From f90a627f9afd1f88b8f7daaa5da48e0060d261e3 Mon Sep 17 00:00:00 2001
From: Vicaversa <xxxkursxxx@gmail.com>
Date: Wed, 4 Mar 2026 11:32:57 +0300
Subject: [PATCH] fix(gateway): add missing UTF-8 encoding to file I/O
 preventing crashes on Windows

On Windows, Python's open() defaults to the system locale encoding
(e.g. cp1254 for Turkish, cp1252 for Western European) instead of
UTF-8. The gateway already uses ensure_ascii=False in json.dumps()
to preserve Unicode characters in chat messages, but the
corresponding open() calls lack encoding="utf-8". This mismatch
causes UnicodeEncodeError / UnicodeDecodeError when users send
non-ASCII messages (Turkish, Japanese, Arabic, emoji, etc.) through
Telegram, Discord, WhatsApp, or Slack on Windows.

The project already fixed this for .env files in hermes_cli/config.py
(line 624) but the gateway module was missed.

Files fixed:
- gateway/session.py: session index + JSONL transcript read/write (5 calls)
- gateway/channel_directory.py: channel directory read/write (3 calls)
- gateway/mirror.py: session index read + transcript append (2 calls)
---
 gateway/channel_directory.py |  6 +++---
 gateway/mirror.py            |  4 ++--
 gateway/session.py           | 10 +++++-----
 3 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/gateway/channel_directory.py b/gateway/channel_directory.py
index 622fed6bd..820743150 100644
--- a/gateway/channel_directory.py
+++ b/gateway/channel_directory.py
@@ -52,7 +52,7 @@ def build_channel_directory(adapters: Dict[Any, Any]) -> Dict[str, Any]:
 
     try:
         DIRECTORY_PATH.parent.mkdir(parents=True, exist_ok=True)
-        with open(DIRECTORY_PATH, "w") as f:
+        with open(DIRECTORY_PATH, "w", encoding="utf-8") as f:
             json.dump(directory, f, indent=2, ensure_ascii=False)
     except Exception as e:
         logger.warning("Channel directory: failed to write: %s", e)
@@ -115,7 +115,7 @@ def _build_from_sessions(platform_name: str) -> List[Dict[str, str]]:
 
     entries = []
     try:
-        with open(sessions_path) as f:
+        with open(sessions_path, encoding="utf-8") as f:
             data = json.load(f)
 
         seen_ids = set()
@@ -147,7 +147,7 @@ def load_directory() -> Dict[str, Any]:
     if not DIRECTORY_PATH.exists():
         return {"updated_at": None, "platforms": {}}
     try:
-        with open(DIRECTORY_PATH) as f:
+        with open(DIRECTORY_PATH, encoding="utf-8") as f:
             return json.load(f)
     except Exception:
         return {"updated_at": None, "platforms": {}}
diff --git a/gateway/mirror.py b/gateway/mirror.py
index 8c2f39983..527fc2c13 100644
--- a/gateway/mirror.py
+++ b/gateway/mirror.py
@@ -73,7 +73,7 @@ def _find_session_id(platform: str, chat_id: str) -> Optional[str]:
         return None
 
     try:
-        with open(_SESSIONS_INDEX) as f:
+        with open(_SESSIONS_INDEX, encoding="utf-8") as f:
             data = json.load(f)
     except Exception:
         return None
@@ -103,7 +103,7 @@ def _append_to_jsonl(session_id: str, message: dict) -> None:
     """Append a message to the JSONL transcript file."""
     transcript_path = _SESSIONS_DIR / f"{session_id}.jsonl"
     try:
-        with open(transcript_path, "a") as f:
+        with open(transcript_path, "a", encoding="utf-8") as f:
             f.write(json.dumps(message, ensure_ascii=False) + "\n")
     except Exception as e:
         logger.debug("Mirror JSONL write failed: %s", e)
diff --git a/gateway/session.py b/gateway/session.py
index b59196b81..e0b8db083 100644
--- a/gateway/session.py
+++ b/gateway/session.py
@@ -317,7 +317,7 @@ class SessionStore:
         
         if sessions_file.exists():
             try:
-                with open(sessions_file, "r") as f:
+                with open(sessions_file, "r", encoding="utf-8") as f:
                     data = json.load(f)
                     for key, entry_data in data.items():
                         self._entries[key] = SessionEntry.from_dict(entry_data)
@@ -332,7 +332,7 @@ class SessionStore:
         sessions_file = self.sessions_dir / "sessions.json"
         
         data = {key: entry.to_dict() for key, entry in self._entries.items()}
-        with open(sessions_file, "w") as f:
+        with open(sessions_file, "w", encoding="utf-8") as f:
             json.dump(data, f, indent=2)
     
     def _generate_session_key(self, source: SessionSource) -> str:
@@ -571,7 +571,7 @@ class SessionStore:
         
         # Also write legacy JSONL (keeps existing tooling working during transition)
         transcript_path = self.get_transcript_path(session_id)
-        with open(transcript_path, "a") as f:
+        with open(transcript_path, "a", encoding="utf-8") as f:
             f.write(json.dumps(message, ensure_ascii=False) + "\n")
     
     def rewrite_transcript(self, session_id: str, messages: List[Dict[str, Any]]) -> None:
@@ -598,7 +598,7 @@ class SessionStore:
         
         # JSONL: overwrite the file
         transcript_path = self.get_transcript_path(session_id)
-        with open(transcript_path, "w") as f:
+        with open(transcript_path, "w", encoding="utf-8") as f:
             for msg in messages:
                 f.write(json.dumps(msg, ensure_ascii=False) + "\n")
 
@@ -620,7 +620,7 @@ class SessionStore:
             return []
         
         messages = []
-        with open(transcript_path, "r") as f:
+        with open(transcript_path, "r", encoding="utf-8") as f:
             for line in f:
                 line = line.strip()
                 if line: