Merge branch 'dev' of ssh://git.commumedia.org:2222/alex/headquarter into dev

apps/api/src/api/tool_instances.py

@@ -1834,7 +1834,8 @@ async def start_instance(
                 instance_port,
             )
             tunnel_info = start_cloudflared_tunnel(
-                host_port=instance.port,
+                container_name=instance.container_name or instance.name,
+                port=instance_port,
             )
             instance.tunnel_id = tunnel_info["pid"]
             instance.public_url = tunnel_info["url"]
@@ -2041,12 +2042,15 @@ async def restart_instance(
                     "error": f"Tool type '{tool_type.name if tool_type else 'unknown'}' has no port configured",
                 }
 
+            instance_port = tool_type.default_port
+
             # Only create tunnel for web-enabled tools
             if tool_type.interface_type == "web":
                 # Create new temporary tunnel
                 try:
                     tunnel_info = start_cloudflared_tunnel(
-                        host_port=instance.port or 0,
+                        container_name=instance.container_name or instance.name,
+                        port=instance_port,
                     )
                     instance.tunnel_id = tunnel_info["pid"]
                     instance.public_url = tunnel_info["url"]
@@ -2279,9 +2283,16 @@ async def recreate_tunnel_endpoint(
                 "message": "Tunnel is already healthy",
             }
 
+    # Get tool type for default port
+    tool_type = await session.get(ToolType, instance.tool_type_id)
+    instance_port = (
+        tool_type.default_port if tool_type and tool_type.default_port else 8080
+    )
+
     try:
         tunnel_info = recreate_tunnel(
-            host_port=instance.port or 0,
+            container_name=instance.container_name or instance.name,
+            port=instance_port,
             old_pid=instance.tunnel_id,
         )
         instance.tunnel_id = tunnel_info["pid"]

apps/api/src/services/docker.py

@@ -384,16 +384,98 @@ def find_free_port(start: int = 10000, end: int = 20000) -> int:
     raise RuntimeError(f"No free port found in range {start}-{end}")
 
 
+def _check_app_binding(
+    container_name: str, port: int
+) -> dict[str, str | bool]:
+    """Diagnose whether the app is bound to 127.0.0.1 or 0.0.0.0.
+
+    Checks from both inside the container (localhost) and outside
+    (via Docker network) to detect binding issues.
+
+    Returns:
+        Dict with 'internal_ok', 'external_ok', 'internal_status',
+        'external_status', and 'diagnosis'.
+    """
+    import subprocess
+
+    result: dict[str, Any] = {
+        "internal_ok": False,
+        "external_ok": False,
+        "internal_status": None,
+        "external_status": None,
+        "diagnosis": "unknown",
+    }
+
+    # Check from inside the container (loopback)
+    internal = subprocess.run(
+        [
+            "docker",
+            "exec",
+            container_name,
+            "sh",
+            "-c",
+            f"curl -s -o /dev/null -w '%{{http_code}}' http://localhost:{port}",
+        ],
+        capture_output=True,
+        text=True,
+        timeout=5,
+    )
+    if internal.returncode == 0:
+        try:
+            result["internal_status"] = int(internal.stdout.strip())
+            result["internal_ok"] = result["internal_status"] > 0
+        except ValueError:
+            pass
+
+    # Check from outside the container (Docker network)
+    external = subprocess.run(
+        [
+            "curl",
+            "-s",
+            "-o",
+            "/dev/null",
+            "-w",
+            "%{http_code}",
+            f"http://{container_name}:{port}",
+        ],
+        capture_output=True,
+        text=True,
+        timeout=5,
+    )
+    if external.returncode == 0:
+        try:
+            result["external_status"] = int(external.stdout.strip())
+            result["external_ok"] = result["external_status"] > 0
+        except ValueError:
+            pass
+
+    # Diagnose binding issue
+    if result["internal_ok"] and not result["external_ok"]:
+        result["diagnosis"] = (
+            f"App appears to be bound to 127.0.0.1:{port} inside the container. "
+            f"It must bind to 0.0.0.0:{port} to be accessible from the tunnel."
+        )
+    elif result["internal_ok"] and result["external_ok"]:
+        result["diagnosis"] = "App is accessible on both interfaces."
+    elif not result["internal_ok"] and not result["external_ok"]:
+        result["diagnosis"] = f"App is not responding on port {port} at all."
+    else:
+        result["diagnosis"] = "Unexpected binding state."
+
+    return result
+
+
 def start_cloudflared_tunnel(
-    host_port: int, timeout: int = 30
+    container_name: str, port: int, timeout: int = 30
 ) -> dict[str, str]:
-    """Start a temporary Cloudflare tunnel to localhost.
+    """Start a temporary Cloudflare tunnel for a container.
 
     Uses 'cloudflared tunnel --url' to create a temporary tunnel
     with a random trycloudflare.com URL.
 
