Fix mita RPC socket path and rate-limit heal recovery.

app.py

@@ -103,7 +103,7 @@ else:
     application_path = os.path.dirname(__file__)
 
 DATA_FILE = os.path.join(application_path, 'data.json')  # legacy JSON; used only for one-shot import / export
-CURRENT_VERSION = "v2.6.8"
+CURRENT_VERSION = "v2.6.9"
 RELEASES_REPO_URL = repo_url()
 RELEASES_API_LATEST = api_latest_url()
 BIN_DIR = os.environ.get('TUNNEL_BIN_DIR', os.path.join(application_path, 'bin'))

managers/mieru_manager.py

@@ -21,7 +21,9 @@ logger = logging.getLogger(__name__)
 
 MIERU_RELEASE = '3.28.0'
 GITHUB_RELEASE = f'https://github.com/enfein/mieru/releases/download/v{MIERU_RELEASE}'
-MITA_SOCK = '/var/run/mita.sock'
+# Official mita UDS (v3.x). Older docs sometimes mention /var/run/mita.sock.
+MITA_SOCK = '/var/run/mita/mita.sock'
+MITA_SOCK_LEGACY = '/var/run/mita.sock'
 # Official package persists applied config here. If this file has portBindings
 # but no users, `mita run` (systemd) auto-starts the proxy and FATAL-exits
 # with "socks5 server listening failed: no user found", crashing the daemon.
@@ -246,10 +248,14 @@ class MieruManager:
         self.ssh.run_sudo_command(
             f"systemctl stop {self.SERVICE_NAME} 2>/dev/null || true; "
             f"systemctl reset-failed {self.SERVICE_NAME} 2>/dev/null || true; "
-            f"rm -f {_q(MITA_SOCK)} /var/run/mita/*.sock "
+            f"rm -f {_q(MITA_SOCK)} {_q(MITA_SOCK_LEGACY)} /var/run/mita/*.sock "
-            f"{_q(MITA_CONFIG_PB)} {_q(MITA_CONFIG_JSON)} 2>/dev/null || true",
+            f"{_q(MITA_CONFIG_PB)} {_q(MITA_CONFIG_JSON)} 2>/dev/null || true; "
+            f"mkdir -p /var/run/mita /etc/mita 2>/dev/null || true",
             timeout=60,
         )
+        # systemd StartLimitBurst: wait out "Start request repeated too quickly".
+        time.sleep(6)
+
         clients = self._ensure_bootstrap_clients(self._read_clients())
         self._write_clients(clients)
         meta = self._read_metadata()
@@ -258,17 +264,26 @@ class MieruManager:
         self._write_file(self.config_path, json.dumps(config, indent=2))
 
         self.ssh.run_sudo_command(
+            f"systemctl reset-failed {self.SERVICE_NAME} 2>/dev/null || true; "
             f"systemctl start {self.SERVICE_NAME}",
             timeout=60,
         )
+        if not self._wait_for_rpc(timeout=60):
+            # Second attempt after another rate-limit window.
+            self.ssh.run_sudo_command(
+                f"systemctl reset-failed {self.SERVICE_NAME} 2>/dev/null || true; "
+                f"systemctl restart {self.SERVICE_NAME}",
+                timeout=60,
+            )
+            time.sleep(3)
             if not self._wait_for_rpc(timeout=45):
                 journal, _, _ = self.ssh.run_sudo_command(
-                f"journalctl -u {self.SERVICE_NAME} -n 40 --no-pager 2>&1",
+                    f"journalctl -u {self.SERVICE_NAME} -n 50 --no-pager 2>&1",
                     timeout=30,
                 )
                 raise RuntimeError(
                     'mita daemon still not ready after heal. '
-                f'journal: {(journal or "").strip()[-500:]}'
+                    f'journal: {(journal or "").strip()[-600:]}'
                 )
         out, err, code = self._mita_cli(
             ['apply', 'config', _q(self.config_path)],
@@ -284,7 +299,8 @@ class MieruManager:
     def _ensure_daemon(self, log=None):
         """Ensure mita systemd unit is up and RPC socket answers."""
         self.ssh.run_sudo_command(
-            f"systemctl enable {self.SERVICE_NAME} 2>/dev/null || true",
+            f"systemctl enable {self.SERVICE_NAME} 2>/dev/null || true; "
+            f"mkdir -p /var/run/mita /etc/mita 2>/dev/null || true",
             timeout=30,
         )
         # Official package expects the operating user in group `mita`.
@@ -308,29 +324,19 @@ class MieruManager:
             timeout=60,
         )
         if not self._wait_for_rpc(timeout=45):
-            # Crash loop / stale socket — wipe broken store and recover.
+            # Crash loop / wrong socket / rate-limit — wipe store and recover.
-            if self._daemon_needs_heal():
-                self._heal_mita_store(log)
-            else:
-                self.ssh.run_sudo_command(
-                    f"systemctl stop {self.SERVICE_NAME} 2>/dev/null || true; "
-                    f"rm -f {_q(MITA_SOCK)} /var/run/mita/*.sock 2>/dev/null || true; "
-                    f"systemctl start {self.SERVICE_NAME}",
-                    timeout=60,
-                )
-                if not self._wait_for_rpc(timeout=45):
-                    # Last resort: heal even if journal didn't match yet.
             self._heal_mita_store(log)
         if log is not None:
             log.append('mita daemon is active')
 
     def _wait_for_rpc(self, timeout=30):
         deadline = time.time() + timeout
-        while time.time() < deadline:
+        sock_check = (
-            sock_out, _, sock_code = self.ssh.run_sudo_command(
+            f"(test -S {_q(MITA_SOCK)} || test -S {_q(MITA_SOCK_LEGACY)}) && echo ok"
-                f"test -S {_q(MITA_SOCK)} && echo ok"
         )
-            if sock_code == 0 and 'ok' in (sock_out or ''):
+        while time.time() < deadline:
+            # Prefer CLI status: if it answers IDLE/RUNNING, RPC is up
+            # regardless of which sock path we expected.
             status_out, _, status_code = self.ssh.run_sudo_command(
                 'mita status 2>&1',
                 timeout=20,
@@ -338,7 +344,10 @@ class MieruManager:
             text = (status_out or '').upper()
             if status_code == 0 and ('IDLE' in text or 'RUNNING' in text):
                 return True
-                # Socket exists but CLI still races — brief pause.
+            sock_out, _, sock_code = self.ssh.run_sudo_command(sock_check)
+            if sock_code == 0 and 'ok' in (sock_out or ''):
+                time.sleep(1)
+                continue
             time.sleep(1.5)
         return False