mirror of
https://github.com/shumaiOne/shumai.git
synced 2026-11-20 04:07:16 +00:00
Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
52330869a2 | ||
|
|
0c561e9b39 | ||
|
|
a236cd3a97 | ||
|
|
c3ef769f51 | ||
|
|
e58dfaa71a | ||
|
|
35b57cc0ab | ||
|
|
5a754bcb94 | ||
|
|
64b68e7d63 | ||
|
|
c2f477a391 | ||
|
|
9263971653 | ||
|
|
79a479c87c | ||
|
|
134eb8b7fa | ||
|
|
e06478df88 | ||
|
|
6e9cf8dfb6 | ||
|
|
d2620f6911 | ||
|
|
4537baa6a2 | ||
|
|
810e0c4cf5 | ||
|
|
07cb648183 | ||
|
|
c6602c9f1c | ||
|
|
86032539ed | ||
|
|
b2ec012e10 | ||
|
|
7fd8623684 | ||
|
|
083753a96d | ||
|
|
4b62c31f29 | ||
|
|
2208d4e0e0 | ||
|
|
df7f4c3c2d | ||
|
|
12323e1416 | ||
|
|
2edc5e1071 | ||
|
|
2162ed9ebe | ||
|
|
6acebb73ec | ||
|
|
7a1d6c0ab5 | ||
|
|
d16e31c0e5 | ||
|
|
d9a8b6a191 | ||
|
|
5ec4cd7fcd | ||
|
|
a7925e3c79 | ||
|
|
472b420620 | ||
|
|
8f55ba1d37 | ||
|
|
7b1428bf51 | ||
|
|
d5b3b1868e | ||
|
|
49f3fc0be5 | ||
|
|
59e641ccb3 | ||
|
|
1d9268b224 | ||
|
|
470a4bd6f7 | ||
|
|
8801d59b2e | ||
|
|
6a20e06982 | ||
|
|
b17abce2c2 | ||
|
|
f67e334016 | ||
|
|
c1de66520e | ||
|
|
37e086d822 | ||
|
|
d21f8ca8de | ||
|
|
6af4e7c2ec | ||
|
|
1f2bdc8c9e | ||
|
|
4c0fd29b7f | ||
|
|
ffef67be8f | ||
|
|
4d100bf542 | ||
|
|
8a75d015a1 | ||
|
|
f806272c06 | ||
|
|
4935eeff28 | ||
|
|
eed0264b9c | ||
|
|
dd82daf65c | ||
|
|
55d9596835 | ||
|
|
cb1c1c502b | ||
|
|
6d4f62d6f6 | ||
|
|
43808216e6 | ||
|
|
f66bb7af73 | ||
|
|
ae86d56a7d | ||
|
|
1cee103b1c | ||
|
|
3c3b6880e4 | ||
|
|
0b84402c83 | ||
|
|
61a61abc7c | ||
|
|
fc878775c2 | ||
|
|
7acf736300 | ||
|
|
9d50301a43 | ||
|
|
7f185ca23c | ||
|
|
94582c9001 | ||
|
|
41b73feeab | ||
|
|
96493a5493 | ||
|
|
93c593545d | ||
|
|
11758c23c0 | ||
|
|
1cd94a77c6 | ||
|
|
5ad3fdbf69 | ||
|
|
851ae49c84 | ||
|
|
82aee9a291 | ||
|
|
1b5cbf936a | ||
|
|
1daeaf51ef | ||
|
|
49ef48a74a | ||
|
|
a680fccb12 | ||
|
|
e67552d8bd | ||
|
|
8080acfb2e | ||
|
|
dbd30a815f | ||
|
|
442568de00 | ||
|
|
d15fc5c6be | ||
|
|
aa6d5ed626 | ||
|
|
283d28bed9 | ||
|
|
315cacd474 | ||
|
|
44ab1e7023 | ||
|
|
beef4e9963 | ||
|
|
990f68fb3b | ||
|
|
ee4933a4f8 | ||
|
|
c91867b8eb | ||
|
|
8608ee027a | ||
|
|
394ddc8db4 | ||
|
|
83455aeaea | ||
|
|
707c091c9b | ||
|
|
d3f5892dd2 | ||
|
|
70b6c33204 | ||
|
|
624a3a6a54 | ||
|
|
03aea2cb36 |
@@ -22,9 +22,9 @@ jobs:
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Bun
|
||||
uses: oven-sh/setup-bun@v1
|
||||
uses: oven-sh/setup-bun@v2
|
||||
with:
|
||||
bun-version: latest
|
||||
bun-version: 1.3.14
|
||||
|
||||
- name: Install dependencies
|
||||
run: bun install
|
||||
@@ -76,9 +76,9 @@ jobs:
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Bun
|
||||
uses: oven-sh/setup-bun@v1
|
||||
uses: oven-sh/setup-bun@v2
|
||||
with:
|
||||
bun-version: latest
|
||||
bun-version: 1.3.14
|
||||
|
||||
- name: Install dependencies
|
||||
run: bun install
|
||||
@@ -118,9 +118,9 @@ jobs:
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Bun
|
||||
uses: oven-sh/setup-bun@v1
|
||||
uses: oven-sh/setup-bun@v2
|
||||
with:
|
||||
bun-version: latest
|
||||
bun-version: 1.3.14
|
||||
|
||||
- name: Install dependencies
|
||||
run: bun install
|
||||
@@ -152,9 +152,9 @@ jobs:
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Bun
|
||||
uses: oven-sh/setup-bun@v1
|
||||
uses: oven-sh/setup-bun@v2
|
||||
with:
|
||||
bun-version: latest
|
||||
bun-version: 1.3.14
|
||||
|
||||
- name: Install dependencies
|
||||
run: bun install
|
||||
|
||||
@@ -36,7 +36,7 @@ jobs:
|
||||
- name: Setup Bun
|
||||
uses: oven-sh/setup-bun@v2
|
||||
with:
|
||||
bun-version: latest
|
||||
bun-version: 1.3.14
|
||||
|
||||
- name: Setup Node.js
|
||||
uses: actions/setup-node@v6
|
||||
|
||||
@@ -54,5 +54,6 @@ jobs:
|
||||
platforms: linux/amd64,linux/arm64
|
||||
context: .
|
||||
push: true
|
||||
provenance: false
|
||||
tags: ${{ steps.meta.outputs.tags }}
|
||||
labels: ${{ steps.meta.outputs.labels }}
|
||||
|
||||
@@ -11,6 +11,7 @@ data/
|
||||
*.db
|
||||
*.diff
|
||||
*.orig
|
||||
code_quality.md
|
||||
.agents
|
||||
|
||||
# Playwright
|
||||
|
||||
@@ -90,7 +90,8 @@ Add any additional context, caveats, or follow-up work.
|
||||
- `bun run format`
|
||||
- `bun run typecheck`
|
||||
- `bun run test`
|
||||
- `bun run test:e2e`
|
||||
- `bun run test:e2e:app`
|
||||
- `bun run test:e2e:webui`
|
||||
- `bun run test:e2e:workflow`
|
||||
|
||||
- **Backend Testing Mandate**: Every backend feature, service method, workflow, and activity MUST be accompanied by comprehensive tests. Logic-heavy code without corresponding test coverage is considered incomplete.
|
||||
@@ -285,7 +286,7 @@ describe('Team API', () => {
|
||||
### Web App E2E Tests
|
||||
|
||||
- Located in `apps/web/e2e/**/*.spec.ts`, organized by domain under `tests/<domain>/` (e.g. `auth`, `project`).
