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

gateway/platforms/discord.py

@@ -456,6 +456,7 @@ class DiscordAdapter(BasePlatformAdapter):
         # show the standard typing gateway event for bots)
         self._typing_tasks: Dict[str, asyncio.Task] = {}
         self._bot_task: Optional[asyncio.Task] = None
+        self._post_connect_task: Optional[asyncio.Task] = None
         # Dedup cache: prevents duplicate bot responses when Discord
         # RESUME replays events after reconnects.
         self._dedup = MessageDeduplicator()
@@ -545,15 +546,14 @@ class DiscordAdapter(BasePlatformAdapter):
 
                 # Resolve any usernames in the allowed list to numeric IDs
                 await adapter_self._resolve_allowed_usernames()
-
-                # Sync slash commands with Discord
-                try:
-                    synced = await adapter_self._client.tree.sync()
-                    logger.info("[%s] Synced %d slash command(s)", adapter_self.name, len(synced))
-                except Exception as e:  # pragma: no cover - defensive logging
-                    logger.warning("[%s] Slash command sync failed: %s", adapter_self.name, e, exc_info=True)
                 adapter_self._ready_event.set()
 
+                if adapter_self._post_connect_task and not adapter_self._post_connect_task.done():
+                    adapter_self._post_connect_task.cancel()
+                adapter_self._post_connect_task = asyncio.create_task(
+                    adapter_self._run_post_connect_initialization()
+                )
+
             @self._client.event
             async def on_message(message: DiscordMessage):
                 # Dedup: Discord RESUME replays events after reconnects (#4777)
@@ -686,14 +686,36 @@ class DiscordAdapter(BasePlatformAdapter):
             except Exception as e:  # pragma: no cover - defensive logging
                 logger.warning("[%s] Error during disconnect: %s", self.name, e, exc_info=True)
 
+        if self._post_connect_task and not self._post_connect_task.done():
+            self._post_connect_task.cancel()
+            try:
+                await self._post_connect_task
+            except asyncio.CancelledError:
+                pass
+
         self._running = False
         self._client = None
         self._ready_event.clear()
+        self._post_connect_task = None
 
         self._release_platform_lock()
 
         logger.info("[%s] Disconnected", self.name)
 
+    async def _run_post_connect_initialization(self) -> None:
+        """Finish non-critical startup work after Discord is connected."""
+        if not self._client:
+            return
+        try:
+            synced = await asyncio.wait_for(self._client.tree.sync(), timeout=30)
+            logger.info("[%s] Synced %d slash command(s)", self.name, len(synced))
+        except asyncio.TimeoutError:
+            logger.warning("[%s] Slash command sync timed out after 30s", self.name)
+        except asyncio.CancelledError:
+            raise
+        except Exception as e:  # pragma: no cover - defensive logging
+            logger.warning("[%s] Slash command sync failed: %s", self.name, e, exc_info=True)
+
     async def _add_reaction(self, message: Any, emoji: str) -> bool:
         """Add an emoji reaction to a Discord message."""
         if not message or not hasattr(message, "add_reaction"):

gateway/platforms/matrix.py

@@ -18,6 +18,7 @@ Environment variables:
     MATRIX_REQUIRE_MENTION      Require @mention in rooms (default: true)
     MATRIX_FREE_RESPONSE_ROOMS  Comma-separated room IDs exempt from mention requirement
     MATRIX_AUTO_THREAD          Auto-create threads for room messages (default: true)
+    MATRIX_RECOVERY_KEY         Recovery key for cross-signing verification after device key rotation
     MATRIX_DM_MENTION_THREADS   Create a thread when bot is @mentioned in a DM (default: false)
 """
 
@@ -104,7 +105,7 @@ MAX_MESSAGE_LENGTH = 4000
 # Uses get_hermes_home() so each profile gets its own Matrix store.
 from hermes_constants import get_hermes_dir as _get_hermes_dir
 _STORE_DIR = _get_hermes_dir("platforms/matrix/store", "matrix/store")
-_CRYPTO_PICKLE_PATH = _STORE_DIR / "crypto_store.pickle"
+_CRYPTO_DB_PATH = _STORE_DIR / "crypto.db"
 
 # Grace period: ignore messages older than this many seconds before startup.
 _STARTUP_GRACE_SECONDS = 5
@@ -165,6 +166,33 @@ def check_matrix_requirements() -> bool:
     return True
 
 
+class _CryptoStateStore:
+    """Adapter that satisfies the mautrix crypto StateStore interface.
+
+    OlmMachine requires a StateStore with ``is_encrypted``,
+    ``get_encryption_info``, and ``find_shared_rooms``.  The basic
+    ``MemoryStateStore`` from ``mautrix.client`` doesn't implement these,
+    so we provide simple implementations that consult the client's room
+    state.
+    """
+
+    def __init__(self, client_state_store: Any, joined_rooms: set):
+        self._ss = client_state_store
+        self._joined_rooms = joined_rooms
+
+    async def is_encrypted(self, room_id: str) -> bool:
+        return (await self.get_encryption_info(room_id)) is not None
+
+    async def get_encryption_info(self, room_id: str):
+        if hasattr(self._ss, "get_encryption_info"):
+            return await self._ss.get_encryption_info(room_id)
+        return None
+
+    async def find_shared_rooms(self, user_id: str) -> list:
+        # Return all joined rooms — simple but correct for a single-user bot.
+        return list(self._joined_rooms)
+
+
 class MatrixAdapter(BasePlatformAdapter):
     """Gateway adapter for Matrix (any homeserver)."""
 
