fix: utf16toStringLoose(Uint16Array) on BE hardware

[Copilot]

Code review identified a copy-paste bug in UTF-16 decoder:

UTF-16 decoder copy-paste error (utf16.js)

Big-endian loose decoder incorrectly referenced decoderFatalBE instead of decoderLooseBE. On big-endian systems, loose UTF-16 decoding would throw instead of replacing invalid sequences with U+FFFD.

-const decoderLoose16 = isLE ? decoderLooseLE : decoderFatalBE
+const decoderLoose16 = isLE ? decoderLooseLE : decoderLooseBE

This is a single-line fix that corrects the decoder reference to use the appropriate loose decoder for big-endian systems.

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Review the codebase and identify mistakes</issue_title>
<issue_description>Ignore tests/wpt and other vendored tests</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes Review the codebase and identify mistakes #43

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

[ChALkeR]

@copilot wif is not an issue, it's made that way for perf, sync is faster. Leave it intact.

[Copilot]

@copilot wif is not an issue, it's made that way for perf, sync is faster. Leave it intact.

Reverted in f052f20. The PR now only fixes the utf16.js decoder bug.