|
||||
- Run via `bun run test:e2e`.
|
||||
- Run via `bun run test:e2e:app`.
|
||||
- **Fixtures**: Use the `owner`, `project`, and `file` fixtures for setup — they seed data through API calls/DB (no slow UI setup). You can add more fixtures if necessary.
|
||||
- **Documentation**: Every test case MUST be documented in [`apps/web/e2e/README.md`](apps/web/e2e/README.md). Add or update the corresponding entry in the README whenever you add, rename, or remove a spec.
|
||||
|
||||
@@ -321,7 +322,8 @@ We use `prisma-json-types-generator` to enforce strict type-safety for Prisma `J
|
||||
|
||||
- Development: Use `bun --bun run prisma migrate dev` to create and apply migrations during development.
|
||||
- Production: Use `bun --bun run prisma migrate deploy` to apply pending migrations in production environments.
|
||||
- **No Manual Migration Creation**: Never create migration SQL files or directories manually by hand. Always use Prisma CLI commands (e.g. `bun --bun run prisma migrate dev --create-only` to generate a migration template, or `bun --bun run prisma migrate dev`) so Prisma correctly tracks migration metadata and checksums.
|
||||
- **No Manual DDL Creation**: Never hand-write **schema (DDL) migration** files or directories. Always generate them with Prisma CLI (`bun --bun run prisma migrate dev --create-only` to create a template, then edit it if needed, or `bun --bun run prisma migrate dev` to apply) so Prisma correctly tracks migration metadata and checksums.
|
||||
- **Data Migrations Are Allowed**: Pure **data migration** SQL (no schema change) may be written by hand, but it MUST live inside a migration generated via `bun --bun run prisma migrate dev --create-only` so it is tracked and applied automatically.
|
||||
- **No Automatic Dev DB Reset**: Do not run `prisma migrate reset --force` or commands that force-reset the database automatically. If migrations become out of sync or a reset is required, stop executing, report the situation to the user, and present suggested manual cleanup/reset steps for the user to execute.
|
||||
|
||||
### Commands
|
||||
|
||||
+8
-2
@@ -1,6 +1,6 @@
|
||||
#syntax=docker/dockerfile:1.7-labs
|
||||
# Stage 1: Builder
|
||||
FROM oven/bun:1 AS builder
|
||||
FROM oven/bun:1.3.14 AS builder
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
@@ -8,6 +8,7 @@ WORKDIR /app
|
||||
COPY package.json bun.lock ./
|
||||
COPY --parents packages/*/package.json ./
|
||||
COPY --parents apps/*/package.json ./
|
||||
COPY patches/ ./patches/
|
||||
|
||||
# Install dependencies (including devDependencies for build tools)
|
||||
RUN bun install --frozen-lockfile
|
||||
@@ -24,7 +25,7 @@ RUN bun run build.ts
|
||||
RUN bun run scripts/extract-runtime-deps.ts
|
||||
|
||||
# Stage 2: Runner
|
||||
FROM oven/bun:1 AS runner
|
||||
FROM oven/bun:1.3.14 AS runner
|
||||
|
||||
# Install ffmpeg/ffprobe
|
||||
COPY --from=mwader/static-ffmpeg:8.1 /ffmpeg /usr/local/bin/
|
||||
@@ -79,6 +80,11 @@ USER root
|
||||
COPY scripts/docker-entrypoint.sh /usr/local/bin/docker-entrypoint.sh
|
||||
RUN chmod +x /usr/local/bin/docker-entrypoint.sh
|
||||
|
||||
# Expose "bun index.js" as "shumai" CLI command (and alias "shuami")
|
||||
RUN printf '#!/bin/sh\nexec bun /app/index.js "$@"\n' > /usr/local/bin/shumai \
|
||||
&& chmod +x /usr/local/bin/shumai \
|
||||
&& ln -s /usr/local/bin/shumai /usr/local/bin/shuami
|
||||
|
||||
ENTRYPOINT ["docker-entrypoint.sh"]
|
||||
|
||||
# Default command: run migrations and start API server
|
||||
|
||||
@@ -9,7 +9,13 @@
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a target="_blank" href="https://shumai.one/">Website</a> | <a target="_blank" href="https://docs.shumai.one/introduction">Docs</a> | <a target="_blank" href="https://staging.shumai.one">Demo</a> | <a target="_blank" href="https://discord.gg/sUzhujK6DD">Discord</a> | <a target="_blank" href="README_CN.md">中文</a>
|
||||
<a href="https://hub.docker.com/r/shumaione/shumai"><img alt="Docker pulls" src="https://img.shields.io/docker/pulls/shumaione/shumai" /></a>
|
||||
<a href="https://github.com/shumaiOne/shumai/releases"><img alt="GitHub latest release" src="https://img.shields.io/github/v/release/shumaiOne/shumai" /></a>
|
||||
<a href="LICENSE"><img alt="License" src="https://img.shields.io/badge/license-MIT-blue" /></a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a target="_blank" href="https://shumai.one/">Website</a> | <a target="_blank" href="https://docs.shumai.one/getting-started/overview">Docs</a> | <a target="_blank" href="https://staging.shumai.one">Demo</a> | <a target="_blank" href="https://discord.gg/sUzhujK6DD">Discord</a> | <a target="_blank" href="README_CN.md">中文</a>
|
||||
</p>
|
||||
|
||||

|
||||
@@ -24,15 +30,20 @@ Shumai is an open-source Frame.io alternative built for creative teams to collab
|
||||
* **Granular Access Control**: Manage workspace permissions with team-level and project-level role-based access control.
|
||||
* **Distributed Transcoding via Temporal**: Offload resource-intensive video transcoding to a background worker pool orchestrated by Temporal.
|
||||
* **Custom Asset Metadata**: Define dynamic metadata fields tailored to your production pipeline.
|
||||
* **Share Link Watermarking**: Protect shared media with customizable text and image watermarks, and save watermark as reusable templates.
|
||||
* **Wide File Format Support**: Preview common creative file formats, including images (with PSD support), videos, audio, and documents, while allowing any file type to be uploaded and stored.
|
||||
* **Office & Document PDF Proxying via Gotenberg**: Convert Word, PowerPoint, Excel, Markdown, HTML, and CSV documents to high-quality PDF proxies for in-browser previewing using [Gotenberg](https://docs.shumai.one/using-shumai/gotenberg).
|
||||
|
||||
But Shumai goes beyond being a Frame.io alternative. With modern models like GPT-Image-2 and Seedance 2.5, AI can already handle a surprising amount of creative work. That means you can create or update videos and images from a simple prompt without having to jump back into Photoshop, Premiere or Houdini. That is why Shumai includes a powerful agent system:
|
||||
|
||||
* **Agent as a Team Member**: Mention a context-aware AI agent with `@mentions` directly in asset comments, just like a real teammate.
|
||||
* **Agent as a One-to-One Assistant**: Chat privately with the agent and ask it to help with tasks.
|
||||
* **Custom Skills & Tools**: Extend the agent by registering custom scripts, tools, and automation skills.
|
||||
* **Model Context Protocol (MCP)**: Connect agents to external tools and APIs through remote MCP servers, with OAuth authentication and per-agent MCP access.
|
||||
* **Isolated Sandbox Execution**: Run agent-submitted scripts safely in a sandboxed environment.
|
||||
* **AI Metadata Autofill**: Automatically fill in custom metadata for new assets.
