Merge pull request #28 from browser-use/sync/harness-013097a

sync: harness 013097a

Author: Alezander9

UPSTREAM.md

@@ -88,6 +88,7 @@ Each upstream has its own append-only table. Add a row every time you pull.
 | 2026-04-28 | `04f7716` | `2125cea` | bcode | 1 upstream commit (PR #243). `src/browser_harness/_ipc.py`: `_TMP.mkdir(parents=True, exist_ok=True)` at module load so a caller-supplied `BH_TMP_DIR` pointing at a non-existent directory no longer fails the first sock/port/pid/log/screenshot write. Prerequisite for browsercode's per-session scratch-dir use case. Protected zone — taken verbatim. Divergences touched: none. |
 | 2026-04-29 | `2125cea` | `997ee45` | bcode | 6 upstream commits (PRs #241, #244, #245). `src/browser_harness/_ipc.py`: when `BH_TMP_DIR` is set, drop the `bu-<NAME>` filename prefix (caller-isolated dir means no shared-tmpdir disambiguation needed); without `BH_TMP_DIR` the original `bu-<NAME>` scheme is unchanged. `src/browser_harness/admin.py`: `_daemon_endpoint_names` short-circuits to the local NAME when `BH_TMP_DIR` is set (no glob); plus catch `SystemError` from `os.kill` on Windows during `restart_daemon`. `src/browser_harness/daemon.py`: discover DevToolsActivePort in Comet and Arc profiles on macOS. `tests/unit/test_admin.py`: 2 new tests for the `BH_TMP_DIR` discovery path. All in protected `src/browser_harness/*.py` + tests — taken verbatim. Smoke test + 12 admin unit tests pass. The `_ipc` filename change pairs with our recent per-session BH_TMP_DIR work (browsercode PR #22) — caller isolation now extends to filenames as well as the dir. Divergences touched: none. |
 | 2026-04-30 | `997ee45` | `660827d` | bcode | 11 upstream commits (PRs #246, #247, #251, #254, #256, #260). `src/browser_harness/daemon.py`: resolve WS via `/json/version` to avoid stale `DevToolsActivePort` path (PR #260) + report `cdp_disconnected` on stale CDP probe in `connection_status` (PR #254) + cleanup remote browser when daemon startup fails (PR #251). `src/browser_harness/admin.py`: companion changes for the daemon fixes. `tests/unit/test_admin.py`: 7 new tests. New domain skills: `agent-workspace/domain-skills/xiaohongshu/scraping.md` (PR #246), and a top-level `domain-skills/shopify-admin/` tree (PR #247: README, embedded-apps, knowledge-base, polaris-inputs). Note: PR #247 added skills at the top-level `domain-skills/` path, not under `agent-workspace/domain-skills/` as the post-#229 layout would suggest — vendored verbatim to match upstream layout. Doc updates: README operator framing (PR #255), install.md heredoc → `-c` flag (PR #256), profile-sync.md same. All files outside divergences — taken verbatim. Smoke test + 19 admin unit tests pass. Divergences touched: none. |
+| 2026-05-01 | `660827d` | `013097a` | bcode | 8 upstream commits (PRs #261, #265, #266). `src/browser_harness/daemon.py` (PR #265): split `DevToolsActivePort` into port + ws-path lines and fall back to `ws://127.0.0.1:<port><ws_path>` when `/json/version` returns 404 (Chrome 147+ disables `/json/*` HTTP discovery on the default user-data-dir). `src/browser_harness/run.py` (PR #266): when no daemon is alive, no local Chrome is listening on 9222/9223 (probed via `/json/version`, not bare TCP), and `BROWSER_USE_API_KEY` is set, auto-bootstrap a cloud daemon. `tests/unit/test_run.py`: 2 new tests for the cloud bootstrap path. PR #261 moved `domain-skills/shopify-admin/` → `agent-workspace/domain-skills/shopify-admin/` upstream — both paths are excluded from the vendored tree per §3, so this rename is a no-op for browsercode (`script/check-harness-diff.sh` filters both via `IGNORED_PATHS_REGEX`). All in protected `src/browser_harness/*.py` + tests — taken verbatim. Smoke test + 23 unit tests pass. Divergences touched: none. |
 
 ---
 

packages/bcode-browser/harness/src/browser_harness/daemon.py

@@ -1,5 +1,5 @@
 """CDP WS holder + IPC relay (Unix socket on POSIX, TCP loopback on Windows). One daemon per BU_NAME."""
-import asyncio, json, os, socket, sys, time, urllib.request
+import asyncio, json, os, socket, sys, time, urllib.error, urllib.request
 from collections import deque
 from pathlib import Path
 
