Fix Phase 1 permission sync: route push via cell-wireguard + DNAT receive

cell-api has no route to remote WG tunnel IPs — only cell-wireguard does.
Fix _push_permissions_to_remote() to use 'docker exec cell-wireguard curl'
so outbound sync HTTP traverses the WG tunnel from the right namespace.

On the receive side, add ensure_cell_api_dnat() which installs three
iptables rules inside cell-wireguard on startup:
  - PREROUTING DNAT: wg0:3000 → cell-api:3000 (Docker bridge IP)
  - POSTROUTING MASQUERADE: so cell-api's reply routes back via wg0
  - FORWARD ACCEPT: allow the wg0→eth0 forwarded traffic

Called from _apply_startup_enforcement() so rules survive container restarts.
Tests updated to mock subprocess.run instead of urllib.request.urlopen.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

api/app.py

@@ -264,6 +264,7 @@ def _apply_startup_enforcement():
         cell_links = cell_link_manager.list_connections()
         firewall_manager.apply_all_peer_rules(peers)
         firewall_manager.apply_all_cell_rules(cell_links)
+        firewall_manager.ensure_cell_api_dnat()
         firewall_manager.apply_all_dns_rules(peers, COREFILE_PATH, _configured_domain(),
                                              cell_links=cell_links)
         logger.info(f"Applied enforcement rules for {len(peers)} peers, {len(cell_links)} cells on startup")

api/cell_link_manager.py

@@ -11,8 +11,7 @@ Each connection is stored in data/cell_links.json and manifests as:
 import json
 import logging
 import os
-import urllib.error
-import urllib.request
+import subprocess
 from datetime import datetime
 from typing import Any, Dict, List, Optional
 
@@ -108,6 +107,10 @@ class CellLinkManager:
 
         The body inverts inbound/outbound: our inbound (what we share with them)
         becomes their outbound (what they receive from us), and vice-versa.
+
+        Uses 'docker exec cell-wireguard curl' so the HTTP request originates
+        from inside cell-wireguard's network namespace, which has routes to
+        remote cell VPN subnets that cell-api (on the Docker bridge) lacks.
         """
         url = link.get('remote_api_url')
         if not url:
@@ -124,22 +127,32 @@ class CellLinkManager:
             },
             'sent_at': datetime.utcnow().isoformat() + 'Z',
         }
-        payload = json.dumps(body).encode('utf-8')
-        req = urllib.request.Request(
-            url.rstrip('/') + '/api/cells/peer-sync/permissions',
-            data=payload,
-            method='POST',
-            headers={'Content-Type': 'application/json'},
-        )
+        payload = json.dumps(body)
+        endpoint = url.rstrip('/') + '/api/cells/peer-sync/permissions'
+
+        cmd = [
+            'docker', 'exec', 'cell-wireguard',
+            'curl', '-s', '-o', '/dev/null', '-w', '%{http_code}',
+            '-X', 'POST',
+            '-H', 'Content-Type: application/json',
+            '-d', payload,
+            '--max-time', str(_PUSH_TIMEOUT),
+            '--connect-timeout', '3',
+            endpoint,
+        ]
         try:
-            with urllib.request.urlopen(req, timeout=_PUSH_TIMEOUT) as resp:
-                if 200 <= resp.status < 300:
-                    return {'ok': True, 'error': None}
-                return {'ok': False, 'error': f'HTTP {resp.status}'}
-        except urllib.error.HTTPError as e:
-            return {'ok': False, 'error': f'HTTP {e.code}'}
-        except urllib.error.URLError as e:
-            return {'ok': False, 'error': str(e.reason)[:200]}
+            result = subprocess.run(
+                cmd, capture_output=True, text=True, timeout=_PUSH_TIMEOUT + 5
+            )
+            if result.returncode != 0:
+                err = (result.stderr or result.stdout or 'curl error').strip()[:200]
+                return {'ok': False, 'error': err}
+            status = result.stdout.strip()
+            if status.startswith('2'):
+                return {'ok': True, 'error': None}
+            return {'ok': False, 'error': f'HTTP {status}'}
+        except subprocess.TimeoutExpired:
+            return {'ok': False, 'error': 'timeout'}
         except Exception as e:
             return {'ok': False, 'error': str(e)[:200]}
 

api/firewall_manager.py

@@ -298,6 +298,51 @@ def apply_all_cell_rules(cell_links: List[Dict[str, Any]]) -> None:
         apply_cell_rules(name, subnet, inbound)
 
 
+def ensure_cell_api_dnat() -> bool:
+    """DNAT wg0:3000 → cell-api:3000 inside cell-wireguard.
+
+    Remote cells push permission updates over the WireGuard tunnel to our
+    wg0 interface on port 3000. Since cell-api only listens on the Docker
+    bridge, we need a DNAT rule inside cell-wireguard's namespace to forward
+    that traffic. Called on every startup so rules survive container restarts.
+    """
+    try:
+        r = _run(['docker', 'inspect', '--format',
+                  '{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}',
+                  'cell-api'], check=False)
+        api_ip = r.stdout.strip()
+        if not api_ip:
+            logger.warning('ensure_cell_api_dnat: cell-api container not found or no IP')
+            return False
+
+        dnat_check = ['-t', 'nat', '-C', 'PREROUTING', '-i', 'wg0', '-p', 'tcp',
+                      '--dport', '3000', '-j', 'DNAT', '--to-destination', f'{api_ip}:3000']
+        dnat_add   = ['-t', 'nat', '-A', 'PREROUTING', '-i', 'wg0', '-p', 'tcp',
+                      '--dport', '3000', '-j', 'DNAT', '--to-destination', f'{api_ip}:3000']
+        if _wg_exec(['iptables'] + dnat_check).returncode != 0:
+            _wg_exec(['iptables'] + dnat_add)
+
+        masq_check = ['-t', 'nat', '-C', 'POSTROUTING', '-o', 'eth0', '-d', api_ip,
+                      '-p', 'tcp', '--dport', '3000', '-j', 'MASQUERADE']
+        masq_add   = ['-t', 'nat', '-A', 'POSTROUTING', '-o', 'eth0', '-d', api_ip,
+                      '-p', 'tcp', '--dport', '3000', '-j', 'MASQUERADE']
+        if _wg_exec(['iptables'] + masq_check).returncode != 0:
+            _wg_exec(['iptables'] + masq_add)
+
+        fwd_check = ['-C', 'FORWARD', '-i', 'wg0', '-o', 'eth0',
+                     '-p', 'tcp', '--dport', '3000', '-j', 'ACCEPT']
+        fwd_add   = ['-I', 'FORWARD', '-i', 'wg0', '-o', 'eth0',
+                     '-p', 'tcp', '--dport', '3000', '-j', 'ACCEPT']
+        if _wg_exec(['iptables'] + fwd_check).returncode != 0:
+            _wg_exec(['iptables'] + fwd_add)
+
+        logger.info(f'ensure_cell_api_dnat: wg0:3000 → {api_ip}:3000')
+        return True
+    except Exception as e:
+        logger.error(f'ensure_cell_api_dnat: {e}')
+        return False
+
+
 # ---------------------------------------------------------------------------
 # DNS ACL (CoreDNS Corefile generation)
 # ---------------------------------------------------------------------------