|
||||
* **Semantic Search**: Find assets by visual or conceptual meaning using vector embeddings (Gemini Embedding 2).
|
||||
* **Resource Quotas**: Set usage limits on AI tokens, costs, and tool execution per member, role, or team-wide, with real-time tracking.
|
||||
|
||||
Here is a short demo video showing what the Shumai agent can do:
|
||||
|
||||
@@ -40,10 +51,16 @@ Here is a short demo video showing what the Shumai agent can do:
|
||||
|
||||
https://github.com/user-attachments/assets/1186067a-72c0-41b9-836f-987438f2332a
|
||||
|
||||
Shumai also brings project management into the creative workflow. A built-in Kanban board helps teams organize tasks, track progress, and collaborate in one place.
|
||||
|
||||
The ultimate goal is an **agentic Kanban**, where agents and team members can work together on tasks. This is still a **work in progress**: you can already create tasks for AI agents, but agents cannot act on those tasks yet.
|
||||
|
||||
<img width="2880" height="2160" alt="localhost_3000_teams_01M0HQR3EEBS0B46K4FK39X2C8_kanban(1080p-2) (1)" src="https://github.com/user-attachments/assets/cd0648d0-c69a-4398-958b-8d15a33378b0" />
|
||||
|
||||
|
||||
|
||||
> [!NOTE]
|
||||
> **Media Processing & Storage:** When uploading media, Shumai always preserves and stores your original raw file. Note that the file size shown in the system represents the original file size and does not include the size of any transcoded files. For all media types (both images and videos), Shumai creates a 480p WebP poster image to serve as the preview in the file list view. Additionally:
|
||||
> **Media Processing & Storage:** When uploading media, Shumai always preserves and stores your original raw file. Note that the file size shown in the system represents the original file size and does not include the size of any transcoded files. For all media types (both images and videos), Shumai creates a 300p WebP poster image to serve as the preview in the file list view. Additionally:
|
||||
> * **For Images:** Shumai generates a high-quality WebP proxy at the exact same resolution as your original file for optimized viewing.
|
||||
> * **For Videos:** It generates at least one proxy video (depending on your transcoding settings), alongside a sprite image and a small preview video (capped at 1600 frames) to enable fast timeline scrubbing and lightning-quick previews.
|
||||
|
||||
@@ -242,11 +259,14 @@ BETTER_AUTH_SECRET=ySxs7DxzHDZBbeeHNPEwBuspYwipBqz5Gk5XdBjNhWw=
|
||||
STORAGE_BACKEND=local
|
||||
SHUMAI_SERVER_PORT=3000
|
||||
AWS_ENDPOINT_URL_S3=http://localhost:3000
|
||||
# Optional: base URL for MCP OAuth redirects (defaults to BETTER_AUTH_URL)
|
||||
MCP_OAUTH_REDIRECT_BASE_URL=http://localhost:3000
|
||||
```
|
||||
|
||||
> [!NOTE]
|
||||
> `SHUMAI_SERVER_PORT` sets the port the server starts on, while `AWS_ENDPOINT_URL_S3` is used by the browser to build file upload URLs.
|
||||
> If deploying on a remote server (e.g. `http://123.456.7.8`) with a mapped port (e.g. `12345:3000` in docker-compose), set `AWS_ENDPOINT_URL_S3` to `http://123.456.7.8:12345`.
|
||||
> `MCP_OAUTH_REDIRECT_BASE_URL` is only needed when MCP servers use OAuth: the authorization redirect URI defaults to `{BETTER_AUTH_URL}/api/mcp/oauth/callback`; set it to an externally reachable URL if the app is served behind a proxy.
|
||||
|
||||
#### Step 6: Run Shumai
|
||||
|
||||
|
||||
+37
-2
@@ -9,8 +9,13 @@
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a target="_blank" href="https://shumai.one/">官方网站</a> | <a target="_blank" href="https://docs.shumai.one/introduction">文档</a> | <a target="_blank" href="https://staging.shumai.one">在线演示</a> | <a target="_blank" href="README.md">English</a>
|
||||
<a href="https://hub.docker.com/r/shumaione/shumai"><img alt="Docker pulls" src="https://img.shields.io/docker/pulls/shumaione/shumai" /></a>
|
||||
<a href="https://github.com/shumaiOne/shumai/releases"><img alt="GitHub latest release" src="https://img.shields.io/github/v/release/shumaiOne/shumai" /></a>
|
||||
<a href="LICENSE"><img alt="License" src="https://img.shields.io/badge/license-MIT-blue" /></a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
<a target="_blank" href="https://shumai.one/">官方网站</a> | <a target="_blank" href="https://docs.shumai.one/getting-started/overview">文档</a> | <a target="_blank" href="https://staging.shumai.one">在线演示</a> | <a target="_blank" href="README.md">English</a>
|
||||
</p>
|
||||
|
||||

|
||||
@@ -25,22 +30,34 @@ Shumai 是一个开源的 Frame.io 替代方案,专为创意团队打造,让
|
||||
* **细粒度权限控制**:支持按团队、项目设置角色权限,方便管理不同成员的访问范围。
|
||||
* **基于 Temporal 的分布式转码**:把吃资源的视频转码任务交给后台 worker 池处理,由 Temporal 统一调度。
|
||||
* **自定义素材元数据**:可以按你的制作流程,自由定义动态元数据字段。
|
||||
* **分享链接水印**:通过可自定义的文字和图片水印保护共享媒体,并将水印配置保存为模板以便重复使用。
|
||||
* **丰富的文件格式支持**:支持预览常见创意文件格式,包括图片(支持 PSD)、视频、音频和文档,同时可上传和存储任意类型的文件。
|
||||
* **基于 Gotenberg 的文档 PDF 转码代理**:通过集成 [Gotenberg](https://docs.shumai.one/using-shumai/gotenberg) 支持将 Word、PowerPoint、Excel、Markdown、HTML 和 CSV 文档高质量转换为 PDF 代理文件进行在线预览。
|
||||
|
||||
但 Shumai 不仅仅只满足于 Frame.io 的开源替代。随着 GPT-Image-2、Seedance 2.5 这类强大模型的问世,AI已经生成产品级的图片/视频。很多时候,你只要给一句提示词,就能直接生成或修改图片和视频,而不用再打开 Photoshop、Premiere 或者 Houdini。也正因为这样,Shumai 才把 AI Agent 做成了核心能力:
|
||||
|
||||
* **Agent 就像团队成员**:你可以在素材评论区里直接用 `@` 提到 AI Agent,像拉一个真实同事进来一起看稿一样。
|
||||
* **Agent 也能当你的私聊助手**:你可以单独和它聊天,让它帮你查东西、做任务。
|
||||
* **自定义技能和工具**:你可以给 Agent 接上自己的脚本、工具和自动化能力。
|
||||
* **Model Context Protocol (MCP) 支持**:通过远程 MCP 服务端为 Agent 接入外部工具与 API,支持 OAuth 鉴权与按 Agent 独立分配访问权限。
|
||||
* **沙箱隔离执行**:Agent 生成的脚本会在隔离环境里运行,更安全。
|
||||
* **AI 自动补全元数据**:新素材上传后,系统可以自动帮你补一些元数据。
|
||||
* **语义搜索**:支持按画面内容或语义找素材,底层用的是向量 embedding(Gemini Embedding 2)。
|
||||
* **资源配额**:支持按成员、角色或全团队对 AI Token、成本和工具调用设置使用上限与实时用量监控。
|
||||
|
||||
下面是一个简短的 demo 视频,展示了 Shumai Agent 能做什么:
|
||||
|
||||
https://github.com/user-attachments/assets/1186067a-72c0-41b9-836f-987438f2332a
|
||||
|
||||
Shumai 也将项目管理融入了创意工作流程。 内置的看板可以帮助团队整理任务以及跟踪进度。
|
||||
|
||||
最终目标是打造一个 Agentic看板,让 Agent 和团队成员能够围绕同一个目标协同工作。目前这一功能仍在开发中: 你已经可以在看板中为 Agent 创建任务,但 Agent 目前还无法自动执行这些任务。
|
||||
|
||||
<img width="2880" height="2160" alt="localhost_3000_teams_01M0HQR3EEBS0B46K4FK39X2C8_kanban(1080p-2) (1)" src="https://github.com/user-attachments/assets/29ff1db1-2d65-4e3c-b467-754b777b406f" />
|
||||
|
||||
|
||||
> [!NOTE]
|
||||
> **媒体处理与存储机制:** 上传媒体文件后,Shumai 始终会保留并存储原始文件。请注意,系统中显示的文件大小为原始文件的大小,不包含转码后生成的代理文件大小。无论图片还是视频,都会额外生成一张 480p 的 WebP 封面图,作为文件列表中的预览图。此外:
|
||||
> **媒体处理与存储机制:** 上传媒体文件后,Shumai 始终会保留并存储原始文件。请注意,系统中显示的文件大小为原始文件的大小,不包含转码后生成的代理文件大小。无论图片还是视频,都会额外生成一张 300p 的 WebP 封面图,作为文件列表中的预览图。此外:
|
||||
>
|
||||
> * **图片:** 会生成一份与原图分辨率完全一致的高质量 WebP 转码版本,在保证画质的同时提升浏览性能。
|
||||
> * **视频:** 会根据转码配置生成至少一个代理视频,同时生成雪碧图(Sprite)和一段最长 1600 帧的低分辨率转码视频,用于实现快速拖动时间轴和即时视频预览。
|
||||
@@ -52,6 +69,24 @@ https://github.com/user-attachments/assets/1186067a-72c0-41b9-836f-987438f2332a
|
||||
以下是使用本地存储运行 Shumai 的快速上手指南。如需了解高级配置(包括 S3 兼容存储配置、Temporal 工作流编排等),请参阅我们的[官方文档](https://docs.shumai.one/getting-started/overview)。
|
||||
|
||||
### 方案一:使用 Docker Compose(推荐)
|
||||
<details>
|
||||
|
||||
<summary>复制这个提示词,让agent帮你安装</summary>
|
||||
|
||||
```
|
||||
请帮我在本机使用 Docker Compose 一键部署 Shumai。
|
||||
|
||||
请严格参考官方文档:
|
||||
https://gh-proxy.com/https://raw.githubusercontent.com/shumaiOne/shumai/main/README_CN.md
|
||||
|
||||
要求:
|
||||
|
||||
1. 只能使用 Docker Compose local方式部署,不要使用其他部署方式。
|
||||
2. 部署前请先检查本机是否已安装并可正常使用 Docker 和 Docker Compose。
|
||||
3. 如果本机未安装 Docker,请立即提醒用户先安装 Docker,并停止后续部署操作。不要自行安装 Docker,也不要采用其他方式部署。
|
||||
4. 获取 `docker-compose-aliyun.yaml` 文件内容时,必须通过 `https://gh-proxy.com` 加速访问,不要直接访问 GitHub Raw 地址。
|
||||
```
|
||||
</details>
|
||||
|
||||
使用 Docker Compose 是运行 Shumai 最快的方式。您无需克隆仓库,也不需要手动安装依赖包。请确保电脑上已安装 [Docker](https://docs.docker.com/get-docker/) 和 [Docker Compose](https://docs.docker.com/compose/install/),然后按照以下步骤操作:
|
||||
|
||||
|
||||
+58
@@ -0,0 +1,58 @@
|
||||
# Security Policy
|
||||
|
||||
## Reporting a Vulnerability
|
||||
|
||||
Please report security vulnerabilities **privately**. Do not open a public issue,
|
||||
pull request or Discord message for a suspected vulnerability, as that discloses it
|
||||
to everyone before a fix exists.
|
||||
|
||||
Use **[GitHub private vulnerability reporting](https://github.com/shumaiOne/shumai/security/advisories/new)**
|
||||
(the "Report a vulnerability" button on the Security tab). If that is unavailable,
|
||||
contact the maintainer directly rather than in a public channel.
|
||||
|
||||
Please include:
|
||||
|
||||
- What the issue is, and the impact you believe it has
|
||||
- The version or commit you tested (`git rev-parse HEAD`, or the image digest)
|
||||
- Steps to reproduce, ideally minimal
|
||||
- Your deployment shape: storage backend, whether the agent feature is enabled,
|
||||
and whether the instance is internet-reachable
|
||||
|
||||
## Supported Versions
|
||||
|
||||
Shumai is pre-1.0 and moves quickly. Security fixes are made against the **latest
|
||||
release**. Users are encouraged to track releases rather than pin indefinitely.
|
||||
|
||||
## Scope
|
||||
|
||||
**In scope** — the application, its API, the shipped Docker images, and the
|
||||
deployment manifests under `docker-compose/`.
|
||||
|
||||
Deployment manifests are explicitly in scope. A default that is unsafe when
|
||||
followed as documented is a real finding, because the documented quickstart is what
|
||||
most operators actually run.
|
||||
|
||||
**Out of scope**
|
||||
|
||||
- Vulnerabilities in third-party dependencies, unless Shumai's use of them is what
|
||||
creates the exposure. Report those upstream.
|
||||
- Findings that require an already-compromised host or database.
|
||||
- Configurations that deviate from the documented deployment.
|
||||
|
||||
## Operator guidance
|
||||
|
||||
Shumai is self-hosted, so several controls belong to the operator rather than to the
|
||||
project:
|
||||
|
||||
- **Set `BETTER_AUTH_SECRET` per deployment.** It signs sessions and, in local
|
||||
storage mode, upload URLs. Never reuse a value from documentation or an example.
|
||||
- **Do not expose the instance to the public internet without a reverse proxy**
|
||||
terminating TLS and applying your own access policy.
|
||||
- **Do not publish the database port.** Set a real database password.
|
||||
- **Treat the agent feature as a code-execution surface.** If you enable it, run it
|
||||
where a compromise is survivable, and review the sandbox network policy.
|
||||
|
||||
## Disclosure
|
||||
|
||||
Please allow a reasonable period for a fix before public disclosure. The maintainer
|
||||
will acknowledge reports and keep reporters informed of progress.
