feat(security): SSRF guard on fetch_url + single-use tool-approval tokens

Two tool/agent-layer hardening changes:

* fetch_url now resolves the target host and refuses to connect if any
  resolved address is loopback, private (RFC1918/ULA), link-local (incl. the
  169.254.169.254 cloud-metadata endpoint), multicast, reserved, or
  unspecified. IPv4-mapped IPv6 is unwrapped first, and the guard re-runs on
  every redirect hop so a public URL cannot 302 its way to an internal target.

* /chat/approve now requires a single-use token minted when the stream pauses
  for approval and delivered only in that stream's tool_request event, compared
  in constant time. Previously the pending approval was keyed solely on a
  client-supplied conversation_id, so anyone who could enumerate a
  conversation_id could approve another client's pending action.

The frontend threads the token from the tool_request event into the approve
call.

Co-authored-by: Cursor <cursoragent@cursor.com>

synapse/tools.py

@@ -60,20 +60,83 @@ async def _web_search(query: str = "", **_) -> str:
     return res or "(no results)"
 
 
+_FETCH_MAX_REDIRECTS = 5
+
+
+def _ip_is_blocked(ip: str) -> bool:
+    """True if an address is one an outbound fetch has no business reaching:
+    loopback, RFC1918/ULA private, link-local (incl. 169.254.169.254 cloud
+    metadata), multicast, reserved, or unspecified. IPv4-mapped IPv6 is unwrapped
+    first so ::ffff:127.0.0.1 can't sneak a loopback past the check."""
+    import ipaddress
+    try:
+        addr = ipaddress.ip_address(ip.split("%")[0])  # drop any IPv6 zone id
+    except ValueError:
+        return True  # unparseable -> refuse rather than guess
+    mapped = getattr(addr, "ipv4_mapped", None)
+    if mapped is not None:
+        addr = mapped
+    return (
+        addr.is_loopback or addr.is_private or addr.is_link_local
+        or addr.is_multicast or addr.is_reserved or addr.is_unspecified
+    )
+
+
+def _ssrf_guard(host: str) -> str | None:
+    """Resolve a hostname and return an error string if ANY of its A/AAAA
+    records is a blocked address, else None. Checking every answer stops a name
+    from smuggling one private record alongside a public one.
+
+    ponytail: this validates then httpx re-resolves on connect, so a sub-second
+    DNS-rebind could still slip a private address through the TOCTOU gap. That's
+    an advanced attack against a playbook-gated, single-user tool; pin the
+    connection to the resolved IP if this ever faces untrusted callers."""
+    import socket
+    if not host:
+        return "missing host"
+    try:
+        infos = socket.getaddrinfo(host, None)
+    except socket.gaierror as e:
+        return f"cannot resolve host: {e}"
+    ips = {info[4][0] for info in infos}
+    if not ips:
+        return "host did not resolve"
+    blocked = [ip for ip in ips if _ip_is_blocked(ip)]
+    if blocked:
+        return f"refusing to fetch a private/loopback/link-local address ({', '.join(sorted(blocked))})"
+    return None
+
+
 async def _fetch_url(url: str = "", **_) -> str:
     import re
     import httpx
+    from urllib.parse import urlparse, urljoin
     url = (url or "").strip()
     if not url.startswith(("http://", "https://")):
         return json.dumps({"error": "url must start with http:// or https://"})
-    # ponytail: no SSRF allow/deny-list — local single-user assistant, and the
-    # tool only runs when a playbook explicitly grants fetch_url. Add host
-    # filtering if this ever serves multiple/untrusted users.
+    # SSRF guard: validate the host of the initial URL AND every redirect hop
+    # against the private/loopback/link-local block-list before connecting, so a
+    # granted fetch_url can't be steered at 127.0.0.1:11434, cloud metadata, or
+    # LAN hosts — and a public URL can't 302 its way there either.
     try:
-        async with httpx.AsyncClient(timeout=15.0, follow_redirects=True) as c:
-            r = await c.get(url, headers={"User-Agent": "NexusOS/1.0"})
-            r.raise_for_status()
-            html = r.text
+        async with httpx.AsyncClient(timeout=15.0, follow_redirects=False) as c:
+            for _ in range(_FETCH_MAX_REDIRECTS + 1):
+                parsed = urlparse(url)
+                if parsed.scheme not in ("http", "https"):
+                    return json.dumps({"error": "only http(s) URLs are allowed"})
+                err = _ssrf_guard(parsed.hostname or "")
+                if err:
+                    return json.dumps({"error": f"blocked: {err}"})
+                r = await c.get(url, headers={"User-Agent": "NexusOS/1.0"})
+                location = r.headers.get("location")
+                if r.is_redirect and location:
+                    url = urljoin(url, location)
+                    continue
+                r.raise_for_status()
+                html = r.text
+                break
+            else:
+                return json.dumps({"error": "too many redirects"})
     except Exception as e:
         return json.dumps({"error": f"fetch failed: {e}"})
     text = re.sub(r"(?is)<(script|style).*?</\1>", " ", html)