@@ -199,6 +227,7 @@ class MatrixAdapter(BasePlatformAdapter):
         )
 
         self._client: Any = None  # mautrix.client.Client
+        self._crypto_db: Any = None  # mautrix.util.async_db.Database
         self._sync_task: Optional[asyncio.Task] = None
         self._closing = False
         self._startup_ts: float = 0.0
@@ -252,6 +281,92 @@ class MatrixAdapter(BasePlatformAdapter):
         self._processed_events_set.add(event_id)
         return False
 
+    # ------------------------------------------------------------------
+    # E2EE helpers
+    # ------------------------------------------------------------------
+
+    async def _verify_device_keys_on_server(self, client: Any, olm: Any) -> bool:
+        """Verify our device keys are on the homeserver after loading crypto state.
+
+        Returns True if keys are valid or were successfully re-uploaded.
+        Returns False if verification fails (caller should refuse E2EE).
+        """
+        try:
+            resp = await client.query_keys({client.mxid: [client.device_id]})
+        except Exception as exc:
+            logger.error(
+                "Matrix: cannot verify device keys on server: %s — refusing E2EE", exc,
+            )
+            return False
+
+        # query_keys returns typed objects (QueryKeysResponse, DeviceKeys
+        # with KeyID keys).  Normalise to plain strings for comparison.
+        device_keys_map = getattr(resp, "device_keys", {}) or {}
+        our_user_devices = device_keys_map.get(str(client.mxid)) or {}
+        our_keys = our_user_devices.get(str(client.device_id))
+
+        if not our_keys:
+            logger.warning("Matrix: device keys missing from server — re-uploading")
+            olm.account.shared = False
+            try:
+                await olm.share_keys()
+            except Exception as exc:
+                logger.error("Matrix: failed to re-upload device keys: %s", exc)
+                return False
+            return True
+
+        # DeviceKeys.keys is a dict[KeyID, str].  Iterate to find the
+        # ed25519 key rather than constructing a KeyID for lookup.
+        server_ed25519 = None
+        keys_dict = getattr(our_keys, "keys", {}) or {}
+        for key_id, key_value in keys_dict.items():
+            if str(key_id).startswith("ed25519:"):
+                server_ed25519 = str(key_value)
+                break
+        local_ed25519 = olm.account.identity_keys.get("ed25519")
+
+        if server_ed25519 != local_ed25519:
+            if olm.account.shared:
+                # Restored account from DB but server has different keys — corrupted state.
+                logger.error(
+                    "Matrix: server has different identity keys for device %s — "
+                    "local crypto state is stale. Delete %s and restart.",
+                    client.device_id,
+                    _CRYPTO_DB_PATH,
+                )
+                return False
+
+            # Fresh account (never uploaded). Server has stale keys from a
+            # previous installation. Try to delete the old device and re-upload.
+            logger.warning(
+                "Matrix: server has stale keys for device %s — attempting re-upload",
+                client.device_id,
+            )
+            try:
+                await client.api.request(
+                    client.api.Method.DELETE
+                    if hasattr(client.api, "Method")
+                    else "DELETE",
+                    f"/_matrix/client/v3/devices/{client.device_id}",
+                )
+                logger.info("Matrix: deleted stale device %s from server", client.device_id)
+            except Exception:
+                # Device deletion often requires UIA or may simply not be
+                # permitted — that's fine, share_keys will try to overwrite.
+                pass
+            try:
+                await olm.share_keys()
+            except Exception as exc:
+                logger.error(
+                    "Matrix: cannot upload device keys for %s: %s. "
+                    "Try generating a new access token to get a fresh device.",
+                    client.device_id,
+                    exc,
+                )
+                return False
+
+        return True
+
     # ------------------------------------------------------------------
     # Required overrides
     # ------------------------------------------------------------------
@@ -350,54 +465,67 @@ class MatrixAdapter(BasePlatformAdapter):
                 return False
             try:
                 from mautrix.crypto import OlmMachine
-                from mautrix.crypto.store import MemoryCryptoStore
+                from mautrix.crypto.store.asyncpg import PgCryptoStore
+                from mautrix.util.async_db import Database
+
+                _STORE_DIR.mkdir(parents=True, exist_ok=True)
+
+                # Remove legacy pickle file from pre-SQLite era.
+                legacy_pickle = _STORE_DIR / "crypto_store.pickle"
+                if legacy_pickle.exists():
+                    logger.info("Matrix: removing legacy crypto_store.pickle (migrated to SQLite)")
+                    legacy_pickle.unlink()
+
+                # Open SQLite-backed crypto store.
+                crypto_db = Database.create(
+                    f"sqlite:///{_CRYPTO_DB_PATH}",
+                    upgrade_table=PgCryptoStore.upgrade_table,
+                )
+                await crypto_db.start()
+                self._crypto_db = crypto_db
 
