Merge branch 'main' of github.com:NousResearch/hermes-agent into feat/ink-refactor

gateway/config.py

@@ -638,6 +638,18 @@ def load_gateway_config() -> GatewayConfig:
                     os.environ["TELEGRAM_IGNORED_THREADS"] = str(ignored_threads)
                 if "reactions" in telegram_cfg and not os.getenv("TELEGRAM_REACTIONS"):
                     os.environ["TELEGRAM_REACTIONS"] = str(telegram_cfg["reactions"]).lower()
+                if "proxy_url" in telegram_cfg and not os.getenv("TELEGRAM_PROXY"):
+                    os.environ["TELEGRAM_PROXY"] = str(telegram_cfg["proxy_url"]).strip()
+                if "disable_link_previews" in telegram_cfg:
+                    plat_data = platforms_data.setdefault(Platform.TELEGRAM.value, {})
+                    if not isinstance(plat_data, dict):
+                        plat_data = {}
+                        platforms_data[Platform.TELEGRAM.value] = plat_data
+                    extra = plat_data.setdefault("extra", {})
+                    if not isinstance(extra, dict):
+                        extra = {}
+                        plat_data["extra"] = extra
+                    extra["disable_link_previews"] = telegram_cfg["disable_link_previews"]
 
             whatsapp_cfg = yaml_cfg.get("whatsapp", {})
             if isinstance(whatsapp_cfg, dict):

gateway/platforms/api_server.py

@@ -902,7 +902,7 @@ class APIServerAdapter(BasePlatformAdapter):
                 return time.monotonic()
 
             # Stream content chunks as they arrive from the agent
-            loop = asyncio.get_event_loop()
+            loop = asyncio.get_running_loop()
             while True:
                 try:
                     delta = await loop.run_in_executor(None, lambda: stream_q.get(timeout=0.5))
@@ -1241,7 +1241,7 @@ class APIServerAdapter(BasePlatformAdapter):
                     await _emit_text_delta(it)
                 # Other types (non-string, non-tuple) are silently dropped.
 
-            loop = asyncio.get_event_loop()
+            loop = asyncio.get_running_loop()
             while True:
                 try:
                     item = await loop.run_in_executor(None, lambda: stream_q.get(timeout=0.5))
@@ -2004,7 +2004,7 @@ class APIServerAdapter(BasePlatformAdapter):
         callers (e.g. the SSE writer) to call ``agent.interrupt()`` from
         another thread to stop in-progress LLM calls.
         """
-        loop = asyncio.get_event_loop()
+        loop = asyncio.get_running_loop()
 
         def _run():
             agent = self._create_agent(

gateway/platforms/base.py

@@ -734,25 +734,56 @@ def merge_pending_message_event(
     pending_messages: Dict[str, MessageEvent],
     session_key: str,
     event: MessageEvent,
+    *,
+    merge_text: bool = False,
 ) -> None:
     """Store or merge a pending event for a session.
 
     Photo bursts/albums often arrive as multiple near-simultaneous PHOTO
     events. Merge those into the existing queued event so the next turn sees
-    the whole burst, while non-photo follow-ups still replace the pending
-    event normally.
+    the whole burst.
+
+    When ``merge_text`` is enabled, rapid follow-up TEXT events are appended
+    instead of replacing the pending turn. This is used for Telegram bursty
+    follow-ups so a multi-part user thought is not silently truncated to only
+    the last queued fragment.
     """
     existing = pending_messages.get(session_key)
-    if (
-        existing
-        and getattr(existing, "message_type", None) == MessageType.PHOTO
-        and event.message_type == MessageType.PHOTO
-    ):
-        existing.media_urls.extend(event.media_urls)
-        existing.media_types.extend(event.media_types)
-        if event.text:
-            existing.text = BasePlatformAdapter._merge_caption(existing.text, event.text)
-        return
+    if existing:
+        existing_is_photo = getattr(existing, "message_type", None) == MessageType.PHOTO
+        incoming_is_photo = event.message_type == MessageType.PHOTO
+        existing_has_media = bool(existing.media_urls)
+        incoming_has_media = bool(event.media_urls)
+
+        if existing_is_photo and incoming_is_photo:
+            existing.media_urls.extend(event.media_urls)
+            existing.media_types.extend(event.media_types)
+            if event.text:
+                existing.text = BasePlatformAdapter._merge_caption(existing.text, event.text)
+            return
+
+        if existing_has_media or incoming_has_media:
+            if incoming_has_media:
+                existing.media_urls.extend(event.media_urls)
+                existing.media_types.extend(event.media_types)
+            if event.text:
+                if existing.text:
+                    existing.text = BasePlatformAdapter._merge_caption(existing.text, event.text)
+                else:
+                    existing.text = event.text
+            if existing_is_photo or incoming_is_photo:
+                existing.message_type = MessageType.PHOTO
+            return
+
+        if (
+            merge_text
+            and getattr(existing, "message_type", None) == MessageType.TEXT
+            and event.message_type == MessageType.TEXT
+        ):
+            if event.text:
+                existing.text = f"{existing.text}\n{event.text}" if existing.text else event.text
+            return
+
     pending_messages[session_key] = event
 