@@ -93,9 +93,13 @@ def get_ws_url():
         raise RuntimeError(f"BU_CDP_URL={url} unreachable after 30s: {last_err} -- is the dedicated automation Chrome running?")
     for base in PROFILES:
         try:
-            port = (base / "DevToolsActivePort").read_text().strip().split("\n", 1)[0].strip()
+            active = (base / "DevToolsActivePort").read_text().splitlines()
         except (FileNotFoundError, NotADirectoryError):
             continue
+        port = active[0].strip() if active else ""
+        ws_path = active[1].strip() if len(active) > 1 else ""
+        if not port:
+            continue
         # Resolve the live WS URL via /json/version instead of trusting the path stored
         # alongside the port in DevToolsActivePort: if Chrome was previously launched
         # with a different --user-data-dir on the same port, that file is left behind
@@ -104,6 +108,12 @@ def get_ws_url():
         while time.time() < deadline:
             try:
                 return json.loads(urllib.request.urlopen(f"http://127.0.0.1:{port}/json/version", timeout=1).read())["webSocketDebuggerUrl"]
+            except urllib.error.HTTPError as e:
+                # Chrome 147+ disables /json/* HTTP discovery on the default user-data-dir;
+                # the ws path Chrome wrote to DevToolsActivePort still works.
+                if e.code == 404 and ws_path:
+                    return f"ws://127.0.0.1:{port}{ws_path}"
+                time.sleep(1)
             except (OSError, KeyError, ValueError):
                 time.sleep(1)
         raise RuntimeError(

packages/bcode-browser/harness/src/browser_harness/run.py

@@ -1,4 +1,4 @@
-import os, sys
+import os, sys, urllib.request
 
 # Windows default stdout encoding is cp1252, which can't encode the 🟢 marker
 # helpers prepend to tab titles (or anything else outside Latin-1). Force UTF-8
@@ -9,6 +9,8 @@
 
 from .admin import (
     _version,
+    NAME,
+    daemon_alive,
     ensure_daemon,
     list_cloud_profiles,
     list_local_profiles,
@@ -44,6 +46,18 @@
 """
 
 
+# Probe /json/version (not a bare TCP connect) so a non-Chrome process bound to
+# 9222/9223 doesn't masquerade as Chrome and skip the cloud bootstrap. Mirrors
+# daemon.py's fallback probe.
+def _local_chrome_listening():
+    for port in (9222, 9223):
+        try:
+            urllib.request.urlopen(f"http://127.0.0.1:{port}/json/version", timeout=0.3).close()
+            return True
+        except OSError: pass
+    return False
+
+
 def main():
     args = sys.argv[1:]
     if args and args[0] in {"-h", "--help"}:
@@ -71,6 +85,8 @@ def main():
     if len(args) < 2:
         sys.exit("Usage: browser-harness -c \"print(page_info())\"")
     print_update_banner()
+    if not daemon_alive() and not _local_chrome_listening() and os.environ.get("BROWSER_USE_API_KEY"):
+        start_remote_daemon(NAME)
     ensure_daemon()
     exec(args[1], globals())
 

packages/bcode-browser/harness/tests/unit/test_run.py

@@ -15,6 +15,29 @@ def test_c_flag_executes_code():
     assert stdout.getvalue().strip() == "hello from -c"
 
 
+def test_cloud_bootstrap_on_headless_server(monkeypatch):
+    """No daemon, no local Chrome, API key set -> auto-provision cloud daemon."""
+    monkeypatch.setenv("BROWSER_USE_API_KEY", "test-key")
+    with patch.object(sys, "argv", ["browser-harness", "-c", "x = 1"]), \
+         patch("browser_harness.run.daemon_alive", return_value=False), \
+         patch("browser_harness.run._local_chrome_listening", return_value=False), \
+         patch("browser_harness.run.start_remote_daemon") as mock_start, \
+         patch("browser_harness.run.ensure_daemon"), \
+         patch("browser_harness.run.print_update_banner"):
+        run.main()
+    mock_start.assert_called_once()
+
+
+def test_local_chrome_listening_rejects_non_chrome():
+    """A bare TCP listener on 9222/9223 must not fool the probe — only a real
+    /json/version response counts as Chrome."""
+    with patch("browser_harness.run.urllib.request.urlopen", side_effect=OSError):
+        assert run._local_chrome_listening() is False
+    with patch("browser_harness.run.urllib.request.urlopen") as mock_open:
+        assert run._local_chrome_listening() is True
+        mock_open.assert_called_once()
+
+
 def test_c_flag_does_not_read_stdin():
     stdin_read = []
     fake_stdin = StringIO("should not be read")