mirror of
https://github.com/ThearchyHelios/AgentLab.git
synced 2026-11-15 00:01:58 +00:00
文档：「界面里的设置」表照设置页的实际页签改——偏好设置补上运行默认值、证据裁判、核查、口径账本、应用一节和界面主题；去掉不存在的「设置 → 应用」页签（应用那几项在偏好设置里，apps、identity-and-security 两篇里的说法一起改），补上「审计」页签；中英两边同步
This commit is contained in:
ThearchyHelios
+1
-1
@@ -112,7 +112,7 @@ Process instances may wait for days, so upgrading in the meantime is normal.
|
||||
|
||||
Click Save as My App on a blueprint to make a personal app that only its owner can see.
|
||||
|
||||
- Users can create them only after an admin enables this under Settings → Apps.
|
||||
- Users can create them only after an admin enables this in the Apps section of Settings → Preferences.
|
||||
- The graph of a personal app uses the same allowlist as Ask Data for users. The data-fetch nodes of templates such as Periodic Dashboard and Exception Handling (list only) are simply Call Tool nodes that query data sources.
|
||||
- Each refresh is an exploratory run: query results are masked at the tool boundary first, data sources are always read-only, and refreshes share a per-person daily cap with on-demand views.
|
||||
- Only the owner can read refreshes and trial runs of personal blueprints: admins and builders can't see these runs, evidence, artifacts, or attachments either, and they aren't listed in run lists.
|
||||
|
||||
@@ -67,16 +67,15 @@ For the app database, checkpoint database, connection pool, PgBouncer, and multi
|
||||
| Location | Contents |
|
||||
|---|---|
|
||||
| Settings → Model Access | Providers and keys |
|
||||
| Settings → Preferences | Drafting model; Allow creating share links in the Apps section; evaluation concurrency, per-question time limit, and per-evaluation and daily spending; run concurrency (admins) |
|
||||
| Settings → Runtime Environment | Sandbox candidates and their availability, the current choice and its reason; current values such as time limits |
|
||||
| Settings → Preferences | Run defaults (default memory scope, default knowledge base, require approval for dangerous tools by default); the evidence judge (judge model and limits); verification (verification model, the switches and limits for double-blind recomputation, adversarial review, and approval inquiry, and the daily spending cap; see [The review suite](evidence.md#the-review-suite)); evaluation concurrency, per-question time limit, and per-evaluation and daily spending; run concurrency (admins); the caliber ledger (automatic issuance by caliber and its daily cap, the caliber matching time limit, the recall limit `ledger.recall_limit`; see [Caliber ledger](evaluation-and-ledger.md#caliber-ledger)); drafting model; apps (the daily cap on on-demand runs per app, letting users create personal apps, allowing share links); interface theme |
|
||||
| Settings → General | Public URL |
|
||||
| Settings → Runtime Environment | Sandbox candidates and their availability, the current choice and its reason; current values such as time limits |
|
||||
| Settings → Identity | Login mode; enabling Ask Data for users |
|
||||
| Settings → Notifications | Channel subscriptions; Mail Service (SMTP) |
|
||||
| Settings → Apps | Letting users create personal apps |
|
||||
| Settings → Access Keys | Service accounts, the personal access key switch, the API reference |
|
||||
| The `ledger` group in Settings | The automatic issuance switch `auto_issue`; the recall limit `ledger.recall_limit` |
|
||||
| Settings → Audit | Audit records |
|
||||
|
||||
Other settings: `notify.digest_at` (the time of the daily task digest), `apps.on_demand_daily_limit` (the daily cap on on-demand runs per app), and the agent token budget, spending budget, and step count.
|
||||
Other settings: `notify.digest_at` (the time of the daily task digest), and the agent token budget, spending budget, and step count.
|
||||
|
||||
## Sandbox backend
|
||||
|
||||
|
||||
@@ -48,7 +48,7 @@ Roles: admin ⊇ builder ⊇ user.
