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/capability/types.ts

@@ -18,6 +18,11 @@ export interface InvokeContext extends CapabilityContext {
   /** agent 调用时的 tool call id / invocation id,用于审计对账 */
   invocationId?: string;
   agentRunId?: string;
+  /**
+   * 本次调用的结果会不会以图片交给模型(Agent 调用时 = 上游模型支持图片输入)。
+   * false:能力不要产出图片(browser.screenshot 改给文字快照);undefined:非 Agent 调用方,按能力缺省。
+   */
+  modelImages?: boolean;
 }
 
 /** handler 实际收到的上下文:注册中心补上服务端生成的幂等键与授权结果 */