Merge main into pr-1482

nanobot/channels/telegram.py

@@ -4,6 +4,8 @@ from __future__ import annotations
 
 import asyncio
 import re
+import time
+import unicodedata
 
 from loguru import logger
 from telegram import BotCommand, ReplyParameters, Update
@@ -14,6 +16,50 @@ from nanobot.bus.events import OutboundMessage
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.config.schema import TelegramConfig
+from nanobot.utils.helpers import split_message
+
+TELEGRAM_MAX_MESSAGE_LEN = 4000  # Telegram message character limit
+
+
+def _strip_md(s: str) -> str:
+    """Strip markdown inline formatting from text."""
+    s = re.sub(r'\*\*(.+?)\*\*', r'\1', s)
+    s = re.sub(r'__(.+?)__', r'\1', s)
+    s = re.sub(r'~~(.+?)~~', r'\1', s)
+    s = re.sub(r'`([^`]+)`', r'\1', s)
+    return s.strip()
+
+
+def _render_table_box(table_lines: list[str]) -> str:
+    """Convert markdown pipe-table to compact aligned text for <pre> display."""
+
+    def dw(s: str) -> int:
+        return sum(2 if unicodedata.east_asian_width(c) in ('W', 'F') else 1 for c in s)
+
+    rows: list[list[str]] = []
+    has_sep = False
+    for line in table_lines:
+        cells = [_strip_md(c) for c in line.strip().strip('|').split('|')]
+        if all(re.match(r'^:?-+:?$', c) for c in cells if c):
+            has_sep = True
+            continue
+        rows.append(cells)
+    if not rows or not has_sep:
+        return '\n'.join(table_lines)
+
+    ncols = max(len(r) for r in rows)
+    for r in rows:
+        r.extend([''] * (ncols - len(r)))
+    widths = [max(dw(r[c]) for r in rows) for c in range(ncols)]
+
+    def dr(cells: list[str]) -> str:
+        return '  '.join(f'{c}{" " * (w - dw(c))}' for c, w in zip(cells, widths))
+
+    out = [dr(rows[0])]
+    out.append('  '.join('─' * w for w in widths))
+    for row in rows[1:]:
+        out.append(dr(row))
+    return '\n'.join(out)
 
 
 def _markdown_to_telegram_html(text: str) -> str:
@@ -31,6 +77,27 @@ def _markdown_to_telegram_html(text: str) -> str:
 
     text = re.sub(r'```[\w]*\n?([\s\S]*?)```', save_code_block, text)
 
+    # 1.5. Convert markdown tables to box-drawing (reuse code_block placeholders)
+    lines = text.split('\n')
+    rebuilt: list[str] = []
+    li = 0
+    while li < len(lines):
+        if re.match(r'^\s*\|.+\|', lines[li]):
+            tbl: list[str] = []
+            while li < len(lines) and re.match(r'^\s*\|.+\|', lines[li]):
+                tbl.append(lines[li])
+                li += 1
+            box = _render_table_box(tbl)
+            if box != '\n'.join(tbl):
+                code_blocks.append(box)
+                rebuilt.append(f"\x00CB{len(code_blocks) - 1}\x00")
+            else:
+                rebuilt.extend(tbl)
+        else:
+            rebuilt.append(lines[li])
+            li += 1
+    text = '\n'.join(rebuilt)
+
     # 2. Extract and protect inline code
     inline_codes: list[str] = []
     def save_inline_code(m: re.Match) -> str:
@@ -79,26 +146,6 @@ def _markdown_to_telegram_html(text: str) -> str:
     return text
 
 
-def _split_message(content: str, max_len: int = 4000) -> list[str]:
-    """Split content into chunks within max_len, preferring line breaks."""
-    if len(content) <= max_len:
-        return [content]
-    chunks: list[str] = []
-    while content:
-        if len(content) <= max_len:
-            chunks.append(content)
-            break
-        cut = content[:max_len]
-        pos = cut.rfind('\n')
-        if pos == -1:
-            pos = cut.rfind(' ')
-        if pos == -1:
-            pos = max_len
-        chunks.append(content[:pos])
-        content = content[pos:].lstrip()
-    return chunks
-
-
 class TelegramChannel(BaseChannel):
     """
     Telegram channel using long polling.
@@ -130,6 +177,7 @@ class TelegramChannel(BaseChannel):
         self._typing_tasks: dict[str, asyncio.Task] = {}  # chat_id -> typing loop task
         self._media_group_buffers: dict[str, dict] = {}
         self._media_group_tasks: dict[str, asyncio.Task] = {}
+        self._message_threads: dict[tuple[str, int], int] = {}
 
     async def start(self) -> None:
         """Start the Telegram bot with long polling."""
@@ -140,16 +188,21 @@ class TelegramChannel(BaseChannel):
         self._running = True
 
         # Build the application with larger connection pool to avoid pool-timeout on long runs
-        req = HTTPXRequest(connection_pool_size=16, pool_timeout=5.0, connect_timeout=30.0, read_timeout=30.0)
+        req = HTTPXRequest(
+            connection_pool_size=16,
+            pool_timeout=5.0,
+            connect_timeout=30.0,
+            read_timeout=30.0,
+            proxy=self.config.proxy if self.config.proxy else None,
+        )
         builder = Application.builder().token(self.config.token).request(req).get_updates_request(req)
-        if self.config.proxy:
-            builder = builder.proxy(self.config.proxy).get_updates_proxy(self.config.proxy)
         self._app = builder.build()
         self._app.add_error_handler(self._on_error)
 