 
@@ -839,6 +870,11 @@ class BasePlatformAdapter(ABC):
         # Gateway shutdown cancels these so an old gateway instance doesn't keep
         # working on a task after --replace or manual restarts.
         self._background_tasks: set[asyncio.Task] = set()
+        # One-shot callbacks to fire after the main response is delivered.
+        # Keyed by session_key.  GatewayRunner uses this to defer
+        # background-review notifications ("💾 Skill created") until the
+        # primary reply has been sent.
+        self._post_delivery_callbacks: Dict[str, Callable] = {}
         self._expected_cancelled_tasks: set[asyncio.Task] = set()
         self._busy_session_handler: Optional[Callable[[MessageEvent, str], Awaitable[bool]]] = None
         # Chats where auto-TTS on voice input is disabled (set by /voice off)
@@ -1905,6 +1941,14 @@ class BasePlatformAdapter(ABC):
             except Exception:
                 pass  # Last resort — don't let error reporting crash the handler
         finally:
+            # Fire any one-shot post-delivery callback registered for this
+            # session (e.g. deferred background-review notifications).
+            _post_cb = getattr(self, "_post_delivery_callbacks", {}).pop(session_key, None)
+            if callable(_post_cb):
+                try:
+                    _post_cb()
+                except Exception:
+                    pass
             # Stop typing indicator
             typing_task.cancel()
             try:

gateway/platforms/slack.py

@@ -366,6 +366,20 @@ class SlackAdapter(BasePlatformAdapter):
             # in an assistant-enabled context. Falls back to reactions.
             logger.debug("[Slack] assistant.threads.setStatus failed: %s", e)
 
+    def _dm_top_level_threads_as_sessions(self) -> bool:
+        """Whether top-level Slack DMs get per-message session threads.
+
+        Defaults to ``True`` so each visible DM reply thread is isolated as its
+        own Hermes session — matching the per-thread behavior channels already
+        have.  Set ``platforms.slack.extra.dm_top_level_threads_as_sessions``
+        to ``false`` in config.yaml to revert to the legacy behavior where all
+        top-level DMs share one continuous session.
+        """
+        raw = self.config.extra.get("dm_top_level_threads_as_sessions")
+        if raw is None:
+            return True  # default: each DM thread is its own session
+        return str(raw).strip().lower() in ("1", "true", "yes", "on")
+
     def _resolve_thread_ts(
         self,
         reply_to: Optional[str] = None,
@@ -996,10 +1010,14 @@ class SlackAdapter(BasePlatformAdapter):
         # Build thread_ts for session keying.
         # In channels: fall back to ts so each top-level @mention starts a
         #   new thread/session (the bot always replies in a thread).
-        # In DMs: only use the real thread_ts — top-level DMs should share
-        #   one continuous session, threaded DMs get their own session.
+        # In DMs: fall back to ts so each top-level DM reply thread gets
+        #   its own session key (matching channel behavior). Set
+        #   dm_top_level_threads_as_sessions: false in config to revert to
+        #   legacy single-session-per-DM-channel behavior.
         if is_dm:
-            thread_ts = event.get("thread_ts") or assistant_meta.get("thread_ts")  # None for top-level DMs
+            thread_ts = event.get("thread_ts") or assistant_meta.get("thread_ts")
+            if not thread_ts and self._dm_top_level_threads_as_sessions():
+                thread_ts = ts
         else:
             thread_ts = event.get("thread_ts") or ts  # ts fallback for channels
 

gateway/platforms/telegram.py

@@ -18,6 +18,10 @@ logger = logging.getLogger(__name__)
 
 try:
     from telegram import Update, Bot, Message, InlineKeyboardButton, InlineKeyboardMarkup
+    try:
+        from telegram import LinkPreviewOptions
+    except ImportError:
+        LinkPreviewOptions = None
     from telegram.ext import (
         Application,
         CommandHandler,
@@ -36,6 +40,7 @@ except ImportError:
     Message = Any
     InlineKeyboardButton = Any
     InlineKeyboardMarkup = Any
+    LinkPreviewOptions = None
     Application = Any
     CommandHandler = Any
     CallbackQueryHandler = Any
@@ -129,6 +134,7 @@ class TelegramAdapter(BasePlatformAdapter):
     # When a chunk is near this limit, a continuation is almost certain.
     _SPLIT_THRESHOLD = 4000
     MEDIA_GROUP_WAIT_SECONDS = 0.8
+    _GENERAL_TOPIC_THREAD_ID = "1"
     
     def __init__(self, config: PlatformConfig):
         super().__init__(config, Platform.TELEGRAM)
@@ -137,6 +143,7 @@ class TelegramAdapter(BasePlatformAdapter):
         self._webhook_mode: bool = False
         self._mention_patterns = self._compile_mention_patterns()
         self._reply_to_mode: str = getattr(config, 'reply_to_mode', 'first') or 'first'
+        self._disable_link_previews: bool = self._coerce_bool_extra("disable_link_previews", False)
         # Buffer rapid/album photo updates so Telegram image bursts are handled
         # as a single MessageEvent instead of self-interrupting multiple turns.
         self._media_batch_delay_seconds = float(os.getenv("HERMES_TELEGRAM_MEDIA_BATCH_DELAY_SECONDS", "0.8"))
@@ -172,6 +179,29 @@ class TelegramAdapter(BasePlatformAdapter):
         allowed_ids = {uid.strip() for uid in allowed_csv.split(",") if uid.strip()}
         return "*" in allowed_ids or user_id in allowed_ids
 
+    @classmethod
+    def _metadata_thread_id(cls, metadata: Optional[Dict[str, Any]]) -> Optional[str]:
+        if not metadata:
+            return None
+        thread_id = metadata.get("thread_id") or metadata.get("message_thread_id")
+        return str(thread_id) if thread_id is not None else None
+
+    @classmethod
+    def _message_thread_id_for_send(cls, thread_id: Optional[str]) -> Optional[int]:
+        if not thread_id or str(thread_id) == cls._GENERAL_TOPIC_THREAD_ID:
+            return None
+        return int(thread_id)
+
+    @classmethod
+    def _message_thread_id_for_typing(cls, thread_id: Optional[str]) -> Optional[int]:
+        if not thread_id:
+            return None
+        return int(thread_id)
+
+    @staticmethod
+    def _is_thread_not_found_error(error: Exception) -> bool:
+        return "thread not found" in str(error).lower()
+
     def _fallback_ips(self) -> list[str]:
         """Return validated fallback IPs from config (populated by _apply_env_overrides)."""
         configured = self.config.extra.get("fallback_ips", []) if getattr(self.config, "extra", None) else []
@@ -202,6 +232,26 @@ class TelegramAdapter(BasePlatformAdapter):
             pass
         return isinstance(error, OSError)
 
