chore: account-manager — runtime_env sibling root, wait-login and browser fixes

scripts/service/login_child_runner.py

@@ -1,36 +1,51 @@
-"""Playwright 登录检测子进程：由 browser_service.cmd_login 以独立解释器启动，argv[1] 为 JSON 配置路径。"""
+"""Playwright 登录检测子进程：由 browser_service 以独立解释器启动，argv[1] 为 JSON 配置路径。
+
+注意：不得在模块顶层 import playwright / jiangchang_skill_core —— 若导入失败，进程会在 main() 之前以退出码 1 退出，
+且写不了 result_path，父进程只能得到 subprocess_error。所有重依赖均在 _run_login_child 内延迟加载。
+"""
+from __future__ import annotations
+
 import json
 import os
 import sys
 import time
+import traceback
 from urllib.parse import urlparse
 
 _scripts_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 if _scripts_dir not in sys.path:
     sys.path.insert(0, _scripts_dir)
 
-from jiangchang_skill_core.unified_logging import attach_unified_file_handler
-from playwright.sync_api import sync_playwright
-
-try:
-    from playwright.sync_api import Error as PlaywrightError
-except ImportError:
-    PlaywrightError = Exception  # type: ignore[misc,assignment]
-
 
 def _is_context_closed_error(ex: BaseException) -> bool:
     s = str(ex).lower()
     if "target closed" in s or "browser has been closed" in s or "context was destroyed" in s:
         return True
-    if isinstance(ex, PlaywrightError) and (
-        "closed" in s or "destroyed" in s
-    ):
+    if "closed" in s or "destroyed" in s:
         return True
     return False
 
 
+def _write_result_file(
+    result_path: str,
+    interactive_ok: bool,
+    end_reason: str,
+    detail: str = "",
+) -> None:
+    if not (result_path or "").strip():
+        return
+    payload: dict = {"interactive_ok": interactive_ok, "end_reason": end_reason}
+    d = (detail or "").strip()
+    if d:
+        payload["detail"] = d[:8000]
+    try:
+        with open(result_path, "w", encoding="utf-8") as rf:
+            json.dump(payload, rf, ensure_ascii=False)
+    except Exception as write_ex:
+        print(f"login_child: failed to write result file: {write_ex}", file=sys.stderr)
+
+
 def page_location_href(p):
-    # Prefer location.href over page.url for SPA (e.g. Sohu shell path lag).
     try:
         href = p.evaluate("() => location.href")
         if href and str(href).strip():
@@ -124,142 +139,240 @@ def evaluate_logged_out_dom(ctx, main_page, bundle):
     return False, ""
 
