fix(gateway): harden health endpoint exposure

2026-07-13 15:16:51 +08:00
parent 2c78976728
commit 3824206ab2
4 changed files with 140 additions and 38 deletions
@@ -19,7 +19,7 @@ services:
    command: ["gateway"]
    restart: unless-stopped
    ports:
-      - 18790:18790
+      - 127.0.0.1:18790:18790
      - 8765:8765
    deploy:
      resources:
@@ -13,7 +13,7 @@ Check these once before Docker, systemd, or LaunchAgent:
 | Secrets are in environment variables or protected config files | API keys, bot tokens, OAuth state, and chat credentials should not be world-readable |
 | `~/.nanobot/` or your custom config/workspace path is persistent | Sessions, memory, channel login state, generated artifacts, and cron jobs live there |
 | Channel access control is intentional | Use `allowFrom`, pairing, WebSocket `token`/`tokenIssueSecret`, or private test channels before exposing the bot |
-| Ports are planned | Gateway health defaults to `18790`; WebUI/WebSocket defaults to `8765`; `nanobot serve` defaults to `8900` |
+| Ports are planned | Gateway health defaults to local-only `127.0.0.1:18790`; WebUI/WebSocket defaults to `8765`; `nanobot serve` defaults to `8900` |
 | Logs are easy to reach | Use `docker compose logs`, `journalctl`, LaunchAgent log files, or `nanobot gateway --verbose` while diagnosing startup |

 Restart the deployed process after editing `config.json`. Long-running processes read config at startup.
@@ -54,6 +54,9 @@ Restart the deployed process after editing `config.json`. Long-running processes
 > ```
 >
 > When the WebSocket `host` is `0.0.0.0`, the channel refuses to start unless `token` or `tokenIssueSecret` is also configured. See [`webui.md#lan-access`](./webui.md#lan-access) for details.
+> The gateway health route itself is intentionally minimal and unauthenticated. When the
+> container binds it to `0.0.0.0`, publish port `18790` to host loopback only; place any
+> remotely monitored health endpoint behind a firewall or reverse proxy.

 ### Docker Compose

@@ -93,7 +96,7 @@ docker run \
  --security-opt apparmor=unconfined \
  --security-opt seccomp=unconfined \
  -v ~/.nanobot:/home/nanobot/.nanobot \
-  -p 18790:18790 -p 8765:8765 \
+  -p 127.0.0.1:18790:18790 -p 8765:8765 \
  nanobot gateway

 # Or run a single command
@@ -998,6 +998,35 @@ def _host_for_local_browser(host: str) -> str:
    return host


+def _gateway_health_url(host: str, port: int) -> str:
+    """Return a health URL that can be opened from this device."""
+    return f"http://{_host_for_local_browser(host)}:{port}/health"
+
+
+def _gateway_health_bind_note(host: str) -> str:
+    """Describe a non-local bind without presenting it as a usable URL."""
+    return "" if is_loopback_host(host) else f" [dim](listening on {host})[/dim]"
+
+
+_GATEWAY_HEALTH_MAX_CONNECTIONS = 64
+_GATEWAY_HEALTH_READ_TIMEOUT_SECONDS = 2.0
+
+
+def _print_gateway_health_endpoint(host: str, port: int) -> None:
+    """Print a usable health URL and make non-loopback binds explicit."""
+    console.print(
+        f"[green]✓[/green] Health endpoint: {_gateway_health_url(host, port)}"
+        f"{_gateway_health_bind_note(host)}"
+    )
+    if is_loopback_host(host):
+        return
+
+    console.print(
+        "[yellow]Warning: the unauthenticated health endpoint is reachable beyond this device. "
+        f"Keep port {port} private or protect it with a firewall or reverse proxy.[/yellow]"
+    )
+
+
 def _webui_bootstrap_secret(config: Config) -> str:
    ws_cfg = _webui_config_dict(config)
    return str(ws_cfg.get("tokenIssueSecret") or ws_cfg.get("token") or "").strip()
@@ -1454,7 +1483,14 @@ def webui(

    console.print()
    console.print(f"WebUI: [cyan]{_webui_display_url(webui_url)}[/cyan]")
-    console.print(f"Gateway health: [cyan]http://{runtime_config.gateway.host}:{effective_gateway_port}/health[/cyan]")
+    gateway_health_url = _gateway_health_url(
+        runtime_config.gateway.host,
+        effective_gateway_port,
+    )
+    console.print(
+        f"Gateway health: [cyan]{gateway_health_url}[/cyan]"
+        f"{_gateway_health_bind_note(runtime_config.gateway.host)}"
+    )
    if no_open:
        console.print("[dim]Browser opening disabled by --no-open.[/dim]")
        if generated_bootstrap_secret:
@@ -1916,42 +1952,52 @@ def _run_gateway(
        """Lightweight HTTP health endpoint on the gateway port."""
        import json as _json

+        connection_slots = asyncio.Semaphore(_GATEWAY_HEALTH_MAX_CONNECTIONS)
+
        async def handle(reader, writer):
-            try:
-                data = await asyncio.wait_for(reader.read(4096), timeout=5)
-            except (asyncio.TimeoutError, ConnectionError):
+            if connection_slots.locked():
                writer.close()
                return

-            request_line = data.split(b"\r\n", 1)[0].decode("utf-8", errors="replace")
-            method, path = "", ""
-            parts = request_line.split(" ")
-            if len(parts) >= 2:
-                method, path = parts[0], parts[1]
+            async with connection_slots:
+                try:
+                    data = await asyncio.wait_for(
+                        reader.read(4096),
+                        timeout=_GATEWAY_HEALTH_READ_TIMEOUT_SECONDS,
+                    )
+                    request_line = data.split(b"\r\n", 1)[0].decode(
+                        "utf-8", errors="replace",
+                    )
+                    method, path = "", ""
+                    parts = request_line.split(" ")
+                    if len(parts) >= 2:
+                        method, path = parts[0], parts[1]

-            if method == "GET" and path == "/health":
-                body = _json.dumps({"status": "ok"})
-                resp = (
-                    f"HTTP/1.0 200 OK\r\n"
-                    f"Content-Type: application/json\r\n"
-                    f"Content-Length: {len(body)}\r\n"
-                    f"\r\n{body}"
-                )
-            else:
-                body = "Not Found"
-                resp = (
-                    f"HTTP/1.0 404 Not Found\r\n"
-                    f"Content-Type: text/plain\r\n"
-                    f"Content-Length: {len(body)}\r\n"
-                    f"\r\n{body}"
-                )
+                    if method == "GET" and path == "/health":
+                        body = _json.dumps({"status": "ok"})
+                        status = "200 OK"
+                        content_type = "application/json"
+                    else:
+                        body = "Not Found"
+                        status = "404 Not Found"
+                        content_type = "text/plain"

-            writer.write(resp.encode())
-            await writer.drain()
-            writer.close()
+                    resp = (
+                        f"HTTP/1.0 {status}\r\n"
+                        f"Content-Type: {content_type}\r\n"
+                        f"Content-Length: {len(body)}\r\n"
+                        "Connection: close\r\n"
+                        f"\r\n{body}"
+                    )
+                    writer.write(resp.encode())
+                    await writer.drain()
+                except (asyncio.TimeoutError, ConnectionError):
+                    pass
+                finally:
+                    writer.close()

        server = await asyncio.start_server(handle, host, health_port)
-        console.print(f"[green]✓[/green] Health endpoint: http://{host}:{health_port}/health")
+        _print_gateway_health_endpoint(host, health_port)
        async with server:
            await server.serve_forever()
    # Register Dream system job (idempotent on restart)
@@ -2763,11 +2763,23 @@ def test_gateway_cli_port_overrides_configured_port(monkeypatch, tmp_path: Path)
    assert "port 18792" in result.stdout


