page-agent-sdk 4.19.1 → 4.19.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +1 -1
- package/README.zh-CN.md +2 -2
- package/dist/page-agent-sdk.headless.js +2 -2
- package/dist/page-agent-sdk.iife.js +3 -3
- package/dist/page-agent-sdk.js +4 -4
- package/dist/page-agent-sdk.legacy.js +4 -4
- package/dist/page-agent-sdk.umd.cjs +3 -3
- package/dist/style.css +1 -1
- package/package.json +1 -1
- package/style.css +1 -1
- package/types/index.d.ts +1 -1
package/README.md
CHANGED
|
@@ -248,7 +248,7 @@ ChatDialog, MessageContent, CodePreview, SkillPanel, DebugDrawer, useChat
|
|
|
248
248
|
| | `tools` / `skills` / `memory` | `Tool[]` / `SkillSpec[]` / `string` | Custom tools / skills / AGENTS.md-style directives |
|
|
249
249
|
| | `images` | `{upload?,describe?,describeTimeoutMs?}` | **Image input (image-input-vision)**: built-in three entry points (📎 pick / drag / paste) → compression gate (long edge ≤1568px, ≤4 per round, >20MB rejected). Multimodal main model (table hit or `llm.vision:true`) → images sent directly as content parts, zero config; text-only main model → configure `describe` to caption each image into the context (image never sent); neither → honest rejection, never silently dropped; `upload` swaps the original for an https URL (integrator OSS). See [usage-guide §6.17](doc/usage-guide.en.md#617-image-input-multimodal-direct--captioning-bypass) |
|
|
250
250
|
| | `dialog.autoQuote` | `boolean` | **Selection quoting · silent capture (page-quote, default false)**: when true, opening the drawer or clicking the input area lazily captures the host page's current text selection (outside the dialog) into a removable quote chip, sent with the next message as question context. Privacy opt-in; `sdk.setQuote/clearQuote` work regardless of this toggle. See [usage-guide §6.20](doc/usage-guide.en.md#620-text-selection-quoting--page-qa-page-quote--read_page--pagecontext) |
|
|
251
|
-
| | `dialog.selectionMenu` | `boolean` | **Selection floating menu (page-quote explicit confirm, default false)**: selecting text floats a "❝ Quote to
|
|
251
|
+
| | `dialog.selectionMenu` | `boolean` | **Selection floating menu (page-quote explicit confirm, default false)**: selecting text floats a "❝ Quote to AI assistant" toolbar above the selection; click = attach the quote chip + open the dialog + focus the input; dismiss on outside click / scroll / Esc; composable with autoQuote. See [usage-guide §6.20](doc/usage-guide.en.md#620-text-selection-quoting--page-qa-page-quote--read_page--pagecontext) |
|
|
252
252
|
| | `capabilities.pageContext` | `boolean` | **Page anchor (default false)**: injects the current page title + URL as a pinned system segment each round (pair with `domInspect`'s read_page for page QA). See [usage-guide §6.20](doc/usage-guide.en.md#620-text-selection-quoting--page-qa-page-quote--read_page--pagecontext) |
|
|
253
253
|
| | `screenshot` | `{renderer?}` | **Screenshot config (take_screenshot)**: assembled when domInspect is on AND (multimodal main model \|\| images.describe); default renderer is html-to-image, pass `renderer` when CSP restricts. See [usage-guide §6.21](doc/usage-guide.en.md#621-screenshot-viewing--page-content-analysis-take_screenshot--page-analysis) |