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@shumai/agent-app",
|
||||
"version": "0.3.3",
|
||||
"version": "0.4.2",
|
||||
"private": true,
|
||||
"type": "module",
|
||||
"bin": {
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
export * from '@shumai/agent/src/workflows/agent-autofill'
|
||||
export * from '@shumai/agent/src/workflows/agent-chat'
|
||||
export * from '@shumai/agent/src/workflows/agent-embedding'
|
||||
export * from '@shumai/agent/src/workflows/agent-tool-call'
|
||||
export * from '@shumai/agent/src/workflows/query-embedding-for-search'
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@shumai/cli",
|
||||
"version": "0.3.3",
|
||||
"version": "0.4.2",
|
||||
"private": true,
|
||||
"type": "module",
|
||||
"bin": {
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@shumai/transcode-app",
|
||||
"version": "0.3.3",
|
||||
"version": "0.4.2",
|
||||
"private": true,
|
||||
"type": "module",
|
||||
"bin": {
|
||||
|
||||
+12
-2
@@ -2,7 +2,7 @@
|
||||
|
||||
Fullstack end-to-end tests for the Shumai web app. They run against a real backend
|
||||
(pgvector container + local S3 storage) served on `http://localhost:5200` and are
|
||||
executed with Playwright via `bun run test:e2e`.
|
||||
executed with Playwright via `bun run test:e2e:app`.
|
||||
|
||||
## Structure
|
||||
|
||||
@@ -56,6 +56,8 @@ apps/web/e2e/
|
||||
|---|---|
|
||||
| Sign up as the first user and become the team owner | `tests/auth/signup.spec.ts` |
|
||||
| Log in with existing credentials | `tests/auth/login.spec.ts` |
|
||||
| Show error when accessing reset-password page without token | `tests/auth/reset-password.spec.ts` |
|
||||
| Reset password with valid token and allow logging in with new password | `tests/auth/reset-password.spec.ts` |
|
||||
|
||||
### team
|
||||
| Test | File |
|
||||
@@ -63,12 +65,13 @@ apps/web/e2e/
|
||||
| Owner invites a member via invite link and the invitee joins | `tests/team/invite-member.spec.ts` |
|
||||
| Owner removes a member via the members dialog; the membership is deleted from the DB | `tests/team/remove-member.spec.ts` |
|
||||
| Owner changes a team member role in the members dialog and permissions update | `tests/team/change-member-role.spec.ts` |
|
||||
| Owner manages resource quotas in settings and resets usage from the dashboard | `tests/team/quotas-settings.spec.ts` |
|
||||
|
||||
### project
|
||||
| Test | File |
|
||||
|---|---|
|
||||
| Owner creates a project with a cover image | `tests/project/create-project.spec.ts` |
|
||||
| Owner uploads a file via the "Upload File" context menu action | `tests/project/upload-file.spec.ts` |
|
||||
| Owner uploads a file or an unsupported file via the "Upload File" context menu action | `tests/project/upload-file.spec.ts` |
|
||||
| Owner deletes a file, finds it in recently deleted, and restores it | `tests/project/delete-restore.spec.ts` |
|
||||
| Owner creates a share link from a file context menu and lands on the share page | `tests/project/create-share-link.spec.ts` |
|
||||
| Owner protects a share with a password; guests must enter it to view | `tests/project/share-password.spec.ts` |
|
||||
@@ -80,10 +83,17 @@ apps/web/e2e/
|
||||
| Owner drags a file into a folder and a folder into another folder | `tests/project/move-folder-file.spec.ts` |
|
||||
| Owner drags a file onto a file to create a version stack | `tests/project/version-stack-create.spec.ts` |
|
||||
| Owner drags a file onto a version stack to add a new version | `tests/project/version-stack-add-version.spec.ts` |
|
||||
| Owner manages version stack: removes version from 3-version stack | `tests/project/version-stack-manage.spec.ts` |
|
||||
| Owner removes version from 2-version stack which dissolves into standalone files | `tests/project/version-stack-manage.spec.ts` |
|
||||
| Dissolving a shared version stack renders the remaining standalone file name on the share page | `tests/project/version-stack-manage.spec.ts` |
|
||||
| Moving a shared file into a shared version stack leaves only 1 stack card on the share page | `tests/project/version-stack-manage.spec.ts` |
|
||||
| Owner searches the file list by an English name keyword | `tests/project/search-file-list.spec.ts` |
|
||||
| Owner searches the file list by Chinese, Japanese, and Korean name keywords | `tests/project/search-file-list.spec.ts` |
|
||||
| Owner searches the file list with a keyword and a filter condition | `tests/project/search-file-list.spec.ts` |
|
||||
| Owner saves a search result as a collection | `tests/project/save-search-collection.spec.ts` |
|
||||
| Image share with watermark + download disabled: no download buttons on public list/detail pages, watermarked proxy served, download-url rejected | `tests/project/share-watermark-no-download.spec.ts` |
|
||||
| Video share with watermark + download disabled: no download buttons on public list/detail pages, watermarked proxy served, download-url rejected | `tests/project/share-watermark-no-download.spec.ts` |
|
||||
| Owner views a file and it appears in recents | `tests/project/recents.spec.ts` |
|
||||
|
||||
### file
|
||||
| Test | File |
|
||||
|
||||
+16
-11
@@ -21,19 +21,23 @@ const currentDir = path.dirname(fileURLToPath(import.meta.url))
|
||||
const envPath = path.resolve(currentDir, '.env.e2e')
|
||||
const fixturesDir = path.resolve(currentDir, '../../../packages/e2e/fixtures')
|
||||
|
||||
// Load E2E environment variables if present
|
||||
if (fs.existsSync(envPath)) {
|
||||
const content = fs.readFileSync(envPath, 'utf8')
|
||||
content.split('\n').forEach((line) => {
|
||||
const parts = line.split('=')
|
||||
if (parts.length >= 2) {
|
||||
const key = parts[0].trim()
|
||||
const value = parts.slice(1).join('=').trim()
|
||||
process.env[key] = value
|
||||
}
|
||||
})
|
||||
function loadEnv() {
|
||||
if (fs.existsSync(envPath)) {
|
||||
const content = fs.readFileSync(envPath, 'utf8')
|
||||
content.split('\n').forEach((line) => {
|
||||
const parts = line.split('=')
|
||||
if (parts.length >= 2) {
|
||||
const key = parts[0].trim()
|
||||
const value = parts.slice(1).join('=').trim()
|
||||
process.env[key] = value
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// Load E2E environment variables if present
|
||||
loadEnv()
|
||||
|
||||
export interface OwnerFixture {
|
||||
/** Page opened in a browser context logged in as the team owner. */
|
||||
page: Page
|
||||
@@ -104,6 +108,7 @@ export const test = base.extend<{
|
||||
prisma: [
|
||||
// eslint-disable-next-line no-empty-pattern
|
||||
async ({}, use) => {
|
||||
loadEnv()
|
||||
const connectionString = process.env.DATABASE_URL
|
||||
const pool = new Pool({ connectionString })
|
||||
const adapter = new PrismaPg(pool)
|
||||
|
||||
@@ -24,14 +24,32 @@ export async function dragCard(page: Page, source: Locator, target: Locator): Pr
|
||||
await page.mouse.move(fromX, fromY)
|
||||
await page.mouse.down()
|
||||
|
||||
// Move in several chunks so the dnd-kit sensor activates mid-drag
|
||||
const dx = toX - fromX
|
||||
const dy = toY - fromY
|
||||
const dist = Math.hypot(dx, dy)
|
||||
|
||||
// Step past the 10px activation constraint to trigger drag activation
|
||||
// and give the browser a brief moment for status to become 'dragging'
|
||||
const activationRatio = dist > 0 ? Math.min(1, 15 / dist) : 1
|
||||
await page.mouse.move(fromX + dx * activationRatio, fromY + dy * activationRatio)
|
||||
await page.waitForTimeout(50)
|
||||
|
||||
// Move in several chunks so the intermediate dragmove handlers run
|
||||
const chunks = 8
|
||||
for (let i = 1; i <= chunks; i++) {
|
||||
const x = fromX + ((toX - fromX) * i) / chunks
|
||||
const y = fromY + ((toY - fromY) * i) / chunks
|
||||
const x = fromX + (dx * i) / chunks
|
||||
const y = fromY + (dy * i) / chunks
|
||||
await page.mouse.move(x, y)
|
||||
await page.waitForTimeout(15)
|
||||
await page.waitForTimeout(20)
|
||||
}
|
||||
|
||||
// Ensure pointer is directly over target center and allow requestAnimationFrame
|
||||
// and collision microtasks to settle before triggering drop
|
||||
await page.mouse.move(toX, toY)
|
||||
await page.evaluate(
|
||||
() => new Promise((resolve) => requestAnimationFrame(() => requestAnimationFrame(resolve))),
|
||||
)
|
||||
await page.waitForTimeout(100)
|
||||
|
||||
await page.mouse.up()
|
||||
}
|
||||
|
||||
@@ -3,18 +3,20 @@ import type { APIRequestContext, Locator, Page } from '@playwright/test'
|
||||
interface CreateShareResponse {
|
||||
id?: string
|
||||
name?: string
|
||||
rootFolderId?: string
|
||||
}
|
||||
|
||||
/**
|
||||
* Locates a file/folder card by its name. File names are rendered as
|
||||
* `EditableText` inputs (not text nodes), so `getByText` does not match them.