-                # account_id and pickle_key are required by mautrix ≥0.21.
-                # Use the Matrix user ID as account_id for stable identity.
-                # pickle_key secures in-memory serialisation; derive from
-                # the same user_id:device_id pair used for the on-disk HMAC.
                 _acct_id = self._user_id or "hermes"
-                _pickle_key = f"{_acct_id}:{self._device_id}"
-                crypto_store = MemoryCryptoStore(
+                _pickle_key = f"{_acct_id}:{self._device_id or 'default'}"
+                crypto_store = PgCryptoStore(
                     account_id=_acct_id,
                     pickle_key=_pickle_key,
+                    db=crypto_db,
                 )
+                await crypto_store.open()
 
-                # Restore persisted crypto state from a previous run.
-                # Uses HMAC to verify integrity before unpickling.
-                pickle_path = _CRYPTO_PICKLE_PATH
-                if pickle_path.exists():
-                    try:
-                        import hashlib, hmac, pickle
-                        raw = pickle_path.read_bytes()
-                        # Format: 32-byte HMAC-SHA256 signature + pickle data.
-                        if len(raw) > 32:
-                            sig, payload = raw[:32], raw[32:]
-                            # Key is derived from the device_id + user_id (stable per install).
-                            hmac_key = f"{self._user_id}:{self._device_id}".encode()
-                            expected = hmac.new(hmac_key, payload, hashlib.sha256).digest()
-                            if hmac.compare_digest(sig, expected):
-                                saved = pickle.loads(payload)  # noqa: S301
-                                if isinstance(saved, MemoryCryptoStore):
-                                    crypto_store = saved
-                                    logger.info("Matrix: restored E2EE crypto store from %s", pickle_path)
-                            else:
-                                logger.warning("Matrix: crypto store HMAC mismatch — ignoring stale/tampered file")
-                    except Exception as exc:
-                        logger.warning("Matrix: could not restore crypto store: %s", exc)
+                crypto_state = _CryptoStateStore(state_store, self._joined_rooms)
+                olm = OlmMachine(client, crypto_store, crypto_state)
 
-                olm = OlmMachine(client, crypto_store, state_store)
-
-                # Set trust policy: accept unverified devices so senders
-                # share Megolm session keys with us automatically.
+                # Accept unverified devices so senders share Megolm
+                # session keys with us automatically.
                 olm.share_keys_min_trust = TrustState.UNVERIFIED
                 olm.send_keys_min_trust = TrustState.UNVERIFIED
 
                 await olm.load()
+
+                # Verify our device keys are still on the homeserver.
+                if not await self._verify_device_keys_on_server(client, olm):
+                    await crypto_db.stop()
+                    await api.session.close()
+                    return False
+
+                # Import cross-signing private keys from SSSS and self-sign
+                # the current device. Required after any device-key rotation
+                # (fresh crypto.db, share_keys re-upload) — otherwise the
+                # device's self-signing signature is stale and peers refuse
+                # to share Megolm sessions with the rotated device.
+                recovery_key = os.getenv("MATRIX_RECOVERY_KEY", "").strip()
+                if recovery_key:
+                    try:
+                        await olm.verify_with_recovery_key(recovery_key)
+                        logger.info("Matrix: cross-signing verified via recovery key")
+                    except Exception as exc:
+                        logger.warning("Matrix: recovery key verification failed: %s", exc)
+
                 client.crypto = olm
                 logger.info(
                     "Matrix: E2EE enabled (store: %s%s)",
-                    str(_STORE_DIR),
+                    str(_CRYPTO_DB_PATH),
                     f", device_id={client.device_id}" if client.device_id else "",
                 )
             except Exception as exc:
@@ -438,6 +566,15 @@ class MatrixAdapter(BasePlatformAdapter):
                 )
                 # Build DM room cache from m.direct account data.
                 await self._refresh_dm_cache()
+
+                # Dispatch events from the initial sync so the OlmMachine
+                # receives to-device key shares queued while we were offline.
+                try:
+                    tasks = client.handle_sync(sync_data)
+                    if tasks:
+                        await asyncio.gather(*tasks)
+                except Exception as exc:
+                    logger.warning("Matrix: initial sync event dispatch error: %s", exc)
             else:
                 logger.warning("Matrix: initial sync returned unexpected type %s", type(sync_data).__name__)
         except Exception as exc:
@@ -466,21 +603,12 @@ class MatrixAdapter(BasePlatformAdapter):
             except (asyncio.CancelledError, Exception):
                 pass
 
