Merge branch 'main' of github.com:NousResearch/hermes-agent into bb/gui

gateway/platforms/discord.py

@@ -2706,8 +2706,13 @@ class DiscordAdapter(BasePlatformAdapter):
 
         Discord's TYPING_START gateway event is unreliable in DMs for bots.
         Instead, start a background loop that hits the typing endpoint every
-        8 seconds (typing indicator lasts ~10s).  The loop is cancelled when
+        12 seconds (typing indicator lasts ~10s).  The loop is cancelled when
         stop_typing() is called (after the response is sent).
+
+        Rate-limit handling: if a 429 is encountered, the loop logs a
+        warning, sleeps for the ``retry_after`` duration (or a sensible
+        default), and continues — it does NOT die on a single rate-limit
+        hit.  Only CancelledError (from stop_typing) stops the loop.
         """
         if not self._client:
             return
@@ -2727,9 +2732,22 @@ class DiscordAdapter(BasePlatformAdapter):
                     except asyncio.CancelledError:
                         return
                     except Exception as e:
-                        logger.debug("Discord typing indicator failed for %s: %s", chat_id, e)
-                        return
-                    await asyncio.sleep(8)
+                        # Don't die on 429 — backoff and continue
+                        retry_after = self._extract_discord_retry_after(e)
+                        if retry_after is not None:
+                            logger.warning(
+                                "Typing indicator rate-limited for %s; retrying in %.1fs",
+                                chat_id, retry_after,
+                            )
+                        else:
+                            logger.debug(
+                                "Discord typing indicator failed for %s: %s",
+                                chat_id, e,
+                            )
+                            return
+                        await asyncio.sleep(retry_after)
+                        continue
+                    await asyncio.sleep(12)
             except asyncio.CancelledError:
                 pass
             finally:

gateway/platforms/telegram.py

@@ -8,12 +8,14 @@ Uses python-telegram-bot library for:
 """
 
 import asyncio
+import dataclasses
 import json
 import logging
 import os
 import tempfile
 import html as _html
 import re
+from datetime import datetime, timezone
 from typing import Dict, List, Optional, Any
 
 logger = logging.getLogger(__name__)
@@ -4178,6 +4180,23 @@ class TelegramAdapter(BasePlatformAdapter):
             return bool(configured)
         return os.getenv("TELEGRAM_REQUIRE_MENTION", "false").lower() in {"true", "1", "yes", "on"}
 
+    def _telegram_observe_unmentioned_group_messages(self) -> bool:
+        """Return whether skipped unmentioned group messages are stored as context.
+
+        When enabled with ``require_mention``, Telegram matches the Yuanbao /
+        OpenClaw-style group UX: observe ordinary group chatter in the session
+        transcript, but only dispatch the agent when the bot is explicitly
+        addressed.
+        """
+        configured = self.config.extra.get("observe_unmentioned_group_messages")
+        if configured is None:
+            configured = self.config.extra.get("ingest_unmentioned_group_messages")
+        if configured is not None:
+            if isinstance(configured, str):
+                return configured.lower() in {"true", "1", "yes", "on"}
+            return bool(configured)
+        return os.getenv("TELEGRAM_OBSERVE_UNMENTIONED_GROUP_MESSAGES", "false").lower() in {"true", "1", "yes", "on"}
+
     def _telegram_guest_mode(self) -> bool:
         """Return whether non-allowlisted groups may trigger via direct @mention."""
         configured = self.config.extra.get("guest_mode")
@@ -4219,6 +4238,30 @@ class TelegramAdapter(BasePlatformAdapter):
             return {str(part).strip() for part in raw if str(part).strip()}
         return {part.strip() for part in str(raw).split(",") if part.strip()}
 
