Handle Unicode BOM in the session file

[kohsuke]

See how PowerShell creates a file with that when redirecting with '>'

See: PowerShell/PowerShell#8592

[Copilot]

Pull request overview

Adds support for reading session IDs from files that include a Unicode BOM (notably produced by PowerShell redirection), ensuring --session @file works across common Windows/PowerShell encodings.

Changes:

• Update SessionId to try decoding @file contents with utf-8-sig, then fall back to utf-16.
• Add unit tests covering session ID files encoded as UTF-8 (with/without BOM) and UTF-16 (with BOM).

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.

File	Description
smart_tests/utils/session.py	Adds BOM-aware decoding strategy when reading session IDs from @path files.
tests/utils/test_session.py	Introduces tests to validate session file decoding across UTF-8/UTF-16 variants.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

If the file isn’t valid UTF-8 or UTF-16 (e.g., latin-1, UTF-16 without BOM, or corrupted), the UTF-16 fallback can raise UnicodeError (often “UTF-16 stream does not start with BOM”), which currently bypasses the outer FileNotFoundError/IOError handling and will surface as an unhandled exception. Consider catching UnicodeError around the decoding attempts and re-raising as BadCmdLineException with a clear message (or iterating through candidate encodings and failing gracefully).

Suggested change

	except UnicodeDecodeError:
	with open(file_path, 'r', encoding='utf-16') as f:
	id = f.read().strip()
	except UnicodeError:
	try:
	with open(file_path, 'r', encoding='utf-16') as f:
	id = f.read().strip()
	except UnicodeError as e:
	raise BadCmdLineException(
	f"Session file '{file_path}' is not a valid UTF-8 or UTF-16 text file: {e}"
	)