From fbca99849e05839869801dc16dd4400ead2e77f9 Mon Sep 17 00:00:00 2001
From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Date: Sat, 11 Jul 2026 19:08:52 +0000
Subject: [PATCH] fix(ci): parse duplicate-issue scan output with gh --slurp

Fixes a JSONDecodeError ('Unterminated string') in the auto-close
duplicate-issue workflow. gh api --paginate emits pages as concatenated
JSON arrays with no separators, so the previous line-based parsing broke
whenever an issue body contained an unescaped line-separator character
(U+2028, form feed, etc.) that str.splitlines treats as a newline.

Use gh api --paginate --slurp to collect pages into a single JSON array
and parse it in one json.loads call, then flatten and drop PRs.
---
 .github/scripts/close_duplicate_issues.py     | 31 ++++++-------
 .../scripts/test_close_duplicate_issues.py    | 44 +++++++++++++++++++
 2 files changed, 58 insertions(+), 17 deletions(-)
 create mode 100644 .github/scripts/test_close_duplicate_issues.py

diff --git a/.github/scripts/close_duplicate_issues.py b/.github/scripts/close_duplicate_issues.py
index ec522af4f88..e0fcfed45dd 100755
--- a/.github/scripts/close_duplicate_issues.py
+++ b/.github/scripts/close_duplicate_issues.py
@@ -39,31 +39,28 @@ def gh(*args: str) -> str:
     return result.stdout
 
 
+def parse_slurped_issues(raw: str) -> list[dict]:
+    """Flatten the pages returned by `gh api --paginate --slurp` and drop PRs."""
+    pages = json.loads(raw)
+    return [
+        issue
+        for page in pages
+        for issue in page
+        if "pull_request" not in issue
+    ]
+
+
 def fetch_open_issues(repo: str | None) -> list[dict]:
-    """Fetch all open issues (excluding PRs) via gh api --paginate."""
+    """Fetch all open issues (excluding PRs) via gh api --paginate --slurp."""
     if repo:
         endpoint = (
             f"repos/{repo}/issues?state=open&per_page=100&sort=created&direction=asc"
         )
     else:
         endpoint = "repos/{owner}/{repo}/issues?state=open&per_page=100&sort=created&direction=asc"
-    cmd = ["api", "--paginate", endpoint]
 
-    raw = gh(*cmd)
-    # gh --paginate concatenates JSON arrays, so we may get multiple arrays
-    issues = []
-    for line in raw.strip().splitlines():
-        line = line.strip()
-        if not line:
-            continue
-        parsed = json.loads(line)
-        if isinstance(parsed, list):
-            issues.extend(parsed)
-        else:
-            issues.append(parsed)
-
-    # Filter out pull requests (they also appear in the issues endpoint)
-    return [i for i in issues if "pull_request" not in i]
+    raw = gh("api", "--paginate", "--slurp", endpoint)
+    return parse_slurped_issues(raw)
 
 
 def close_as_duplicate(
diff --git a/.github/scripts/test_close_duplicate_issues.py b/.github/scripts/test_close_duplicate_issues.py
new file mode 100644
index 00000000000..e8a733d7b0f
--- /dev/null
+++ b/.github/scripts/test_close_duplicate_issues.py
@@ -0,0 +1,44 @@
+import importlib.util
+import json
+from pathlib import Path
+
+_MODULE_PATH = Path(__file__).with_name("close_duplicate_issues.py")
+_spec = importlib.util.spec_from_file_location("close_duplicate_issues", _MODULE_PATH)
+assert _spec is not None and _spec.loader is not None
+close_duplicate_issues = importlib.util.module_from_spec(_spec)
+_spec.loader.exec_module(close_duplicate_issues)
+
+parse_slurped_issues = close_duplicate_issues.parse_slurped_issues
+
+
+def test_parse_handles_line_separator_chars_in_body() -> None:
+    payload = [
+        [
+            {"number": 1, "title": "first", "body": "before\u2028after\x0cend"},
+            {"number": 2, "title": "second", "body": "normal"},
+        ]
+    ]
+    raw = json.dumps(payload, ensure_ascii=False)
+    assert "\u2028" in raw
+    assert len(raw.splitlines()) > 1
+
+    issues = parse_slurped_issues(raw)
+
+    assert [i["number"] for i in issues] == [1, 2]
+    assert issues[0]["body"] == "before\u2028after\x0cend"
+
+
+def test_parse_flattens_pages_and_drops_pull_requests() -> None:
+    payload = [
+        [
+            {"number": 1, "title": "issue one"},
+            {"number": 2, "title": "a pr", "pull_request": {"url": "x"}},
+        ],
+        [
+            {"number": 3, "title": "issue three"},
+        ],
+    ]
+
+    issues = parse_slurped_issues(json.dumps(payload))
+
+    assert [i["number"] for i in issues] == [1, 3]