+    def _coerce_bool_extra(self, key: str, default: bool = False) -> bool:
+        value = self.config.extra.get(key) if getattr(self.config, "extra", None) else None
+        if value is None:
+            return default
+        if isinstance(value, str):
+            lowered = value.strip().lower()
+            if lowered in ("true", "1", "yes", "on"):
+                return True
+            if lowered in ("false", "0", "no", "off"):
+                return False
+            return default
+        return bool(value)
+
+    def _link_preview_kwargs(self) -> Dict[str, Any]:
+        if not getattr(self, "_disable_link_previews", False):
+            return {}
+        if LinkPreviewOptions is not None:
+            return {"link_preview_options": LinkPreviewOptions(is_disabled=True)}
+        return {"disable_web_page_preview": True}
+
     async def _handle_polling_network_error(self, error: Exception) -> None:
         """Reconnect polling after a transient network interruption.
 
@@ -549,7 +599,7 @@ class TelegramAdapter(BasePlatformAdapter):
                 "write_timeout": _env_float("HERMES_TELEGRAM_HTTP_WRITE_TIMEOUT", 20.0),
             }
 
-            proxy_url = resolve_proxy_url()
+            proxy_url = resolve_proxy_url("TELEGRAM_PROXY")
             disable_fallback = (os.getenv("HERMES_TELEGRAM_DISABLE_FALLBACK_IPS", "").strip().lower() in ("1", "true", "yes", "on"))
             fallback_ips = self._fallback_ips()
             if not fallback_ips:
@@ -615,14 +665,14 @@ class TelegramAdapter(BasePlatformAdapter):
                 from telegram.error import NetworkError, TimedOut
             except ImportError:
                 NetworkError = TimedOut = OSError  # type: ignore[misc,assignment]
-            _max_connect = 3
+            _max_connect = 8
             for _attempt in range(_max_connect):
                 try:
                     await self._app.initialize()
                     break
                 except (NetworkError, TimedOut, OSError) as init_err:
                     if _attempt < _max_connect - 1:
-                        wait = 2 ** _attempt
+                        wait = min(2 ** _attempt, 15)
                         logger.warning(
                             "[%s] Connect attempt %d/%d failed: %s — retrying in %ds",
                             self.name, _attempt + 1, _max_connect, init_err, wait,
@@ -823,7 +873,7 @@ class TelegramAdapter(BasePlatformAdapter):
                 ]
             
             message_ids = []
-            thread_id = metadata.get("thread_id") if metadata else None
+            thread_id = self._metadata_thread_id(metadata)
             
             try:
                 from telegram.error import NetworkError as _NetErr
@@ -843,7 +893,7 @@ class TelegramAdapter(BasePlatformAdapter):
             for i, chunk in enumerate(chunks):
                 should_thread = self._should_thread_reply(reply_to, i)
                 reply_to_id = int(reply_to) if should_thread else None
-                effective_thread_id = int(thread_id) if thread_id else None
+                effective_thread_id = self._message_thread_id_for_send(thread_id)
 
                 msg = None
                 for _send_attempt in range(3):
@@ -856,6 +906,7 @@ class TelegramAdapter(BasePlatformAdapter):
                                 parse_mode=ParseMode.MARKDOWN_V2,
                                 reply_to_message_id=reply_to_id,
                                 message_thread_id=effective_thread_id,
+                                **self._link_preview_kwargs(),
                             )
                         except Exception as md_error:
                             # Markdown parsing failed, try plain text
@@ -868,6 +919,7 @@ class TelegramAdapter(BasePlatformAdapter):
                                     parse_mode=None,
                                     reply_to_message_id=reply_to_id,
                                     message_thread_id=effective_thread_id,
+                                    **self._link_preview_kwargs(),
                                 )
                             else:
                                 raise
@@ -878,8 +930,7 @@ class TelegramAdapter(BasePlatformAdapter):
                         # (not transient network issues). Detect and handle
                         # specific cases instead of blindly retrying.
                         if _BadReq and isinstance(send_err, _BadReq):
-                            err_lower = str(send_err).lower()
-                            if "thread not found" in err_lower and effective_thread_id is not None:
+                            if self._is_thread_not_found_error(send_err) and effective_thread_id is not None:
                                 # Thread doesn't exist — retry without
                                 # message_thread_id so the message still
                                 # reaches the chat.
@@ -889,6 +940,7 @@ class TelegramAdapter(BasePlatformAdapter):
                                 )
                                 effective_thread_id = None
                                 continue
+                            err_lower = str(send_err).lower()
                             if "message to be replied not found" in err_lower and reply_to_id is not None:
                                 # Original message was deleted before we
                                 # could reply — clear reply target and retry
@@ -1055,6 +1107,7 @@ class TelegramAdapter(BasePlatformAdapter):
                 text=text,
                 parse_mode=ParseMode.MARKDOWN,
                 reply_markup=keyboard,
+                **self._link_preview_kwargs(),
             )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
@@ -1076,16 +1129,17 @@ class TelegramAdapter(BasePlatformAdapter):
 
         try:
             cmd_preview = command[:3800] + "..." if len(command) > 3800 else command
+            # Escape backticks that would break Markdown v1 inline code parsing
+            safe_cmd = cmd_preview.replace("`", "'")
+            safe_desc = description.replace("`", "'").replace("*", "∗")
             text = (
                 f"⚠️ *Command Approval Required*\n\n"
-                f"`{cmd_preview}`\n\n"
-                f"Reason: {description}"
+                f"`{safe_cmd}`\n\n"
+                f"Reason: {safe_desc}"
             )
 
