From 075bdd5c3cd523012c7a4b63cb080a9ca9d938ba Mon Sep 17 00:00:00 2001
From: Xubin Ren <xubinrencs@gmail.com>
Date: Tue, 7 Apr 2026 05:56:52 +0000
Subject: [PATCH] refactor: move SafeFileHistory to module level + add
 regression tests

- Promote _SafeFileHistory to module-level SafeFileHistory for testability
- Add 5 regression tests: surrogates, normal text, emoji, mixed CJK, multi-surrogates

Made-with: Cursor
---
 nanobot/cli/commands.py             | 24 +++++++++-------
 tests/cli/test_safe_file_history.py | 44 +++++++++++++++++++++++++++++
 2 files changed, 58 insertions(+), 10 deletions(-)
 create mode 100644 tests/cli/test_safe_file_history.py

diff --git a/nanobot/cli/commands.py b/nanobot/cli/commands.py
index 2e18045f4..a1fb7c0e0 100644
--- a/nanobot/cli/commands.py
+++ b/nanobot/cli/commands.py
@@ -33,6 +33,19 @@ from rich.table import Table
 from rich.text import Text
 
 from nanobot import __logo__, __version__
+
+
+class SafeFileHistory(FileHistory):
+    """FileHistory subclass that sanitizes surrogate characters on write.
+
+    On Windows, special Unicode input (emoji, mixed-script) can produce
+    surrogate characters that crash prompt_toolkit's file write.
+    See issue #2846.
+    """
+
+    def store_string(self, string: str) -> None:
+        safe = string.encode("utf-8", errors="surrogateescape").decode("utf-8", errors="replace")
+        super().store_string(safe)
 from nanobot.cli.stream import StreamRenderer, ThinkingSpinner
 from nanobot.config.paths import get_workspace_path, is_default_workspace
 from nanobot.config.schema import Config
@@ -118,17 +131,8 @@ def _init_prompt_session() -> None:
     history_file = get_cli_history_path()
     history_file.parent.mkdir(parents=True, exist_ok=True)
 
-    # Wrap FileHistory to sanitize surrogate characters on write.
-    # Without this, special Unicode input (emoji, mixed-script) crashes
-    # prompt_toolkit's history file write on Windows with UnicodeEncodeError.
-    # See issue #2846.
-    class _SafeFileHistory(FileHistory):
-        def store_string(self, string: str) -> None:
-            safe = string.encode("utf-8", errors="surrogateescape").decode("utf-8", errors="replace")
-            super().store_string(safe)
-
     _PROMPT_SESSION = PromptSession(
-        history=_SafeFileHistory(str(history_file)),
+        history=SafeFileHistory(str(history_file)),
         enable_open_in_editor=False,
         multiline=False,  # Enter submits (single line mode)
     )
diff --git a/tests/cli/test_safe_file_history.py b/tests/cli/test_safe_file_history.py
new file mode 100644
index 000000000..78b5e2339
--- /dev/null
+++ b/tests/cli/test_safe_file_history.py
@@ -0,0 +1,44 @@
+"""Regression tests for SafeFileHistory (issue #2846).
+
+Surrogate characters in CLI input must not crash history file writes.
+"""
+
+from nanobot.cli.commands import SafeFileHistory
+
+
+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())
+        assert len(entries) == 1
+        assert "\udce9" not in entries[0]
+        assert "hello" in entries[0]
+        assert "world" in entries[0]
+
+    def test_normal_text_unchanged(self, tmp_path):
+        hist = SafeFileHistory(str(tmp_path / "history"))
+        hist.store_string("normal ascii text")
+        entries = list(hist.load_history_strings())
+        assert entries[0] == "normal ascii text"
+
+    def test_emoji_preserved(self, tmp_path):
+        hist = SafeFileHistory(str(tmp_path / "history"))
+        hist.store_string("hello 🐈 nanobot")
+        entries = list(hist.load_history_strings())
+        assert entries[0] == "hello 🐈 nanobot"
+
+    def test_mixed_unicode_preserved(self, tmp_path):
+        """CJK + emoji + latin should all pass through cleanly."""
+        hist = SafeFileHistory(str(tmp_path / "history"))
+        hist.store_string("你好 hello こんにちは 🎉")
+        entries = list(hist.load_history_strings())
+        assert entries[0] == "你好 hello こんにちは 🎉"
+
+    def test_multiple_surrogates(self, tmp_path):
+        hist = SafeFileHistory(str(tmp_path / "history"))
+        hist.store_string("\udce9\udcf1\udcff")
+        entries = list(hist.load_history_strings())
+        assert len(entries) == 1
+        assert "\udce9" not in entries[0]