feat(browser): vision automation loop with screenshots, coordinate actions and bounded challenge solving

- browser.screenshot returns the page as an image content block (≤1280px wide, JPEG quality
  configurable) for vision-capable upstreams; non-vision upstreams get a redacted text snapshot.
  Login pages / password fields are marked sensitive and withheld unless a
  browser.sensitive_screenshot grant exists and allowSensitive is passed.
- browser.click_at / type_at / scroll / wait act in screenshot pixels; the server converts via
  viewport/DPR, requires automation control and an allowlisted host, and writes a thumbnail
  evidence file (DATA_DIR/tmp/evidence) referenced from agent_run_event.
- browser.solve_challenge runs a bounded child agent_run (vision caps only, maxSteps ≤ 12,
  budget), judges success from page facts, stops immediately on 2FA / SMS / device confirmation,
  and otherwise moves the session to waiting with evidence and a takeover link.
- PiAgentRuntime passes modelImage outputs as pi-ai image content when model.input has image;
  the ledger never stores image data; coordinate actions use per-invocation idempotency keys.
- Tests: image codec, runtime image content, E14 e2e (login solved, 2FA stop, step limit,
  sensitive withheld). Real camofox 1.17.0 check on example.com recorded in the runbook.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

packages/adapters/src/browser/provider.ts

@@ -60,6 +60,21 @@ export interface BrowserProvider {
   sessionInfo(sessionId: string): BrowserSessionInfo | null;
   /** 等待进行中的操作收尾(接管前调用) */
   drain(sessionId: string): Promise<void>;
+  /**
+   * 页面度量(VIS-1 坐标换算与敏感判定):视口 CSS 尺寸、DPR、是否有密码框、页面文字样本(只在服务端判定用,不外传)。
+   * 只读,不要求自动化控制权;上游不支持 evaluate 时返回 null。
+   */
+  pageMetrics(ref: TabRef): Promise<PageMetrics | null>;
+}
+
+export interface PageMetrics {
+  viewportWidth: number;
+  viewportHeight: number;
+  devicePixelRatio: number;
+  /** 页面上有 input[type=password] */
+  passwordField: boolean;
+  /** document.body.innerText 前 4000 字(判定二次验证等,不进模型、不落日志) */
+  textSample: string;
 }
 
 /** 动作发起方:自动化(Agent/任务)或持有接管租约的人 */