|
||||
| MCP stdio, endpoints and credentials, capability governance, model access | ✓ | Read-only | ✗ |
|
||||
| Apps: use / view all instances / build and publish | ✓ | Can use and view; managing requires being the creator or having a Manage grant | Use and view per grants |
|
||||
| Shared blueprints: read, edit, trial run, create publish plans | ✓ | Ones they created, and ones that come from apps they manage | ✗ |
|
||||
| Create personal apps, refresh, submit for review | ✓ | ✓ | Not by default; an admin can enable it under Settings → Apps |
|
||||
| Create personal apps, refresh, submit for review | ✓ | ✓ | Not by default; an admin can enable it in the Apps section of Settings → Preferences |
|
||||
| Other people's personal apps: name, owner, created and updated times, archiving | ✓ | ✗ | ✗ |
|
||||
| Other people's personal apps: pages, refresh and trial-run runs, evidence, attachments, blueprints | ✗ | ✗ | ✗ |
|
||||
| Handle tasks assigned to oneself, verify actions | ✓ | ✓ | ✓ |
|
||||
|
||||
+1
-1
@@ -112,7 +112,7 @@
|
||||
|
||||
在蓝图上点「存成我的应用」，做出只给拥有者自己看的个人应用。
|
||||
|
||||
- 使用者要管理员在「设置 → 应用」里开启后才能建。
|
||||
- 使用者要管理员在「设置 → 偏好设置」的「应用」一节里开启后才能建。
|
||||
- 个人应用的图和使用者的问数据用同一份白名单。周期看板、异常处置（只看清单）这些模板的取数节点，就是查数据源的调用工具节点。
|
||||
- 每次刷新是一次探索运行：查询结果在工具边界先遮罩，数据源一律只读，和按需视图共用每人每天的次数上限。
|
||||
- 刷新和个人蓝图的试运行只有拥有者读得到：管理员、搭建者也看不到这些运行、证据、工件和附件，运行列表里不列。
|
||||
|
||||
@@ -67,16 +67,15 @@ AgentLab 放在反向代理后面、或者要给外部系统回调时，设对
|
||||
| 位置 | 内容 |
|
||||
|---|---|
|
||||
| 设置 → 模型接入 | provider 和密钥 |
|
||||
| 设置 → 偏好设置 | 起草模型；「应用」一节的「允许建分享链接」；评测的并发、每题时限、单次和每日金额；运行并发（管理员） |
|
||||
| 设置 → 运行环境 | 沙箱候选和可用性、当前选中项和选择原因；时限等当前值 |
|
||||
| 设置 → 偏好设置 | 运行默认值（默认记忆作用域、默认知识库、危险工具默认需要人工审批）；证据裁判（裁判模型和各项上限）；核查（核查模型，双盲复算、反方审稿、审批质询的开关和上限，每日金额上限，见[复核套件](evidence.md#复核套件)）；评测的并发、每题时限、单次和每日金额；运行并发（管理员）；口径账本（自动按口径出具的开关和每日上限、口径比对时限、召回上限 `ledger.recall_limit`，见[口径账本](evaluation-and-ledger.md#口径账本)）；起草模型；应用（每个应用每天的按需运行上限、让使用者建个人应用、允许建分享链接）；界面主题 |
|
||||
| 设置 → 通用 | 对外访问地址 |
|
||||
| 设置 → 运行环境 | 沙箱候选和可用性、当前选中项和选择原因；时限等当前值 |
|
||||
| 设置 → 身份 | 登录方式；给使用者开启问数据 |
|
||||
| 设置 → 通知 | 渠道订阅；邮件服务（SMTP） |
|
||||
| 设置 → 应用 | 让使用者建个人应用 |
|
||||
| 设置 → 访问密钥 | 服务账号、个人访问密钥的开关、接口说明 |
|
||||
| 设置里的 `ledger` 一组 | 自动出具开关 `auto_issue`；召回上限 `ledger.recall_limit` |
|
||||
| 设置 → 审计 | 审计记录 |
|
||||
|
||||
其他设置项：`notify.digest_at`（每天待办汇总的时间）、`apps.on_demand_daily_limit`（每个应用每天的按需运行上限），以及 agent 的令牌预算、金额预算和步数。
|
||||
其他设置项：`notify.digest_at`（每天待办汇总的时间），以及 agent 的令牌预算、金额预算和步数。
|
||||
|
||||
## 沙箱后端
|
||||
|
||||
|
||||
@@ -48,7 +48,7 @@ cd backend && python -m app.auth reset-admin --username admin # 不给 --passw
|
||||
| MCP 的 stdio、端点和凭据、能力治理、模型接入 | ✓ | 只读 | ✗ |
|
||||
| 应用：使用 / 查看全部实例 / 搭建发布 | ✓ | 能用能看；管理要创建者或有管理授权 | 按授权使用、查看 |
|
||||
| 共享蓝图：读、改、试运行、出发布单 | ✓ | 自己建的、自己管理的应用出自的 | ✗ |
|
||||
| 建个人应用、刷新、提交审核 | ✓ | ✓ | 默认不能，管理员可在「设置 → 应用」开启 |
|
||||
| 建个人应用、刷新、提交审核 | ✓ | ✓ | 默认不能，管理员可在「设置 → 偏好设置」的「应用」一节开启 |
|
||||
| 别人的个人应用：名称、拥有者、创建和更新时间，归档 | ✓ | ✗ | ✗ |
|
||||
| 别人的个人应用：页面、刷新和试运行的运行、证据、附件、蓝图 | ✗ | ✗ | ✗ |
|
||||
| 处理派给自己的待办、核实动作 | ✓ | ✓ | ✓ |
|
||||
|
||||
Reference in New Issue
Block a user