feat: 浏览器扩展支持交互式页面操作 (browser_act)

在原有只读抓取 (browser_fetch_page) 基础上,新增 observe→act 循环,
让 Agent 能在用户的 Chrome 中实际操作网页:点击/输入/滚动/等待/页内跳转。

后端:
- 新工具 browser_act,按 session 复用标签页,返回带编号的可交互元素清单+正文
- browser_context 任务队列扩展 kind/session_id/action 与 observation 结果
- /api/browser-context 路由下发 act 任务、接收 observation
- BrowserContextConfig 增加 actions_enabled 等开关,tools.py 两级门控
- 接线 app.py 路由挂载、app_config.py 配置字段、config.yaml 工具注册

前端:
- ChatPage 处理「发送当前页」回跳的 browser_context query 参数并自动提交

扩展 (browser-extension/deer-web-clipper):
- shared.js 自包含注入函数 deerObservePage / deerPerformAction
- background.js 按 kind 分发任务,session→tab 映射存 chrome.storage.session

测试:tests/test_browser_act.py(队列往返 + 工具校验 + 模拟扩展成功路径,8 passed)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
AdministratorandClaude Opus 4.8 committed 2026-06-08 13:47:00 +08:00
1 parent 0001f86826
commit d4a71ce384
24 files changed
+4499 -162