             # Resolve thread context for thread replies
-            thread_id = None
-            if metadata:
-                thread_id = metadata.get("thread_id") or metadata.get("message_thread_id")
+            thread_id = self._metadata_thread_id(metadata)
 
             # We'll use the message_id as part of callback_data to look up session_key
             # Send a placeholder first, then update — or use a counter.
@@ -1111,9 +1165,11 @@ class TelegramAdapter(BasePlatformAdapter):
                 "text": text,
                 "parse_mode": ParseMode.MARKDOWN,
                 "reply_markup": keyboard,
+                **self._link_preview_kwargs(),
             }
-            if thread_id:
-                kwargs["message_thread_id"] = int(thread_id)
+            message_thread_id = self._message_thread_id_for_send(thread_id)
+            if message_thread_id is not None:
+                kwargs["message_thread_id"] = message_thread_id
 
             msg = await self._bot.send_message(**kwargs)
 
@@ -1181,6 +1237,7 @@ class TelegramAdapter(BasePlatformAdapter):
                 parse_mode=ParseMode.MARKDOWN,
                 reply_markup=keyboard,
                 message_thread_id=int(thread_id) if thread_id else None,
+                **self._link_preview_kwargs(),
             )
 
             # Store picker state keyed by chat_id
@@ -1545,23 +1602,23 @@ class TelegramAdapter(BasePlatformAdapter):
             with open(audio_path, "rb") as audio_file:
                 # .ogg files -> send as voice (round playable bubble)
                 if audio_path.endswith((".ogg", ".opus")):
-                    _voice_thread = metadata.get("thread_id") if metadata else None
+                    _voice_thread = self._metadata_thread_id(metadata)
                     msg = await self._bot.send_voice(
                         chat_id=int(chat_id),
                         voice=audio_file,
                         caption=caption[:1024] if caption else None,
                         reply_to_message_id=int(reply_to) if reply_to else None,
-                        message_thread_id=int(_voice_thread) if _voice_thread else None,
+                        message_thread_id=self._message_thread_id_for_send(_voice_thread),
                     )
                 else:
                     # .mp3 and others -> send as audio file
-                    _audio_thread = metadata.get("thread_id") if metadata else None
+                    _audio_thread = self._metadata_thread_id(metadata)
                     msg = await self._bot.send_audio(
                         chat_id=int(chat_id),
                         audio=audio_file,
                         caption=caption[:1024] if caption else None,
                         reply_to_message_id=int(reply_to) if reply_to else None,
-                        message_thread_id=int(_audio_thread) if _audio_thread else None,
+                        message_thread_id=self._message_thread_id_for_send(_audio_thread),
                     )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
@@ -1591,14 +1648,14 @@ class TelegramAdapter(BasePlatformAdapter):
             if not os.path.exists(image_path):
                 return SendResult(success=False, error=f"Image file not found: {image_path}")
 
-            _thread = metadata.get("thread_id") if metadata else None
+            _thread = self._metadata_thread_id(metadata)
             with open(image_path, "rb") as image_file:
                 msg = await self._bot.send_photo(
                     chat_id=int(chat_id),
                     photo=image_file,
                     caption=caption[:1024] if caption else None,
                     reply_to_message_id=int(reply_to) if reply_to else None,
-                    message_thread_id=int(_thread) if _thread else None,
+                    message_thread_id=self._message_thread_id_for_send(_thread),
                 )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
@@ -1629,7 +1686,7 @@ class TelegramAdapter(BasePlatformAdapter):
                 return SendResult(success=False, error=f"File not found: {file_path}")
 
             display_name = file_name or os.path.basename(file_path)
-            _thread = metadata.get("thread_id") if metadata else None
+            _thread = self._metadata_thread_id(metadata)
 
             with open(file_path, "rb") as f:
                 msg = await self._bot.send_document(
@@ -1638,7 +1695,7 @@ class TelegramAdapter(BasePlatformAdapter):
                     filename=display_name,
                     caption=caption[:1024] if caption else None,
                     reply_to_message_id=int(reply_to) if reply_to else None,
-                    message_thread_id=int(_thread) if _thread else None,
+                    message_thread_id=self._message_thread_id_for_send(_thread),
                 )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
@@ -1662,14 +1719,14 @@ class TelegramAdapter(BasePlatformAdapter):
             if not os.path.exists(video_path):
                 return SendResult(success=False, error=f"Video file not found: {video_path}")
 
-            _thread = metadata.get("thread_id") if metadata else None
+            _thread = self._metadata_thread_id(metadata)
             with open(video_path, "rb") as f:
                 msg = await self._bot.send_video(
                     chat_id=int(chat_id),
                     video=f,
                     caption=caption[:1024] if caption else None,
                     reply_to_message_id=int(reply_to) if reply_to else None,
-                    message_thread_id=int(_thread) if _thread else None,
+                    message_thread_id=self._message_thread_id_for_send(_thread),
                 )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
@@ -1699,13 +1756,13 @@ class TelegramAdapter(BasePlatformAdapter):
 
