fix(dingtalk,api): validate session webhook URL origin, cap webhook cache, reject header injection

dingtalk.py: The session_webhook URL from incoming DingTalk messages is POSTed to
without any origin validation (line 290), enabling SSRF attacks via crafted webhook
URLs (e.g. http://169.254.169.254/ to reach cloud metadata).  Add a regex check
that only accepts the official DingTalk API origin (https://api.dingtalk.com/).
Also cap _session_webhooks dict at 500 entries with FIFO eviction to prevent
unbounded memory growth from long-running gateway instances.

api_server.py: The X-Hermes-Session-Id request header is accepted and echoed back
into response headers (lines 675, 697) without sanitization.  A session ID
containing \r\n enables HTTP response splitting / header injection.  Add a check
that rejects session IDs containing control characters (\r, \n, \x00).

Co-Authored-By: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>

gateway/platforms/api_server.py

@@ -24,6 +24,7 @@ import hmac
 import json
 import logging
 import os
+import re
 import sqlite3
 import time
 import uuid
@@ -574,6 +575,12 @@ class APIServerAdapter(BasePlatformAdapter):
                     ),
                     status=403,
                 )
+            # Sanitize: reject control characters that could enable header injection.
+            if re.search(r'[\r\n\x00]', provided_session_id):
+                return web.json_response(
+                    {"error": {"message": "Invalid session ID", "type": "invalid_request_error"}},
+                    status=400,
+                )
             session_id = provided_session_id
             try:
                 db = self._ensure_session_db()