diff --git a/AGENTS.md b/AGENTS.md index 42dd31b0..b661250d 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -647,3 +647,24 @@ Web 端实时通道曾长期双轨（REST 任务轮询为主 + Socket.IO 辅助 2. 确认后端 formatter（`tool_result_formatter`）与前端 renderer（`toolRenderers.ts`）已覆盖该工具。 3. 个人空间勾选 UI 自动出现（注册表经 `/api/personalization` 的 `tool_loading_registry` 下发，类目标签 i18n key `personalization.toolLoadingCat.` 需双语补齐）。 4. 跑 `test/test_tool_loading.py`（注册表完整性断言会校验数量与结构）。 + +--- + +## 14) 网页提取白名单直提（2026-09-12 新增） + +> 实现唯一权威：`modules/webpage_extractor.py`。 + +### 14.1 机制一句话 + +`extract_webpage` / `save_webpage` 不再全部走 Tavily：命中白名单的域名在本机直提（免费、零配额），失败或未命中才回退 Tavily。开关与追加域名在个人空间（工具页），存 personalization.json 的 `webpage_direct_extract_enabled`（默认 true）/ `webpage_direct_extract_domains`。 + +### 14.2 硬约束（改代码必须知道） + +1. **统一入口是 `extract_single_url()`**：白名单判定 → `_direct_extract()` → 失败回退 `tavily_extract()`。两个工具调用点都走它，不要绕过单写 tavily 路径。 +2. **降级链**：GitHub blob 页 → jsDelivr CDN（`cdn.jsdelivr.net/gh/{owner}/{repo}@{branch}/{path}`，国内可用、无限速）→ GitHub API contents（备用，匿名限 60 次/时）→ trafilatura 通用提取 → Tavily。**不要用 raw.githubusercontent.com**（国内被 DNS 污染，实测不可达）。 +3. **trafilatura 是可选依赖**：`import` 失败时通用直提静默失效（GitHub 直链不依赖它仍可用），白名单不会报错；已进 `requirements.txt`，正式部署应装上。 +4. **blob URL 的 branch 按单段解析**（`[^/?#]+`）；含斜杠的分支名解析失败会自然降级 trafilatura → Tavily，属预期行为。 +5. **域名匹配 = 精确或子域名后缀**：`github.com` 命中 `gist.github.com`；用户输入经 `_normalize_domain` 清洗（容忍粘贴完整 URL）。 +6. **新增 personalization 键必须双注册**（`DEFAULT_PERSONALIZATION_CONFIG` + `sanitize_personalization_payload`），否则保存后被静默丢弃（见 .astrion/memory/personalization_config_whitelist.md）。 +7. **返回格式**沿用 `🌐 网页内容 (N 字符)` 骨架，新增 `[提取方式: ...]` 标注（i18n key `webpage.method_label` / `webpage.method_*`），模型侧无感知。 +8. **read-before-edit 已读白名单**含 `recall_project_memory`（recall 返回记忆文件全文，视为已读）；`search_project_memory` 只回片段，刻意不标记。 diff --git a/core/main_terminal_parts/tools_execution.py b/core/main_terminal_parts/tools_execution.py index c0217361..51584d80 100644 --- a/core/main_terminal_parts/tools_execution.py +++ b/core/main_terminal_parts/tools_execution.py @@ -72,7 +72,12 @@ from modules.memory_manager import MemoryManager from modules.terminal_manager import TerminalManager from modules.todo_manager import TodoManager from modules.sub_agent import SubAgentManager -from modules.webpage_extractor import extract_webpage_content, tavily_extract +from modules.webpage_extractor import ( + extract_single_url, + extract_webpage_content, + resolve_direct_extract_config, + tavily_extract, +) from modules.ocr_client import OCRClient from modules.easter_egg_manager import EasterEggManager from modules.personalization_manager import ( @@ -741,7 +746,9 @@ class MainTerminalToolsExecutionMixin: return visited def _mark_file_read_from_result(self, tool_name: str, arguments: Dict[str, Any], result: Dict[str, Any]) -> None: - if tool_name not in {"read_file", "read_skill"}: + # recall_project_memory 内部即读取记忆文件全文（走 _handle_read_tool）， + # 视为已读，避免后续 edit_file 被要求重复 read_file。 + if tool_name not in {"read_file", "read_skill", "recall_project_memory"}: return if not isinstance(result, dict) or not result.get("success"): return @@ -1768,11 +1775,16 @@ class MainTerminalToolsExecutionMixin: try: # 从config获取API密钥 from config import TAVILY_API_KEY + try: + _prefs = load_personalization_config(self.data_dir) or {} + except Exception: + _prefs = {} full_content, _ = await extract_webpage_content( - urls=url, + urls=url, api_key=TAVILY_API_KEY, extract_depth="basic", - max_urls=1 + max_urls=1, + direct_config=resolve_direct_extract_config(_prefs), ) # 字符数检查 @@ -1815,92 +1827,57 @@ class MainTerminalToolsExecutionMixin: except ImportError: TAVILY_API_KEY = None - if not TAVILY_API_KEY or TAVILY_API_KEY == "your-tavily-api-key": - result = { - "success": False, - "error": tr("tools_exec.tavily_key_missing"), - "url": url, - "path": target_path - } - else: + # 白名单直提优先（无需 Tavily key）；未命中/失败自动回退 Tavily + try: try: - extract_result = await tavily_extract( - urls=url, - api_key=TAVILY_API_KEY, - extract_depth="basic", - max_urls=1 - ) + _prefs = load_personalization_config(self.data_dir) or {} + except Exception: + _prefs = {} + extract_one = await extract_single_url( + url, + TAVILY_API_KEY, + extract_depth="basic", + direct_config=resolve_direct_extract_config(_prefs), + ) - if not extract_result or "error" in extract_result: - error_message = extract_result.get("error", tr("tools_exec.extract_failed_no_content")) if isinstance(extract_result, dict) else tr("tools_exec.extract_failed") + if not extract_one.get("success"): + result = { + "success": False, + "error": extract_one.get("error", tr("tools_exec.extract_failed_no_content")), + "url": url, + "path": target_path + } + else: + content_to_save = extract_one.get("content") or "" + write_result = self.file_manager.write_file(target_path, content_to_save, mode="w") + + if not write_result.get("success"): result = { "success": False, - "error": error_message, + "error": write_result.get("error", tr("tools_exec.write_file_failed")), "url": url, "path": target_path } else: - results_list = extract_result.get("results", []) if isinstance(extract_result, dict) else [] + char_count = len(content_to_save) + byte_size = len(content_to_save.encode("utf-8")) + result = { + "success": True, + "url": url, + "path": write_result.get("path", target_path), + "char_count": char_count, + "byte_size": byte_size, + "extract_method": extract_one.get("method"), + "message": tr("tools_exec.webpage_saved", path=write_result.get('path', target_path)) + } - primary_result = None - for item in results_list: - if item.get("raw_content"): - primary_result = item - break - if primary_result is None and results_list: - primary_result = results_list[0] - - if not primary_result: - failed_list = extract_result.get("failed_results", []) if isinstance(extract_result, dict) else [] - result = { - "success": False, - "error": tr("tools_exec.extract_result_empty"), - "url": url, - "path": target_path, - "failed": failed_list - } - else: - content_to_save = primary_result.get("raw_content") or primary_result.get("content") or "" - - if not content_to_save: - result = { - "success": False, - "error": tr("tools_exec.webpage_content_empty"), - "url": url, - "path": target_path - } - else: - write_result = self.file_manager.write_file(target_path, content_to_save, mode="w") - - if not write_result.get("success"): - result = { - "success": False, - "error": write_result.get("error", tr("tools_exec.write_file_failed")), - "url": url, - "path": target_path - } - else: - char_count = len(content_to_save) - byte_size = len(content_to_save.encode("utf-8")) - result = { - "success": True, - "url": url, - "path": write_result.get("path", target_path), - "char_count": char_count, - "byte_size": byte_size, - "message": tr("tools_exec.webpage_saved", path=write_result.get('path', target_path)) - } - - if isinstance(extract_result, dict) and extract_result.get("failed_results"): - result["warnings"] = extract_result["failed_results"] - - except Exception as e: - result = { - "success": False, - "error": tr("tools_exec.webpage_save_failed", error=str(e)), - "url": url, - "path": target_path - } + except Exception as e: + result = { + "success": False, + "error": tr("tools_exec.webpage_save_failed", error=str(e)), + "url": url, + "path": target_path + } elif tool_name == "run_command": permission_mode = "unrestricted" diff --git a/modules/i18n_messages/modules_misc.py b/modules/i18n_messages/modules_misc.py index b5e94519..e65be358 100644 --- a/modules/i18n_messages/modules_misc.py +++ b/modules/i18n_messages/modules_misc.py @@ -214,6 +214,26 @@ MESSAGES = { "zh-CN": "❌ 未能提取到任何内容", "en-US": "❌ No content could be extracted", }, + "webpage.method_label": { + "zh-CN": "提取方式: {method}", + "en-US": "Extraction method: {method}", + }, + "webpage.method_jsdelivr": { + "zh-CN": "直连 jsDelivr", + "en-US": "Direct jsDelivr", + }, + "webpage.method_github_api": { + "zh-CN": "直连 GitHub API", + "en-US": "Direct GitHub API", + }, + "webpage.method_trafilatura": { + "zh-CN": "直连 trafilatura", + "en-US": "Direct trafilatura", + }, + "webpage.method_tavily": { + "zh-CN": "Tavily", + "en-US": "Tavily", + }, # ── mcp_client_manager（manager.py + http_client.py） ── "mcp.server_not_found": { diff --git a/modules/personalization_manager.py b/modules/personalization_manager.py index d5a68a27..0ab4ba5a 100644 --- a/modules/personalization_manager.py +++ b/modules/personalization_manager.py @@ -3,9 +3,10 @@ from __future__ import annotations import json +import re from copy import deepcopy from pathlib import Path -from typing import Any, Dict, Optional, Union +from typing import Any, Dict, List, Optional, Union try: from config.limits import REASONING_EFFORT_LEVELS @@ -31,6 +32,9 @@ ALLOWED_UI_LOCALES = {"zh-CN", "en-US"} GOAL_MAX_TURNS_MIN = 1 GOAL_MAX_TURNS_MAX = 100 GOAL_MAX_TURNS_DEFAULT = 5 + +# 网页提取直提白名单：用户可追加的域名数量上限 +MAX_DIRECT_EXTRACT_DOMAINS = 50 GOAL_MAX_TOKENS_MIN = 1_000 GOAL_MAX_TOKENS_MAX = 100_000_000 @@ -98,6 +102,10 @@ DEFAULT_PERSONALIZATION_CONFIG: Dict[str, Any] = { # 仅在创建对话时快照一次；已有对话以其对话文件中的快照为准，改这里不影响。 "tool_loading_enabled": True, "tool_loading_deferred": None, + # 网页提取白名单直提：命中白名单的域名用本机直提（GitHub 直链 / trafilatura）， + # 未命中才走 Tavily；开关默认开启，domains 为用户追加的白名单域名（内置 github.com 不在此列）。 + "webpage_direct_extract_enabled": True, + "webpage_direct_extract_domains": [], "default_model": None, "image_compression": "original", # original / 1080p / 720p / 540p "auto_shallow_compress_enabled": False, @@ -754,6 +762,27 @@ def sanitize_personalization_payload( else: base["review_agents"] = _sanitize_review_agents(base.get("review_agents")) + # 网页提取白名单直提：开关（默认开启）+ 用户追加的域名列表 + if "webpage_direct_extract_enabled" in data: + base["webpage_direct_extract_enabled"] = bool(data.get("webpage_direct_extract_enabled")) + else: + base["webpage_direct_extract_enabled"] = bool(base.get("webpage_direct_extract_enabled", True)) + + raw_domains = data.get("webpage_direct_extract_domains", base.get("webpage_direct_extract_domains")) + if not isinstance(raw_domains, list): + raw_domains = [] + clean_domains: List[str] = [] + for item in raw_domains[:MAX_DIRECT_EXTRACT_DOMAINS]: + if not isinstance(item, str): + continue + d = item.strip().lower().strip(".") + if "//" in d: + d = d.split("//", 1)[1] + d = d.split("/")[0].split("?")