ci: require an open issue for first-time contributor PRs (#7169)

* ci: require an open issue for first-time contributor PRs

Gate anyone who is not a returning contributor, and allow the PR only when a closing keyword points at an open issue in this repo.

* ci: accept any open issue mention for first-timer PRs

Drop the closing-keyword regex so #123, owner/repo#N, or an issue URL is enough when that issue is open.

* ci: ignore foreign owner/repo#N in first-timer issue gate

Bare #123 no longer matches the suffix of other/repo#123, so an open local issue cannot keep that PR open.

Author: Vidit-Ostwal

.github/CONTRIBUTING.md

@@ -103,8 +103,8 @@ chore(deps): bump pydantic to 2.11
 - Keep PRs focused — avoid bundling unrelated changes
 - PRs over 500 lines are labeled `size/XL` automatically
 - Title must follow the same conventional commit format
-- Link related issues where applicable (`Fixes #123`, `Closes #123`, or `Resolves #123`)
-- First-time contributors must open or pick an existing issue first, then include a closing keyword (`Fixes #N`, `Closes #N`, or `Resolves #N`) in the PR title or body. PRs without a linked issue are closed automatically.
+- Link related issues where applicable (`#123`, `Fixes #123`, or the issue URL)
+- First-time contributors must open or pick an existing **open** issue first, then mention it in the PR title or body (for example `#123`). PRs without a linked open issue are closed automatically.
 
 ## Testing
 

.github/pull_request_template.md

@@ -3,9 +3,8 @@
 Fixes #
 
 <!--
-First-time contributors must link an existing issue in this repo.
-Use a closing keyword: Fixes #123, Closes #123, or Resolves #123.
-PRs without a linked issue are closed automatically.
+First-time contributors must mention an existing open issue in this repo
+(for example #123). PRs without a linked open issue are closed automatically.
 -->
 
 ## Summary

.github/workflows/ftc-require-issue.yml

@@ -14,17 +14,21 @@ concurrency:
 
 jobs:
   require-issue:
+    # Allow-list returning contributors. FIRST_TIMER / FIRST_TIME_CONTRIBUTOR
+    # are often NONE on pull_request_target at opened time, which skipped the
+    # previous deny-list and left first-timer PRs open.
     if: >
       github.event.pull_request.user.type != 'Bot' &&
-      contains(fromJSON('["FIRST_TIME_CONTRIBUTOR","FIRST_TIMER"]'),
-               github.event.pull_request.author_association)
+      !contains(fromJSON('["MEMBER","OWNER","COLLABORATOR","CONTRIBUTOR"]'),
+                github.event.pull_request.author_association)
     runs-on: ubuntu-latest
     steps:
-      - name: Require a closing-keyword issue
+      - name: Require an open issue
         env:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           PR_NUMBER: ${{ github.event.pull_request.number }}
           REPO: ${{ github.repository }}
+          AUTHOR_ASSOCIATION: ${{ github.event.pull_request.author_association }}
         run: |
           python3 << 'PY'
           import json
@@ -36,13 +40,17 @@ jobs:
           repo = os.environ["REPO"]
           pr_number = os.environ["PR_NUMBER"]
           owner, name = repo.split("/", 1)
+          print(
+              "author_association=",
+              os.environ.get("AUTHOR_ASSOCIATION", ""),
+              sep="",
+          )
 
-          keyword = r"(?:close[sd]?|fix(?:es|ed)?|resolve[sd]?)"
           patterns = (
-              re.compile(rf"(?i)\b{keyword}\s+#(\d+)\b"),
-              re.compile(rf"(?i)\b{keyword}\s+{re.escape(owner)}/{re.escape(name)}#(\d+)\b"),
+              re.compile(r"(?<![\w./-])#(\d+)\b"),
+              re.compile(rf"{re.escape(owner)}/{re.escape(name)}#(\d+)\b"),
               re.compile(
-                  rf"(?i)\b{keyword}\s+https://github\.com/{re.escape(owner)}/{re.escape(name)}/issues/(\d+)\b"
+                  rf"https://github\.com/{re.escape(owner)}/{re.escape(name)}/issues/(\d+)\b"
               ),
           )
 
@@ -51,7 +59,7 @@ jobs:
                   subprocess.check_output(["gh", *args], text=True)
               )
 
-          def is_repo_issue(number: int) -> bool:
+          def is_open_repo_issue(number: int) -> bool:
               result = subprocess.run(
                   ["gh", "api", f"repos/{repo}/issues/{number}"],
                   capture_output=True,
@@ -64,7 +72,10 @@ jobs:
                   raise RuntimeError(
                       f"GitHub API error looking up #{number}: {stderr}"
                   )
-              return "pull_request" not in json.loads(result.stdout)
+              payload = json.loads(result.stdout)
+              if "pull_request" in payload:
+                  return False
+              return (payload.get("state") or "").lower() == "open"
 
           pr = gh_json(
               "pr", "view", pr_number, "--repo", repo, "--json", "title,body,state"
@@ -75,18 +86,18 @@ jobs:
               for pattern in patterns
               for match in pattern.findall(text)
           }
-          if any(is_repo_issue(number) for number in sorted(candidates)):
+          if any(is_open_repo_issue(number) for number in sorted(candidates)):
               sys.exit(0)
 
           if (pr.get("state") or "").upper() == "CLOSED":
               sys.exit(0)
 
           comment = f"""Thanks for the pull request.
           
