Stop Harbor agents after interception

Author: rgarcia

src/clawbench/eval/harbor_adapter.py

@@ -327,6 +327,10 @@ def setup_script(browser_runtime: str = "local") -> str:
   --extra-info-dir /extra_info \
   --output-dir /my-info
 
+# Harbor installs its stock agent before step setup. Wrap that executable so
+# ClawBench's existing /data/.stop-requested signal ends the agent cleanly.
+/app/src/harbor/wrap-harbor-agent.sh
+
 {kernel_setup}/app/src/harbor/start-runtime.sh
 
 for _ in $(seq 1 60); do

src/clawbench/runtime/harbor/wrap-harbor-agent.sh

@@ -0,0 +1,70 @@
+#!/bin/bash
+set -euo pipefail
+
+wrap_agent() {
+  local executable=$1
+  local path real
+
+  path=$(command -v "$executable" 2>/dev/null || true)
+  if [[ -z "$path" && -x "$HOME/.local/bin/$executable" ]]; then
+    path="$HOME/.local/bin/$executable"
+  fi
+  [[ -n "$path" && -x "$path" ]] || return 0
+
+  real="${path}.clawbench-real"
+  if [[ ! -e "$real" ]]; then
+    mv "$path" "$real"
+  fi
+
+  cat >"$path" <<'WRAPPER'
+#!/bin/bash
+set +e
+
+real="${BASH_SOURCE[0]}.clawbench-real"
+stop_file=${CLAWBENCH_STOP_FILE:-/data/.stop-requested}
+stop_result=${CLAWBENCH_STOP_RESULT:-/data/agent-stop.json}
+rm -f "$stop_file" "$stop_result"
+
+"$real" "$@" <&0 &
+agent_pid=$!
+(
+  while kill -0 "$agent_pid" 2>/dev/null; do
+    if [[ -f "$stop_file" ]]; then
+      detected_at=$(date +%s.%N)
+      kill -INT "$agent_pid" 2>/dev/null || true
+      for _ in $(seq 1 20); do
+        kill -0 "$agent_pid" 2>/dev/null || break
+        sleep 0.1
+      done
+      if kill -0 "$agent_pid" 2>/dev/null; then
+        kill -TERM "$agent_pid" 2>/dev/null || true
+      fi
+      printf '{"stop_detected_at":%s,"signal":"INT"}\n' "$detected_at" >"$stop_result"
+      exit 0
+    fi
+    sleep 0.1
+  done
+) &
+watcher_pid=$!
+
+wait "$agent_pid"
+status=$?
+kill "$watcher_pid" 2>/dev/null || true
+wait "$watcher_pid" 2>/dev/null || true
+
+if [[ -f "$stop_file" ]]; then
+  exit 0
+fi
+exit "$status"
+WRAPPER
+  chmod 0755 "$path"
+}
+
+if (( $# > 0 )); then
+  for executable in "$@"; do
+    wrap_agent "$executable"
+  done
+else
+  wrap_agent claude
+  wrap_agent codex
+fi

src/clawbench/runtime/runtime-server/server.py

@@ -493,6 +493,7 @@ def activate_session_target(session_id, reason):
             if not INTERCEPTION_FILE.exists():
                 result = {
                     "intercepted": True,
+                    "intercepted_at": time.time(),
                     "request": request_obj,
                     "schema": eval_schema,
                 }

tests/test_harbor_kernel_control.py

@@ -5,7 +5,9 @@
 import importlib.util
 import json
 import re
+import subprocess
 import sys
+import time
 import tomllib
 from pathlib import Path
 
@@ -22,6 +24,9 @@
 KERNEL_BROWSER_SCRIPT = (
     REPO_ROOT / "src" / "clawbench" / "runtime" / "harbor" / "kernel-browser.py"
 )
+HARBOR_AGENT_WRAPPER = (
+    REPO_ROOT / "src" / "clawbench" / "runtime" / "harbor" / "wrap-harbor-agent.sh"
+)
 
 
 def _task() -> dict:
@@ -114,6 +119,7 @@ def test_kernel_setup_and_test_scripts_wire_lifecycle(
     assert "export CLAWBENCH_BROWSER_CDP_URL_FILE=" in setup
     assert "trap cleanup_browser EXIT" in setup
     assert "kernel-browser.py cleanup" in setup
+    assert "wrap-harbor-agent.sh" in setup
     assert "127.0.0.1:7878/json/version" in setup
 
     test = (tests / "test.sh").read_text()
@@ -124,6 +130,40 @@ def test_kernel_setup_and_test_scripts_wire_lifecycle(
     assert (env_dir / "harbor" / "browser_runtime_providers.py").is_file()
 
 
+def test_stop_wrapper_interrupts_agent_and_exits_cleanly(tmp_path: Path) -> None:
+    bin_dir = tmp_path / "bin"
+    bin_dir.mkdir()
+    fake_agent = bin_dir / "claude"
+    started = tmp_path / "started"
+    stop_file = tmp_path / "stop-requested"
+    stop_result = tmp_path / "agent-stop.json"
+    fake_agent.write_text(
+        "#!/bin/bash\n"
+        "trap 'exit 130' INT\n"
+        'touch "$FAKE_AGENT_STARTED"\n'
+        "while true; do sleep 0.1; done\n"
+    )
+    fake_agent.chmod(0o755)
+    env = {
+        "PATH": f"{bin_dir}:/usr/bin:/bin",
+        "HOME": str(tmp_path),
+        "FAKE_AGENT_STARTED": str(started),
+        "CLAWBENCH_STOP_FILE": str(stop_file),
+        "CLAWBENCH_STOP_RESULT": str(stop_result),
+    }
+
+    subprocess.run([HARBOR_AGENT_WRAPPER, "claude"], env=env, check=True)
+    process = subprocess.Popen([fake_agent], env=env)
+    deadline = time.monotonic() + 2
+    while not started.exists() and time.monotonic() < deadline:
+        time.sleep(0.01)
+    assert started.exists()
+
+    stop_file.touch()
+    assert process.wait(timeout=3) == 0
+    assert json.loads(stop_result.read_text())["signal"] == "INT"
+
+
 def test_local_runtime_default_has_no_kernel_hooks(tmp_path: Path) -> None:
     case = tmp_path / "case"
     case.mkdir()