         try:
             # Telegram can send photos directly from URLs (up to ~5MB)
-            _photo_thread = metadata.get("thread_id") if metadata else None
+            _photo_thread = self._metadata_thread_id(metadata)
             msg = await self._bot.send_photo(
                 chat_id=int(chat_id),
                 photo=image_url,
                 caption=caption[:1024] if caption else None,  # Telegram caption limit
                 reply_to_message_id=int(reply_to) if reply_to else None,
-                message_thread_id=int(_photo_thread) if _photo_thread else None,
+                message_thread_id=self._message_thread_id_for_send(_photo_thread),
             )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
@@ -1728,6 +1785,7 @@ class TelegramAdapter(BasePlatformAdapter):
                     photo=image_data,
                     caption=caption[:1024] if caption else None,
                     reply_to_message_id=int(reply_to) if reply_to else None,
+                    message_thread_id=self._message_thread_id_for_send(_photo_thread),
                 )
                 return SendResult(success=True, message_id=str(msg.message_id))
             except Exception as e2:
@@ -1753,13 +1811,13 @@ class TelegramAdapter(BasePlatformAdapter):
             return SendResult(success=False, error="Not connected")
         
         try:
-            _anim_thread = metadata.get("thread_id") if metadata else None
+            _anim_thread = self._metadata_thread_id(metadata)
             msg = await self._bot.send_animation(
                 chat_id=int(chat_id),
                 animation=animation_url,
                 caption=caption[:1024] if caption else None,
                 reply_to_message_id=int(reply_to) if reply_to else None,
-                message_thread_id=int(_anim_thread) if _anim_thread else None,
+                message_thread_id=self._message_thread_id_for_send(_anim_thread),
             )
             return SendResult(success=True, message_id=str(msg.message_id))
         except Exception as e:
@@ -1776,12 +1834,23 @@ class TelegramAdapter(BasePlatformAdapter):
         """Send typing indicator."""
         if self._bot:
             try:
-                _typing_thread = metadata.get("thread_id") if metadata else None
-                await self._bot.send_chat_action(
-                    chat_id=int(chat_id),
-                    action="typing",
-                    message_thread_id=int(_typing_thread) if _typing_thread else None,
-                )
+                _typing_thread = self._metadata_thread_id(metadata)
+                message_thread_id = self._message_thread_id_for_typing(_typing_thread)
+                try:
+                    await self._bot.send_chat_action(
+                        chat_id=int(chat_id),
+                        action="typing",
+                        message_thread_id=message_thread_id,
+                    )
+                except Exception as e:
+                    if message_thread_id is not None and self._is_thread_not_found_error(e):
+                        await self._bot.send_chat_action(
+                            chat_id=int(chat_id),
+                            action="typing",
+                            message_thread_id=None,
+                        )
+                    else:
+                        raise
             except Exception as e:
                 # Typing failures are non-fatal; log at debug level only.
                 logger.debug(
@@ -2726,7 +2795,9 @@ class TelegramAdapter(BasePlatformAdapter):
 
         # Resolve DM topic name and skill binding
         thread_id_raw = message.message_thread_id
-        thread_id_str = str(thread_id_raw) if thread_id_raw else None
+        thread_id_str = str(thread_id_raw) if thread_id_raw is not None else None
+        if chat_type == "group" and thread_id_str is None and getattr(chat, "is_forum", False):
+            thread_id_str = self._GENERAL_TOPIC_THREAD_ID
         chat_topic = None
         topic_skill = None
 

gateway/platforms/telegram_network.py

@@ -46,7 +46,7 @@ _SEED_FALLBACK_IPS: list[str] = ["149.154.167.220"]
 def _resolve_proxy_url() -> str | None:
     # Delegate to shared implementation (env vars + macOS system proxy detection)
     from gateway.platforms.base import resolve_proxy_url
-    return resolve_proxy_url()
+    return resolve_proxy_url("TELEGRAM_PROXY")
 
 
 class TelegramFallbackTransport(httpx.AsyncBaseTransport):

gateway/platforms/wecom_callback.py

@@ -258,6 +258,20 @@ class WecomCallbackAdapter(BasePlatformAdapter):
                 )
                 event = self._build_event(app, decrypted)
                 if event is not None:
+                    # Deduplicate: WeCom retries callbacks on timeout,
+                    # producing duplicate inbound messages (#10305).
+                    if event.message_id:
+                        now = time.time()
+                        if event.message_id in self._seen_messages:
+                            if now - self._seen_messages[event.message_id] < MESSAGE_DEDUP_TTL_SECONDS:
+                                logger.debug("[WecomCallback] Duplicate MsgId %s, skipping", event.message_id)
+                                return web.Response(text="success", content_type="text/plain")
+                            del self._seen_messages[event.message_id]
+                        self._seen_messages[event.message_id] = now
+                        # Prune expired entries when cache grows large
+                        if len(self._seen_messages) > 2000:
+                            cutoff = now - MESSAGE_DEDUP_TTL_SECONDS
+                            self._seen_messages = {k: v for k, v in self._seen_messages.items() if v > cutoff}
                     # Record which app this user belongs to.
                     if event.source and event.source.user_id:
                         map_key = self._user_app_key(

gateway/run.py

@@ -24,6 +24,7 @@ import signal
 import tempfile
 import threading
 import time
+from contextvars import copy_context
 from pathlib import Path
 from datetime import datetime
 from typing import Dict, Optional, Any, List
@@ -834,7 +835,7 @@ class GatewayRunner:
         session_key: Optional[str] = None,
     ):
         """Run the sync memory flush in a thread pool so it won't block the event loop."""
-        loop = asyncio.get_event_loop()
+        loop = asyncio.get_running_loop()
         await loop.run_in_executor(
             None,
             self._flush_memories_for_session,
@@ -2925,6 +2926,32 @@ class GatewayRunner:
                     merge_pending_message_event(adapter._pending_messages, _quick_key, event)
                 return None
 
