Sandbox: Beenden sammelt den ganzen Baum ein und wartet nicht ewig auf Rohre (#654)

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

src/ClawdDotNet.Core/Sandbox/BwrapSandbox.cs

@@ -251,7 +251,13 @@ public sealed class BwrapSandbox : ISandboxRunner
                 throw;
         }
 
-        await Task.WhenAll(stdout, stderr);
+        // After a stop, the streams end with the processes — but a reader must never hang on a
+        // pipe something still holds. Bounded, then the result is what arrived.
+        var pumps = Task.WhenAll(stdout, stderr);
+        if (timedOut || output.Truncated)
+            await Task.WhenAny(pumps, Task.Delay(TimeSpan.FromSeconds(5), CancellationToken.None));
+        else
+            await pumps;
         if (timedOut)
             _logger.LogWarning("Sandbox run of {Program} stopped after {Timeout}", request.Executable, request.Limits.Timeout);
 
@@ -280,16 +286,75 @@ public sealed class BwrapSandbox : ISandboxRunner
         }
     }
 
-    /// <summary>bwrap dies, and with it — die-with-parent, own PID namespace — everything inside.</summary>
+    /// <summary>
+    /// Stops the run: everything below bwrap is collected first, then all of it is killed.
+    ///
+    /// <para><b>Not trusting <c>--die-with-parent</c>.</b> The kernel clears the parent-death
+    /// signal when a process changes its credentials — and bwrap does exactly that while it
+    /// builds the user namespace. Seen on the test machine: bwrap's monitor was gone, the
+    /// sandbox lived on under PID 1 and kept the output pipe open. Killing the sandbox's own
+    /// PID 1 (the init of its PID namespace) takes every process inside with it.</para>
+    /// </summary>
     private static void Kill(Process process)
     {
+        int root;
         try
         {
-            if (!process.HasExited)
-                process.Kill(entireProcessTree: true);
+            root = process.Id;
         }
-        catch (InvalidOperationException) { }
-        catch (System.ComponentModel.Win32Exception) { }
+        catch (InvalidOperationException)
+        {
+            return;
+        }
+
+        foreach (var pid in Descendants(root).Append(root))
+        {
+            try
+            {
+                using var victim = Process.GetProcessById(pid);
+                victim.Kill();
+            }
+            catch (ArgumentException) { }            // already gone
+            catch (InvalidOperationException) { }
+            catch (System.ComponentModel.Win32Exception) { }
+        }
+    }
+
+    /// <summary>All processes below <paramref name="root"/>, from /proc — collected before anything is killed.</summary>
+    private static IEnumerable<int> Descendants(int root)
+    {
+        var children = new Dictionary<int, List<int>>();
+        foreach (var dir in Directory.EnumerateDirectories("/proc"))
+        {
+            if (!int.TryParse(Path.GetFileName(dir), out var pid))
+                continue;
+            try
+            {
+                // /proc/<pid>/stat: "pid (comm) state ppid …" — comm may hold spaces and parentheses.
+                var stat = File.ReadAllText(Path.Combine(dir, "stat"));
+                var fields = stat[(stat.LastIndexOf(')') + 2)..].Split(' ');
+                if (int.TryParse(fields[1], out var parent))
+                {
+                    if (!children.TryGetValue(parent, out var list))
+                        children[parent] = list = [];
+                    list.Add(pid);
+                }
+            }
+            catch (IOException) { }                  // it ended meanwhile
+            catch (UnauthorizedAccessException) { }
+        }
+
+        var result = new List<int>();
+        var queue = new Queue<int>([root]);
+        while (queue.Count > 0 && result.Count < 10_000)
+        {
+            foreach (var child in children.GetValueOrDefault(queue.Dequeue()) ?? [])
+            {
+                result.Add(child);
+                queue.Enqueue(child);
+            }
+        }
+        return result;
     }
 
     private static string Kilobytes(long bytes) => Math.Max(1, bytes / 1024).ToString(CultureInfo.InvariantCulture);