Release v1.0.53: account docs split, remove login flow, SCHEMA reference

scripts/service/browser_service.py

@@ -1,23 +1,16 @@
-"""Chromium/Edge 检测与 Playwright 登录、仅打开浏览器。"""
+"""Chromium/Edge 检测与 Playwright：仅打开浏览器（不写库、不做登录态 DOM 检测）。"""
 import json
 import os
 import subprocess
 import sys
 import tempfile
-import time
-from urllib.parse import urlparse
 
-from db.accounts_repo import get_account_by_id, touch_account_updated_at
+from db.accounts_repo import get_account_by_id
 from util.logging_config import (
     get_skill_logger,
-    get_skill_log_file_path,
     subprocess_env_with_trace,
 )
-from util.platforms import (
-    PLATFORMS,
-    PLATFORM_URLS,
-    _LOGIN_LOGGED_OUT_DOM_GENERIC_SELECTORS,
-)
+from util.platforms import PLATFORM_URLS
 
 # 子进程入口脚本与本模块同目录（独立解释器执行，非 import）
 _SERVICE_DIR = os.path.dirname(os.path.abspath(__file__))
@@ -69,284 +62,13 @@ def resolve_chromium_channel():
 
 
 def _print_browser_install_hint():
-    print("❌ 未检测到 Google Chrome 或 Microsoft Edge，请先安装后再登录：")
+    print("❌ 未检测到 Google Chrome 或 Microsoft Edge，请先安装：")
     print("   • Chrome: https://www.google.com/chrome/")
     print("   • Edge:   https://www.microsoft.com/zh-cn/edge")
 
