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/agent/src/runtime/port.ts

@@ -95,6 +95,8 @@ export interface AgentRunHandle {
   readonly sessionPath: string;
   /** 打开已有会话时发现的未完成操作数;>0 时应调用 resume() */
   readonly pendingOperations: number;
+  /** 上游模型支持图片输入(视觉自动化需要);fake 模型按创建参数 */
+  readonly supportsImages?: boolean;
   /** 从 fromSeq(含)开始回放并持续推送事件;close() 后结束 */
   events(fromSeq?: number): AsyncIterable<AgentRunEvent>;
   /** 本进程已产生的全部事件快照 */