-        # Persist E2EE crypto store before closing so the next restart
-        # can decrypt events using sessions from this run.
-        if self._client and self._encryption and getattr(self._client, "crypto", None):
+        # Close the SQLite crypto store database.
+        if hasattr(self, "_crypto_db") and self._crypto_db:
             try:
-                import hashlib, hmac, pickle
-                crypto_store = self._client.crypto.crypto_store
-                _STORE_DIR.mkdir(parents=True, exist_ok=True)
-                pickle_path = _CRYPTO_PICKLE_PATH
-                payload = pickle.dumps(crypto_store)
-                hmac_key = f"{self._user_id}:{self._device_id}".encode()
-                sig = hmac.new(hmac_key, payload, hashlib.sha256).digest()
-                pickle_path.write_bytes(sig + payload)
-                logger.info("Matrix: persisted E2EE crypto store to %s", pickle_path)
+                await self._crypto_db.stop()
             except Exception as exc:
-                logger.debug("Matrix: could not persist crypto store on disconnect: %s", exc)
+                logger.debug("Matrix: could not close crypto DB on disconnect: %s", exc)
 
         if self._client:
             try:
@@ -853,13 +981,6 @@ class MatrixAdapter(BasePlatformAdapter):
                     except Exception as exc:
                         logger.warning("Matrix: sync event dispatch error: %s", exc)
 
-                # Share keys periodically if E2EE is enabled.
-                if self._encryption and getattr(client, "crypto", None):
-                    try:
-                        await client.crypto.share_keys()
-                    except Exception as exc:
-                        logger.warning("Matrix: E2EE key share failed: %s", exc)
-
                 # Retry any buffered undecrypted events.
                 if self._pending_megolm:
                     await self._retry_pending_decryptions()

gateway/platforms/webhook.py

@@ -201,6 +201,7 @@ class WebhookAdapter(BasePlatformAdapter):
             "dingtalk",
             "feishu",
             "wecom",
+            "wecom_callback",
             "weixin",
             "bluebubbles",
         ):