+    def _telegram_group_allowed_chats(self) -> set[str]:
+        """Return Telegram chats authorized at group scope."""
+        raw = self.config.extra.get("group_allowed_chats")
+        if raw is None:
+            raw = os.getenv("TELEGRAM_GROUP_ALLOWED_CHATS", "")
+        if isinstance(raw, list):
+            return {str(part).strip() for part in raw if str(part).strip()}
+        return {part.strip() for part in str(raw).split(",") if part.strip()}
+
+    def _telegram_observe_allowed_chats(self) -> set[str]:
+        """Chats where observed group context may use a shared source.
+
+        ``group_allowed_chats`` is the gateway authorization allowlist for
+        user-less group sources.  ``allowed_chats`` remains an optional response
+        gate; when set, observed context must satisfy both lists.
+        """
+        group_allowed = self._telegram_group_allowed_chats()
+        if not group_allowed:
+            return set()
+        response_allowed = self._telegram_allowed_chats()
+        if response_allowed:
+            return group_allowed & response_allowed
+        return group_allowed
+
     def _telegram_allowed_topics(self) -> set[str]:
         """Return the whitelist of Telegram forum topic IDs this bot handles.
 
@@ -4466,6 +4509,126 @@ class TelegramAdapter(BasePlatformAdapter):
         cleaned = re.sub(rf"(?i)@{username}\b[,:\-]*\s*", "", text).strip()
         return cleaned or text
 
+    def _should_observe_unmentioned_group_message(self, message: Message) -> bool:
+        """Return True when a group message should be stored but not dispatched."""
+        if not self._telegram_observe_unmentioned_group_messages():
+            return False
+        if not self._is_group_chat(message):
+            return False
+
+        thread_id = getattr(message, "message_thread_id", None)
+        allowed_topics = self._telegram_allowed_topics()
+        if allowed_topics:
+            topic_id = str(thread_id) if thread_id is not None else self._GENERAL_TOPIC_THREAD_ID
+            if topic_id not in allowed_topics:
+                return False
+
+        if thread_id is not None:
+            try:
+                if int(thread_id) in self._telegram_ignored_threads():
+                    return False
+            except (TypeError, ValueError):
+                return False
+
+        chat_id_str = str(getattr(getattr(message, "chat", None), "id", ""))
+        if self._telegram_exclusive_bot_mentions() and self._explicit_bot_mentions_exclude_self(message):
+            return False
+
+        allowed = self._telegram_observe_allowed_chats()
+        # Observed context is shared at chat/topic scope so a later trigger from
+        # another user can see it.  Require an explicit chat allowlist; that
+        # keeps shared observed history limited to operator-approved groups and
+        # lets gateway authorization pass even after the shared session source
+        # drops the per-sender user_id.
+        if not allowed or chat_id_str not in allowed:
+            return False
+
+        # Only observe messages skipped by the require_mention gate.  If the
+        # message would be processed normally, let the dispatcher handle it;
+        # if require_mention is disabled, every group message is a request.
+        if chat_id_str in self._telegram_free_response_chats():
+            return False
+        if not self._telegram_require_mention():
+            return False
+        if self._is_reply_to_bot(message):
+            return False
+        if self._message_mentions_bot(message):
+            return False
+        if self._message_matches_mention_patterns(message):
+            return False
+        return True
+
+    def _telegram_group_observe_shared_source(self, source):
+        """Return a chat/topic-scoped source for observed Telegram group context."""
+        return dataclasses.replace(source, user_id=None, user_name=None, user_id_alt=None)
+
+    def _telegram_group_observe_attributed_text(self, event: MessageEvent) -> str:
+        user_id = event.source.user_id or "unknown"
+        sender = event.source.user_name or user_id
+        return f"[{sender}|{user_id}]\n{event.text or ''}"
+
+    def _telegram_group_observe_channel_prompt(self) -> str:
+        username = getattr(getattr(self, "_bot", None), "username", None) or "unknown"
+        bot_id = getattr(getattr(self, "_bot", None), "id", None) or "unknown"
+        return (
+            "You are handling a Telegram group chat message.\n"
+            f"- Your identity: user_id={bot_id}, @-mention name in this group=@{username}\n"
+            "- Lines in history prefixed with `[nickname|user_id]` are observed Telegram group context "
+            "and are not necessarily addressed to you.\n"
+            "- Treat only the current new message as a request explicitly directed at you, "
+            "and answer it directly."
+        )
+
+    def _apply_telegram_group_observe_attribution(self, event: MessageEvent) -> MessageEvent:
+        """Align triggered group turns with observed-history attribution."""
+        if not self._telegram_observe_unmentioned_group_messages():
+            return event
+        raw_message = getattr(event, "raw_message", None)
+        if not raw_message or not self._is_group_chat(raw_message):
+            return event
+        chat_id_str = str(getattr(getattr(raw_message, "chat", None), "id", ""))
+        allowed = self._telegram_observe_allowed_chats()
+        if not allowed or chat_id_str not in allowed:
+            return event
+        shared_source = self._telegram_group_observe_shared_source(event.source)
+        observe_prompt = self._telegram_group_observe_channel_prompt()
+        channel_prompt = f"{event.channel_prompt}\n\n{observe_prompt}" if event.channel_prompt else observe_prompt
+        return dataclasses.replace(
+            event,
+            text=self._telegram_group_observe_attributed_text(event),
+            source=shared_source,
+            channel_prompt=channel_prompt,
+        )
+
+    def _observe_unmentioned_group_message(self, message: Message, msg_type: MessageType, update_id: Optional[int] = None) -> None:
+        """Append skipped group chatter to the target session without dispatching."""
+        store = getattr(self, "_session_store", None)
+        if not store:
+            return
+        try:
+            event = self._build_message_event(message, msg_type, update_id=update_id)
+            shared_source = self._telegram_group_observe_shared_source(event.source)
+            session_entry = store.get_or_create_session(shared_source)
+            entry = {
+                "role": "user",
+                "content": self._telegram_group_observe_attributed_text(event),
+                "timestamp": datetime.now(tz=timezone.utc).isoformat(),
+                "observed": True,
+            }
+            if event.message_id:
+                entry["message_id"] = str(event.message_id)
+            store.append_to_transcript(session_entry.session_id, entry)
+            adapter_name = getattr(self, "name", "telegram")
+            logger.info(
+                "[%s] Telegram group message observed (no bot trigger): chat=%s from=%s",
+                adapter_name,
+                getattr(getattr(message, "chat", None), "id", "unknown"),
+                event.source.user_id or "unknown",
+            )
+        except Exception as exc:
+            adapter_name = getattr(self, "name", "telegram")
+            logger.warning("[%s] Failed to observe Telegram group message: %s", adapter_name, exc)
+
     def _should_process_message(self, message: Message, *, is_command: bool = False) -> bool:
         """Apply Telegram group trigger rules.
 
