fix(cli): sanitize surrogate code points before entering message bus

On Windows, prompt_toolkit produces lone surrogate code points (e.g.
🐈) for emoji input. These propagate through the message bus
and crash at json.dumps() / file write time because surrogates cannot
be encoded as UTF-8.

Extract _sanitize_surrogates() that round-trips through UTF-16 to
reconstruct paired surrogates into real characters (e.g. 🐈🐈), replacing unpaired surrogates with U+FFFD. Apply it at the CLI
input path and reuse in SafeFileHistory.
This commit is contained in:
chengyongru
2026-05-09 01:03:34 +08:00
committed by Xubin Ren
parent bbdf1db30d
commit 908f1246d8
2 changed files with 43 additions and 5 deletions
+30 -2
View File
@@ -3,12 +3,40 @@
Surrogate characters in CLI input must not crash history file writes.
"""
from nanobot.cli.commands import SafeFileHistory
from nanobot.cli.commands import SafeFileHistory, _sanitize_surrogates
class TestSanitizeSurrogates:
def test_paired_surrogates_reconstructed(self):
"""Windows console produces \\ud83d\\udc08 for U+1F408 — must be restored."""
result = _sanitize_surrogates("你为什么会用 🐈")
assert result == "你为什么会用 🐈"
def test_lone_surrogates_replaced(self):
result = _sanitize_surrogates("hello \udce9 world")
assert "\udce9" not in result
assert "hello" in result
assert "world" in result
def test_normal_text_unchanged(self):
assert _sanitize_surrogates("normal ascii text") == "normal ascii text"
def test_emoji_already_correct(self):
"""Properly encoded emoji should pass through unchanged."""
assert _sanitize_surrogates("hello 🐈 nanobot") == "hello 🐈 nanobot"
def test_mixed_unicode_preserved(self):
assert _sanitize_surrogates("你好 hello こんにちは 🎉") == "你好 hello こんにちは 🎉"
def test_multiple_lone_surrogates(self):
result = _sanitize_surrogates("\udce9\udcf1\udcff")
assert "\udce9" not in result
assert "\udcf1" not in result
assert "\udcff" not in result
class TestSafeFileHistory:
def test_surrogate_replaced(self, tmp_path):
"""Surrogate pairs are replaced with U+FFFD, not crash."""
hist = SafeFileHistory(str(tmp_path / "history"))
hist.store_string("hello \udce9 world")
entries = list(hist.load_history_strings())