dsh-plugin-playwright
适用于 DeepSeek Harness 的 Playwright 浏览器自动化工具
插件会安装到这里；不确定时保持 web。
npx -y @deepseek-ai/dsh plugin --profile web add dsh-plugin-playwright@0.2.0Plugin Playwright 以 dsh-plugin-playwright 发布，当前版本为 0.2.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。
点击下方 Badge 复制 Markdown，粘贴到 README 即可。
验证 package.json 声明的 GitHub 仓库，即可管理这个公开页面。认领后，Hub 会优先安排当前版本的安全扫描，并在通过后公开展示结果。
认领这个 Plugin →Playwright browser automation tools for DeepSeek Harness.
This plugin registers the browser_* tool family on the Harness tool registry, launching a real Chromium/Firefox/WebKit browser so an agent can navigate pages, interact with elements, read the accessibility tree, capture files, and manage a session — all through structured tool calls.
Design note: this codebase is written as an independent DSH plugin, organized by user intent (navigate / interact / inspect / control / capture / power) rather than by a generic Playwright port. It builds on the browser automation concepts popularised by the wider Playwright tooling ecosystem.
Add the plugin to a DSH profile and activate it:
# Add the plugin to the `web` profile (dsh plugin forwards to pnpm in the profile dir)
dsh plugin --profile web add dsh-plugin-playwright
Because the browser is a peer of your machine UI, you need a real browser engine. Playwright downloads its own managed builds on first launch (npx playwright install chromium); alternatively set executablePath to a pre-installed browser (see Configuration).
After activation, an agent can drive a page like this:
browser_snapshot returns the accessibility tree with numeric refs.browser_navigate { "url": "https://example.com" }.browser_click { "ref": 4 } or browser_type { "selector": "#q", "text": "hello" }.browser_console_messages / browser_network_requests.browser_screenshot saves a PNG under the output directory.The browser is launched lazily on the first tool call and closed when the plugin fiber disposes.
Configuration is declared via the schema in src/config.ts. The shipped defaults (in cordis.patch.yml) are headless and horizontally-scoped. The meaningful knobs:
| Field | Default | Meaning |
|---|---|---|
browser | chromium | Engine: firefox / webkit / msedge (msedge ⇒ chromium + msedge channel) |
headless | true | No visible window |
executablePath | — | Launch this browser binary instead of Playwright's managed build; overrides channel |
userDataDir | — | Persistent profile dir (chromium/msedge only); cookies/localStorage survive restarts |
isolated | false | If true, every tool call gets a fresh context closed at call end (no state between calls) |
viewport | 1280×720 | Initial viewport |
device / locale / timezoneId / colorScheme | — | Device descriptor, locale, IANA timezone, color scheme |
outputDir | .dsh/playwright | Where screenshots / PDFs / traces are written |
timeoutMs | 30000 | Default per-action timeout |
navigationWaitUntil | load | Default wait condition for navigation |
capabilities | see below | Per-capability toggles |
evaluate | false | Enables the browser_evaluate escape hatch (off by default) |
Gate whole tools or strip data from results:
capabilities:
accessibility: true # attach a snapshot to state-bearing results
screenshot: true # register browser_screenshot
pdf: true # register browser_pdf (chromium/msedge)
network: true # register browser_network_requests + capture network
tracing: false # register browser_tracing_start/stop
storageState: false # register browser_storage_state + browser_init_script
Tools are organized into behaviour modules (see Architecture). All tool names, parameters and outputs are stable contracts.
| Tool | What it does |
|---|---|
browser_navigate | Load a URL and wait; returns URL + title + snapshot |
browser_back / browser_forward | History navigation |
browser_reload | Reload the active page |
browser_wait_for | Wait for a CSS selector to reach a state |
| Tool | What it does |
|---|---|
browser_click | Click by element ref or CSS selector (supports button/modifiers/count) |
browser_type | Fill an input/textarea (clear-by-default), or type without clearing |
browser_type_submit | Type then press Enter (forms, search boxes) |
browser_select_option | Select <select> options by value/label |
browser_hover / browser_focus | Hover / focus an element |
browser_press_key | Press a key or shortcut on an element or the page |
browser_drag | Drag one element onto another |
browser_upload_file | Set files on an <input type=file> |
| Tool | What it does |
|---|---|
browser_snapshot | Accessibility tree with numeric refs for interactive elements |
browser_console_messages | Captured console messages (ring buffer) |
browser_network_requests | Captured request/response entries, filterable by URL/method/status |
| Tool | What it does |
|---|---|
browser_tab_new / browser_tab_switch / browser_tab_close / browser_tab_list | Tab lifecycle |
browser_resize | Resize the active viewport |
browser_init_script (capability) | Register a script that runs on every future page load |
browser_storage_state (capability) | Return cookies + localStorage of the shared context |
| Tool | What it does |
|---|---|
browser_screenshot (capability) | Save a screenshot under the output directory |
browser_pdf (capability) | Print to PDF (chromium/msedge) |
browser_tracing_start / browser_tracing_stop (capability) | Start/stop capture and write a trace zip |
| Tool | What it does |
|---|---|
browser_evaluate (config evaluate) | Evaluate arbitrary JS in the page (reads and writes; disabled by default) |
src/
├── index.ts Assembly: register tools + own the browser lifecycle
├── config.ts Configuration schema + defaults
├── browser.ts BrowserSession, CallHandle, withAbort (lazy start, shared/isolated)
├── snapshot.ts ariaSnapshot → JSON tree + ref→locator map
└── tools/
├── schema.ts Shared value contracts (state / tab / file results)
├── util.ts Cross-cutting helpers (pageState, resolveLocator, abortable, …)
├── factory.ts createTools(session, config) — assembles all behaviour modules
├── navigation.ts / interact.ts / inspect.ts / control.ts / capture.ts / power.ts
└── ... each module owns one behaviour group (see catalog above)
Every tool configures an execute(body) that runs through session.run, which resolves a CallHandle — the shared persistent context by default, or a throwaway per-call context in isolated mode. Cancellation (AbortSignal) is bridged into Playwright operations via withAbort.
pnpm install # install dependencies
pnpm typecheck # run tsc over src + test
pnpm smoke # mount the plugin and drive a real headless chromium
See AGENTS.md for the maintainer's map of the codebase and the convention for adding tools.
This plugin is an independent DSH implementation. Notable design choices:
isolated gives per-call transparency. Shared state survives between calls by default.render projection, validated against the harness's lossless-JSON rules.browser_evaluate gated. The arbitrary-JS escape hatch is off unless you explicitly opt in.