 
-def _login_timeout_seconds():
-    try:
-        return max(60, int((os.getenv("JIANGCHANG_LOGIN_TIMEOUT_SECONDS") or "300").strip()))
-    except ValueError:
-        return 300
-
-
-def _login_poll_interval_seconds():
-    """轮询间隔，默认 1.5s。"""
-    try:
-        v = float((os.getenv("JIANGCHANG_LOGIN_POLL_INTERVAL_SECONDS") or "1.5").strip())
-        return max(0.5, min(v, 10.0))
-    except ValueError:
-        return 1.5
-
-
-def _login_dom_grace_seconds() -> float:
-    """goto 后等待再开始 DOM 判定，减轻跳转中途误判。默认 4s，JIANGCHANG_LOGIN_DOM_GRACE_SECONDS。"""
-    try:
-        v = float((os.getenv("JIANGCHANG_LOGIN_DOM_GRACE_SECONDS") or "4").strip())
-        return max(0.0, min(v, 60.0))
-    except ValueError:
-        return 4.0
-
-
-def _login_out_bundle_for(platform_key: str) -> dict:
-    """传给子进程：anchor + 未登录可见的选择器列表。"""
-    spec = PLATFORMS.get(platform_key, {}) if platform_key else {}
-    anchor = (urlparse(PLATFORM_URLS.get(platform_key, "") or "").netloc or "").lower()
-    spec_lo_dom = [
-        str(s).strip()
-        for s in (spec.get("login_logged_out_selectors") or [])
-        if s is not None and str(s).strip()
-    ]
-    if bool(spec.get("login_skip_generic_logged_out_dom")):
-        logged_out_dom_selectors = list(spec_lo_dom)
-    else:
-        logged_out_dom_selectors = list(_LOGIN_LOGGED_OUT_DOM_GENERIC_SELECTORS) + spec_lo_dom
-    return {
-        "logged_out_dom_selectors": logged_out_dom_selectors,
-        "anchor_host": anchor,
-    }
-
-
-def _run_login_browser_session(
-    target: dict,
-    timeout_sec: int,
-    *,
-    verbose_ui: bool = True,
-) -> tuple[bool, str]:
-    """
-    启动 Playwright 登录检测子进程；**是否已登录以子进程 DOM 判定为准**。
-
-    若 DOM 判定成功则刷新该账号 `updated_at`，便于 `pick-web` 等按最近活跃选号；**是否已登录仅以本次检测为准**。
-
-    返回 (是否已登录成功, end_reason)：end_reason 为 login_child 写入的 reason，失败时可能为
-    timeout / user_closed / subprocess_error。
-    """
-    log = get_skill_logger()
-    account_id = target.get("id")
-    channel = resolve_chromium_channel()
-    if not channel:
-        log.warning("login_aborted no_chromium_channel")
-        if verbose_ui:
-            _print_browser_install_hint()
-        return False, "no_channel"
-
-    try:
-        import playwright  # noqa: F401
-    except ImportError:
-        log.error("login_aborted playwright_missing")
-        if verbose_ui:
-            print("ERROR:需要 playwright Python 包：请在匠厂共享环境中已含 playwright；本机需安装 Google Chrome 或 Microsoft Edge（channel 模式，无需 playwright install chromium）")
-        return False, "playwright_missing"
-
-    profile_dir = (target.get("profile_dir") or "").strip()
-    if not profile_dir:
-        log.warning("login_aborted profile_dir_empty account_id=%s", account_id)
-        if verbose_ui:
-            print("ERROR:PROFILE_DIR_MISSING 库中 profile_dir 为空。")
-        return False, "profile_missing"
-
-    os.makedirs(profile_dir, exist_ok=True)
-    url = (target.get("url") or "").strip() or PLATFORM_URLS.get(
-        target["platform"], "https://www.google.com"
-    )
-    platform = (target.get("platform") or "").strip().lower()
-    poll_sec = _login_poll_interval_seconds()
-    dom_grace_sec = _login_dom_grace_seconds()
-
-    browser_name = "Google Chrome" if channel == "chrome" else "Microsoft Edge"
-    if verbose_ui:
-        print(f"正在为账号 [{target['name']}] 打开 {browser_name} …")
-        print(f"访问地址：{url}")
-        if platform == "gemini":
-            print(
-                "Gemini / Google 登录：若提示「浏览器不安全」或「无法登录」，请关闭本窗口后，"
-                "用普通 Chrome 启动参数 --user-data-dir= 指向下面 profile 目录，在普通浏览器里完成"
-                " Google 登录后完全退出 Chrome，再执行本 login；详见 llm-manager Gemini 引擎说明。"
-            )
-            print(f"  （本账号 profile 目录）{profile_dir}")
-        print(
-            "请在窗口内完成登录。系统根据页面是否仍出现「登录」等未登录控件判断；"
-            "成功后自动关闭窗口并写入状态（无需手动关浏览器）。"
-        )
-        print(
-            f"页面加载后先等待约 {dom_grace_sec:g} 秒再开始检测（减轻跳转误判，可用 JIANGCHANG_LOGIN_DOM_GRACE_SECONDS 调整）。"
-        )
-        print(f"轮询间隔约 {poll_sec} 秒；全程最长 {timeout_sec} 秒。")
-
-    log_file = get_skill_log_file_path()
-    log.info(
-        "login_browser_start account_id=%s platform=%s channel=%s timeout_sec=%s poll_sec=%s "
-        "dom_grace_sec=%s profile_dir=%s start_url=%s log_file=%s",
-        account_id,
-        platform,
-        channel,
-        timeout_sec,
-        poll_sec,
-        dom_grace_sec,
-        profile_dir,
-        url,
-        log_file,
-    )
-    cfg = {
-        "channel": channel,
-        "profile_dir": profile_dir,
-        "url": url,
-        "timeout_sec": timeout_sec,
-        "poll_interval": poll_sec,
-        "dom_grace_sec": dom_grace_sec,
-        "login_detect_bundle": _login_out_bundle_for(platform),
-        "log_file": log_file,
-    }
-    with tempfile.NamedTemporaryFile(
-        mode="w", suffix=".json", delete=False, encoding="utf-8"
-    ) as rf:
-        result_path = rf.name
-    cfg["result_path"] = result_path
-    with tempfile.NamedTemporaryFile(
-        mode="w", suffix=".json", delete=False, encoding="utf-8"
-    ) as jf:
-        json.dump(cfg, jf, ensure_ascii=False)
-        cfg_path = jf.name
-    proc_rc = None
-    child_hard_timeout = False
-    child_stderr = ""
-    child_stdout = ""
-    try:
-        r = subprocess.run(
-            [sys.executable, "-m", "service.login_child_runner", cfg_path],
-            cwd=_SCRIPTS_ROOT,
