From 91ea3ae4b2e5214390f0865329648f9cffbbc8bc Mon Sep 17 00:00:00 2001
From: Teknium <127238744+teknium1@users.noreply.github.com>
Date: Sun, 3 May 2026 12:10:20 -0700
Subject: [PATCH] test(skills): add bytes-vs-str equivalence and on-disk hash
 parity tests

Follow-up on #9925 cherry-pick adding two additional tests:
- bytes content hashes identically to its str-decoded form
- mixed bytes+str bundle hash equals the on-disk content_hash from
  skills_guard (the production invariant used to detect drift)

Also map dodofun@126.com and 1615063567@qq.com in AUTHOR_MAP so the
CI contributor check passes for the cherry-picked commit.

Co-authored-by: LeonSGP43 <cine.dreamer.one@gmail.com>
Co-authored-by: zhao0112 <1615063567@qq.com>
---
 scripts/release.py             |  2 ++
 tests/tools/test_skills_hub.py | 47 ++++++++++++++++++++++++++++++++++
 2 files changed, 49 insertions(+)

diff --git a/scripts/release.py b/scripts/release.py
index 9bc2e8c447..d7fab88b03 100755
--- a/scripts/release.py
+++ b/scripts/release.py
@@ -633,6 +633,8 @@ AUTHOR_MAP = {
     "cirwel@The-CIRWEL-Group.local": "CIRWEL",
     "molvikar8@gmail.com": "molvikar",
     "nftpoetrist@gmail.com": "nftpoetrist",
+    "dodofun@126.com": "colorcross",
+    "1615063567@qq.com": "zhao0112",
     "leozeli@qq.com": "leozeli",
     "linlehao@cuhk.edu.cn": "LehaoLin",
     "liutong@isacas.ac.cn": "I3eg1nner",
diff --git a/tests/tools/test_skills_hub.py b/tests/tools/test_skills_hub.py
index 40143adc84..1969272411 100644
--- a/tests/tools/test_skills_hub.py
+++ b/tests/tools/test_skills_hub.py
@@ -917,6 +917,53 @@ class TestCheckForSkillUpdates:
 
         assert digest.startswith("sha256:")
 
+    def test_bundle_content_hash_bytes_matches_str_equivalent(self):
+        """Bytes content must hash identically to its str-decoded form."""
+        text_bundle = SkillBundle(
+            name="demo-skill",
+            files={
+                "SKILL.md": "same content",
+                "references/checklist.md": "- [ ] security\n",
+            },
+            source="github",
+            identifier="owner/repo/demo-skill",
+            trust_level="community",
+        )
+        bytes_bundle = SkillBundle(
+            name="demo-skill",
+            files={
+                "SKILL.md": b"same content",
+                "references/checklist.md": b"- [ ] security\n",
+            },
+            source="github",
+            identifier="owner/repo/demo-skill",
+            trust_level="community",
+        )
+
+        assert bundle_content_hash(bytes_bundle) == bundle_content_hash(text_bundle)
+
+    def test_bundle_content_hash_mixed_matches_on_disk(self, tmp_path):
+        """In-memory bundle hash must equal on-disk content_hash for mixed bytes+str."""
+        from tools.skills_guard import content_hash
+
+        bundle = SkillBundle(
+            name="demo-skill",
+            files={
+                "SKILL.md": b"# Demo Skill\n",
+                "references/checklist.md": "- [ ] security\n",
+            },
+            source="github",
+            identifier="owner/repo/demo-skill",
+            trust_level="community",
+        )
+        skill_dir = tmp_path / "demo-skill"
+        skill_dir.mkdir()
+        (skill_dir / "SKILL.md").write_bytes(b"# Demo Skill\n")
+        (skill_dir / "references").mkdir()
+        (skill_dir / "references" / "checklist.md").write_text("- [ ] security\n")
+
+        assert bundle_content_hash(bundle) == content_hash(skill_dir)
+
     def test_reports_update_when_remote_hash_differs(self):
         lock = MagicMock()
         lock.list_installed.return_value = [{