|
||||
* The returned locator points at the card wrapper div (right-clickable to open
|
||||
* the card context menu).
|
||||
* Locates a file/folder card by its name. Matches both read-only text nodes
|
||||
* and active EditableText inputs. The returned locator points at the card
|
||||
* wrapper div (right-clickable to open the card context menu).
|
||||
*/
|
||||
export function fileCard(page: Page, name: string): Locator {
|
||||
return page
|
||||
.locator('div.group')
|
||||
.filter({ has: page.locator(`input[value="${name}"]`) })
|
||||
.locator('[data-testid="file-card"]')
|
||||
.filter({
|
||||
has: page.locator(`input[value="${name}"]`).or(page.getByText(name, { exact: true })),
|
||||
})
|
||||
.first()
|
||||
}
|
||||
|
||||
@@ -23,7 +25,7 @@ export async function apiCreateShare(
|
||||
request: APIRequestContext,
|
||||
projectId: string,
|
||||
name: string,
|
||||
): Promise<{ id: string; name: string }> {
|
||||
): Promise<{ id: string; name: string; rootFolderId: string }> {
|
||||
const res = await request.post(`/api/projects/${projectId}/shares`, {
|
||||
data: { name },
|
||||
})
|
||||
@@ -31,10 +33,10 @@ export async function apiCreateShare(
|
||||
throw new Error(`Create share API failed (${res.status()}): ${await res.text()}`)
|
||||
}
|
||||
const body = (await res.json()) as CreateShareResponse
|
||||
if (!body.id || !body.name) {
|
||||
if (!body.id || !body.name || !body.rootFolderId) {
|
||||
throw new Error(`Create share returned an unexpected response: ${JSON.stringify(body)}`)
|
||||
}
|
||||
return { id: body.id, name: body.name }
|
||||
return { id: body.id, name: body.name, rootFolderId: body.rootFolderId }
|
||||
}
|
||||
|
||||
/** Adds assets to a share link through the API. */
|
||||
@@ -51,6 +53,66 @@ export async function apiAddAssetsToShare(
|
||||
}
|
||||
}
|
||||
|
||||
/** Updates share link settings (e.g. `allowDownload`) through the API. */
|
||||
export async function apiUpdateShare(
|
||||
request: APIRequestContext,
|
||||
shareId: string,
|
||||
patch: { allowDownload?: boolean },
|
||||
): Promise<void> {
|
||||
const res = await request.put(`/api/shares/${shareId}`, { data: patch })
|
||||
if (!res.ok()) {
|
||||
throw new Error(`Update share API failed (${res.status()}): ${await res.text()}`)
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Enables a text watermark on the share link through the API. Uses the same
|
||||
* default block shape the watermark editor produces (a "CONFIDENTIAL" text
|
||||
* block), so the transcode workflow runs against a realistic config.
|
||||
*/
|
||||
export async function apiEnableShareWatermark(
|
||||
request: APIRequestContext,
|
||||
shareId: string,
|
||||
): Promise<void> {
|
||||
const res = await request.put(`/api/shares/${shareId}/watermark`, {
|
||||
data: {
|
||||
enabled: true,
|
||||
config: {
|
||||
blocks: [
|
||||
{
|
||||
id: `wm-${Date.now()}`,
|
||||
type: 'text',
|
||||
text: 'CONFIDENTIAL',
|
||||
x: 0.5,
|
||||
y: 0.5,
|
||||
// size is a fraction (0..1) of the canvas width
|
||||
size: 0.05,
|
||||
color: '#999999',
|
||||
opacity: 0.5,
|
||||
rotation: -30,
|
||||
},
|
||||
],
|
||||
},
|
||||
},
|
||||
})
|
||||
if (!res.ok()) {
|
||||
throw new Error(`Enable share watermark API failed (${res.status()}): ${await res.text()}`)
|
||||
}
|
||||
}
|
||||
|
||||
/** Requests a public download URL. Returns status + body for assertions. */
|
||||
export async function apiPublicDownloadUrl(
|
||||
request: APIRequestContext,
|
||||
shareId: string,
|
||||
fileId: string,
|
||||
key: string,
|
||||
): Promise<{ status: number; body: unknown }> {
|
||||
const res = await request.post(`/api/shares/${shareId}/files/${fileId}/download-url`, {
|
||||
data: { key },
|
||||
})
|
||||
return { status: res.status(), body: await res.json().catch(() => null) }
|
||||
}
|
||||
|
||||
/** Uploads a file asset through the official API upload task endpoints. */
|
||||
export async function apiUploadFile(
|
||||
request: APIRequestContext,
|
||||
|
||||
@@ -32,4 +32,7 @@ async function start() {
|
||||
await import('../src/index.ts')
|
||||
}
|
||||
|
||||
start().catch(console.error)
|
||||
start().catch((err) => {
|
||||
console.error('Failed to start E2E server:', err)
|
||||
process.exit(1)
|
||||
})
|
||||
|
||||
@@ -0,0 +1,63 @@
|
||||
import { expect, test } from '../../fixtures'
|
||||
import { apiSignup, E2E_PASSWORD, uniqueEmail } from '../../helpers/auth'
|
||||
import { loginViaUi } from '../../helpers/ui'
|
||||
|
||||
test('should show error when accessing reset-password page without token', async ({ page }) => {
|
||||
await page.goto('/reset-password')
|
||||
await expect(page.getByText('Invalid or missing reset token.')).toBeVisible()
|
||||
await expect(page.getByRole('button', { name: 'Go to Login' })).toBeVisible()
|
||||
})
|
||||
|
||||
test('should reset password with valid token and allow logging in with new password', async ({
|
||||
page,
|
||||
request,
|
||||
prisma,
|
||||
}) => {
|
||||
const email = uniqueEmail('reset-pw')
|
||||
const oldPassword = E2E_PASSWORD
|
||||
const newPassword = 'newSecretPassword123'
|
||||
|
||||
// 1. Seed user
|
||||
await apiSignup(request, email, oldPassword)
|
||||
|
||||
// 2. Request password reset via API
|
||||
const resetRes = await request.post('/api/auth/request-password-reset', {
|
||||
data: {
|
||||
email,
|
||||
redirectTo: '/reset-password',
|
||||
},
|
||||
})
|
||||
expect(resetRes.ok()).toBe(true)
|
||||
|
||||
// Retrieve the generated verification token from DB
|
||||
const verification = await prisma.verification.findFirst({
|
||||
where: {
|
||||
identifier: { startsWith: 'reset-password:' },
|
||||
},
|
||||
orderBy: { createdAt: 'desc' },
|
||||
})
|
||||
expect(verification).not.toBeNull()
|
||||
const token = verification!.identifier.replace('reset-password:', '')
|
||||
|
||||
// 3. Open reset password page with token
|
||||
await page.goto(`/reset-password?token=${token}`)
|
||||
|
||||
// 4. Fill in new password and confirmation
|
||||
await page.locator('input#password').fill(newPassword)
|
||||
await page.locator('input#confirmPassword').fill(newPassword)
|
||||
|
||||
// 5. Submit form