@@ -4590,11 +4753,14 @@ class TelegramAdapter(BasePlatformAdapter):
         if not msg or not msg.text:
             return
         if not self._should_process_message(msg):
+            if self._should_observe_unmentioned_group_message(msg):
+                self._observe_unmentioned_group_message(msg, MessageType.TEXT, update_id=update.update_id)
             return
         await self._ensure_forum_commands(update.message)
 
         event = self._build_message_event(msg, MessageType.TEXT, update_id=update.update_id)
         event.text = self._clean_bot_trigger_text(event.text)
+        event = self._apply_telegram_group_observe_attribution(event)
         self._enqueue_text_event(event)
 
     async def _handle_command(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
@@ -4607,6 +4773,8 @@ class TelegramAdapter(BasePlatformAdapter):
         await self._ensure_forum_commands(msg)
 
         event = self._build_message_event(msg, MessageType.COMMAND, update_id=update.update_id)
+        event.text = self._clean_bot_trigger_text(event.text)
+        event = self._apply_telegram_group_observe_attribution(event)
         await self.handle_message(event)
 
     async def _handle_location_message(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
@@ -4615,6 +4783,8 @@ class TelegramAdapter(BasePlatformAdapter):
         if not msg:
             return
         if not self._should_process_message(msg):
+            if self._should_observe_unmentioned_group_message(msg):
+                self._observe_unmentioned_group_message(msg, MessageType.LOCATION, update_id=update.update_id)
             return
 
         venue = getattr(msg, "venue", None)
@@ -4644,6 +4814,7 @@ class TelegramAdapter(BasePlatformAdapter):
 
         event = self._build_message_event(msg, MessageType.LOCATION, update_id=update.update_id)
         event.text = "\n".join(parts)
+        event = self._apply_telegram_group_observe_attribution(event)
         await self.handle_message(event)
 