+            _telegram_followup_grace = float(
+                os.getenv("HERMES_TELEGRAM_FOLLOWUP_GRACE_SECONDS", "3.0")
+            )
+            _started_at = self._running_agents_ts.get(_quick_key, 0)
+            if (
+                source.platform == Platform.TELEGRAM
+                and event.message_type == MessageType.TEXT
+                and _telegram_followup_grace > 0
+                and _started_at
+                and (time.time() - _started_at) <= _telegram_followup_grace
+            ):
+                logger.debug(
+                    "Telegram follow-up arrived %.2fs after run start for %s — queueing without interrupt",
+                    time.time() - _started_at,
+                    _quick_key[:20],
+                )
+                adapter = self.adapters.get(source.platform)
+                if adapter:
+                    merge_pending_message_event(
+                        adapter._pending_messages,
+                        _quick_key,
+                        event,
+                        merge_text=True,
+                    )
+                return None
+
             running_agent = self._running_agents.get(_quick_key)
             if running_agent is _AGENT_PENDING_SENTINEL:
                 # Agent is being set up but not ready yet.
@@ -2938,7 +2965,12 @@ class GatewayRunner:
                 # agent starts.
                 adapter = self.adapters.get(source.platform)
                 if adapter:
-                    adapter._pending_messages[_quick_key] = event
+                    merge_pending_message_event(
+                        adapter._pending_messages,
+                        _quick_key,
+                        event,
+                        merge_text=True,
+                    )
                 return None
             if self._draining:
                 if self._queue_during_drain_enabled():
@@ -3746,12 +3778,13 @@ class GatewayRunner:
                                     model=_hyg_model,
                                     max_iterations=4,
                                     quiet_mode=True,
+                                    skip_memory=True,
                                     enabled_toolsets=["memory"],
                                     session_id=session_entry.session_id,
                                 )
                                 _hyg_agent._print_fn = lambda *a, **kw: None
 
-                                loop = asyncio.get_event_loop()
+                                loop = asyncio.get_running_loop()
                                 _compressed, _ = await loop.run_in_executor(
                                     None,
                                     lambda: _hyg_agent._compress_context(
@@ -4400,31 +4433,16 @@ class GatewayRunner:
     
     async def _handle_profile_command(self, event: MessageEvent) -> str:
         """Handle /profile — show active profile name and home directory."""
-        from hermes_constants import get_hermes_home, display_hermes_home
-        from pathlib import Path
+        from hermes_constants import display_hermes_home
+        from hermes_cli.profiles import get_active_profile_name
 
-        home = get_hermes_home()
         display = display_hermes_home()
+        profile_name = get_active_profile_name()
 
-        # Detect profile name from HERMES_HOME path
-        # Profile paths look like: ~/.hermes/profiles/<name>
-        profiles_parent = Path.home() / ".hermes" / "profiles"
-        try:
-            rel = home.relative_to(profiles_parent)
-            profile_name = str(rel).split("/")[0]
-        except ValueError:
-            profile_name = None
-
-        if profile_name:
-            lines = [
-                f"👤 **Profile:** `{profile_name}`",
-                f"📂 **Home:** `{display}`",
-            ]
-        else:
-            lines = [
-                "👤 **Profile:** default",
-                f"📂 **Home:** `{display}`",
-            ]
+        lines = [
+            f"👤 **Profile:** `{profile_name}`",
+            f"📂 **Home:** `{display}`",
+        ]
 
         return "\n".join(lines)
 
@@ -5087,6 +5105,7 @@ class GatewayRunner:
     async def _handle_personality_command(self, event: MessageEvent) -> str:
         """Handle /personality command - list or set a personality."""
         import yaml
+        from hermes_constants import display_hermes_home
 
         args = event.get_command_args().strip().lower()
         config_path = _hermes_home / 'config.yaml'
@@ -5104,7 +5123,7 @@ class GatewayRunner:
             personalities = {}
 
         if not personalities:
-            return "No personalities configured in `~/.hermes/config.yaml`"
+            return f"No personalities configured in `{display_hermes_home()}/config.yaml`"
 
         if not args:
             lines = ["🎭 **Available Personalities**\n"]
@@ -5825,8 +5844,7 @@ class GatewayRunner:
                     task_id=task_id,
                 )
 
-            loop = asyncio.get_event_loop()
-            result = await loop.run_in_executor(None, run_sync)
+            result = await self._run_in_executor_with_context(run_sync)
 
             response = result.get("final_response", "") if result else ""
             if not response and result and result.get("error"):
@@ -6008,8 +6026,7 @@ class GatewayRunner:
                     task_id=task_id,
                 )
 
-            loop = asyncio.get_event_loop()
-            result = await loop.run_in_executor(None, run_sync)
+            result = await self._run_in_executor_with_context(run_sync)
 
             response = (result.get("final_response") or "") if result else ""
             if not response and result and result.get("error"):
@@ -6332,6 +6349,7 @@ class GatewayRunner:
                 model=model,
                 max_iterations=4,
                 quiet_mode=True,
+                skip_memory=True,
                 enabled_toolsets=["memory"],
                 session_id=session_entry.session_id,
             )
@@ -6344,7 +6362,7 @@ class GatewayRunner:
             if compress_start >= compress_end:
                 return "Nothing to compress yet (the transcript is still all protected context)."
 