gateway/platforms/wecom_callback.py

@@ -0,0 +1,387 @@
+"""WeCom callback-mode adapter for self-built enterprise applications.
+
+Unlike the bot/websocket adapter in ``wecom.py``, this handles the standard
+WeCom callback flow: WeCom POSTs encrypted XML to an HTTP endpoint, the
+adapter decrypts it, queues the message for the agent, and immediately
+acknowledges.  The agent's reply is delivered later via the proactive
+``message/send`` API using an access-token.
+
+Supports multiple self-built apps under one gateway instance, scoped by
+``corp_id:user_id`` to avoid cross-corp collisions.
+"""
+
+from __future__ import annotations
+
+import asyncio
+import logging
+import socket as _socket
+import time
+from typing import Any, Dict, List, Optional
+from xml.etree import ElementTree as ET
+
+try:
+    from aiohttp import web
+
+    AIOHTTP_AVAILABLE = True
+except ImportError:
+    web = None  # type: ignore[assignment]
+    AIOHTTP_AVAILABLE = False
+
+try:
+    import httpx
+
+    HTTPX_AVAILABLE = True
+except ImportError:
+    httpx = None  # type: ignore[assignment]
+    HTTPX_AVAILABLE = False
+
+from gateway.config import Platform, PlatformConfig
+from gateway.platforms.base import BasePlatformAdapter, MessageEvent, MessageType, SendResult
+from gateway.platforms.wecom_crypto import WXBizMsgCrypt, WeComCryptoError
+
+logger = logging.getLogger(__name__)
+
+DEFAULT_HOST = "0.0.0.0"
+DEFAULT_PORT = 8645
+DEFAULT_PATH = "/wecom/callback"
+ACCESS_TOKEN_TTL_SECONDS = 7200
+MESSAGE_DEDUP_TTL_SECONDS = 300
+
+
+def check_wecom_callback_requirements() -> bool:
+    return AIOHTTP_AVAILABLE and HTTPX_AVAILABLE
+
+
+class WecomCallbackAdapter(BasePlatformAdapter):
+    def __init__(self, config: PlatformConfig):
+        super().__init__(config, Platform.WECOM_CALLBACK)
+        extra = config.extra or {}
+        self._host = str(extra.get("host") or DEFAULT_HOST)
+        self._port = int(extra.get("port") or DEFAULT_PORT)
+        self._path = str(extra.get("path") or DEFAULT_PATH)
+        self._apps: List[Dict[str, Any]] = self._normalize_apps(extra)
+        self._runner: Optional[web.AppRunner] = None
+        self._site: Optional[web.TCPSite] = None
+        self._app: Optional[web.Application] = None
+        self._http_client: Optional[httpx.AsyncClient] = None
+        self._message_queue: asyncio.Queue[MessageEvent] = asyncio.Queue()
+        self._poll_task: Optional[asyncio.Task] = None
+        self._seen_messages: Dict[str, float] = {}
+        self._user_app_map: Dict[str, str] = {}
+        self._access_tokens: Dict[str, Dict[str, Any]] = {}
+
+    # ------------------------------------------------------------------
+    # App normalisation
+    # ------------------------------------------------------------------
+
+    @staticmethod
+    def _user_app_key(corp_id: str, user_id: str) -> str:
+        return f"{corp_id}:{user_id}" if corp_id else user_id
+
+    @staticmethod
+    def _normalize_apps(extra: Dict[str, Any]) -> List[Dict[str, Any]]:
+        apps = extra.get("apps")
+        if isinstance(apps, list) and apps:
+            return [dict(app) for app in apps if isinstance(app, dict)]
+        if extra.get("corp_id"):
+            return [
+                {
+                    "name": extra.get("name") or "default",
+                    "corp_id": extra.get("corp_id", ""),
+                    "corp_secret": extra.get("corp_secret", ""),
+                    "agent_id": str(extra.get("agent_id", "")),
+                    "token": extra.get("token", ""),
+                    "encoding_aes_key": extra.get("encoding_aes_key", ""),
+                }
+            ]
+        return []
+
+    # ------------------------------------------------------------------
+    # Lifecycle
+    # ------------------------------------------------------------------
+
+    async def connect(self) -> bool:
+        if not self._apps:
+            logger.warning("[WecomCallback] No callback apps configured")
+            return False
+        if not check_wecom_callback_requirements():
+            logger.warning("[WecomCallback] aiohttp/httpx not installed")
+            return False
+
+        # Quick port-in-use check.
+        try:
+            with _socket.socket(_socket.AF_INET, _socket.SOCK_STREAM) as sock:
+                sock.settimeout(1)
+                sock.connect(("127.0.0.1", self._port))
+            logger.error("[WecomCallback] Port %d already in use", self._port)
+            return False
+        except (ConnectionRefusedError, OSError):
+            pass
+
+        try:
+            self._http_client = httpx.AsyncClient(timeout=20.0)
+            self._app = web.Application()
+            self._app.router.add_get("/health", self._handle_health)
+            self._app.router.add_get(self._path, self._handle_verify)
+            self._app.router.add_post(self._path, self._handle_callback)
+            self._runner = web.AppRunner(self._app)
+            await self._runner.setup()
+            self._site = web.TCPSite(self._runner, self._host, self._port)
+            await self._site.start()
+            self._poll_task = asyncio.create_task(self._poll_loop())
+            self._mark_connected()
+            logger.info(
+                "[WecomCallback] HTTP server listening on %s:%s%s",
+                self._host, self._port, self._path,
+            )
+            for app in self._apps:
+                try:
+                    await self._refresh_access_token(app)
+                except Exception as exc:
+                    logger.warning(
+                        "[WecomCallback] Initial token refresh failed for app '%s': %s",
+                        app.get("name", "default"), exc,
+                    )
+            return True
+        except Exception:
+            await self._cleanup()
+            logger.exception("[WecomCallback] Failed to start")
+            return False
+
+    async def disconnect(self) -> None:
+        self._running = False
+        if self._poll_task:
+            self._poll_task.cancel()
+            try:
+                await self._poll_task
+            except asyncio.CancelledError:
+                pass
+            self._poll_task = None
+        await self._cleanup()
+        self._mark_disconnected()
+        logger.info("[WecomCallback] Disconnected")
+
+    async def _cleanup(self) -> None:
+        self._site = None
+        if self._runner:
+            await self._runner.cleanup()
+            self._runner = None
+        self._app = None
+        if self._http_client:
+            await self._http_client.aclose()
+            self._http_client = None
+
+    # ------------------------------------------------------------------
+    # Outbound: proactive send via access-token API
+    # ------------------------------------------------------------------
+
+    async def send(
+        self,
+        chat_id: str,
+        content: str,
+        reply_to: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
+    ) -> SendResult:
+        app = self._resolve_app_for_chat(chat_id)
+        touser = chat_id.split(":", 1)[1] if ":" in chat_id else chat_id
+        try:
+            token = await self._get_access_token(app)
+            payload = {
+                "touser": touser,
+                "msgtype": "text",
+                "agentid": int(str(app.get("agent_id") or 0)),
+                "text": {"content": content[:2048]},
+                "safe": 0,
+            }
+            resp = await self._http_client.post(
+                f"https://qyapi.weixin.qq.com/cgi-bin/message/send?access_token={token}",
+                json=payload,
+            )
+            data = resp.json()
+            if data.get("errcode") != 0:
+                return SendResult(success=False, error=str(data))
+            return SendResult(
+                success=True,
+                message_id=str(data.get("msgid", "")),
+                raw_response=data,
