
(# AMD Notebooks, # Kaggle Notebooks) with their own nb/*.ipynb link
tables and no intervening ###, so those notebooks were mis-filed under
the previous stale section (all 148 AMD notebooks landed in Other
Notebooks on an --amd build). Reset on any heading level and strip a
leading emoji/symbol run so the domain notebooks get their own clean
folder.

Also run tests/validate_studio_features.py explicitly in the repo CPU
job. It is named validate_* (not test_*) so pytest never collected it,
which meant a regression in the notebook view, Colab compat, strip,
JupyterLab defaults or login branding failed CI only when run by hand.
---
 .github/workflows/studio-backend-ci.yml |  6 ++++++
 docker/unsloth_nb_view.py               | 11 ++++++++++-
 2 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/.github/workflows/studio-backend-ci.yml b/.github/workflows/studio-backend-ci.yml
index 3022127a2b..c0abd78d74 100644
--- a/.github/workflows/studio-backend-ci.yml
+++ b/.github/workflows/studio-backend-ci.yml
@@ -238,3 +238,9 @@ jobs:
               echo "::endgroup::"
           done
 
+      - name: Docker JupyterLab/notebook feature validation
+        # Named validate_studio_features.py (not test_*.py) so pytest's default
+        # discovery skips it; run it explicitly here so a regression in the
+        # notebook view, Colab compat, strip, JupyterLab defaults or login
+        # branding fails CI instead of only when someone runs it by hand.
+        run: python tests/validate_studio_features.py
diff --git a/docker/unsloth_nb_view.py b/docker/unsloth_nb_view.py
index 9c74081999..0d6bb5a4f3 100644
--- a/docker/unsloth_nb_view.py
+++ b/docker/unsloth_nb_view.py
@@ -51,6 +51,10 @@ def clean_section(title):
     # Drop a trailing run of '#', surrounding whitespace and any emoji/symbols
     # that sometimes lead a header; keep ASCII text, digits and a few separators.
     title = title.strip().strip("#").strip()
+    # Strip a leading run of emoji / symbols / punctuation that some domain
+    # headers lead with (e.g. "🐧 AMD Notebooks", "📒 Kaggle Notebooks") so the
+    # folder label is clean text.
+    title = re.sub(r"^[^\w]+", "", title)
     title = title.replace("-", " ").replace("/", " ")
     title = re.sub(r"\s+", " ", title).strip()
     return title
@@ -74,8 +78,13 @@ def parse_readme(readme_path):
     rows = []
     seen_pairs = set()  # (section, filename) already emitted
     section = None
+    # Reset on ANY markdown heading, not just `###`. The catalog uses `#`/`##`
+    # domain headers (e.g. "# AMD Notebooks", "# Kaggle Notebooks") that carry
+    # their own `nb/*.ipynb` link tables directly, with no intervening `###`.
+    # Matching only `###` left `section` stale, so those links were mis-filed
+    # under the previous section instead of getting their own folder.
     for line in text.splitlines():
-        m = re.match(r"^###\s+(.*)$", line)
+        m = re.match(r"^#{1,6}\s+(.*)$", line)
         if m:
             section = clean_section(m.group(1))
             continue