[0] + if d and re.fullmatch(r"[a-z0-9.-]+", d) and "." in d and d not in clean_domains: + clean_domains.append(d) + base["webpage_direct_extract_domains"] = clean_domains + return base diff --git a/modules/webpage_extractor.py b/modules/webpage_extractor.py index c03cf7d4..7a6f0a8b 100644 --- a/modules/webpage_extractor.py +++ b/modules/webpage_extractor.py @@ -1,24 +1,52 @@ # modules/webpage_extractor.py - 网页内容提取模块 +# +# 提取分两层： +# 1. 白名单域名走本机直提（免费、零配额）：GitHub 代码文件页有专属直链适配 +# （jsDelivr CDN → GitHub API 备用），其余白名单页面用 trafilatura 提取正文。 +# 2. 未命中白名单（或直提失败）回退 Tavily 云端提取。 +# +# trafilatura 为可选依赖：未安装时通用直提静默失效，仅 GitHub 直链仍可用。 + +import base64 +import re +from typing import Any, Dict, List, Optional, Tuple, Union +from urllib.parse import urlparse import httpx -import json -from typing import Dict, Any, List, Union, Tuple -from utils.logger import setup_logger +from utils.logger import setup_logger from modules.i18n import tr logger = setup_logger(__name__) +try: + import trafilatura as _trafilatura +except ImportError: # 可选依赖 + _trafilatura = None + +# 内置直提白名单域名（个人空间可追加；子域名自动匹配） +BUILTIN_DIRECT_EXTRACT_DOMAINS: Tuple[str, ...] = ("github.com",) + +_DIRECT_REQUEST_HEADERS = { + "User-Agent": ( + "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) " + "AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0 Safari/537.36" + ), + "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8", +} +_DIRECT_TIMEOUT = 30 + + async def tavily_extract(urls: Union[str, List[str]], api_key: str, extract_depth: str = "basic", max_urls: int = 1) -> Dict[str, Any]: """ 执行Tavily网页内容提取 - + Args: urls: 要提取的URL（字符串或列表） api_key: Tavily API密钥 extract_depth: 提取深度 (basic/advanced) max_urls: 最大提取URL数量 - + Returns: 提取结果字典 """ @@ -65,10 +93,10 @@ async def tavily_extract(urls: Union[str, List[str]], api_key: str, extract_dept def format_extract_results(results: Dict[str, Any]) -> str: """ 格式化提取结果为简洁版本 - + Args: results: tavily_extract返回的结果 - + Returns: 格式化后的内容字符串 """ @@ -79,12 +107,12 @@ def format_extract_results(results: Dict[str, Any]) -> str: return tr("webpage.no_content") formatted_parts = [] - + # 成功提取的结果 for i, result in enumerate(results["results"], 1): url = result.get("url", "N/A") raw_content = result.get("raw_content", "").strip() - + if raw_content: content_length = len(raw_content) formatted_parts.append(f"🌐 网页内容 ({content_length} 字符):") @@ -104,24 +132,238 @@ def format_extract_results(results: Dict[str, Any]) -> str: return "\n".join(formatted_parts) -async def extract_webpage_content(urls: Union[str, List[str]], api_key: str, extract_depth: str = "basic", max_urls: int = 1) -> Tuple[str, str]: +# ============================================================ +# 白名单直提 +# ============================================================ + +def _normalize_domain(raw: Any) -> str: + """把用户输入规范化为小写裸域名（容忍粘贴完整 URL / 前导点 / 路径）。""" + if not isinstance(raw, str): + return "" + d = raw.strip().lower() + if not d: + return "" + if "://" in d: + d = _url_hostname(d) or d + d = d.split("/")[0].split("?")