     # ------------------------------------------------------------------
@@ -4788,8 +4959,23 @@ class TelegramAdapter(BasePlatformAdapter):
         if not update.message:
             return
         if not self._should_process_message(update.message):
+            if self._should_observe_unmentioned_group_message(update.message):
+                _m = update.message
+                if _m.sticker:
+                    _observe_type = MessageType.STICKER
+                elif _m.photo:
+                    _observe_type = MessageType.PHOTO
+                elif _m.video:
+                    _observe_type = MessageType.VIDEO
+                elif _m.audio:
+                    _observe_type = MessageType.AUDIO
+                elif _m.voice:
+                    _observe_type = MessageType.VOICE
+                else:
+                    _observe_type = MessageType.DOCUMENT
+                self._observe_unmentioned_group_message(_m, _observe_type, update_id=update.update_id)
             return
-        
+
         msg = update.message
         
         # Determine media type
@@ -4817,9 +5003,14 @@ class TelegramAdapter(BasePlatformAdapter):
         # Handle stickers: describe via vision tool with caching
         if msg.sticker:
             await self._handle_sticker(msg, event)
+            event = self._apply_telegram_group_observe_attribution(event)
             await self.handle_message(event)
             return
-        
+
+        # Apply observe attribution after caption is set; sticker is handled above
+        # because _handle_sticker overwrites event.text with its vision description.
+        event = self._apply_telegram_group_observe_attribution(event)
+
         # Download photo to local image cache so the vision tool can access it
         # even after Telegram's ephemeral file URLs expire (~1 hour).
         if msg.photo:

gateway/platforms/yuanbao.py

@@ -1410,41 +1410,43 @@ class RecallGuardMiddleware(InboundMiddleware):
             logger.warning("[%s] Recall: failed to resolve session: %s", adapter.name, exc)
             return
 
-        # Read JSONL directly — SQLite doesn't preserve message_id field.
-        transcript: list = []
+        # Load transcript from canonical store (state.db).  Since PR #29278
+        # added a ``platform_message_id`` column to the messages table and
+        # ``append_to_transcript`` wires the incoming dict's ``message_id``
+        # into it, ``load_transcript`` returns rows with ``message_id`` set
+        # for any message that was observed with one — Branch A1 (exact id
+        # match) is the canonical path again.
         try:
-            path = store.get_transcript_path(sid)
-            if path.exists():
-                with open(path, "r", encoding="utf-8") as f:
-                    for line in f:
-                        line = line.strip()
-                        if line:
-                            try:
-                                transcript.append(json.loads(line))
-                            except json.JSONDecodeError:
-                                pass
+            transcript = store.load_transcript(sid)
         except Exception as exc:
             logger.warning("[%s] Recall: failed to load transcript: %s", adapter.name, exc)
             return
 
-        # Branch A: redact — try message_id first, then content fallback.
-        # Observed messages have message_id; agent-processed @bot messages
-        # only have content (run.py doesn't write message_id to transcript).
+        # Branch A1: exact platform message_id match. Authoritative when the
+        # row was persisted with a platform_message_id (observed group
+        # messages and any inbound message whose adapter carried a msg_id).
         target = None
+        branch_label = ""
         for entry in transcript:
             if entry.get("message_id") == recalled_id:
                 target = entry
+                branch_label = "branch A1: id match"
                 break
+        # Branch A2: content-match fallback for messages that lack an exact
+        # platform id on the row — e.g. agent-processed @bot messages
+        # (run.py doesn't carry msg_id through) or older rows persisted
+        # before the platform_message_id column existed.
         if target is None and recalled_content:
             for entry in transcript:
                 if entry.get("role") == "user" and entry.get("content") == recalled_content:
                     target = entry
+                    branch_label = "branch A2: content match"
                     break
         if target is not None:
             target["content"] = cls._REDACTED
             try:
                 store.rewrite_transcript(sid, transcript)
-                logger.info("[%s] Recall: redacted msg_id=%s (branch A)", adapter.name, recalled_id)
+                logger.info("[%s] Recall: redacted msg_id=%s (%s)", adapter.name, recalled_id, branch_label)
             except Exception as exc:
                 logger.warning("[%s] Recall: rewrite_transcript failed: %s", adapter.name, exc)
             return