+            )
+        except Exception as exc:
+            return SendResult(success=False, error=str(exc))
+
+    def _resolve_app_for_chat(self, chat_id: str) -> Dict[str, Any]:
+        """Pick the app associated with *chat_id*, falling back sensibly."""
+        app_name = self._user_app_map.get(chat_id)
+        if not app_name and ":" not in chat_id:
+            # Legacy bare user_id — try to find a unique match.
+            matching = [k for k in self._user_app_map if k.endswith(f":{chat_id}")]
+            if len(matching) == 1:
+                app_name = self._user_app_map.get(matching[0])
+        app = self._get_app_by_name(app_name) if app_name else None
+        return app or self._apps[0]
+
+    async def get_chat_info(self, chat_id: str) -> Dict[str, Any]:
+        return {"name": chat_id, "type": "dm"}
+
+    # ------------------------------------------------------------------
+    # Inbound: HTTP callback handlers
+    # ------------------------------------------------------------------
+
+    async def _handle_health(self, request: web.Request) -> web.Response:
+        return web.json_response({"status": "ok", "platform": "wecom_callback"})
+
+    async def _handle_verify(self, request: web.Request) -> web.Response:
+        """GET endpoint — WeCom URL verification handshake."""
+        msg_signature = request.query.get("msg_signature", "")
+        timestamp = request.query.get("timestamp", "")
+        nonce = request.query.get("nonce", "")
+        echostr = request.query.get("echostr", "")
+        for app in self._apps:
+            try:
+                crypt = self._crypt_for_app(app)
+                plain = crypt.verify_url(msg_signature, timestamp, nonce, echostr)
+                return web.Response(text=plain, content_type="text/plain")
+            except Exception:
+                continue
+        return web.Response(status=403, text="signature verification failed")
+
+    async def _handle_callback(self, request: web.Request) -> web.Response:
+        """POST endpoint — receive an encrypted message callback."""
+        msg_signature = request.query.get("msg_signature", "")
+        timestamp = request.query.get("timestamp", "")
+        nonce = request.query.get("nonce", "")
+        body = await request.text()
+
+        for app in self._apps:
+            try:
+                decrypted = self._decrypt_request(
+                    app, body, msg_signature, timestamp, nonce,
+                )
+                event = self._build_event(app, decrypted)
+                if event is not None:
+                    # Record which app this user belongs to.
+                    if event.source and event.source.user_id:
+                        map_key = self._user_app_key(
+                            str(app.get("corp_id") or ""), event.source.user_id,
+                        )
+                        self._user_app_map[map_key] = app["name"]
+                    await self._message_queue.put(event)
+                # Immediately acknowledge — the agent's reply will arrive
+                # later via the proactive message/send API.
+                return web.Response(text="success", content_type="text/plain")
+            except WeComCryptoError:
+                continue
+            except Exception:
+                logger.exception("[WecomCallback] Error handling message")
+                break
+        return web.Response(status=400, text="invalid callback payload")
+
+    async def _poll_loop(self) -> None:
+        """Drain the message queue and dispatch to the gateway runner."""
+        while True:
+            event = await self._message_queue.get()
+            try:
+                task = asyncio.create_task(self.handle_message(event))
+                self._background_tasks.add(task)
+                task.add_done_callback(self._background_tasks.discard)
+            except Exception:
+                logger.exception("[WecomCallback] Failed to enqueue event")
+
+    # ------------------------------------------------------------------
+    # XML / crypto helpers
+    # ------------------------------------------------------------------
+
+    def _decrypt_request(
+        self, app: Dict[str, Any], body: str,
+        msg_signature: str, timestamp: str, nonce: str,
+    ) -> str:
+        root = ET.fromstring(body)
+        encrypt = root.findtext("Encrypt", default="")
+        crypt = self._crypt_for_app(app)
+        return crypt.decrypt(msg_signature, timestamp, nonce, encrypt).decode("utf-8")
+
+    def _build_event(self, app: Dict[str, Any], xml_text: str) -> Optional[MessageEvent]:
+        root = ET.fromstring(xml_text)
+        msg_type = (root.findtext("MsgType") or "").lower()
+        # Silently acknowledge lifecycle events.
+        if msg_type == "event":
+            event_name = (root.findtext("Event") or "").lower()
+            if event_name in {"enter_agent", "subscribe"}:
+                return None
+        if msg_type not in {"text", "event"}:
+            return None
+
+        user_id = root.findtext("FromUserName", default="")
+        corp_id = root.findtext("ToUserName", default=app.get("corp_id", ""))
+        scoped_chat_id = self._user_app_key(corp_id, user_id)
+        content = root.findtext("Content", default="").strip()
+        if not content and msg_type == "event":
+            content = "/start"
+        msg_id = (
+            root.findtext("MsgId")
+            or f"{user_id}:{root.findtext('CreateTime', default='0')}"
+        )
+        source = self.build_source(
+            chat_id=scoped_chat_id,
+            chat_name=user_id,
+            chat_type="dm",
+            user_id=user_id,
+            user_name=user_id,
+        )
+        return MessageEvent(
+            text=content,
+            message_type=MessageType.TEXT,
+            source=source,
+            raw_message=xml_text,
+            message_id=msg_id,
+        )
+
+    def _crypt_for_app(self, app: Dict[str, Any]) -> WXBizMsgCrypt:
+        return WXBizMsgCrypt(
+            token=str(app.get("token") or ""),
+            encoding_aes_key=str(app.get("encoding_aes_key") or ""),
+            receive_id=str(app.get("corp_id") or ""),
+        )
+
+    def _get_app_by_name(self, name: Optional[str]) -> Optional[Dict[str, Any]]:
+        if not name:
+            return None
+        for app in self._apps:
+            if app.get("name") == name:
+                return app
+        return None
+
+    # ------------------------------------------------------------------
+    # Access-token management
+    # ------------------------------------------------------------------
+
+    async def _get_access_token(self, app: Dict[str, Any]) -> str:
+        cached = self._access_tokens.get(app["name"])
+        now = time.time()
+        if cached and cached.get("expires_at", 0) > now + 60:
+            return cached["token"]
+        return await self._refresh_access_token(app)
+
+    async def _refresh_access_token(self, app: Dict[str, Any]) -> str:
+        resp = await self._http_client.get(
+            "https://qyapi.weixin.qq.com/cgi-bin/gettoken",
+            params={
+                "corpid": app.get("corp_id"),
+                "corpsecret": app.get("corp_secret"),
+            },
+        )
+        data = resp.json()
+        if data.get("errcode") != 0:
+            raise RuntimeError(f"WeCom token refresh failed: {data}")
+        token = data["access_token"]
+        expires_in = int(data.get("expires_in", ACCESS_TOKEN_TTL_SECONDS))
+        self._access_tokens[app["name"]] = {
+            "token": token,
+            "expires_at": time.time() + expires_in,
+        }
+        logger.info(
+            "[WecomCallback] Token refreshed for app '%s' (corp=%s), expires in %ss",
+            app.get("name", "default"),
+            app.get("corp_id", ""),
+            expires_in,
+        )
+        return token

