Fix Kernel-backed Red Cross benchmark

Author: rgarcia

docs/harbor.md

@@ -116,7 +116,7 @@ By default each Harbor trial runs Chromium inside its own container. Pass `--bro
 uv run clawbench-harbor-adapt \
   --output-dir ./harbor-datasets/clawbench-v2-kernel \
   --browser-runtime kernel \
-  --browser-runtime-options '{"stealth": false}' \
+  --browser-runtime-options '{"stealth": true}' \
   --task-ids v2-1134-chapter-finder-redcross \
   --overwrite
 ```

src/clawbench/runner/run_support/browser_runtime/providers.py

@@ -585,13 +585,9 @@ def start(self, task: dict[str, Any], time_limit_s: int) -> BrowserSession:
         timeout_seconds = min(259200, max(10, time_limit_s + 120))
         payload = {
             **self.options,
+            "stealth": self.options.get("stealth", True),
             "headless": False,
             "timeout_seconds": timeout_seconds,
-            "viewport": {
-                "width": 1920,
-                "height": 1080,
-                "refresh_rate": 25,
-            },
         }
         try:
             result = self._request_json("POST", "/browsers", payload)

src/clawbench/runtime/harbor/kernel-browser.py

@@ -100,7 +100,9 @@ def _public_metadata(state: dict[str, Any]) -> dict[str, Any]:
         "session_id": metadata.get("session_id"),
         "replay_id": inner.get("replay_id") or metadata.get("replay_id"),
         "region": inner.get("region") or metadata.get("region"),
-        "stealth": inner.get("stealth") or metadata.get("stealth"),
+        "stealth": (
+            inner["stealth"] if "stealth" in inner else metadata.get("stealth")
+        ),
         "timeout_seconds": (
             inner.get("timeout_seconds") or metadata.get("timeout_seconds")
         ),

test-cases/v2/v2-1134-chapter-finder-redcross/task.json

@@ -17,8 +17,11 @@
   },
   "instruction": "Find the nearest Red Cross chapter to zip code 90210 using the local chapter finder on redcross.org",
   "eval_schema": {
-    "url_pattern": "redcross\\.org\\/find-your-local-chapter",
-    "method": "GET"
+    "url_pattern": "redcross\\.org/api/lookup/v1/region-mappings/90210(?:\\?|$)",
+    "method": "GET",
+    "params": {
+      "type": "RCO"
+    }
   },
   "time_limit": 30,
   "extra_info": []

tests/test_browser_runtime.py

@@ -398,7 +398,7 @@ def fake_urlopen(
     monkeypatch.setattr(urllib.request, "urlopen", fake_urlopen)
     provider = KernelRuntimeProvider(
         api_key="kernel-secret",
-        options={"stealth": True, "region": "us-east"},
+        options={"region": "us-east"},
         replay_poll_interval_s=0,
         replay_poll_timeout_s=1,
     )
@@ -413,7 +413,6 @@ def fake_urlopen(
         "region": "us-east",
         "headless": False,
         "timeout_seconds": 1920,
-        "viewport": {"width": 1920, "height": 1080, "refresh_rate": 25},
     }
     assert session.provider == "kernel"
     assert session.recording_mode == "provider-download"

tests/test_harbor_kernel_control.py

@@ -4,6 +4,7 @@
 
 import importlib.util
 import json
+import re
 import sys
 import tomllib
 from pathlib import Path
@@ -52,6 +53,27 @@ def adapted_kernel_task(tmp_path: Path) -> Path:
     )
 
 
+def test_redcross_task_intercepts_zip_lookup_not_chapter_finder_page() -> None:
+    task_path = (
+        REPO_ROOT
+        / "test-cases"
+        / "v2"
+        / "v2-1134-chapter-finder-redcross"
+        / "task.json"
+    )
+    schema = json.loads(task_path.read_text())["eval_schema"]
+
+    assert not re.search(
+        schema["url_pattern"],
+        "https://www.redcross.org/find-your-local-chapter.html",
+    )
+    assert re.search(
+        schema["url_pattern"],
+        "https://www.redcross.org/api/lookup/v1/region-mappings/90210?type=RCO",
+    )
+    assert schema["params"] == {"type": "RCO"}
+
+
 def test_kernel_runtime_selection_writes_bridge_env_and_pinned_mcp(
     adapted_kernel_task: Path,
 ) -> None:
@@ -229,7 +251,11 @@ def __init__(self) -> None:
             cdp_url="wss://kernel.example/browser/sess-123/cdp?token=secret-token",
             viewer_url="https://kernel.example/live/sess-123",
             viewer_url_sensitive=True,
-            metadata={"replay_id": "replay-9", "region": "us-east"},
+            metadata={
+                "replay_id": "replay-9",
+                "region": "us-east",
+                "stealth": False,
+            },
             recording_mode="provider-download",
         )
 
@@ -304,6 +330,7 @@ def test_start_writes_state_and_credential_free_metadata(
     metadata = json.loads(module.METADATA_FILE.read_text())
     assert metadata["session_id"] == "sess-123"
     assert metadata["replay_id"] == "replay-9"
+    assert metadata["stealth"] is False
     assert metadata["cdp_bridge_url"] == "http://127.0.0.1:7878"
     blob = module.METADATA_FILE.read_text()
     assert "k-test-key" not in blob