 
-def main():
-    with open(sys.argv[1], encoding="utf-8") as f:
-        c = json.load(f)
-    bundle = c.get("login_detect_bundle") or {}
-    poll = float(c.get("poll_interval", 1.5))
+def _run_login_child(c: dict) -> None:
+    """单次登录检测；结果一律写入 c['result_path']（由 finally 保证）。"""
+    result_path = (c.get("result_path") or "").strip()
     try:
-        dom_grace = float(c.get("dom_grace_sec", 4.0))
-    except (TypeError, ValueError):
-        dom_grace = 4.0
-    if dom_grace < 0:
-        dom_grace = 0.0
-    t0 = time.time()
-    deadline = t0 + float(c["timeout_sec"])
+        from playwright.sync_api import sync_playwright
+    except ImportError:
+        _write_result_file(
+            result_path,
+            False,
+            "playwright_missing",
+            traceback.format_exc(),
+        )
+        return
+
     interactive_ok = False
     end_reason = "timeout"
-    result_path = c.get("result_path") or ""
-    log_path = (c.get("log_file") or "").strip()
+    ctx = None
     lg = None
-    if log_path:
-        lg = attach_unified_file_handler(
-            log_path,
-            skill_slug="account-manager",
-            logger_name="openclaw.skill.account_manager.login_child",
-        )
     last_eval_detail = ""
-    with sync_playwright() as p:
-        ctx = p.chromium.launch_persistent_context(
-            user_data_dir=c["profile_dir"],
-            headless=False,
-            channel=c["channel"],
-            no_viewport=True,
-            args=["--start-maximized"],
-        )
+    detail_msg = ""
+
+    try:
         try:
-            page = ctx.pages[0] if ctx.pages else ctx.new_page()
-            page.goto(c["url"], wait_until="domcontentloaded", timeout=60000)
-            if dom_grace > 0:
-                time.sleep(dom_grace)
-            if lg is not None:
-                lg.info(
-                    "goto_done initial_pages=%s poll_interval_sec=%s dom_grace_sec=%s",
-                    len(ctx.pages or []),
-                    poll,
-                    dom_grace,
+            from jiangchang_skill_core.unified_logging import attach_unified_file_handler
+        except Exception as e:
+            end_reason = "logging_import_failed"
+            detail_msg = traceback.format_exc()
+            print(detail_msg, file=sys.stderr)
+            return
+
+        try:
+            profile_dir = (c.get("profile_dir") or "").strip()
+            if not profile_dir:
+                end_reason = "profile_missing"
+                detail_msg = "profile_dir empty in config"
+                return
+
+            os.makedirs(profile_dir, exist_ok=True)
+            try:
+                n_entries = len(os.listdir(profile_dir))
+            except OSError as e:
+                end_reason = "profile_dir_unusable"
+                detail_msg = f"{type(e).__name__}: {e}"
+                return
+        except Exception as e:
+            end_reason = "profile_dir_unusable"
+            detail_msg = traceback.format_exc()
+            print(detail_msg, file=sys.stderr)
+            return
+
+        log_path = (c.get("log_file") or "").strip()
+        if log_path:
+            try:
+                lg = attach_unified_file_handler(
+                    log_path,
+                    skill_slug="account-manager",
+                    logger_name="openclaw.skill.account_manager.login_child",
                 )
-            while time.time() < deadline:
-                iter_start = time.time()
-                try:
-                    still_logged_out, detail = evaluate_logged_out_dom(ctx, page, bundle)
-                    ok = not still_logged_out
-                    last_eval_detail = detail
+            except Exception as e:
+                lg = None
+                print(f"login_child: attach_unified_file_handler failed: {e}", file=sys.stderr)
+
+        if lg is not None:
+            lg.info(
+                "login_child_start profile_dir=%r profile_entry_count=%s channel=%r url=%r timeout_sec=%r",
+                profile_dir,
+                n_entries,
+                c.get("channel"),
+                c.get("url"),
+                c.get("timeout_sec"),
+            )
+
+        bundle = c.get("login_detect_bundle") or {}
+        poll = float(c.get("poll_interval", 1.5))
+        try:
+            dom_grace = float(c.get("dom_grace_sec", 4.0))
+        except (TypeError, ValueError):
+            dom_grace = 4.0
+        if dom_grace < 0:
+            dom_grace = 0.0
+        t0 = time.time()
+        deadline = t0 + float(c["timeout_sec"])
+
+        with sync_playwright() as p:
+            try:
+                ctx = p.chromium.launch_persistent_context(
+                    user_data_dir=profile_dir,
+                    headless=False,
+                    channel=c["channel"],
+                    no_viewport=True,
+                    args=["--start-maximized"],
+                )
+            except Exception as e:
+                if _is_context_closed_error(e):
+                    end_reason = "user_closed"
+                else:
+                    end_reason = "launch_failed"
+                    detail_msg = f"{type(e).__name__}: {e}"
                     if lg is not None:
-                        parts = []
-                        for tab in list(ctx.pages or []):
-                            try:
-                                href = page_location_href(tab)
-                                pu = (tab.url or "").strip()
-                                parts.append("href=%r playwright_url=%r" % (href, pu))
-                            except Exception:
-                                parts.append("(tab_read_error)")
-                        lg.debug(
-                            "poll iter_start_elapsed=%.1fs deadline_in=%.1fs tabs=%s poll_interval_sec=%s logged_out=%s ok=%s detail=%s | %s",
-                            iter_start - t0,
-                            deadline - iter_start,
-                            len(ctx.pages or []),
-                            poll,
-                            still_logged_out,
-                            ok,
-                            detail,
-                            " ; ".join(parts) if parts else "no_tabs",
-                        )
-                    if ok:
-                        interactive_ok = True
-                        end_reason = "login_ok"
-                        if lg is not None:
-                            lg.info("login_detected_ok %s", detail)
-                        break
-                except Exception as ex:
-                    if _is_context_closed_error(ex):
-                        end_reason = "user_closed"
-                        if lg is not None:
-                            lg.warning("login_poll_browser_closed err=%s", ex)
-                        break
-                    if lg is not None:
-                        lg.warning("poll_exception err=%s", ex, exc_info=True)
-                spent = time.time() - iter_start
-                time.sleep(max(0.0, poll - spent))
-            if not interactive_ok and end_reason != "user_closed":
+                        lg.exception("launch_persistent_context failed: %s", e)
