page-agent-sdk 2.30.0 → 2.32.0
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 +5 -3
- package/README.zh-CN.md +5 -3
- package/dist/page-agent-sdk.iife.js +132 -131
- package/dist/page-agent-sdk.js +1890 -1340
- package/dist/page-agent-sdk.umd.cjs +30 -29
- package/package.json +1 -1
- package/skills/page-agent-sdk-integrate/references/api.md +8 -0
- package/skills/precise-value-protection/SKILL.md +49 -0
- package/types/index.d.ts +34 -0
package/README.md
CHANGED
|
@@ -8,7 +8,7 @@
|
|
|
8
8
|
|
|
9
9
|
[](https://www.npmjs.com/package/page-agent-sdk)
|
|
10
10
|
[](https://github.com/whyymj/page-agent-sdk/blob/master/LICENSE)
|
|
11
|
-
[](#self-tests)
|
|
12
12
|
|
|
13
13
|
---
|
|
14
14
|
|
|
@@ -142,6 +142,8 @@ CDN zero-config: `<script src="https://unpkg.com/page-agent-sdk"></script>` →
|
|
|
142
142
|
| 📌 cross-compress working memory (2.20+) | Pin recent read/query paths + hashes across compression; no re-fetch, correct optimistic-lock hash | `capabilities.workingMemory` |
|
|
143
143
|
| 🤖 unattended automation (2.20+) | Resource budget guard (`tokenBudget`/`timeBudgetMs`) + fatal-error auto-recovery (`maxAutoRetries`: restore checkpoint + retry) + cross-refresh resume + `sdk.batch(tasks)` batch processing | `capabilities.automation` |
|
|
144
144
|
| 📐 context resilience (2.30+) | Hard floor `contextWindow ≥200K` (rejects <200K models like legacy `deepseek`/`gpt-4o`/`glm-4.5` at startup); three gates (compress/trim/offload) thresholds follow the live window after `setLlm`; reactive retry on `context_length_exceeded` (aggressive trim → single retry, never fails raw); vfs large-result refs protected from LRU eviction + OOM 1.5× fallback; system-prompt budget (25% window, drops non-pinned segments, keeps base/mission/workingMemory) | built-in |
|
|
145
|
+
| 🎯 focus auto-switch (2.31+) | AI auto-judges task scope → `set_focus` (local task) / `clear_focus` (global/done); focus persists across refresh/session-switch (restore validates path via `getSchemaAtPath`, drops if invalid); spawned subagents inherit parent focus (three-layer convergence; parent unfocused → child no focus middleware, zero regression) | `capabilities.focus` + `toolMode:'advanced'` |
|
|
146
|
+
| 🔒 precise-value protection (2.32+) | `data.resources: [{path, mode}]` protects exact-value fields: `freeze` (read-only, value hidden via `⟦frozen:path⟧` placeholder, FROZEN_FIELD on write) / `verbatim` (preserved verbatim, `⟦res:handle⟧`, modify via `resource_update` else VERBATIM_MISMATCH); write-side enforcement across commitSetToBind/applyPatches/eval + resource tools (`resource_get/update/list/delete`, advanced) + cross-compression pin | `data.resources` + `capabilities.vfs` |
|
|
145
147
|
|
|
146
148
|
Capabilities default on (`verify`/`approval`/`checkpoint` default off; **proactive `humanConfirm` default on** — AI asks when uncertain/multi-plan instead of guessing). Turn off unneeded ones via `capabilities` to save tokens.