[0].strip(".") + if not re.fullmatch(r"[a-z0-9.-]+", d or "") or "." not in d: + return "" + return d + + +def _url_hostname(url: str) -> str: + try: + return (urlparse(str(url)).hostname or "").lower() + except Exception: + return "" + + +def resolve_direct_extract_config(personalization: Optional[Dict[str, Any]]) -> Dict[str, Any]: + """从 personalization 配置解析直提设置。 + + Returns: + {"enabled": bool, "domains": [...]} —— domains 已合并内置域名并规范化。 """ - 完整的网页内容提取流程 - + personalization = personalization or {} + enabled = bool(personalization.get("webpage_direct_extract_enabled", True)) + extra = personalization.get("webpage_direct_extract_domains") + if not isinstance(extra, list): + extra = [] + domains: List[str] = [] + for item in list(BUILTIN_DIRECT_EXTRACT_DOMAINS) + extra: + nd = _normalize_domain(item) + if nd and nd not in domains: + domains.append(nd) + return {"enabled": enabled, "domains": domains} + + +def is_whitelisted_url(url: str, domains: List[str]) -> bool: + """域名等于白名单条目或为其子域名即命中。""" + host = _url_hostname(url) + if not host: + return False + return any(host == d or host.endswith("." + d) for d in domains) + + +_GITHUB_BLOB_RE = re.compile( + r"^https?://(?:www\.)?github\.com/([^/?#]+)/([^/?#]+)/blob/([^/?#]+)/([^?#]+?)(?:[?#].*)?$", + re.IGNORECASE, +) + + +def parse_github_blob_url(url: str) -> Optional[Tuple[str, str, str, str]]: + """解析 GitHub blob 页面 URL，返回 (owner, repo, branch, path)；非 blob 页返回 None。 + + 注意：branch 按单段处理（覆盖 main/master 等常见场景）；含斜杠的分支名 + 会解析失败并自然降级到通用提取，不会报错。 + """ + m = _GITHUB_BLOB_RE.match(str(url).strip()) + if not m: + return None + return m.group(1), m.group(2), m.group(3), m.group(4) + + +async def _fetch_jsdelivr_raw(client: httpx.AsyncClient, owner: str, repo: str, branch: str, path: str) -> Optional[str]: + """经 jsDelivr CDN 拿 GitHub 文件原文（免费、无限速，替代被墙的 raw.githubusercontent.com）。""" + cdn_url = f"https://cdn.jsdelivr.net/gh/{owner}/{repo}@{branch}/{path}" + try: + resp = await client.get(cdn_url, timeout=_DIRECT_TIMEOUT) + if resp.status_code == 200 and resp.text: + return resp.text + logger.info(f"jsDelivr 直链返回 {resp.status_code}: {cdn_url}") + except Exception as e: + logger.info(f"jsDelivr 直链失败 {cdn_url}: {e}") + return None + + +async def _fetch_github_api_raw(client: httpx.AsyncClient, owner: str, repo: str, branch: str, path: str) -> Optional[str]: + """经 GitHub 官方 contents API 拿文件原文（备用；匿名限 60 次/小时，>1MB 文件不返回内容）。""" + api_url = f"https://api.github.com/repos/{owner}/{repo}/contents/{path}?ref={branch}" + try: + resp = await client.get(api_url, headers={"Accept": "application/vnd.github+json"}, timeout=_DIRECT_TIMEOUT) + if resp.status_code != 200: + logger.info(f"GitHub API 返回 {resp.status_code}: {api_url}") + return None + data = resp.json() + if isinstance(data, dict) and data.get("encoding") == "base64" and data.get("content"): + return base64.b64decode(data["content"]).decode("utf-8", errors="replace") + except Exception as e: + logger.info(f"GitHub API 失败 {api_url}: {e}") + return None + + +def _trafilatura_extract(html: str, url: str) -> Optional[str]: + """trafilatura 通用正文提取（markdown 输出，保留标题/代码块结构）。""" + if _trafilatura is None: + return None + try: + text = _trafilatura.extract( + html, + url=url, + output_format="markdown", + include_links=False, + include_images=False, + ) + if text and text.strip(): + return text.strip() + except Exception as e: + logger.info(f"trafilatura 提取失败 {url}: {e}") + return None + + +async def _direct_extract(client: httpx.AsyncClient, url: str) -> Tuple[Optional[str], str]: + """白名单直提主流程。