dsh-browser-playwright-codex 0.6.5 → 0.7.0

package/lib/tool.js

@@ -21,6 +21,7 @@ export const Config = z.object({
     allowEvaluate: z.boolean().default(false),
     allowCdp: z.boolean().default(false),
     registerDisabledTools: z.boolean().default(false),
+    diagnostics: z.boolean().default(false),
     maxWaitMs: z.number().default(60000),
     interactiveOnlyDefault: z.boolean().default(false),
     extract: z.object({
@@ -50,6 +51,7 @@ export function apply(ctx, config) {
         allowEvaluate: config.allowEvaluate,
         allowCdp: config.allowCdp,
         extractConfigured: config.extract?.provider !== undefined && config.extract?.model !== undefined,
+        diagnostics: config.diagnostics,
         registerDisabledTools: config.registerDisabledTools,
     };
     const registered = new Set(registeredSuffixes(surface));
@@ -262,6 +264,8 @@ export function apply(ctx, config) {
         description: 'Replace the value of the input or select referenced by the latest snapshot. ' +
             '`value` is accepted as an alias of `text`. ' +
             'For <select> elements the text selects the matching option label. ' +
+            'Credential fields (password, one-time code, card number) are refused with CREDENTIAL_FIELD: ' +
+            'a human types secrets in the visible window, so ask them and re-snapshot instead. ' +
             'IRON RULE: after filling, verify in the returned snapshot that the field actually holds the value. ' +
             'Frameworks can silently reject or transform input (controlled components, contenteditable editors, ' +
             'input-mask/currency fields). If the value is wrong or missing, do NOT blindly re-fill or append — ' +
@@ -584,58 +588,62 @@ export function apply(ctx, config) {
             return (await session.cdp(args.method, args.params ?? {}, exec.signal));
         },
     }));
-    ctx.tools.register(defineTool({
-        name: p('console_messages'),
-        description: 'Return recent console messages and uncaught page errors from the tab this session is driving, newest last. ' +
-            'Use it right after an action that reported success but produced no visible change: a thrown page error or a failed ' +
-            'subresource is the usual reason a click or fill did not take effect. Read-only observation, it never acts on the page. ' +
-            'Capture starts when this session first drives a tab, so an empty list on a fresh tab is normal. ' +
-            'In persistent mode all sessions share one window, so entries describe that shared page.',
-        parameters: {
-            level: {
-                type: 'string',
-                description: "Filter by level: 'all' (default), 'error' (errors + uncaught page errors), 'warning', 'info', 'log', 'debug'.",
+    if (config.diagnostics || config.registerDisabledTools) {
+        ctx.tools.register(defineTool({
+            name: p('console_messages'),
+            description: 'Return recent console messages and uncaught page errors from the tab this session is driving, newest last. ' +
+                'Use it right after an action that reported success but produced no visible change: a thrown page error or a failed ' +
+                'subresource is the usual reason a click or fill did not take effect. Read-only observation, it never acts on the page. ' +
+                'Capture starts when this session first drives a tab, so an empty list on a fresh tab is normal. ' +
+                'In persistent mode all sessions share one window, so entries describe that shared page.',
+            parameters: {
+                level: {
+                    type: 'string',
+                    description: "Filter by level: 'all' (default), 'error' (errors + uncaught page errors), 'warning', 'info', 'log', 'debug'.",
+                },
+                limit: { type: 'number', description: 'Max entries to return, newest last. Default 50, cap 200.' },
             },
-            limit: { type: 'number', description: 'Max entries to return, newest last. Default 50, cap 200.' },
-        },
-        output: {
-            schema: { type: 'json' },
-            render: (_args, value) => [
-                { type: 'text', text: renderDiagnostics('console', value) },
-            ],
-        },
