feat(triage): scope Greptile auto-closer to external contributors + dry-run by default

- close_low_quality_prs.py now filters by GitHub author_association via
  the REST API: PRs from OWNER / MEMBER / COLLABORATOR (and bot accounts)
  are skipped with a new 'skip-internal' summary bucket.
- close_low_quality_prs.yml now defaults workflow_dispatch close=false,
  and ignores 'close=true' unless the new repo variable
  AGENT_SHIN_ENABLED is set to 'true'. Scheduled runs are dry-run only
  until the team flips that switch.
- Updated unit tests: one new test asserting internal authors are
  skipped, and an autouse fixture treats unspecified test PRs as
  external so the rest of the suite still exercises the close path.

Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>

.github/scripts/close_low_quality_prs.py

@@ -50,6 +50,10 @@ SCORE_PATTERN = re.compile(
     re.IGNORECASE,
 )
 
+# `author_association` values for internal BerriAI contributors who should be
+# exempt from auto-triage.
+INTERNAL_AUTHOR_ASSOCIATIONS = frozenset({"OWNER", "MEMBER", "COLLABORATOR"})
+
 
 def gh(*args: str) -> str:
     """Run a `gh` CLI command and return stdout. Raises on non-zero exit."""
@@ -85,6 +89,38 @@ def fetch_open_prs(repo: str | None) -> list[dict]:
     return json.loads(raw)
 
 
+def fetch_pr_author_association(pr_number: int, repo: str | None) -> str:
+    """Return the GitHub `author_association` for a PR, uppercase.
+
+    Values: OWNER, MEMBER, COLLABORATOR, CONTRIBUTOR, FIRST_TIME_CONTRIBUTOR,
+    FIRST_TIMER, MANNEQUIN, NONE. Returns "" on lookup failure.
+    """
+    endpoint = (
+        f"repos/{repo}/pulls/{pr_number}"
+        if repo
+        else f"repos/{{owner}}/{{repo}}/pulls/{pr_number}"
+    )
+    try:
+        data = json.loads(gh("api", endpoint))
+    except subprocess.CalledProcessError:
+        return ""
+    return (data.get("author_association") or "").upper()
+
+
+def is_external_pr_author(pr: dict, repo: str | None) -> bool:
+    """Return True if the PR author is an external OSS contributor.
+
+    Internal = `OWNER` / `MEMBER` / `COLLABORATOR` association, or a bot login.
+    """
+    login = ((pr.get("author") or {}).get("login") or "").lower()
+    if login.endswith("[bot]") or login in {"dependabot", "github-actions"}:
+        return False
+    association = fetch_pr_author_association(pr["number"], repo)
+    if association in INTERNAL_AUTHOR_ASSOCIATIONS:
+        return False
+    return True
+
+
 def fetch_pr_comments(pr_number: int, repo: str | None) -> list[dict]:
     """Fetch issue-level comments on a PR (where Greptile posts its summary)."""
     endpoint = (
@@ -203,7 +239,7 @@ def evaluate_pr(
     """Decide whether to close `pr`.
 
     Returns (action, score_or_none, age_days_or_none) where action is one of:
-        "skip-draft", "skip-too-young", "skip-optout-label",
+        "skip-draft", "skip-too-young", "skip-optout-label", "skip-internal",
         "skip-no-greptile-score", "skip-score-ok", or "close".
     """
     if pr.get("isDraft"):
@@ -217,6 +253,11 @@ def evaluate_pr(
     if age_days < min_age_days:
         return ("skip-too-young", None, age_days)
 
+    # Only auto-close external OSS contributors. Internal contributors
+    # (BerriAI org members) handle their own backlog.
+    if not is_external_pr_author(pr, repo):
+        return ("skip-internal", None, age_days)
+
     comments = fetch_pr_comments(pr["number"], repo)
     extraction = extract_greptile_score(comments)
     if extraction is None:
@@ -298,6 +339,7 @@ def main() -> int:
         "skip-draft": 0,
         "skip-too-young": 0,
         "skip-optout-label": 0,
+        "skip-internal": 0,
         "skip-no-greptile-score": 0,
         "skip-score-ok": 0,
     }

.github/workflows/close_low_quality_prs.yml

@@ -20,7 +20,7 @@ on:
       close:
         description: "Actually close matching PRs (false = dry run)."
         required: false
-        default: "true"
+        default: "false"
         type: choice
         options:
           - "true"
@@ -62,7 +62,11 @@ jobs:
       - name: Run low-quality PR closer
         env:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          CLOSE_FLAG: ${{ github.event.inputs.close || 'true' }}
+          # Default to dry-run for scheduled triggers as well. The repo
+          # variable AGENT_SHIN_ENABLED must be "true" before scheduled runs
+          # actually close PRs, AND workflow_dispatch must opt-in via close=true.
+          CLOSE_FLAG: ${{ github.event.inputs.close || 'false' }}
+          AGENT_SHIN_ENABLED: ${{ vars.AGENT_SHIN_ENABLED }}
           MIN_AGE_DAYS: ${{ github.event.inputs.min_age_days || '7' }}
           MIN_SCORE: ${{ github.event.inputs.min_score || '4' }}
           LIMIT: ${{ github.event.inputs.limit || '25' }}
@@ -74,7 +78,12 @@ jobs:
             --min-score "${MIN_SCORE}"
             --limit "${LIMIT}"
           )
-          if [ "${CLOSE_FLAG}" = "true" ]; then
+          if [ "${AGENT_SHIN_ENABLED:-false}" != "true" ]; then
+            echo "::notice::AGENT_SHIN_ENABLED is not 'true' -> forcing dry-run regardless of close input."
+          elif [ "${CLOSE_FLAG}" = "true" ]; then
             ARGS+=(--close)
+            echo "::notice::Running in close-on-fail mode."
+          else
+            echo "::notice::AGENT_SHIN_ENABLED is true but close=false -> dry-run."
           fi
           python3 .github/scripts/close_low_quality_prs.py "${ARGS[@]}"

tests/test_litellm/test_github_close_low_quality_prs.py

@@ -139,6 +139,13 @@ class TestEvaluatePr:
             "url": f"https://example.com/pr/{number}",
         }
 
+    @pytest.fixture(autouse=True)
+    def _external_author(self, closer_module, monkeypatch):
+        """Treat every test PR as external unless overridden."""
+        monkeypatch.setattr(
+            closer_module, "is_external_pr_author", lambda pr, repo: True
+        )
+
     def test_should_skip_drafts(self, closer_module, _now, monkeypatch):
         monkeypatch.setattr(
             closer_module,
@@ -263,6 +270,27 @@ class TestEvaluatePr:
         assert action == "close"
         assert score == 1
 
+    def test_should_skip_internal_authors(self, closer_module, _now, monkeypatch):
+        # Override the fixture for this one test.
+        monkeypatch.setattr(
+            closer_module, "is_external_pr_author", lambda pr, repo: False
+        )
+        monkeypatch.setattr(
+            closer_module,
+            "fetch_pr_comments",
+            lambda *a, **kw: pytest.fail("should not fetch comments for internal"),
+        )
+        action, score, _ = closer_module.evaluate_pr(
+            self._make_pr(created_days_ago=14),
+            now=_now,
+            min_age_days=7,
+            min_score=4,
+            repo=None,
+            optout_labels=set(),
+        )
+        assert action == "skip-internal"
+        assert score is None
+
 
 class TestHasOptoutLabel:
     def test_should_match_label_case_insensitively(self, closer_module):