No files matched your search

@@ -0,0 +1,148 @@
const textFields = [
"apiBaseUrl",
"webBaseUrl",
"accessToken",
"defaultPrompt",
"workerId",
"taskPollIntervalSeconds",
"taskPageLoadTimeoutSeconds",
];
const checkboxFields = [
"autoDiscoverServiceUrl",
"tokenSyncEnabled",
"pageAssistantEnabled",
"taskPollingEnabled",
"closeTaskTabs",
];
function formatServiceStatus(settings) {
if (!settings.lastServiceSyncAt) {
return `当前服务地址:${settings.webBaseUrl || DEER_CLIPPER_DEFAULTS.webBaseUrl};API:${settings.apiBaseUrl || DEER_CLIPPER_DEFAULTS.apiBaseUrl}`;
}
return `当前服务地址:${settings.webBaseUrl || ""};API:${settings.apiBaseUrl || ""}\n上次识别:${settings.lastServiceSyncAt}(${settings.lastServiceSyncSource || "unknown source"})`;
}
function formatTokenStatus(settings) {
if (!settings.lastTokenSyncAt) {
return "Token 尚未自动同步。";
}
return `上次 token 同步:${settings.lastTokenSyncAt}(${settings.lastTokenSyncSource || "unknown source"})`;
}
async function loadSettings() {
const settings = await chrome.storage.sync.get(DEER_CLIPPER_DEFAULTS);
if (!settings.workerId) {
settings.workerId = deerMakeWorkerId();
await chrome.storage.sync.set({ workerId: settings.workerId });
}
document.getElementById("apiBaseUrl").placeholder =
DEER_CLIPPER_DEFAULTS.apiBaseUrl || "在 config.js 中配置默认 API 地址";
document.getElementById("webBaseUrl").placeholder =
DEER_CLIPPER_DEFAULTS.webBaseUrl || "在 config.js 中配置默认前端地址";
for (const field of textFields) {
document.getElementById(field).value = settings[field] ?? "";
}
for (const field of checkboxFields) {
document.getElementById(field).checked = Boolean(settings[field]);
}
document.getElementById("serviceStatus").textContent = formatServiceStatus(settings);
document.getElementById("tokenStatus").textContent = formatTokenStatus(settings);
}
async function saveSettings() {
const next = {};
for (const field of textFields) {
next[field] = document.getElementById(field).value.trim();
}
for (const field of checkboxFields) {
next[field] = document.getElementById(field).checked;
}
next.apiBaseUrl = deerNormalizeBaseUrl(next.apiBaseUrl || DEER_CLIPPER_DEFAULTS.apiBaseUrl);
next.webBaseUrl = deerNormalizeBaseUrl(next.webBaseUrl || DEER_CLIPPER_DEFAULTS.webBaseUrl);
next.defaultPrompt = next.defaultPrompt || DEER_CLIPPER_DEFAULT_PROMPT;
next.workerId = next.workerId || deerMakeWorkerId();
next.taskPollIntervalSeconds = Math.max(3, Number(next.taskPollIntervalSeconds || DEER_CLIPPER_DEFAULTS.taskPollIntervalSeconds));
next.taskPageLoadTimeoutSeconds = Math.max(5, Number(next.taskPageLoadTimeoutSeconds || DEER_CLIPPER_DEFAULTS.taskPageLoadTimeoutSeconds));
await chrome.storage.sync.set(next);
const settings = await chrome.storage.sync.get(DEER_CLIPPER_DEFAULTS);
document.getElementById("status").textContent = "已保存。";
document.getElementById("serviceStatus").textContent = formatServiceStatus(settings);
document.getElementById("tokenStatus").textContent = formatTokenStatus(settings);
}
function sendDiscoverServiceMessage() {
return new Promise((resolve, reject) => {
chrome.runtime.sendMessage({ type: "zncm-discover-service" }, (response) => {
const error = chrome.runtime.lastError;
if (error) {
reject(new Error(error.message));
return;
}
resolve(response || { ok: false, message: "服务地址识别没有返回结果。" });
});
});
}
function sendSyncTokenMessage() {
return new Promise((resolve, reject) => {
chrome.runtime.sendMessage({ type: "zncm-sync-token" }, (response) => {
const error = chrome.runtime.lastError;
if (error) {
reject(new Error(error.message));
return;
}
resolve(response || { ok: false, message: "Token 同步没有返回结果。" });
});
});
}
async function discoverServiceNow() {
const button = document.getElementById("discoverService");
button.disabled = true;
document.getElementById("serviceStatus").textContent = "正在识别服务地址...";
try {
await chrome.storage.sync.set({
autoDiscoverServiceUrl: document.getElementById("autoDiscoverServiceUrl").checked,
apiBaseUrl: deerNormalizeBaseUrl(document.getElementById("apiBaseUrl").value || DEER_CLIPPER_DEFAULTS.apiBaseUrl),
webBaseUrl: deerNormalizeBaseUrl(document.getElementById("webBaseUrl").value || DEER_CLIPPER_DEFAULTS.webBaseUrl),
});
const response = await sendDiscoverServiceMessage();
const settings = await chrome.storage.sync.get(DEER_CLIPPER_DEFAULTS);
document.getElementById("apiBaseUrl").value = settings.apiBaseUrl || "";
document.getElementById("webBaseUrl").value = settings.webBaseUrl || "";
document.getElementById("serviceStatus").textContent = response.message || formatServiceStatus(settings);
} catch (error) {
document.getElementById("serviceStatus").textContent = error instanceof Error ? error.message : "服务地址识别失败。";
} finally {
button.disabled = false;
}
}
async function syncTokenNow() {
const button = document.getElementById("syncToken");
button.disabled = true;
document.getElementById("tokenStatus").textContent = "正在同步 zncm token...";
try {
await chrome.storage.sync.set({
tokenSyncEnabled: document.getElementById("tokenSyncEnabled").checked,
apiBaseUrl: deerNormalizeBaseUrl(document.getElementById("apiBaseUrl").value || DEER_CLIPPER_DEFAULTS.apiBaseUrl),
webBaseUrl: deerNormalizeBaseUrl(document.getElementById("webBaseUrl").value || DEER_CLIPPER_DEFAULTS.webBaseUrl),
});
const response = await sendSyncTokenMessage();
const settings = await chrome.storage.sync.get(DEER_CLIPPER_DEFAULTS);
document.getElementById("accessToken").value = settings.accessToken || "";
document.getElementById("apiBaseUrl").value = settings.apiBaseUrl || "";
document.getElementById("webBaseUrl").value = settings.webBaseUrl || "";
document.getElementById("serviceStatus").textContent = formatServiceStatus(settings);
document.getElementById("tokenStatus").textContent = response.message || formatTokenStatus(settings);
} catch (error) {
document.getElementById("tokenStatus").textContent = error instanceof Error ? error.message : "Token 同步失败。";
} finally {
button.disabled = false;
}
}
document.getElementById("save").addEventListener("click", saveSettings);
document.getElementById("discoverService").addEventListener("click", discoverServiceNow);
document.getElementById("syncToken").addEventListener("click", syncTokenNow);
void loadSettings();