返回 (内容, method)；全部失败返回 (None, "")。""" + blob = parse_github_blob_url(url) + if blob: + owner, repo, branch, path = blob + content = await _fetch_jsdelivr_raw(client, owner, repo, branch, path) + if content is not None: + return content, "jsdelivr" + content = await _fetch_github_api_raw(client, owner, repo, branch, path) + if content is not None: + return content, "github_api" + # 直链均失败 → 继续走通用提取兜底 + + if _trafilatura is not None: + try: + resp = await client.get(url, timeout=_DIRECT_TIMEOUT) + if resp.status_code == 200 and resp.text: + text = _trafilatura_extract(resp.text, url) + if text: + return text, "trafilatura" + else: + logger.info(f"直提抓取返回 {resp.status_code}: {url}") + except Exception as e: + logger.info(f"直提抓取失败 {url}: {e}") + return None, "" + + +def _format_single_result(url: str, content: str, method: Optional[str] = None) -> str: + """格式化单条提取结果（沿用 🌐 骨架，附提取方式标注）。""" + header = f"🌐 网页内容 ({len(content)} 字符)" + if method: + header += f" [{tr('webpage.method_label', method=tr(f'webpage.method_{method}'))}]" + return "\n".join([ + header + ":", + f"📍 URL: {url}", + "=" * 50, + content, + "=" * 50, + ]) + + +async def extract_single_url( + url: str, + api_key: Optional[str], + extract_depth: str = "basic", + direct_config: Optional[Dict[str, Any]] = None, +) -> Dict[str, Any]: + """统一单 URL 提取：白名单直提优先，失败/未命中回退 Tavily。 + + Args: + url: 目标 URL + api_key: Tavily API 密钥（可为 None；直提命中时不需要） + extract_depth: Tavily 提取深度 + direct_config: resolve_direct_extract_config() 的返回；None 视为关闭直提 + + Returns: + {"success": bool, "url": str, "content": str, "method": str} 或 + {"success": False, "url": str, "error": str, "method": str} + """ + direct_config = direct_config or {} + + if direct_config.get("enabled") and is_whitelisted_url(url, direct_config.get("domains") or []): + content, method = None, "" + try: + async with httpx.AsyncClient(headers=_DIRECT_REQUEST_HEADERS, follow_redirects=True) as client: + content, method = await _direct_extract(client, url) + except Exception as e: + logger.info(f"白名单直提异常 {url}: {e}") + if content is not None: + return {"success": True, "url": url, "content": content, "method": method} + logger.info(f"白名单直提未取到内容，回退 Tavily: {url}") + + results = await tavily_extract(url, api_key, extract_depth, 1) + if "error" in results: + return {"success": False, "url": url, "error": results["error"], "method": "tavily"} + for item in results.get("results") or []: + raw = (item.get("raw_content") or "").strip() + if raw: + return {"success": True, "url": url, "content": raw, "method": "tavily"} + return {"success": False, "url": url, "error": tr("webpage.no_content"), "method": "tavily"} + + +async def extract_webpage_content( + urls: Union[str, List[str]], + api_key: str, + extract_depth: str = "basic", + max_urls: int = 1, + direct_config: Optional[Dict[str, Any]] = None, +) -> Tuple[str, str]: + """ + 完整的网页内容提取流程（白名单直提优先，Tavily 兜底） + Args: urls: 要提取的URL（字符串或列表） api_key: Tavily API密钥 extract_depth: 提取深度 (basic/advanced) max_urls: 最大提取URL数量 - + direct_config: 直提配置（resolve_direct_extract_config 返回）；None=关闭直提 + Returns: (完整内容, 完整内容) - 为了兼容性返回相同内容两份 """ - # 执行提取 - results = await tavily_extract(urls, api_key, extract_depth, max_urls) - - # 格式化结果 - formatted_content = format_extract_results(results) - - # 返回相同内容（简化版本，不需要长短版本区分） - return formatted_content, formatted_content \ No newline at end of file + if isinstance(urls, str): + urls = [urls] + urls = urls[:max_urls] + + formatted_parts: List[str] = [] + for url in urls: + result = await extract_single_url(url, api_key, extract_depth=extract_depth, direct_config=direct_config) + if result.get("success"): + formatted_parts.append(_format_single_result(url, result["content"], result.get("method"))) + else: + formatted_parts.append(tr("webpage.format_failed", error=result.get("error"))) + + formatted_content = "\n".join(formatted_parts) + return formatted_content, formatted_content diff --git a/requirements.txt b/requirements.txt index 3fe979da..dada09b0 100644 --- a/requirements.txt +++ b/requirements.txt @@ -8,3 +8,6 @@ openai cryptography pillow pyyaml>=6.0 +# 网页白名单直提的正文识别引擎（可选依赖：import 失败时代码自动降级为全走 Tavily， +# 但正式部署应装上，否则直提白名单只剩 GitHub 直链可用） +trafilatura diff --git a/static/src/components/personalization/styles/settings-shared.css b/static/src/components/personalization/styles/settings-shared.css index 1f0a2638..bacb44d4 100644 --- a/static/src/components/personalization/styles/settings-shared.css +++ b/static/src/components/personalization/styles/settings-shared.css @@ -561,6 +561,65 @@ body[data-theme='dark'] .settings-floating-menu { gap: 8px; } +/* 直提白名单域名列表：分隔线区分行，不套圆角卡片 */ +.settings-domain-list { + display: flex; + flex-direction: column; + margin: 4px 0 10px; +} + +.settings-domain-row { + display: flex; + align-items: center; + justify-content: space-between; + gap: 8px; + height: 36px; + padding: 0 2px; + border-bottom: 1px solid var(--theme-control-border); +} + +.settings-domain-row:last-child { + border-bottom: none; +} + +.settings-domain-row .settings-row-title { + min-width: 0; + overflow: hidden; + text-overflow: ellipsis; + white-space: nowrap; +} + +.settings-domain-badge { + flex: none; + display: inline-flex; + align-items: center; + height: 28px; /* 与 .settings-domain-remove 同高同居中机制，保证文字视觉对齐 */ + margin-right: 10px; /* 抵消删除按钮的水平 padding，使两者文字右缘对齐 */ + font-size: 12px; + line-height: 1; + color: var(--text-secondary); +} + +.settings-domain-remove { + flex: none; + height: 28px; + padding: 0 10px; + border: none; + border-radius: 6px; + background: transparent; + color: var(--text-secondary); + font-size: 12px; + line-height: 1; + cursor: pointer; +} + +@media (hover: hover) { + .settings-domain-remove:hover { + background: var(--hover-bg); + color: var(--state-warning); + } +} + .settings-add-row input, .settings-number-row input { min-width: 0; diff --git a/static/src/components/personalization/tabs/ToolsTab.vue b/static/src/components/personalization/tabs/ToolsTab.vue index 2d0bd031..0d35dd18 100644 --- a/static/src/components/personalization/tabs/ToolsTab.vue +++ b/static/src/components/personalization/tabs/ToolsTab.vue @@ -1,5 +1,5 @@