     Args:
-        host_port: Host-mapped port number (e.g. from find_free_port)
+        container_name: Name of the Docker container to tunnel to
+        port: Port number the container listens on
         timeout: Maximum seconds to wait for tunnel URL
 
     Returns:
@@ -404,9 +486,11 @@ def start_cloudflared_tunnel(
 
     logger = logging.getLogger(__name__)
 
-    # First verify the container is accessible via the host-mapped port
+    # First verify the container is accessible from the Docker network
-    logger.info("Checking connectivity to localhost:%d...", host_port)
+    logger.info("Checking connectivity to %s:%d...", container_name, port)
-    for attempt in range(10):
+    accessible = False
+    last_status = None
+    for attempt in range(30):  # 30 attempts × 1s = 30s max wait for app startup
         check = subprocess.run(
             [
                 "curl",
@@ -415,27 +499,65 @@ def start_cloudflared_tunnel(
                 "/dev/null",
                 "-w",
                 "%{http_code}",
-                f"http://localhost:{host_port}",
+                "--max-time",
+                "3",
+                f"http://{container_name}:{port}",
             ],
             capture_output=True,
             text=True,
             timeout=5,
         )
+        status_str = check.stdout.strip()
         logger.info(
-            "Connectivity check %d: http_code=%s", attempt + 1, check.stdout.strip()
+            "Connectivity check %d/%d: http_code=%s (rc=%d)",
+            attempt + 1,
+            30,
+            status_str,
+            check.returncode,
         )
-        if check.returncode == 0:
+        try:
-            break
+            last_status = int(status_str)
+            # Accept 2xx, 3xx, 401, 403 as "app is listening"
+            if last_status in (401, 403) or 200 <= last_status < 400:
+                accessible = True
+                logger.info(
+                    "App on %s:%d is ready (HTTP %d)",
+                    container_name,
+                    port,
+                    last_status,
+                )
+                break
+        except ValueError:
+            pass
+
+        if check.returncode != 0:
+            logger.debug(
+                "curl failed: stderr=%s", check.stderr.strip() if check.stderr else ""
+            )
         time.sleep(1)
-    else:
+
+    if not accessible:
         logger.warning(
-            "localhost:%d not responding to curl checks", host_port
+            "Container %s:%d not responding after 30s (last status: %s). "
+            "Running binding diagnostics...",
+            container_name,
+            port,
+            last_status,
+        )
+        diagnosis = _check_app_binding(container_name, port)
+        logger.warning(
+            "Binding diagnosis: internal=%s (HTTP %s), external=%s (HTTP %s). %s",
+            diagnosis["internal_ok"],
+            diagnosis["internal_status"],
+            diagnosis["external_ok"],
+            diagnosis["external_status"],
+            diagnosis["diagnosis"],
         )
 
     # Run cloudflared in background, capture output
-    logger.info("Starting cloudflared tunnel to http://localhost:%d", host_port)
+    logger.info("Starting cloudflared tunnel to http://%s:%d", container_name, port)
     proc = subprocess.Popen(
-        ["cloudflared", "tunnel", "--url", f"http://localhost:{host_port}"],
+        ["cloudflared", "tunnel", "--url", f"http://{container_name}:{port}"],
         stdout=subprocess.PIPE,
         stderr=subprocess.STDOUT,
         text=True,
@@ -490,14 +612,15 @@ def stop_cloudflared_tunnel(pid: str) -> None:
 
 
 def recreate_tunnel(
-    host_port: int, old_pid: str | None = None
+    container_name: str, port: int, old_pid: str | None = None
 ) -> dict[str, str]:
     """Recreate a temporary Cloudflare tunnel.
 
     Stops the old tunnel (if pid provided) and starts a new one.
 
     Args:
-        host_port: Host-mapped port number (e.g. from find_free_port)
+        container_name: Name of the Docker container to tunnel to
+        port: Port number the container listens on
         old_pid: Optional PID of the old tunnel process to stop
 
     Returns:
@@ -506,7 +629,7 @@ def recreate_tunnel(
     if old_pid:
         stop_cloudflared_tunnel(old_pid)
 
-    return start_cloudflared_tunnel(host_port)
+    return start_cloudflared_tunnel(container_name, port)
 
 
 def check_tunnel_health(url: str, timeout: int = 10) -> dict[str, Any]:

apps/api/src/services/lifecycle_hooks.py

@@ -120,9 +120,9 @@ async def publish_lifecycle_event(
     # Create notification for instance owner (fire-and-forget)
     # Skip intermediate "starting" notifications — only notify on terminal states
     # (failed or successful attempts)
-    _is_starting_intermediate = (
+    _is_starting_intermediate = event_type == "instance.started" and (
-        event_type == "instance.started" and (status or instance.status) == "starting"
+        status or instance.status
-    )
+    ) == "starting"
     if _is_starting_intermediate:
         return