-        async execute(args, exec) {
-            const session = await acquire(exec);
-            // The canonical value is a wire value; the framework types tool outputs as JSON.
-            return session.consoleMessages(args ?? {});
-        },
-    }));
-    ctx.tools.register(defineTool({
-        name: p('network_requests'),
-        description: 'Return recent network requests from the tab this session is driving, newest last: method, URL, status, ' +
-            'resource type, duration, and the failure text for requests that never completed. Use it to tell "the page did not ' +
-            'react" apart from "the request behind it failed", and to find the API call an action triggered. ' +
-            'Read-only; response bodies are not captured. In persistent mode all sessions share one window, so entries describe that shared page.',
-        parameters: {
-            urlContains: {
-                type: 'string',
-                description: 'Only return requests whose URL contains this substring (case-insensitive).',
+            output: {
+                schema: { type: 'json' },
+                render: (_args, value) => [
+                    { type: 'text', text: renderDiagnostics('console', value) },
+                ],
             },
-            failedOnly: { type: 'boolean', description: 'Only return requests that failed or returned status >= 400.' },
-            limit: { type: 'number', description: 'Max entries to return, newest last. Default 50, cap 200.' },
-        },
-        output: {
-            schema: { type: 'json' },
-            render: (_args, value) => [
-                { type: 'text', text: renderDiagnostics('network', value) },
-            ],
-        },
-        async execute(args, exec) {
-            const session = await acquire(exec);
-            // The canonical value is a wire value; the framework types tool outputs as JSON.
-            return session.networkRequests(args ?? {});
-        },
-    }));
+            async execute(args, exec) {
+                const session = await acquire(exec);
+                // The canonical value is a wire value; the framework types tool outputs as JSON.
+                return session.consoleMessages(args ?? {});
+            },
+        }));
+    }
+    if (config.diagnostics || config.registerDisabledTools) {
+        ctx.tools.register(defineTool({
+            name: p('network_requests'),
+            description: 'Return recent network requests from the tab this session is driving, newest last: method, URL, status, ' +
+                'resource type, duration, and the failure text for requests that never completed. Use it to tell "the page did not ' +
+                'react" apart from "the request behind it failed", and to find the API call an action triggered. ' +
+                'Read-only; response bodies are not captured. In persistent mode all sessions share one window, so entries describe that shared page.',
+            parameters: {
+                urlContains: {
+                    type: 'string',
+                    description: 'Only return requests whose URL contains this substring (case-insensitive).',
+                },
+                failedOnly: { type: 'boolean', description: 'Only return requests that failed or returned status >= 400.' },
+                limit: { type: 'number', description: 'Max entries to return, newest last. Default 50, cap 200.' },
+            },
+            output: {
+                schema: { type: 'json' },
+                render: (_args, value) => [
+                    { type: 'text', text: renderDiagnostics('network', value) },
+                ],
+            },
+            async execute(args, exec) {
+                const session = await acquire(exec);
+                // The canonical value is a wire value; the framework types tool outputs as JSON.
+                return session.networkRequests(args ?? {});
+            },
+        }));
+    }
     ctx.tools.register(defineTool({
         name: p('close'),
         description: "Release this session's browser window. Persistent mode shares one window, so it closes only when the last session releases it; the profile keeps login state either way, so the next browser call reopens it still signed in (reset the profile to clear cookies).",

