Files
UHD_Media_Tool/apps/web
rootandClaude Opus 5.5 c437c6bff6 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]>
2026-09-29 01:27:48 +08:00
..

@umt/web

React Router 7 SPA 控制台(ssr:false),沿用 uhd_web 设计系统(token 见 app/app.css,规范见 docs/design/)。只通过 /api/v1 与 server 通信,请求/响应类型一律来自 @umt/contracts,不手写重复 DTO。开发端口 5180,/api 代理到 http://localhost:4380。

命令

在仓库根目录执行:

  • deno task dev:web:开发服务器(5180)。
  • cd apps/web && deno task build:生产构建到 build/client,由 server 的 WEB_ROOT 同端口托管。
  • cd apps/web && deno task test:单测(app/**/*.test.ts)。
  • deno task test:web:smoke:Playwright 全页面冒烟,前提与环境变量见仓库 README。
  • deno task check:tokens:设计 token 守卫。

目录

  • app/routes/:页面(routes.ts 登记全部路由);app/routes/console/ 为控制台。
  • app/api/:按资源分的 react-query hook,路径与 schema 取 @umt/contracts 的 Api 注册表。
  • app/components/:业务组件与 ui/ 基础组件。
  • Agent 页的 ?mock=1 演示模式只在开发构建或后端 pi.provider = "fake" 时生效,生产构建连真实模型时忽略。