-            loop = asyncio.get_event_loop()
+            loop = asyncio.get_running_loop()
             compressed, _ = await loop.run_in_executor(
                 None,
                 lambda: tmp_agent._compress_context(msgs, "", approx_tokens=approx_tokens, focus_topic=focus_topic)
@@ -6697,6 +6715,11 @@ class GatewayRunner:
         import asyncio as _asyncio
 
         args = event.get_command_args().strip()
+
+        # Normalize Unicode dashes (Telegram/iOS auto-converts -- to em/en dash)
+        import re as _re
+        args = _re.sub(r'[\u2012\u2013\u2014\u2015](days|source)', r'--\1', args)
+
         days = 30
         source = None
 
@@ -6724,7 +6747,7 @@ class GatewayRunner:
             from hermes_state import SessionDB
             from agent.insights import InsightsEngine
 
-            loop = _asyncio.get_event_loop()
+            loop = _asyncio.get_running_loop()
 
             def _run_insights():
                 db = SessionDB()
@@ -6741,7 +6764,7 @@ class GatewayRunner:
 
     async def _handle_reload_mcp_command(self, event: MessageEvent) -> str:
         """Handle /reload-mcp command -- disconnect and reconnect all MCP servers."""
-        loop = asyncio.get_event_loop()
+        loop = asyncio.get_running_loop()
         try:
             from tools.mcp_tool import shutdown_mcp_servers, discover_mcp_tools, _servers, _lock
 
@@ -7422,7 +7445,13 @@ class GatewayRunner:
         """Restore session context variables to their pre-handler values."""
         from gateway.session_context import clear_session_vars
         clear_session_vars(tokens)
-    
+
+    async def _run_in_executor_with_context(self, func, *args):
+        """Run blocking work in the thread pool while preserving session contextvars."""
+        loop = asyncio.get_running_loop()
+        ctx = copy_context()
+        return await loop.run_in_executor(None, ctx.run, func, *args)
+
     async def _enrich_message_with_vision(
         self,
         user_text: str,
@@ -8456,7 +8485,7 @@ class GatewayRunner:
         stream_consumer_holder = [None]  # Mutable container for stream consumer
         
         # Bridge sync step_callback → async hooks.emit for agent:step events
-        _loop_for_step = asyncio.get_event_loop()
+        _loop_for_step = asyncio.get_running_loop()
         _hooks_ref = self.hooks
 
         def _step_callback_sync(iteration: int, prev_tools: list) -> None:
@@ -8694,6 +8723,7 @@ class GatewayRunner:
                     session_id=session_id,
                     platform=platform_key,
                     user_id=source.user_id,
+                    gateway_session_key=session_key,
                     session_db=self._session_db,
                     fallback_model=self._fallback_model,
                 )
@@ -8713,8 +8743,11 @@ class GatewayRunner:
             agent.service_tier = self._service_tier
             agent.request_overrides = turn_route.get("request_overrides")
 
-            # Background review delivery — send "💾 Memory updated" etc. to user
-            def _bg_review_send(message: str) -> None:
+            _bg_review_release = threading.Event()
+            _bg_review_pending: list[str] = []
+            _bg_review_pending_lock = threading.Lock()
+
+            def _deliver_bg_review_message(message: str) -> None:
                 if not _status_adapter:
                     return
                 try:
@@ -8729,7 +8762,32 @@ class GatewayRunner:
                 except Exception as _e:
                     logger.debug("background_review_callback error: %s", _e)
 
+            def _release_bg_review_messages() -> None:
+                _bg_review_release.set()
+                with _bg_review_pending_lock:
+                    pending = list(_bg_review_pending)
+                    _bg_review_pending.clear()
+                for queued in pending:
+                    _deliver_bg_review_message(queued)
+
+            # Background review delivery — send "💾 Memory updated" etc. to user
+            def _bg_review_send(message: str) -> None:
+                if not _status_adapter:
+                    return
+                if not _bg_review_release.is_set():
+                    with _bg_review_pending_lock:
+                        if not _bg_review_release.is_set():
+                            _bg_review_pending.append(message)
+                            return
+                _deliver_bg_review_message(message)
+
             agent.background_review_callback = _bg_review_send
+            # Register the release hook on the adapter so base.py's finally
+            # block can fire it after delivering the main response.
+            if _status_adapter and session_key:
+                _pdc = getattr(_status_adapter, "_post_delivery_callbacks", None)
+                if _pdc is not None:
+                    _pdc[session_key] = _release_bg_review_messages
 
             # Store agent reference for interrupt support
             agent_holder[0] = agent
@@ -8925,7 +8983,7 @@ class GatewayRunner:
             _resolved_model = getattr(_agent, "model", None) if _agent else None
 
             if not final_response:
-                error_msg = f"⚠️ {result['error']}" if result.get("error") else "(No response generated)"
+                error_msg = f"⚠️ {result['error']}" if result.get("error") else ""
                 return {
                     "final_response": error_msg,
                     "messages": result.get("messages", []),
@@ -9169,9 +9227,8 @@ class GatewayRunner:
             _agent_warning_raw = float(os.getenv("HERMES_AGENT_TIMEOUT_WARNING", 900))
             _agent_warning = _agent_warning_raw if _agent_warning_raw > 0 else None
             _warning_fired = False
-            loop = asyncio.get_event_loop()
             _executor_task = asyncio.ensure_future(
-                loop.run_in_executor(None, run_sync)
+                self._run_in_executor_with_context(run_sync)
             )
 