gateway/platforms/wecom_crypto.py

@@ -0,0 +1,142 @@
+"""WeCom BizMsgCrypt-compatible AES-CBC encryption for callback mode.
+
+Implements the same wire format as Tencent's official ``WXBizMsgCrypt``
+SDK so that WeCom can verify, encrypt, and decrypt callback payloads.
+"""
+
+from __future__ import annotations
+
+import base64
+import hashlib
+import os
+import secrets
+import socket
+import struct
+from typing import Optional
+from xml.etree import ElementTree as ET
+
+from cryptography.hazmat.backends import default_backend
+from cryptography.hazmat.primitives.ciphers import Cipher, algorithms, modes
+
+
+class WeComCryptoError(Exception):
+    pass
+
+
+class SignatureError(WeComCryptoError):
+    pass
+
+
+class DecryptError(WeComCryptoError):
+    pass
+
+
+class EncryptError(WeComCryptoError):
+    pass
+
+
+class PKCS7Encoder:
+    block_size = 32
+
+    @classmethod
+    def encode(cls, text: bytes) -> bytes:
+        amount_to_pad = cls.block_size - (len(text) % cls.block_size)
+        if amount_to_pad == 0:
+            amount_to_pad = cls.block_size
+        pad = bytes([amount_to_pad]) * amount_to_pad
+        return text + pad
+
+    @classmethod
+    def decode(cls, decrypted: bytes) -> bytes:
+        if not decrypted:
+            raise DecryptError("empty decrypted payload")
+        pad = decrypted[-1]
+        if pad < 1 or pad > cls.block_size:
+            raise DecryptError("invalid PKCS7 padding")
+        if decrypted[-pad:] != bytes([pad]) * pad:
+            raise DecryptError("malformed PKCS7 padding")
+        return decrypted[:-pad]
+
+
+def _sha1_signature(token: str, timestamp: str, nonce: str, encrypt: str) -> str:
+    parts = sorted([token, timestamp, nonce, encrypt])
+    return hashlib.sha1("".join(parts).encode("utf-8")).hexdigest()
+
+
+class WXBizMsgCrypt:
+    """Minimal WeCom callback crypto helper compatible with BizMsgCrypt semantics."""
+
+    def __init__(self, token: str, encoding_aes_key: str, receive_id: str):
+        if not token:
+            raise ValueError("token is required")
+        if not encoding_aes_key:
+            raise ValueError("encoding_aes_key is required")
+        if len(encoding_aes_key) != 43:
+            raise ValueError("encoding_aes_key must be 43 chars")
+        if not receive_id:
+            raise ValueError("receive_id is required")
+
+        self.token = token
+        self.receive_id = receive_id
+        self.key = base64.b64decode(encoding_aes_key + "=")
+        self.iv = self.key[:16]
+
+    def verify_url(self, msg_signature: str, timestamp: str, nonce: str, echostr: str) -> str:
+        plain = self.decrypt(msg_signature, timestamp, nonce, echostr)
+        return plain.decode("utf-8")
+
+    def decrypt(self, msg_signature: str, timestamp: str, nonce: str, encrypt: str) -> bytes:
+        expected = _sha1_signature(self.token, timestamp, nonce, encrypt)
+        if expected != msg_signature:
+            raise SignatureError("signature mismatch")
+        try:
+            cipher_text = base64.b64decode(encrypt)
+        except Exception as exc:
+            raise DecryptError(f"invalid base64 payload: {exc}") from exc
+        try:
+            cipher = Cipher(algorithms.AES(self.key), modes.CBC(self.iv), backend=default_backend())
+            decryptor = cipher.decryptor()
+            padded = decryptor.update(cipher_text) + decryptor.finalize()
+            plain = PKCS7Encoder.decode(padded)
+            content = plain[16:]  # skip 16-byte random prefix
+            xml_length = socket.ntohl(struct.unpack("I", content[:4])[0])
+            xml_content = content[4:4 + xml_length]
+            receive_id = content[4 + xml_length:].decode("utf-8")
+        except WeComCryptoError:
+            raise
+        except Exception as exc:
+            raise DecryptError(f"decrypt failed: {exc}") from exc
+
+        if receive_id != self.receive_id:
+            raise DecryptError("receive_id mismatch")
+        return xml_content
+
+    def encrypt(self, plaintext: str, nonce: Optional[str] = None, timestamp: Optional[str] = None) -> str:
+        nonce = nonce or self._random_nonce()
+        timestamp = timestamp or str(int(__import__("time").time()))
+        encrypt = self._encrypt_bytes(plaintext.encode("utf-8"))
+        signature = _sha1_signature(self.token, timestamp, nonce, encrypt)
+        root = ET.Element("xml")
+        ET.SubElement(root, "Encrypt").text = encrypt
+        ET.SubElement(root, "MsgSignature").text = signature
+        ET.SubElement(root, "TimeStamp").text = timestamp
+        ET.SubElement(root, "Nonce").text = nonce
+        return ET.tostring(root, encoding="unicode")
+
+    def _encrypt_bytes(self, raw: bytes) -> str:
+        try:
+            random_prefix = os.urandom(16)
+            msg_len = struct.pack("I", socket.htonl(len(raw)))
+            payload = random_prefix + msg_len + raw + self.receive_id.encode("utf-8")
+            padded = PKCS7Encoder.encode(payload)
+            cipher = Cipher(algorithms.AES(self.key), modes.CBC(self.iv), backend=default_backend())
+            encryptor = cipher.encryptor()
+            encrypted = encryptor.update(padded) + encryptor.finalize()
+            return base64.b64encode(encrypted).decode("utf-8")
+        except Exception as exc:
+            raise EncryptError(f"encrypt failed: {exc}") from exc
+
+    @staticmethod
+    def _random_nonce(length: int = 10) -> str:
+        alphabet = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"
+        return "".join(secrets.choice(alphabet) for _ in range(length))

