Thanks @pablogsal for the PR, and @ambv for merging it 🌮🎉.. I'm working now to backport this PR to: 3.9, 3.10.
🐍🍒⛏🤖

Sorry, @pablogsal and @ambv, I could not cleanly backport this to 3.10 due to a conflict.
Please backport using cherry_picker on command line.
cherry_picker fdcc46d9554094994f78bedf6dc9220e5d5ee668 3.10

Sorry @pablogsal and @ambv, I had trouble checking out the 3.9 backport branch.
Please backport using cherry_picker on command line.
cherry_picker fdcc46d9554094994f78bedf6dc9220e5d5ee668 3.9

GH-29661 is a backport of this pull request to the 3.10 branch.

@pablogsal, backporting this to 3.9 is more involved as the parser is much simpler in this case, see:

There is no assert that failed in the original bug report, there is no get_error_line function, there is no fp_interactive, there is no TestCase under which you put the new test in.

Let me know if you'd like me to still proceed with the backport. The current 3.11 crasher doesn't produce too terrible of a result under 3.9:

❯ python3.9 /tmp/crash.py
  File "/tmp/crash.py", line 3

    ^
SyntaxError: unexpected EOF while parsing

@pablogsal, backporting this to 3.9 is more involved as the parser is much simpler in this case, see:

cpython/Parser/pegen/pegen.c

Lines 424 to 434 in e8d41ee

	if (p->start_rule == Py_file_input) {
	error_line = PyErr_ProgramTextObject(p->tok->filename, (int) lineno);
	}
	if (!error_line) {
	Py_ssize_t size = p->tok->inp - p->tok->buf;
	error_line = PyUnicode_DecodeUTF8(p->tok->buf, size, "replace");
	if (!error_line) {
	goto error;
	}
	}

There is no assert that failed in the original bug report, there is no get_error_line function, there is no fp_interactive, there is no TestCase under which you put the new test in.

Let me know if you'd like me to still proceed with the backport. The current 3.11 crasher doesn't produce too terrible of a result under 3.9:

❯ python3.9 /tmp/crash.py
  File "/tmp/crash.py", line 3

    ^
SyntaxError: unexpected EOF while parsing

Thanks @ambv ! I will give it a go but as this doesn't crash in 3.9 I'm ok to just leave as is, as in this way we can also avoid potential unintended side effects in 3.9.