+@pytest.mark.parametrize(
+    ("host", "display_url", "warns_about_public_bind"),
+    [
+        ("127.0.0.1", "http://127.0.0.1:18791/health", False),
+        ("0.0.0.0", "http://127.0.0.1:18791/health", True),
+    ],
+)
 def test_gateway_health_endpoint_binds_and_serves_expected_responses(
-    monkeypatch, tmp_path: Path
+    monkeypatch,
+    tmp_path: Path,
+    host: str,
+    display_url: str,
+    warns_about_public_bind: bool,
 ) -> None:
    config_file = _write_instance_config(tmp_path)
    config = Config()
+    config.gateway.host = host
    config.gateway.port = 18791
    captured: dict[str, object] = {}

@@ -2873,21 +2885,25 @@ def test_gateway_health_endpoint_binds_and_serves_expected_responses(
    result = runner.invoke(app, ["gateway", "--config", str(config_file)])

    assert result.exit_code == 0
-    assert captured["host"] == "127.0.0.1"
+    assert captured["host"] == host
    assert captured["port"] == 18791
-    assert "Health endpoint: http://127.0.0.1:18791/health" in result.stdout
+    assert f"Health endpoint: {display_url}" in result.stdout
+    assert ("unauthenticated health endpoint" in result.stdout) is warns_about_public_bind
+    assert ("listening on 0.0.0.0" in result.stdout) is warns_about_public_bind
+
+    health_handler = captured["handler"]
+    assert callable(health_handler)

    def _call_handler(path: str) -> tuple[str, _FakeWriter]:
        request = f"GET {path} HTTP/1.1\r\nHost: localhost\r\n\r\n".encode()
        writer = _FakeWriter()
-        handler = captured["handler"]
-        assert callable(handler)
-        asyncio.run(handler(_FakeReader(request), writer))
+        asyncio.run(health_handler(_FakeReader(request), writer))
        return writer.output.decode(), writer

    root_response, root_writer = _call_handler("/")
    assert root_writer.closed is True
    assert "HTTP/1.0 404 Not Found" in root_response
+    assert "Connection: close" in root_response
    assert root_response.endswith("\r\n\r\nNot Found")

    health_response, health_writer = _call_handler("/health")
@@ -2901,6 +2917,43 @@ def test_gateway_health_endpoint_binds_and_serves_expected_responses(
    assert "HTTP/1.0 404 Not Found" in missing_response
    assert missing_response.endswith("\r\n\r\nNot Found")

+    if host == "127.0.0.1":
+        async def _exercise_connection_limit() -> None:
+            release = asyncio.Event()
+            all_started = asyncio.Event()
+            started = 0
+
+            class _BlockingReader:
+                async def read(self, _size: int) -> bytes:
+                    nonlocal started
+                    started += 1
+                    if started == cli_commands._GATEWAY_HEALTH_MAX_CONNECTIONS:
+                        all_started.set()
+                    await release.wait()
+                    return b"GET /health HTTP/1.1\r\n\r\n"
+
+            active_writers = [
+                _FakeWriter() for _ in range(cli_commands._GATEWAY_HEALTH_MAX_CONNECTIONS)
+            ]
+            active_tasks = [
+                asyncio.create_task(health_handler(_BlockingReader(), writer))
+                for writer in active_writers
+            ]
+            await asyncio.wait_for(all_started.wait(), timeout=1)
+
+            overflow_writer = _FakeWriter()
+            await health_handler(
+                _FakeReader(b"GET /health HTTP/1.1\r\n\r\n"),
+                overflow_writer,
+            )
+            assert overflow_writer.closed is True
+            assert overflow_writer.output == b""
+
+            release.set()
+            await asyncio.gather(*active_tasks)
+
+        asyncio.run(_exercise_connection_limit())
+

 def test_gateway_shutdown_lets_agent_task_own_mcp_cleanup(
    monkeypatch,