gateway/platforms/weixin.py

@@ -734,6 +734,42 @@ def _split_delivery_units_for_weixin(content: str) -> List[str]:
     return [unit for unit in units if unit]
 
 
+def _looks_like_chatty_line_for_weixin(line: str) -> bool:
+    """Return True when a line looks like a standalone chat utterance."""
+    stripped = line.strip()
+    if not stripped:
+        return False
+    if len(stripped) > 48:
+        return False
+    if line.startswith((" ", "\t")):
+        return False
+    if stripped.startswith((">", "-", "*", "【")):
+        return False
+    if re.match(r"^\*\*[^*]+\*\*$", stripped):
+        return False
+    if re.match(r"^\d+\.\s", stripped):
+        return False
+    return True
+
+
+def _looks_like_heading_line_for_weixin(line: str) -> bool:
+    """Return True when a short line behaves like a plain-text heading."""
+    stripped = line.strip()
+    if not stripped:
+        return False
+    return len(stripped) <= 24 and stripped.endswith((":", "："))
+
+
+def _should_split_short_chat_block_for_weixin(block: str) -> bool:
+    """Split only chat-like multiline blocks into separate bubbles."""
+    lines = [line for line in block.splitlines() if line.strip()]
+    if not 2 <= len(lines) <= 6:
+        return False
+    if _looks_like_heading_line_for_weixin(lines[0]):
+        return False
+    return all(_looks_like_chatty_line_for_weixin(line) for line in lines)
+
+
 def _pack_markdown_blocks_for_weixin(content: str, max_length: int) -> List[str]:
     if len(content) <= max_length:
         return [content]
@@ -787,9 +823,15 @@ def _split_text_for_weixin_delivery(
             chunks.extend(_pack_markdown_blocks_for_weixin(unit, max_length))
         return chunks or [content]
 
-    # Compact (default): single message when under the limit.
+    # Compact (default): single message when under the limit — unless the
+    # content looks like a short chatty exchange, in which case split into
+    # separate bubbles for a more natural chat feel.
     if len(content) <= max_length:
-        return [content]
+        return (
+            _split_delivery_units_for_weixin(content)
+            if _should_split_short_chat_block_for_weixin(content)
+            else [content]
+        )
     return _pack_markdown_blocks_for_weixin(content, max_length) or [content]