         # Add command handlers
         self._app.add_handler(CommandHandler("start", self._on_start))
         self._app.add_handler(CommandHandler("new", self._forward_command))
+        self._app.add_handler(CommandHandler("stop", self._forward_command))
         self._app.add_handler(CommandHandler("help", self._on_help))
 
         # Add message handler for text, photos, voice, documents
@@ -225,21 +278,25 @@ class TelegramChannel(BaseChannel):
             logger.warning("Telegram bot not running")
             return
 
-        self._stop_typing(msg.chat_id)
+        # Only stop typing indicator for final responses
+        if not msg.metadata.get("_progress", False):
+            self._stop_typing(msg.chat_id)
 
         try:
             chat_id = int(msg.chat_id)
         except ValueError:
             logger.error("Invalid chat_id: {}", msg.chat_id)
             return
+        reply_to_message_id = msg.metadata.get("message_id")
         message_thread_id = msg.metadata.get("message_thread_id")
+        if message_thread_id is None and reply_to_message_id is not None:
+            message_thread_id = self._message_threads.get((msg.chat_id, reply_to_message_id))
         thread_kwargs = {}
         if message_thread_id is not None:
             thread_kwargs["message_thread_id"] = message_thread_id
 
         reply_params = None
         if self.config.reply_to_message:
-            reply_to_message_id = msg.metadata.get("message_id")
             if reply_to_message_id:
                 reply_params = ReplyParameters(
                     message_id=reply_to_message_id,
@@ -275,27 +332,65 @@ class TelegramChannel(BaseChannel):
 
         # Send text content
         if msg.content and msg.content != "[empty message]":
-            for chunk in _split_message(msg.content):
-                try:
-                    html = _markdown_to_telegram_html(chunk)
-                    await self._app.bot.send_message(
-                        chat_id=chat_id,
-                        text=html,
-                        parse_mode="HTML",
-                        reply_parameters=reply_params,
-                        **thread_kwargs,
-                    )
-                except Exception as e:
-                    logger.warning("HTML parse failed, falling back to plain text: {}", e)
-                    try:
-                        await self._app.bot.send_message(
-                            chat_id=chat_id,
-                            text=chunk,
-                            reply_parameters=reply_params,
-                            **thread_kwargs,
-                        )
-                    except Exception as e2:
-                        logger.error("Error sending Telegram message: {}", e2)
+            is_progress = msg.metadata.get("_progress", False)
+
+            for chunk in split_message(msg.content, TELEGRAM_MAX_MESSAGE_LEN):
+                # Final response: simulate streaming via draft, then persist
+                if not is_progress:
+                    await self._send_with_streaming(chat_id, chunk, reply_params, thread_kwargs)
+                else:
+                    await self._send_text(chat_id, chunk, reply_params, thread_kwargs)
+
+    async def _send_text(
+        self,
+        chat_id: int,
+        text: str,
+        reply_params=None,
+        thread_kwargs: dict | None = None,
+    ) -> None:
+        """Send a plain text message with HTML fallback."""
+        try:
+            html = _markdown_to_telegram_html(text)
+            await self._app.bot.send_message(
+                chat_id=chat_id, text=html, parse_mode="HTML",
+                reply_parameters=reply_params,
+                **(thread_kwargs or {}),
+            )
+        except Exception as e:
+            logger.warning("HTML parse failed, falling back to plain text: {}", e)
+            try:
+                await self._app.bot.send_message(
+                    chat_id=chat_id,
+                    text=text,
+                    reply_parameters=reply_params,
+                    **(thread_kwargs or {}),
+                )
+            except Exception as e2:
+                logger.error("Error sending Telegram message: {}", e2)
+
+    async def _send_with_streaming(
+        self,
+        chat_id: int,
+        text: str,
+        reply_params=None,
+        thread_kwargs: dict | None = None,
+    ) -> None:
+        """Simulate streaming via send_message_draft, then persist with send_message."""
+        draft_id = int(time.time() * 1000) % (2**31)
+        try:
+            step = max(len(text) // 8, 40)
+            for i in range(step, len(text), step):
+                await self._app.bot.send_message_draft(
+                    chat_id=chat_id, draft_id=draft_id, text=text[:i],
+                )
+                await asyncio.sleep(0.04)
+            await self._app.bot.send_message_draft(
+                chat_id=chat_id, draft_id=draft_id, text=text,
+            )
+            await asyncio.sleep(0.15)
+        except Exception:
+            pass
+        await self._send_text(chat_id, text, reply_params, thread_kwargs)
 
     async def _on_start(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
         """Handle /start command."""
@@ -347,12 +442,23 @@ class TelegramChannel(BaseChannel):
             "is_forum": bool(getattr(message.chat, "is_forum", False)),
         }
 
+    def _remember_thread_context(self, message) -> None:
+        """Cache topic thread id by chat/message id for follow-up replies."""
+        message_thread_id = getattr(message, "message_thread_id", None)
+        if message_thread_id is None:
+            return
+        key = (str(message.chat_id), message.message_id)
+        self._message_threads[key] = message_thread_id
+        if len(self._message_threads) > 1000:
+            self._message_threads.pop(next(iter(self._message_threads)))
+
     async def _forward_command(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
         """Forward slash commands to the bus for unified handling in AgentLoop."""
         if not update.message or not update.effective_user:
             return
         message = update.message
         user = update.effective_user
+        self._remember_thread_context(message)
         await self._handle_message(
             sender_id=self._sender_id(user),
             chat_id=str(message.chat_id),
@@ -370,6 +476,7 @@ class TelegramChannel(BaseChannel):
         user = update.effective_user
         chat_id = message.chat_id
         sender_id = self._sender_id(user)
+        self._remember_thread_context(message)
 
         # Store chat_id for replies
         self._chat_ids[sender_id] = chat_id