-            timeout=timeout_sec + 180,
-            env=subprocess_env_with_trace(),
-            capture_output=True,
-            text=True,
-            encoding="utf-8",
-            errors="replace",
-        )
-        proc_rc = r.returncode
-        child_stderr = (r.stderr or "").strip()
-        child_stdout = (r.stdout or "").strip()
-        if child_stderr:
-            log.warning(
-                "login_child_stderr account_id=%s len=%s tail=%s",
-                account_id,
-                len(child_stderr),
-                child_stderr[-6000:],
-            )
-        if child_stdout and proc_rc != 0:
-            log.warning(
-                "login_child_stdout account_id=%s len=%s tail=%s",
-                account_id,
-                len(child_stdout),
-                child_stdout[-2000:],
-            )
-        if proc_rc != 0:
-            if verbose_ui:
-                print("⚠️ 浏览器子进程非零退出，以结果 JSON 为准（若已写入）")
-            log.info(
-                "login_subprocess_nonzero_return code=%s (exit code 不单独作为成败依据，见 result JSON)",
-                proc_rc,
-            )
-    except subprocess.TimeoutExpired as ex:
-        child_hard_timeout = True
-        if verbose_ui:
-            print("⚠️ 浏览器子进程等待超时，按「限时内未完成登录」处理")
-        log.warning("login_subprocess_hard_timeout err=%s", ex)
-    finally:
-        try:
-            os.unlink(cfg_path)
-        except OSError:
-            pass
-
-    interactive_ok = False
-    end_reason = "timeout" if child_hard_timeout else "subprocess_error"
-    child_detail = ""
-    try:
-        with open(result_path, encoding="utf-8") as rf:
-            data = json.load(rf)
-            interactive_ok = bool(data.get("interactive_ok"))
-            er = str(data.get("end_reason") or "").strip()
-            if er:
-                end_reason = er
-            elif interactive_ok:
-                end_reason = "login_ok"
-            elif not child_hard_timeout:
-                end_reason = "timeout"
-            child_detail = str(data.get("detail") or "").strip()
-        if child_detail:
-            log.warning("login_child_result_detail account_id=%s detail=%s", account_id, child_detail[:8000])
-    except Exception as read_ex:
-        log.error(
-            "login_child_result_read_failed account_id=%s err=%s proc_rc=%s stderr_tail=%s",
-            account_id,
-            read_ex,
-            proc_rc,
-            (child_stderr or "")[-3000:],
-        )
-        if child_hard_timeout:
-            end_reason = "timeout"
-            interactive_ok = False
-        elif proc_rc is not None and proc_rc != 0:
-            end_reason = "child_crash"
-        else:
-            end_reason = "subprocess_error"
-    try:
-        os.unlink(result_path)
-    except OSError:
-        pass
-
-    time.sleep(0.5)
-    ok = interactive_ok
-    log.info(
-        "login_finished account_id=%s interactive_ok=%s end_reason=%s subprocess_rc=%s marking_db=%s",
-        account_id,
-        interactive_ok,
-        end_reason,
-        proc_rc,
-        ok,
-    )
-    if ok:
-        touch_account_updated_at(account_id)
-    return ok, end_reason if not ok else "login_ok"
-
-
-def cmd_login(account_id):
-    log = get_skill_logger()
-    log.info("login_command account_id=%r", account_id)
-    target = get_account_by_id(account_id)
-    if not target:
-        log.warning("login_aborted account_not_found account_id=%r", account_id)
-        print("ERROR:ACCOUNT_NOT_FOUND")
-        return
-
-    timeout_sec = _login_timeout_seconds()
-    ok, _end_reason = _run_login_browser_session(target, timeout_sec, verbose_ui=True)
-    log_file = get_skill_log_file_path()
-    if ok:
-        print("✅ 已判定页面登录成功")
-    else:
-        log.warning(
-            "login_not_detected account_id=%s platform=%s see_log=%s",
-            target.get("id"),
-            (target.get("platform") or "").strip().lower(),
-            log_file,
-        )
-        print("⚠️ 未检测到有效登录。请关闭其他占用该用户目录的浏览器后重试，或延长 JIANGCHANG_LOGIN_TIMEOUT_SECONDS 后再登录。")
-        print(f"ℹ️ 详细轮询日志见：{log_file}（可将 JIANGCHANG_LOG_LEVEL=DEBUG 打开更细粒度）")
-
-
 def cmd_open(account_id):
-    """打开该账号的持久化浏览器，仅用于肉眼确认是否已登录；不写数据库。"""
+    """打开该账号的持久化浏览器，仅用于肉眼核对；不写数据库、不判定是否已登录。"""
     get_skill_logger().info("open account_id=%r", account_id)
     target = get_account_by_id(account_id)
     if not target:
@@ -362,7 +84,10 @@ def cmd_open(account_id):
     try:
         import playwright  # noqa: F401
     except ImportError:
-        print("ERROR:需要 playwright Python 包：请在匠厂共享环境中已含 playwright；本机需安装 Google Chrome 或 Microsoft Edge（channel 模式，无需 playwright install chromium）")
+        print(
+            "ERROR:需要 playwright Python 包：请在匠厂共享环境中已含 playwright；"
+            "本机需安装 Google Chrome 或 Microsoft Edge（channel 模式，无需 playwright install chromium）"
+        )
         return
 
     profile_dir = (target.get("profile_dir") or "").strip()
@@ -376,8 +101,7 @@ def cmd_open(account_id):
     browser_name = "Google Chrome" if channel == "chrome" else "Microsoft Edge"
     print(f"正在打开 [{target['name']}] 的 {browser_name}（仅查看，不写入数据库）")
     print(f"地址：{url}")
-    print("请在本窗口中自行确认登录态。关闭浏览器后命令结束。")
-    print("需要自动检测登录时，请执行：python main.py login <id>")
+    print("是否已登录由业务侧（如大模型网页引擎）在使用账号时自行处理；本命令不做登录检测。")
 
     cfg = {"channel": channel, "profile_dir": profile_dir, "url": url}
     with tempfile.NamedTemporaryFile(