Gateway JSON file UnicodeDecodeError handling

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

• #39488 fix(gateway): tolerate non-UTF-8 status/pid files in gateway status reads

  merged to main

  files: gateway/status.py, tests/gateway/test_status.py

  Show the diff

  • gateway/status.py

    @@ -227,7 +227,10 @@ def _read_json_file(path: Path) -> Optional[dict[str, Any]]:
             return None
         try:
             raw = path.read_text(encoding="utf-8").strip()
    -    except OSError:
    +    except (OSError, UnicodeDecodeError):
    +        # OSError: file vanished or permission flipped between exists() and
    +        # read. UnicodeDecodeError: file holds non-UTF-8 / binary garbage
    +        # (a truncated or clobbered status file). Either way it's unusable.
             return None
         if not raw:
             return None
    @@ -249,8 +252,9 @@ def _read_pid_record(pid_path: Optional[Path] = None) -> Optional[dict]:
     
         try:
             raw = pid_path.read_text().strip()
    -    except OSError:
    -        # File was deleted between exists() and read_text(), or permission flipped.
    +    except (OSError, UnicodeDecodeError):
    +        # File was deleted between exists() and read_text(), permission
    +        # flipped, or it holds non-UTF-8 / binary garbage.
             return None
         if not raw:
             return None

  • tests/gateway/test_status.py

    @@ -1036,3 +1036,28 @@ def test_ps_fallback_used_when_proc_returns_empty(self, monkeypatch):
             )
             result = status._read_process_cmdline(12345)
             assert "hermes_cli/main.py" in result
    +
    +
    +class TestCorruptStatusFiles:
    +    """A status / pid file holding non-UTF-8 (binary) bytes must read as
    +    None, not crash the gateway status path with UnicodeDecodeError."""
    +
    +    def test_read_json_file_returns_none_on_binary_garbage(self, tmp_path):
    +        p = tmp_path / "runtime.json"
    +        p.write_bytes(b"\xff\xfe\x00\x80not utf-8\x81")
    +        assert status._read_json_file(p) is None
    +
    +    def test_read_json_file_still_parses_valid_json(self, tmp_path):
    +        p = tmp_path / "runtime.json"
    +        p.write_text(json.dumps({"pid": 7}), encoding="utf-8")
    +        assert status._read_json_file(p) == {"pid": 7}
    +
    +    def test_read_pid_record_returns_none_on_binary_garbage(self, tmp_path):
    +        p = tmp_path / "gateway.pid"
    +        p.write_bytes(b"\xff\xfe\x00\x80\x81")
    +        assert status._read_pid_record(p) is None
    +
    +    def test_read_pid_record_still_parses_bare_pid(self, tmp_path):
    +        p = tmp_path / "gateway.pid"
    +        p.write_text("4242", encoding="utf-8")
    +        assert status._read_pid_record(p) == {"pid": 4242}