|
|
254
254
|
| | `capabilities.domEdit` | `boolean` | **DOM editing (default false; requires domInspect)**: assembles `dom_edit` (atomic batch ops on the host page — set_text/set_html/set_attr/add_class/set_style/insert/remove/move/highlight) + `dom_restore` (snapshot rollback, stack of 20). Unique-selector discipline, dangerous-content gate (script / on\* / javascript:), SDK-own-DOM protection; edits are session-ephemeral — data-driven pages should edit data (`write`) instead. See [usage-guide §6.22](doc/usage-guide.en.md#622-dom-editing-dom_edit--dom_restore) |
|
package/README.zh-CN.md
CHANGED
|
@@ -173,7 +173,7 @@ CDN 零配置:`<script src="https://unpkg.com/page-agent-sdk"></script>` → `
|
|
|
173
173
|
| 🧭 指令执行力增强 (3.35+) | **完结门禁**:todos 有未完成项却欲纯文本收尾 → 回灌「双出口」反馈续跑(≤2 次),防「拆 3 项做 1 项就收口」的莫名中断;**问句意图守卫**:正则三档启发式逐消息定性问句,命中注入「先答勿做」pin 段(跨压缩存活),防长对话提问被历史拖着误路由成操作(如问「这是啥组件」却去生成代码)。均默认开、零配置、宁漏勿误 | 内置 |
|
|
174
174
|
| 🎨 子 agent 模型/思考分层 | `createHtmlSubagent({ llm, thinkingMode })`:代码生成子 agent 独立强模型(主保持轻量编排)+ 思考深度锁定(`'deep'` 注入思考参数质量优先 / `'simple'` 剥除省 token;顶层 `subagent.thinkingMode` 全局缺省)。仅 LLMConfig 构造路径生效(预构造实例 warn+no-op);需模型支持思考(deepseek thinking 版/claude);`inspect().subagent.subagents` 反射生效状态 | `createHtmlSubagent({ llm, thinkingMode })` |
|
|
175
175
|
| 🖼 图片输入 | 对话框内置三入口(📎 选择/拖拽/粘贴截图)→ 压缩闸(长边 ≤1568px/单轮 ≤4 张/超 20MB 拒);主模型多模态(gpt-4o/claude/qwen-vl 查表,或 `llm.vision:true`)→ 图片直发 content parts 零配置;纯文本主模型(deepseek 等)→ 配 `images.describe` 逐图识图转述注入(图不直发);都不配则诚实拒绝不静默丢图;`images.upload` 原图换 https URL(集成方 OSS);持久化只存缩略图 + vfs 引用 | `images: { upload?, describe? }` + `llm.vision` |
|
|
176
|
-
| ❝ 划词引用 | 用户选中页面文字 → 引用 chip 自动挂上(打开抽屉/点输入框双懒捕获)→ 随下一条消息作为提问上下文;`AgentMessage.quote` 消息级字段(content 干净,气泡结构化引用块,LLM 前缀注入,随消息持久化);`sdk.setQuote/clearQuote` 宿主 API(headless 同享);来源自动推导 = 页面 title + 最近在前标题;排队/快捷指令不消费(与图片同口径);隐私 opt-in 默认关;另有 `dialog.selectionMenu` 显式确认形态(划选浮出「❝
|
|
176
|
+
| ❝ 划词引用 | 用户选中页面文字 → 引用 chip 自动挂上(打开抽屉/点输入框双懒捕获)→ 随下一条消息作为提问上下文;`AgentMessage.quote` 消息级字段(content 干净,气泡结构化引用块,LLM 前缀注入,随消息持久化);`sdk.setQuote/clearQuote` 宿主 API(headless 同享);来源自动推导 = 页面 title + 最近在前标题;排队/快捷指令不消费(与图片同口径);隐私 opt-in 默认关;另有 `dialog.selectionMenu` 显式确认形态(划选浮出「❝ 引用到 AI 助手」工具条,点击挂引用并打开对话框) | `dialog.autoQuote` / `dialog.selectionMenu` + `sdk.setQuote` |
|
|
177
177
|
| 📖 页面问答 | `read_page` 读当前页正文纯文本(智能定位 article/main/[role=main]/.content,排除 SDK 自身 DOM 与 script/style,`hasMore` 分页续读,大结果自动外存 vfs);`pageContext` 每轮注入当前页 title+URL 锚点 pin 段(跨压缩;子 agent 不继承) | `capabilities: { domInspect: true, pageContext: true }` |
|
|
178
178
|
| 📸 截图查看 | `take_screenshot` 三模式(selector 局部 / fullPage 整页 / 视口);条件注入(domInspect 开 && vision 主模型 \|\| images.describe,不满足 warn 留痕);分层图通道(vision → 工具结果后合成 user 消息 image parts,免疫 trim/offload;纯文本 → describe 转述);压缩闸 ≤1568 + 原图收 vfs;工具步骤行缩略图观察面;`page-analysis` skill(问题分型/探索纪律/回答纪律) | `capabilities: { domInspect: true }` + `llm.vision` 或 `images.describe` + `screenshot.renderer`(可选) |
|
|
179
179
|
| 🖍 DOM 编辑 | `dom_edit` 批量原子操作(set_text/set_html/set_attr/add_class/set_style/insert/remove/move/highlight)+ `dom_restore` 快照回滚(栈 20 批);唯一 selector 纪律(多匹配拒)/危险闸(script·on*·javascript: 拒)/SDK 自身 DOM 保护/单根快照 256KB 上限;改动为会话临时态,数据驱动页面仍走 write | `capabilities: { domInspect: true, domEdit: true }` |
