fix(telegram): use UTF-16 code units for message length splitting (#8725)

Port from nearai/ironclaw#2304: Telegram's 4096 character limit is
measured in UTF-16 code units, not Unicode codepoints. Characters
outside the Basic Multilingual Plane (emoji like 😀, CJK Extension B,
musical symbols) are surrogate pairs: 1 Python char but 2 UTF-16 units.

Previously, truncate_message() used Python's len() which counts
codepoints. This could produce chunks exceeding Telegram's actual limit
when messages contain many astral-plane characters.

Changes:
- Add utf16_len() helper and _prefix_within_utf16_limit() for
  UTF-16-aware string measurement and truncation
- Add _custom_unit_to_cp() binary-search helper that maps a custom-unit
  budget to the largest safe codepoint slice position
- Update truncate_message() to accept optional len_fn parameter
- Telegram adapter now passes len_fn=utf16_len when splitting messages
- Fix fallback truncation in Telegram error handler to use
  _prefix_within_utf16_limit instead of codepoint slicing
- Update send_message_tool.py to use utf16_len for Telegram platform
- Add comprehensive tests: utf16_len, _prefix_within_utf16_limit,
  truncate_message with len_fn (emoji splitting, content preservation,
  code block handling)
- Update mock lambdas in reply_mode tests to accept **kw for len_fn

tools/send_message_tool.py

@@ -322,7 +322,7 @@ async def _send_to_platform(platform, pconfig, chat_id, message, thread_id=None,
     (preserves code-block boundaries, adds part indicators).
     """
     from gateway.config import Platform
-    from gateway.platforms.base import BasePlatformAdapter
+    from gateway.platforms.base import BasePlatformAdapter, utf16_len
     from gateway.platforms.telegram import TelegramAdapter
     from gateway.platforms.discord import DiscordAdapter
     from gateway.platforms.slack import SlackAdapter
@@ -354,9 +354,11 @@ async def _send_to_platform(platform, pconfig, chat_id, message, thread_id=None,
 
     # Smart-chunk the message to fit within platform limits.
     # For short messages or platforms without a known limit this is a no-op.
+    # Telegram measures length in UTF-16 code units, not Unicode codepoints.
     max_len = _MAX_LENGTHS.get(platform)
     if max_len:
-        chunks = BasePlatformAdapter.truncate_message(message, max_len)
+        _len_fn = utf16_len if platform == Platform.TELEGRAM else None
+        chunks = BasePlatformAdapter.truncate_message(message, max_len, len_fn=_len_fn)
     else:
         chunks = [message]