package/locale/en.json

@@ -1,6 +1,6 @@
 {
   "meta": {
     "title": "Browser Automation",
-    "description": "Playwright-powered browser capability for DeepSeek Harness: accessibility-snapshot interaction with stable element refs, session-scoped browser sessions, screenshots as attachments."
+    "description": "Playwright-powered browser capability for DeepSeek Harness: accessibility-snapshot interaction with stable element refs, session-scoped browser sessions, screenshots as attachments — with the Settings card (on/off, page-reading mode, capability gates, signed-in sites) built in."
   }
 }

package/locale/zh.json

@@ -1,6 +1,6 @@
 {
   "meta": {
     "title": "浏览器自动化",
-    "description": "浏览器自动化（Playwright）：无障碍快照交互 + 稳定元素引用、会话级浏览器实例、截图作为附件。"
+    "description": "浏览器自动化（Playwright）：无障碍快照交互 + 稳定元素引用 + 会话级浏览器实例 + 截图附件；自带设置卡（总开关 / 页面识别方式 / 强力工具闸门 / 已登录站点名单）。"
   }
 }

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "dsh-browser-playwright-codex",
-  "version": "0.6.5",
-  "description": "Browser automation for DeepSeek Harness: fill in forms, scrape lists and work across tabs in real pages, using the logins you already have. Runs in a visible window that stays quiet when minimised, and stops for sign-ins, CAPTCHAs and native dialogs instead of confirming for you.",
+  "version": "0.7.0",
+  "description": "Browser automation for DeepSeek Harness, one plugin: fill in forms, scrape lists and work across tabs in real pages, using the logins you already have. Runs in a visible window that stays quiet when minimised; native dialogs are parked instead of confirmed, CAPTCHA pages are flagged with a note that says stop and hand the page back, password / one-time-code / card fields are refused by browser_fill, and the Settings card (enable/disable, page-reading mode, capability gates) now lives inside this package.",
   "license": "MIT",
   "type": "module",
   "main": "lib/index.js",
@@ -28,7 +28,14 @@
     },
     "./cordis.patch.yml": "./cordis.patch.yml",
     "./package.json": "./package.json",
-    "./locale/*.json": "./locale/*.json"
+    "./locale/*.json": "./locale/*.json",
+    "./client": {
+      "default": "./lib/client.js"
+    },
+    "./plugin": {
+      "types": "./lib/plugin.d.ts",
+      "default": "./lib/plugin.js"
+    }
   },
   "files": [
     "lib",
@@ -42,7 +49,7 @@
     "scripts/dsh-browser-verify.mjs"
   ],
   "scripts": {
-    "build": "node node_modules/typescript/bin/tsc -p tsconfig.json",
+    "build": "node node_modules/typescript/bin/tsc -p tsconfig.json && node scripts/build-client.mjs",
     "typecheck": "node node_modules/typescript/bin/tsc -p tsconfig.tests.json",
     "test": "node --test \"tests/*.test.ts\"",
     "test:scenarios": "node --test tests/scenarios.test.ts tests/tool-scenarios.test.ts",
@@ -57,13 +64,13 @@
     "preflight": "node scripts/preflight.mjs ."
   },
   "dependencies": {
-    "@deepseek-ai/schemastery": "*",
+    "@deepseek-ai/schemastery": "^3.18.4",
     "playwright-core": "~1.62.1"
   },
   "peerDependencies": {
-    "@deepseek-ai/cordis": "*",
-    "@deepseek-ai/dsh-llm": "*",
-    "@deepseek-ai/dsh-tools": "*"
+    "@deepseek-ai/cordis": ">=4.0.4",
+    "@deepseek-ai/dsh-llm": ">=0.2.0-rc.1",
+    "@deepseek-ai/dsh-tools": ">=0.2.0-rc.1"
   },
   "devDependencies": {
     "@deepseek-ai/cordis": "4.0.4",
@@ -82,8 +89,21 @@
   "dsh": {
     "bundle": {
       "patch": "./cordis.patch.yml"
+    },
+    "client": {
+      "platform": "web",
+      "inject": []
     }
   },
+  "engines": {
+    "node": "^22.19.0 || >=24.0.0"
+  },
+  "packageManager": "pnpm@10.31.0",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/miqian-nomad/dsh-browser-playwright-codex.git"
+  },
+  "homepage": "https://github.com/miqian-nomad/dsh-browser-playwright-codex#readme",
   "keywords": [
     "deepseek-harness",
     "dsh",
@@ -98,15 +118,7 @@
     "form-filling",
     "deepseek",
     "ai-agent",
-    "rpa"
-  ],
-  "engines": {
-    "node": "^22.19.0 || >=24.0.0"
-  },
-  "packageManager": "pnpm@10.31.0",
-  "repository": {
-    "type": "git",
-    "url": "git+https://github.com/miqian-nomad/dsh-browser-playwright-codex.git"
-  },
-  "homepage": "https://github.com/miqian-nomad/dsh-browser-playwright-codex#readme"
+    "rpa",
+    "settings"
+  ]
 }