|
||||
await page.getByRole('button', { name: 'Reset Password' }).click()
|
||||
|
||||
// 6. Verify success state
|
||||
await expect(page.getByText('Password reset successfully!')).toBeVisible()
|
||||
|
||||
// 7. Click Go to Login
|
||||
await page.getByRole('button', { name: 'Go to Login' }).click()
|
||||
await expect(page).toHaveURL('/login')
|
||||
|
||||
// 8. Log in with the new password
|
||||
await loginViaUi(page, email, newPassword)
|
||||
await expect(page).toHaveURL(/\/teams\/[^/]+/)
|
||||
await expect(page.getByRole('heading', { name: 'Projects' })).toBeVisible()
|
||||
})
|
||||
@@ -40,8 +40,8 @@ test('owner should create a project with a cover image', async ({ owner, prisma
|
||||
await expect(page).toHaveURL(/\/projects\/[^/]+/)
|
||||
await expect(page.locator(`text=${projectName}`).first()).toBeVisible()
|
||||
|
||||
// Back on the dashboard the new project card is visible with its cover
|
||||
await page.click('button[aria-label="Dashboard"]')
|
||||
// Back on the home page the new project card is visible with its cover
|
||||
await page.click('button[aria-label="Home"]')
|
||||
await expect(page).toHaveURL(/\/teams\/[^/]+/)
|
||||
await expect(page.locator(`img[alt="${projectName}"]`)).toBeVisible()
|
||||
|
||||
|
||||
@@ -0,0 +1,35 @@
|
||||
import { expect, test } from '../../fixtures'
|
||||
import { fileCard } from '../../helpers/files'
|
||||
|
||||
test('owner views a file and it appears in recents', async ({ file }) => {
|
||||
const { page, projectId, fileName, fileId } = file
|
||||
|
||||
// Open the file details page to record view
|
||||
await page.goto(`/projects/${projectId}/files/${fileId}`)
|
||||
await expect(page.getByText(fileName).first()).toBeVisible()
|
||||
|
||||
// Navigate to Recents page via sidebar or direct URL
|
||||
await page.goto(`/projects/${projectId}`)
|
||||
await page.getByText('Recently Viewed').first().click()
|
||||
await expect(page).toHaveURL(new RegExp(`/projects/${projectId}/recents`))
|
||||
|
||||
// The viewed file should be visible in recents
|
||||
const card = fileCard(page, fileName)
|
||||
await expect(card).toBeVisible()
|
||||
|
||||
// Toolbar should show hint text instead of action buttons
|
||||
await expect(
|
||||
page.getByText('This page displays the 100 most recent files you viewed in this project.'),
|
||||
).toBeVisible()
|
||||
await expect(page.getByRole('button', { name: 'Field' })).not.toBeVisible()
|
||||
await expect(page.getByRole('button', { name: 'Search' })).not.toBeVisible()
|
||||
await expect(page.getByText('AGENTS.md')).not.toBeVisible()
|
||||
|
||||
// Right-clicking the file should NOT show the context menu
|
||||
await card.click({ button: 'right' })
|
||||
await expect(page.getByRole('menuitem', { name: 'Delete' })).not.toBeVisible()
|
||||
await expect(page.getByRole('menuitem', { name: 'Download' })).not.toBeVisible()
|
||||
|
||||
// The per-item overflow menu must also be unavailable on the read-only Recents page.
|
||||
await expect(card.getByRole('button')).toHaveCount(0)
|
||||
})
|
||||
@@ -0,0 +1,184 @@
|
||||
import { expect, test } from '../../fixtures'
|
||||
import {
|
||||
apiAddAssetsToShare,
|
||||
apiCreateShare,
|
||||
apiEnableShareWatermark,
|
||||
apiPublicDownloadUrl,
|
||||
apiUpdateShare,
|
||||
fileCard,
|
||||
} from '../../helpers/files'
|
||||
|
||||
/**
|
||||
* The watermarked + download-disabled combination is frequently used together:
|
||||
* guests can preview the content but never download it, and any previewed proxy
|
||||
* carries a watermark. This covers both watermarkable media types (image and
|
||||
* video) and asserts, per type:
|
||||
* - the public share list page exposes no download affordance,
|
||||
* - the public share file detail page exposes no download affordance,
|
||||
* - the proxy loaded in the detail page is the watermarked version, and
|
||||
* - the download-url endpoint rejects guest download attempts with 403.
|
||||
*/
|
||||
for (const mediaType of ['image', 'video'] as const) {
|
||||
// NOTE: `test.use` must be scoped per describe block — a bare `test.use`
|
||||
// inside a `for` loop leaks the last iteration's value to every test.
|
||||
test.describe(`${mediaType} share`, () => {
|
||||
test.use({ fileOptions: { mediaType } })
|
||||
|
||||
// Transcoding (original + watermark) happens through the local workflow
|
||||
// executor, so this test needs a much larger budget than the 60s default.
|
||||
test.setTimeout(300_000)
|
||||
|
||||
test('with watermark + download disabled: no download buttons, watermarked proxy', async ({
|
||||
file,
|
||||
browser,
|
||||
prisma,
|
||||
}) => {
|
||||
const { context, projectId, fileName, fileId } = file
|
||||
|
||||
// The watermark transcode re-encodes from the existing transcode slots, so
|
||||
// the original transcode must finish first.
|
||||
await expect
|
||||
.poll(
|
||||
async () => {
|
||||
const asset = await prisma.asset.findUnique({ where: { id: fileId } })
|
||||
return asset?.status
|
||||
},
|
||||
{ timeout: 60_000 },
|
||||
)
|
||||
.toBe('processed')
|
||||
|
||||
// Seed the share through the API (setup, not the flow under test)
|
||||
const share = await apiCreateShare(context.request, projectId, 'Watermarked Share')
|
||||
await apiAddAssetsToShare(context.request, share.id, [fileId])
|
||||
await apiUpdateShare(context.request, share.id, { allowDownload: false })
|
||||
await apiEnableShareWatermark(context.request, share.id)
|
||||
|
||||
// Wait for the watermark transcode to complete and the share to be ready
|
||||
await expect
|
||||
.poll(
|
||||
async () => {
|
||||
const link = await prisma.shareLink.findUnique({ where: { id: share.id } })
|
||||
return link?.watermarkStatus
|
||||
},
|
||||
{ timeout: 120_000 },
|
||||
)
|
||||
.toBe('ready')
|
||||
|
||||
const saved = await prisma.shareLink.findUnique({ where: { id: share.id } })
|
||||
expect(saved?.allowDownload).toBe(false)
|
||||
expect(saved?.watermarkConfigId).not.toBeNull()
|
||||
|
||||
// The share root contains a symlink pointing at the real asset; the public
|
||||
// detail page navigates with the symlink id (mirrors the real double-click flow).