|
|
@@ -251,7 +251,7 @@ ChatDialog, MessageContent, CodePreview, SkillPanel, DebugDrawer, useChat
|
|
|
251
251
|
| | `schemaHint` | `{maxKeys?,maxChars?}` · 默认 `{15,4000}` | **(2.18+) 大 schema 分层披露阈值**:超则 systemPrompt 只注入顶层概览(不带约束/不递归),深层约束按需 `schema_data` 查;小 schema 无感(全量) |
|
|
252
252
|
| | `images` | `{upload?,describe?,describeTimeoutMs?}` | **图片输入(image-input-vision)**:对话框内置三入口(📎/拖拽/粘贴)→ 压缩闸(长边≤1568/≤4 张/超 20MB 拒)。主模型多模态(查表或 `llm.vision:true`)→ 图片直发 content parts,零配置;纯文本主模型 → 配 `describe` 逐图识图转述注入(图不直发),都不配则诚实拒绝不静默丢图;`upload` 原图换 https URL(集成方 OSS)。见 [usage-guide §6.17](doc/usage-guide.md#617-图片输入多模态直发--识图转述旁路) |
|
|
253
253
|
| | `dialog.autoQuote` | `boolean` | **划词引用·静默捕获(page-quote,默认 false)**:true 时打开抽屉/点输入区瞬间懒捕获宿主页面(对话框外)当前选中文本挂「引用 chip」(可删),随下一条消息发给 LLM。隐私 opt-in;`sdk.setQuote/clearQuote` 不受此开关影响。见 [usage-guide §6.20](doc/usage-guide.md#620-划词引用与页面问答page-quote--read_page--pagecontext) |
|
|
254
|
-
| | `dialog.selectionMenu` | `boolean` | **划词浮动菜单(page-quote 显式确认,默认 false)**:划选文字浮出「❝
|
|
254
|
+
| | `dialog.selectionMenu` | `boolean` | **划词浮动菜单(page-quote 显式确认,默认 false)**:划选文字浮出「❝ 引用到 AI 助手」工具条,点击 = 挂引用 chip + 打开对话框 + 聚焦输入;点别处/滚动/Esc 消失;与 autoQuote 独立可组合。见 [usage-guide §6.20](doc/usage-guide.md#620-划词引用与页面问答page-quote--read_page--pagecontext) |
|
|
255
255
|
| | `capabilities.pageContext` | `boolean` | **页面锚点(默认 false)**:每轮 system 注入当前页 title+URL(pin 段跨压缩;配合 `domInspect` 的 read_page 读正文答问)。见 [usage-guide §6.20](doc/usage-guide.md#620-划词引用与页面问答page-quote--read_page--pagecontext) |
|
|
256
256
|
| | `screenshot` | `{renderer?}` | **截图配置组(take_screenshot)**:装配条件 = domInspect 开 &&(多模态主模型 \|\| images.describe);默认渲染 html-to-image,CSP 限制时传 `renderer` 自定义。见 [usage-guide §6.21](doc/usage-guide.md#621-截图查看与页面内容分析take_screenshot--page-analysis) |
|
|
257
257
|
| | `capabilities.domEdit` | `boolean` | **DOM 编辑(默认 false;需 domInspect)**:装配 `dom_edit`(宿主页面批量原子操作:set_text/set_html/set_attr/add_class/set_style/insert/remove/move/highlight)+ `dom_restore`(快照回滚,栈 20 批)。唯一 selector 纪律/危险闸(script·on\*·javascript:)//SDK 自身 DOM 保护;改动为会话临时态 —— 数据驱动页面应改数据(`write`)。见 [usage-guide §6.22](doc/usage-guide.md#622-dom-编辑dom_edit--dom_restore) |
|
|
@@ -16691,7 +16691,7 @@ var q_ = {
|
|
|
16691
16691
|
quoteChipTitle: "将随下一条消息作为引用发送(❝ 划词引用)",
|
|
16692
16692
|
quoteRemove: "移除引用",
|
|
16693
16693
|
screenshotAlt: "截图查看(点击放大)",
|
|
16694
|
-
selectionMenuLabel: "
|
|
16694
|
+
selectionMenuLabel: "引用到 AI 助手",
|
|
16695
16695
|
selectionMenuTitle: "把选中文本作为引用加入对话框,随下一条消息发给 AI",
|
|
16696
16696
|
imageCountLimitPrefix: "单轮最多 ",
|
|
16697
16697
|
imageCountLimitSuffix: " 张图片",
|
|
@@ -16925,7 +16925,7 @@ var q_ = {
|
|
|
16925
16925
|
quoteChipTitle: "Will be quoted with your next message",
|
|
16926
16926
|
quoteRemove: "Remove quote",
|
|
16927
16927
|
screenshotAlt: "Screenshot (click to enlarge)",
|
|
16928
|
-
selectionMenuLabel: "Quote to
|
|
16928
|
+
selectionMenuLabel: "Quote to AI assistant",
|
|
16929
16929
|
selectionMenuTitle: "Add the selected text to the dialog as a quote, sent with your next message",
|
|
16930
16930
|
imageCountLimitPrefix: "Up to ",
|
|
16931
16931
|
imageCountLimitSuffix: " images per message",
|