-          First-time contributors need an associated issue before we can review a PR.
+          First-time contributors need an associated open issue before we can review a PR.
           
-          1. Open an issue with a [template](https://github.com/{repo}/issues/new/choose), or pick an existing one.
-          2. Open a new PR (or reopen this one) whose title or body includes a closing keyword, for example `Fixes #123`.
+          1. Open an issue with a [template](https://github.com/{repo}/issues/new/choose), or pick an existing open one.
+          2. Open a new PR (or reopen this one) whose title or body mentions that issue, for example `#123`.
           
           See the [contributing guide](https://github.com/{repo}/blob/main/.github/CONTRIBUTING.md).
           """

lib/crewai/tests/ci/test_ftc_require_issue.py

@@ -0,0 +1,101 @@
+"""Regression tests for the first-time contributor issue-gate workflow."""
+
+from __future__ import annotations
+
+import json
+import os
+from pathlib import Path
+from unittest import mock
+
+import pytest
+
+WORKFLOW_PATH = Path(__file__).resolve().parents[4] / (
+    ".github/workflows/ftc-require-issue.yml"
+)
+
+
+def _embedded_python() -> str:
+    text = WORKFLOW_PATH.read_text()
+    start = text.index("python3 << 'PY'\n") + len("python3 << 'PY'\n")
+    end = text.rindex("\n          PY\n")
+    indent = "          "
+    return "\n".join(
+        line[len(indent) :] if line.startswith(indent) else line
+        for line in text[start:end].splitlines()
+    )
+
+
+def _run_gate(
+    *,
+    title: str,
+    body: str,
+    issue_payloads: dict[int, dict],
+    expect_exit: int | None = 0,
+) -> list[list[str]]:
+    calls: list[list[str]] = []
+
+    def fake_check_output(args: list[str], **_kwargs: object) -> str:
+        if args[:2] == ["gh", "pr"] and "view" in args:
+            return json.dumps({"title": title, "body": body, "state": "OPEN"})
+        raise AssertionError(f"unexpected check_output: {args}")
+
+    def fake_run(args: list[str], **_kwargs: object) -> mock.Mock:
+        calls.append(list(args))
+        result = mock.Mock()
+        result.returncode = 0
+        result.stderr = ""
+        result.stdout = ""
+        if args[:2] == ["gh", "api"] and "/issues/" in args[2]:
+            number = int(args[2].rsplit("/", 1)[-1])
+            result.stdout = json.dumps(issue_payloads[number])
+        return result
+
+    env = {
+        "REPO": "crewAIInc/crewAI",
+        "PR_NUMBER": "99",
+        "AUTHOR_ASSOCIATION": "FIRST_TIME_CONTRIBUTOR",
+    }
+    with (
+        mock.patch.dict(os.environ, env, clear=False),
+        mock.patch("subprocess.check_output", side_effect=fake_check_output),
+        mock.patch("subprocess.run", side_effect=fake_run),
+    ):
+        compiled = compile(_embedded_python(), "<workflow>", "exec")
+        if expect_exit is None:
+            exec(compiled, {})  # noqa: S102
+        else:
+            with pytest.raises(SystemExit) as exited:
+                exec(compiled, {})  # noqa: S102
+            assert exited.value.code == expect_exit
+    return calls
+
+
+@pytest.mark.parametrize(
+    "body",
+    [
+        "Related to #123",
+        "crewAIInc/crewAI#123",
+        "https://github.com/crewAIInc/crewAI/issues/123",
+    ],
+)
+def test_open_issue_mention_blocks_close(body: str) -> None:
+    calls = _run_gate(
+        title="feat: example",
+        body=body,
+        issue_payloads={123: {"state": "open"}},
+    )
+
+    assert not any(call[:3] == ["gh", "pr", "close"] for call in calls)
+    assert any(call[:2] == ["gh", "api"] and call[2].endswith("/issues/123") for call in calls)
+
+
+def test_foreign_repo_reference_closes_pr() -> None:
+    calls = _run_gate(
+        title="feat: example",
+        body="other/repo#123",
+        issue_payloads={123: {"state": "open"}},
+        expect_exit=None,
+    )
+
+    assert any(call[:3] == ["gh", "pr", "close"] for call in calls)
+    assert not any(call[:2] == ["gh", "api"] for call in calls)