|
|
147
149
|
|
|
@@ -523,8 +525,8 @@ function switchTo(i: number) {
|
|
|
523
525
|
## Self-tests
|
|
524
526
|
|
|
525
527
|
```bash
|
|
526
|
-
npm test #
|
|
527
|
-
npm run test:e2e #
|
|
528
|
+
npm test # 1480 assertions (tsx, source-level; no LLM dependency)
|
|
529
|
+
npm run test:e2e # 376 integration assertions (node, built dist; covers APIs/options/modules/simple&complex scenes: default systemPrompt(capability overview) / dynamic register + inspect sync / inspect(tools/middleware/subagent/verify/mcp/todos/lastCompression/checkpoints reflect config) / custom tools/middleware/skills/memory injection / runtime dynamic reconfiguration(setTools/addTool/removeTool/setLlm/setMemory/setSubagents reflect) / switchSession(on/off) / shareContext on/off sharing/independent / storage backends + object config / presets(3) / checkpoint / exports complete(39+ fns/components) / util fns usable(isQuotaError/estimateTokens/jpEval/searchJson) / source=builtin / mount boundary / hook multi-listener / llm config / hide/show / error scenes)
|
|
528
530
|
```
|
|
529
531
|
|
|
530
532
|
## Local npm package test
|
package/README.zh-CN.md
CHANGED
|
@@ -8,7 +8,7 @@
|
|
|
8
8
|
|
|
9
9
|
[](https://www.npmjs.com/package/page-agent-sdk)
|
|
10
10
|
[](https://github.com/whyymj/page-agent-sdk/blob/master/LICENSE)
|
|
11
|
-
[](#自测)
|
|
12
12
|
|
|
13
13
|
---
|
|
14
14
|
|
|
@@ -137,6 +137,8 @@ CDN 零配置：`<script src="https://unpkg.com/page-agent-sdk"></script>` → `
|
|
|
137
137
|
| 💾 持久化 | IndexedDB 多会话 + 配额淘汰 + 切换 | `storage` |
|
|
138
138
|
| 🤖 无人值守自动化 (2.20+) | 资源预算闸（`tokenBudget`/`timeBudgetMs`）+ 致命错误自动恢复（`maxAutoRetries`：回退 checkpoint + 重试）+ 刷新续跑 + `sdk.batch(tasks)` 批处理 | `capabilities.automation` |
|
|
139
139
|
| 📐 上下文健壮性 (2.30+) | 硬地板 `contextWindow ≥200K`(启动拒绝 <200K 模型如老款 `deepseek`/`gpt-4o`/`glm-4.5`);三道闸(压缩/trim/offload)阈值在 `setLlm` 后跟随实时窗口;遇 `context_length_exceeded` 反应性重试(激进 trim → 重试一次,不裸失败);vfs 大结果引用受保护免 LRU 淘汰 + OOM 1.5× 兜底;系统段预算(25% 窗口,丢弃非 pin 段保 base/mission/workingMemory) | 内置 |
|
|
140
|
+
| 🎯 focus 自动切换 (2.31+) | AI 自动判断任务范围 → `set_focus`(局部任务)/ `clear_focus`(全局/完成);focus 跨刷新/切会话持久化(restore 经 `getSchemaAtPath` 校验 path,失效丢弃);子 agent 继承主焦点(三层收敛;主未聚焦 → 子无 focus 中间件,零回归) | `capabilities.focus` + `toolMode:'advanced'` |
|
|
141
|
+
| 🔒 精确值保护 (2.32+) | `data.resources: [{path, mode}]` 保护需精确保存字段:`freeze`(只读,精确值经 `⟦frozen:path⟧` 占位符不入消息流,写撞 FROZEN_FIELD)/ `verbatim`(原样保留,`⟦res:handle⟧`,改值经 `resource_update` 否则 VERBATIM_MISMATCH);写侧强制覆盖 commitSetToBind/applyPatches/eval + 资源工具(`resource_get/update/list/delete`,advanced)+ 跨压缩 pin | `data.resources` + `capabilities.vfs` |
|
|
140
142
|
|
|
141
143
|
能力默认开（`verify`/`approval`/`checkpoint` 默认关；**主动征询 `humanConfirm` 默认开**——AI 遇不确定/多方案主动问你、不猜测），可经 `capabilities` 关掉无用的省 token。
|
|
142
144
|
|
|
@@ -468,8 +470,8 @@ function switchTo(i: number) {
|
|
|
468
470
|
## 自测
|
|
469
471
|
|
|
470
472
|
```bash
|
|
471
|
-
npm test #
|
|
472
|
-
npm run test:e2e #
|
|
473
|
+
npm test # 1480 项断言（tsx 源码级，不依赖 LLM）
|
|
474
|
+
npm run test:e2e # 376 项集成断言（node 跑构建产物 dist；覆盖各 API/配置项/功能模块/简单与复杂场景：默认 systemPrompt(含能力概述) / 动态注册与 inspect 同步 / inspect(tools/middleware/subagent/verify/mcp/todos/lastCompression/checkpoints 反映配置) / 自定义 tools/middleware/skills/memory 注入 / 运行时动态重配置(setTools/addTool/removeTool/setLlm/setMemory/setSubagents 反映) / switchSession(开/未开) / shareContext 开/关共享独立 / storage 后端+对象配置 / presets 三预设 / checkpoint / 导出项完整(39+ 函数/组件) / 工具函数可用(isQuotaError/estimateTokens/jpEval/searchJson) / source=builtin / mount 边界 / hook 多监听器 / llm 配置 / 错误场景）
|
|
473
475
|
```
|
|
474
476
|
|
|
475
477
|
## 本地 npm 包测试
|