             _inactivity_timeout = False
@@ -9436,16 +9493,18 @@ class GatewayRunner:
                                 pass
                         except Exception as e:
                             logger.debug("Stream consumer wait before queued message failed: %s", e)
+                    _previewed = bool(result.get("response_previewed"))
                     _already_streamed = bool(
-                        _sc
-                        and (
-                            getattr(_sc, "final_response_sent", False)
-                            or getattr(_sc, "already_sent", False)
-                        )
+                        (_sc and getattr(_sc, "final_response_sent", False))
+                        or _previewed
                     )
                     first_response = result.get("final_response", "")
                     if first_response and not _already_streamed:
                         try:
+                            logger.info(
+                                "Queued follow-up for session %s: final stream delivery not confirmed; sending first response before continuing.",
+                                session_key[:20] if session_key else "?",
+                            )
                             await adapter.send(
                                 source.chat_id,
                                 first_response,
@@ -9453,6 +9512,22 @@ class GatewayRunner:
                             )
                         except Exception as e:
                             logger.warning("Failed to send first response before queued message: %s", e)
+                    elif first_response:
+                        logger.info(
+                            "Queued follow-up for session %s: skipping resend because final streamed delivery was confirmed.",
+                            session_key[:20] if session_key else "?",
+                        )
+                    # Release deferred bg-review notifications now that the
+                    # first response has been delivered.  Pop from the
+                    # adapter's callback dict (prevents double-fire in
+                    # base.py's finally block) and call it.
+                    if adapter and hasattr(adapter, "_post_delivery_callbacks"):
+                        _bg_cb = adapter._post_delivery_callbacks.pop(session_key, None)
+                        if callable(_bg_cb):
+                            try:
+                                _bg_cb()
+                            except Exception:
+                                pass
                 # else: interrupted — discard the interrupted response ("Operation
                 # interrupted." is just noise; the user already knows they sent a
                 # new message).
@@ -9472,6 +9547,19 @@ class GatewayRunner:
                         return result
                     next_message_id = getattr(pending_event, "message_id", None)
 
+                # Restart typing indicator so the user sees activity while
+                # the follow-up turn runs.  The outer _process_message_background
+                # typing task is still alive but may be stale.
+                _followup_adapter = self.adapters.get(source.platform)
+                if _followup_adapter:
+                    try:
+                        await _followup_adapter.send_typing(
+                            source.chat_id,
+                            metadata=_status_thread_metadata,
+                        )
+                    except Exception:
+                        pass
+
                 return await self._run_agent(
                     message=next_message,
                     context_prompt=context_prompt,
@@ -9532,13 +9620,22 @@ class GatewayRunner:
         # final answer.  Suppressing delivery here leaves the user staring
         # at silence.  (#10xxx — "agent stops after web search")
         _sc = stream_consumer_holder[0]
-        if _sc and isinstance(response, dict) and not response.get("failed"):
+        if isinstance(response, dict) and not response.get("failed"):
             _final = response.get("final_response") or ""
             _is_empty_sentinel = not _final or _final == "(empty)"
-            if not _is_empty_sentinel and (
-                getattr(_sc, "final_response_sent", False)
-                or getattr(_sc, "already_sent", False)
-            ):
+            _streamed = bool(
+                _sc and getattr(_sc, "final_response_sent", False)
+            )
+            # response_previewed means the interim_assistant_callback already
+            # sent the final text via the adapter (non-streaming path).
+            _previewed = bool(response.get("response_previewed"))
+            if not _is_empty_sentinel and (_streamed or _previewed):
+                logger.info(
+                    "Suppressing normal final send for session %s: final delivery already confirmed (streamed=%s previewed=%s).",
+                    session_key[:20] if session_key else "?",
+                    _streamed,
+                    _previewed,
+                )
                 response["already_sent"] = True
         
         return response
@@ -9752,7 +9849,7 @@ async def start_gateway(config: Optional[GatewayConfig] = None, replace: bool =
     def restart_signal_handler():
         runner.request_restart(detached=False, via_service=True)
     
-    loop = asyncio.get_event_loop()
+    loop = asyncio.get_running_loop()
     if threading.current_thread() is threading.main_thread():
         for sig in (signal.SIGINT, signal.SIGTERM):
             try:

gateway/session.py

@@ -301,6 +301,8 @@ def build_session_context_prompt(
     lines.append("")
     lines.append("**Delivery options for scheduled tasks:**")
     
+    from hermes_constants import display_hermes_home
+
     # Origin delivery
     if context.source.platform == Platform.LOCAL:
         lines.append("- `\"origin\"` → Local output (saved to files)")
@@ -309,9 +311,11 @@ def build_session_context_prompt(
             _hash_chat_id(context.source.chat_id) if redact_pii else context.source.chat_id
         )
         lines.append(f"- `\"origin\"` → Back to this chat ({_origin_label})")
-    
+
     # Local always available
-    lines.append("- `\"local\"` → Save to local files only (~/.hermes/cron/output/)")
+    lines.append(
+        f"- `\"local\"` → Save to local files only ({display_hermes_home()}/cron/output/)"
+    )
     
     # Platform home channels
     for platform, home in context.home_channels.items():

gateway/stream_consumer.py

@@ -403,18 +403,20 @@ class GatewayStreamConsumer:
 
         except asyncio.CancelledError:
             # Best-effort final edit on cancellation
+            _best_effort_ok = False
             if self._accumulated and self._message_id:
                 try:
-                    await self._send_or_edit(self._accumulated)
+                    _best_effort_ok = bool(await self._send_or_edit(self._accumulated))
                 except Exception:
                     pass
-            # If we delivered any content before being cancelled, mark the
-            # final response as sent so the gateway's already_sent check
-            # doesn't trigger a duplicate message.  The 5-second
-            # stream_task timeout (gateway/run.py) can cancel us while
-            # waiting on a slow Telegram API call — without this flag the
-            # gateway falls through to the normal send path.
-            if self._already_sent:
+            # Only confirm final delivery if the best-effort send above
+            # actually succeeded OR if the final response was already
+            # confirmed before we were cancelled.  Previously this
+            # promoted any partial send (already_sent=True) to
+            # final_response_sent — which suppressed the gateway's
+            # fallback send even when only intermediate text (e.g.
+            # "Let me search…") had been delivered, not the real answer.
+            if _best_effort_ok and not self._final_response_sent:
                 self._final_response_sent = True
         except Exception as e:
             logger.error("Stream consumer error: %s", e)