+                    print(detail_msg, file=sys.stderr)
+                return
+
+            try:
+                page = ctx.pages[0] if ctx.pages else ctx.new_page()
+                page.goto(c["url"], wait_until="domcontentloaded", timeout=60000)
+                if dom_grace > 0:
+                    time.sleep(dom_grace)
                 if lg is not None:
-                    lg.warning("login_poll_exhausted detail=%s", last_eval_detail)
-                rem = max(0.0, deadline - time.time())
-                if rem > 0:
+                    lg.info(
+                        "goto_done initial_pages=%s poll_interval_sec=%s dom_grace_sec=%s",
+                        len(ctx.pages or []),
+                        poll,
+                        dom_grace,
+                    )
+                while time.time() < deadline:
+                    iter_start = time.time()
                     try:
-                        ctx.wait_for_event("close", timeout=rem * 1000)
-                    except Exception:
-                        pass
-            else:
-                if lg is not None:
-                    lg.info("login_dom_ok_preparing_to_release_profile_dir")
-                if interactive_ok:
-                    # 给 Cookie/会话落盘一点时间；随后必须关闭上下文，否则 llm-manager 无法再对同一 profile 启动持久化浏览器
+                        still_logged_out, dom_detail = evaluate_logged_out_dom(ctx, page, bundle)
+                        ok = not still_logged_out
+                        last_eval_detail = dom_detail
+                        if lg is not None:
+                            parts = []
+                            for tab in list(ctx.pages or []):
+                                try:
+                                    href = page_location_href(tab)
+                                    pu = (tab.url or "").strip()
+                                    parts.append("href=%r playwright_url=%r" % (href, pu))
+                                except Exception:
+                                    parts.append("(tab_read_error)")
+                            lg.debug(
+                                "poll elapsed=%.1fs left=%.1fs tabs=%s logged_out=%s ok=%s detail=%s | %s",
+                                iter_start - t0,
+                                deadline - iter_start,
+                                len(ctx.pages or []),
+                                still_logged_out,
+                                ok,
+                                dom_detail,
+                                " ; ".join(parts) if parts else "no_tabs",
+                            )
+                        if ok:
+                            interactive_ok = True
+                            end_reason = "login_ok"
+                            if lg is not None:
+                                lg.info("login_detected_ok %s", dom_detail)
+                            break
+                    except Exception as ex:
+                        if _is_context_closed_error(ex):
+                            end_reason = "user_closed"
+                            if lg is not None:
+                                lg.warning("login_poll_browser_closed err=%s", ex)
+                            break
+                        if lg is not None:
+                            lg.warning("poll_exception err=%s", ex, exc_info=True)
+                    spent = time.time() - iter_start
+                    time.sleep(max(0.0, poll - spent))
+
+                if not interactive_ok and end_reason != "user_closed":
+                    if lg is not None:
+                        lg.warning("login_poll_exhausted detail=%s", last_eval_detail)
+                    rem = max(0.0, deadline - time.time())
+                    if rem > 0:
+                        try:
+                            ctx.wait_for_event("close", timeout=rem * 1000)
+                        except Exception:
+                            pass
+                elif interactive_ok:
+                    if lg is not None:
+                        lg.info("login_dom_ok_preparing_to_release_profile_dir")
                     print(
                         "INFO:LOGIN_DOM_OK 页面检测已判定登录成功；约 2 秒后关闭本窗口以释放用户目录，供后续大模型网页会话使用。",
                         flush=True,
                     )
                     time.sleep(2.0)
-        except Exception as e:
-            if _is_context_closed_error(e):
-                end_reason = "user_closed"
+            except Exception as e:
                 interactive_ok = False
-                if lg is not None:
-                    lg.warning("login_runner_browser_closed err=%s", e)
-            else:
-                if lg is not None:
-                    lg.exception("login_runner_fatal err=%s", e)
-                print(e, file=sys.stderr)
-                raise
-        finally:
-            if result_path:
+                if _is_context_closed_error(e):
+                    end_reason = "user_closed"
+                    if lg is not None:
+                        lg.warning("login_runner_browser_closed err=%s", e)
+                else:
+                    end_reason = "page_error"
+                    detail_msg = traceback.format_exc()
+                    if lg is not None:
+                        lg.exception("login_runner_page_err %s", e)
+                    print(detail_msg, file=sys.stderr)
+            finally:
                 try:
-                    with open(result_path, "w", encoding="utf-8") as rf:
-                        json.dump(
-                            {
-                                "interactive_ok": interactive_ok,
-                                "end_reason": end_reason,
-                            },
-                            rf,
-                            ensure_ascii=False,
-                        )
+                    ctx.close()
                 except Exception:
                     pass
+                ctx = None
+
+    except Exception as e:
+        interactive_ok = False
+        end_reason = "child_fatal"
+        detail_msg = traceback.format_exc()
+        if lg is not None:
+            lg.exception("login_child_unhandled %s", e)
+        print(detail_msg, file=sys.stderr)
+    finally:
+        if ctx is not None:
             try:
                 ctx.close()
             except Exception:
                 pass
+        _write_result_file(result_path, interactive_ok, end_reason, detail_msg)
+
+
+def _entrypoint() -> None:
+    """读取配置 → 运行检测；任意异常都写入 result JSON，进程以 0 退出（由父进程读 JSON 判定成败）。"""
+    result_path = ""
+    if len(sys.argv) < 2:
+        print("login_child: missing cfg path argv", file=sys.stderr)
+        return
+
+    cfg_path = sys.argv[1]
+    try:
+        with open(cfg_path, encoding="utf-8") as f:
+            c = json.load(f)
+    except Exception:
+        tb = traceback.format_exc()
+        print(tb, file=sys.stderr)
+        return
+
+    result_path = (c.get("result_path") or "").strip()
+
+    try:
+        _run_login_child(c)
+    except Exception:
+        tb = traceback.format_exc()
+        print(tb, file=sys.stderr)
+        _write_result_file(result_path, False, "child_fatal", tb)
 
 
 if __name__ == "__main__":
-    main()
+    _entrypoint()