package/scripts/dsh-browser-verify.mjs

@@ -13,6 +13,8 @@
  *
  * 读 lib/，但**必须先 build**：npm run verify 会先跑 npm run build，直接
  * node scripts/... 跑则会撞上最后一组检查（lib/ 不旧于 src/）。
+ * npm 安装形态没有 src/（files 里不含它）：最后一组自动**跳过并说明**，不算失败，
+ * 所以从 npm 装上之后这条命令照样能跑通 —— README 的「装到即可跑」必须是真的。
  *
  * 为什么不像测试那样用 tsx 直读 src/：tsx（esbuild keepNames）会把传给
  * page.evaluate 的函数包成 __name(...)，而页面里没有这个符号 ——
@@ -20,7 +22,7 @@
  * 失效。lib/ 是编译产物，没有这层包裹，也正好是宿主真正加载的东西。
  */
 import http from 'node:http'
-import { readdirSync, statSync } from 'node:fs'
+import { existsSync, readdirSync, statSync } from 'node:fs'
 import os from 'node:os'
 import path from 'node:path'
 import { PlaywrightProvider } from '../lib/provider.js'
@@ -32,12 +34,13 @@ import { getEffectiveEngine, setSnapshotEngine } from '../lib/runtime-state.js'
 // 设置页的「页面识别方式」存在 ~/.dsh/dsh-browser-playwright.state.json，运行时状态层
 // 允许用 DSH_BROWSER_STATE_FILE 把它指向别处（src/runtime-state.ts 里为测试留的开关）。
 // 指向一个不存在的文件 = engine 回到配置默认值 legacy，本脚本的期望值就是按它写的。
-// 不隔离的话：用户把开关拨到「智能模式」，这份 57 项验收就会假失败（2026-10-01 实测）。
+// 不隔离的话：用户把开关拨到「智能模式」，这份验收就会假失败（2026-10-01 实测）。
 // 注意 [1]–[7] 因此都跑在兼容模式下；智能模式由 [8] 显式切过去跑（隔离状态文件里切，
 // 不碰用户的真实选择）。
 process.env.DSH_BROWSER_STATE_FILE = path.join(os.tmpdir(), 'dsh-browser-verify-state-isolated.json')
 
 let pass = 0
+let skipped = 0
 const failures = []
 function check(name, ok, detail) {
   if (ok) {
@@ -455,22 +458,31 @@ await provider.dispose()
 server.close()
 
 // [7] lib/ 是宿主真正加载的产物：源码改完没 build，跑绿了也是白跑。
+// npm 包里没有 src/（package.json 的 files 只收 lib/），安装形态下这一组无从比较：
+// 跳过并说明原因，不记失败、不影响退出码 —— 否则装上 npm 包之后这条命令必崩，
+// 与 README/CHANGELOG 的「装到即可跑」直接矛盾。
 console.log('[7] lib/ 与 src/ 同步（宿主加载 lib/）')
-const stale = []
-for (const file of readdirSync(new URL('../src', import.meta.url))) {
-  if (!file.endsWith('.ts') || file.endsWith('.d.ts')) continue
-  const src = statSync(new URL('../src/' + file, import.meta.url)).mtimeMs
-  const built = statSync(new URL('../lib/' + file.replace(/\.ts$/, '.js'), import.meta.url), {
-    throwIfNoEntry: false,
-  })
-  if (built === undefined || built.mtimeMs < src) stale.push(file.replace(/\.ts$/, '.js'))
+if (!existsSync(new URL('../src', import.meta.url))) {
+  skipped += 1
+  console.log('  （跳过）没有 src/：这是 npm 安装形态')
+} else {
+  const stale = []
+  for (const file of readdirSync(new URL('../src', import.meta.url))) {
+    if (!file.endsWith('.ts') || file.endsWith('.d.ts')) continue
+    const src = statSync(new URL('../src/' + file, import.meta.url)).mtimeMs
+    const built = statSync(new URL('../lib/' + file.replace(/\.ts$/, '.js'), import.meta.url), {
+      throwIfNoEntry: false,
+    })
+    if (built === undefined || built.mtimeMs < src) stale.push(file.replace(/\.ts$/, '.js'))
+  }
+  check('lib/ 不旧于 src/（旧了就先 npm run build）', stale.length === 0, stale.join(', '))
 }
-check('lib/ 不旧于 src/（旧了就先 npm run build）', stale.length === 0, stale.join(', '))
 
 console.log('')
+const skipNote = skipped > 0 ? '，跳过 ' + skipped + ' 项' : ''
 console.log(
   failures.length === 0
-    ? '全部通过 (' + pass + ' 项)'
+    ? '全部通过 (' + pass + ' 项' + skipNote + ')'
     : '失败 ' + failures.length + ' 项 / 共 ' + (pass + failures.length) + ' 项: ' + failures.join(', '),
 )
 process.exit(failures.length === 0 ? 0 : 1)