|
||||
const symlink = await prisma.asset.findFirst({
|
||||
where: { parentId: share.rootFolderId, targetId: fileId },
|
||||
})
|
||||
expect(symlink).not.toBeNull()
|
||||
|
||||
// Original (unwatermarked) transcode keys, to prove they are never served
|
||||
const asset = await prisma.asset.findUnique({ where: { id: fileId } })
|
||||
const media = asset?.media as {
|
||||
imageTranscodes?: Array<{ key: string }>
|
||||
videoTranscodes?: Array<{ key: string }>
|
||||
original?: { key: string } | null
|
||||
} | null
|
||||
const originalKeys =
|
||||
(mediaType === 'image' ? media?.imageTranscodes : media?.videoTranscodes)?.map(
|
||||
(t) => t.key,
|
||||
) ?? []
|
||||
|
||||
const guestContext = await browser.newContext()
|
||||
const guestPage = await guestContext.newPage()
|
||||
try {
|
||||
// ---------------- Public share list page ----------------
|
||||
await guestPage.goto(`/share/${share.id}`)
|
||||
await expect(fileCard(guestPage, fileName)).toBeVisible()
|
||||
|
||||
// Card context menu: no Download item
|
||||
const card = fileCard(guestPage, fileName)
|
||||
const kebab = card.locator('button', {
|
||||
has: guestPage.locator('svg.lucide-ellipsis'),
|
||||
})
|
||||
await kebab.click()
|
||||
await expect(guestPage.locator('[data-radix-menu-content]').first()).toBeAttached()
|
||||
await expect(guestPage.getByRole('menuitem', { name: 'Download' })).toHaveCount(0)
|
||||
await guestPage.keyboard.press('Escape')
|
||||
// Wait for the Radix menu to fully unmount before interacting again:
|
||||
// while its exit animation is running its dismiss layer can intercept
|
||||
// the outside pointerdown and swallow the next click.
|
||||
await guestPage
|
||||
.waitForFunction(() => !document.querySelector('[data-radix-menu-content]'), null, {
|
||||
timeout: 10_000,
|
||||
})
|
||||
.catch(() => {})
|
||||
|
||||
// Selection bar: selecting the file must not surface a Download button.
|
||||
// Click the card checkbox (selects directly) instead of the card body:
|
||||
// the preview area (video sprite scrubber) re-renders on hover and can
|
||||
// race with a body click.
|
||||
const checkbox = card.getByRole('checkbox')
|
||||
await checkbox.click()
|
||||
await expect(guestPage.getByText(/1 file selected/)).toBeVisible()
|
||||
await expect(guestPage.getByRole('button', { name: 'Download' })).toHaveCount(0)
|
||||
|
||||
// ---------------- Public share file detail page ----------------
|
||||
// Capture every network request so we can prove the loaded proxy is the
|
||||
// watermarked one and no original transcode key is ever requested.
|
||||
const watermarkedRequests: string[] = []
|
||||
const allRequests: string[] = []
|
||||
guestPage.on('request', (req) => {
|
||||
const url = req.url()
|
||||
allRequests.push(url)
|
||||
if (url.includes('-watermark-')) watermarkedRequests.push(url)
|
||||
})
|
||||
|
||||
const detailFileId = symlink!.id
|
||||
await guestPage.goto(`/share/${share.id}/files/${detailFileId}`)
|
||||
|
||||
// The viewer (image canvas / video element) renders the proxy
|
||||
if (mediaType === 'image') {
|
||||
await expect(guestPage.locator('canvas').first()).toBeVisible({ timeout: 30_000 })
|
||||
} else {
|
||||
await expect(guestPage.locator('video').first()).toBeVisible({ timeout: 30_000 })
|
||||
}
|
||||
|
||||
// The proxy actually loaded is the watermarked version, and no original
|
||||
// (unwatermarked) transcode key was requested
|
||||
await expect.poll(() => watermarkedRequests.length, { timeout: 30_000 }).toBeGreaterThan(0)
|
||||
const leaked = allRequests.filter((url) => originalKeys.some((key) => url.includes(key)))
|
||||
expect(leaked).toEqual([])
|
||||
|
||||
// No download affordance in the viewer control bar
|
||||
await expect(guestPage.getByTitle('Download')).toHaveCount(0)
|
||||
await expect(guestPage.getByTitle('Download original image')).toHaveCount(0)
|
||||
await expect(guestPage.getByRole('button', { name: 'Download' })).toHaveCount(0)
|
||||
|
||||
// Top-nav file dropdown: no Download item (video: also no resolution submenu)
|
||||
await guestPage.getByRole('button', { name: new RegExp(fileName) }).click()
|
||||
await expect(guestPage.locator('[data-radix-menu-content]').first()).toBeAttached()
|
||||
await expect(guestPage.getByRole('menuitem', { name: 'Download' })).toHaveCount(0)
|
||||
if (mediaType === 'video') {
|
||||
await expect(
|
||||
guestPage.locator('[data-radix-menu-content]').getByText('Original', { exact: true }),
|
||||
).toHaveCount(0)
|
||||
await expect(
|
||||
guestPage.locator('[data-radix-menu-content]').getByText('MP4', { exact: true }),
|
||||
).toHaveCount(0)
|
||||
}
|
||||
|
||||
// ---------------- Backend enforcement ----------------
|
||||
// Guests cannot obtain a download URL even when they know the storage key
|
||||
const originalKey = originalKeys[0] || media?.original?.key || ''
|
||||
const download = await apiPublicDownloadUrl(
|
||||
guestContext.request,
|
||||
share.id,
|
||||
detailFileId,
|
||||
originalKey,
|
||||
)
|
||||
expect(download.status).toBe(403)
|
||||
} finally {
|
||||
await guestContext.close()
|
||||
}
|
||||
})
|
||||
})
|
||||
}
|
||||
@@ -47,3 +47,39 @@ test('owner uploads a file via the "Upload File" context menu action', async ({
|
||||
const projectRow = await prisma.project.findUnique({ where: { id: projectId } })
|
||||
expect(asset!.parentId).toBe(projectRow?.rootFolderId)
|
||||
})
|
||||
|
||||
test('owner uploads an unsupported file via context menu action', async ({ project, prisma }) => {
|
||||
const { page, projectId } = project
|
||||
const fileName = `e2e-upload-${Date.now()}.bin`
|
||||
const binBuffer = Buffer.from([0x00, 0x01, 0x02, 0x03])
|
||||
|
||||
await page.goto(`/projects/${projectId}`)
|
||||
await expect(page.getByText('This folder is empty')).toBeVisible()
|
||||
|
||||
await page.getByText('This folder is empty').click({ button: 'right' })
|
||||
const [fileChooser] = await Promise.all([
|
||||
page.waitForEvent('filechooser'),
|
||||
page.getByRole('menuitem', { name: 'Upload File' }).click(),
|
||||
])
|
||||
await fileChooser.setFiles({
|
||||
name: fileName,
|
||||
mimeType: 'application/octet-stream',
|
||||
buffer: binBuffer,
|
||||
})
|
||||
|
||||
const card = fileCard(page, fileName)
|
||||
await expect(card).toBeVisible()
|
||||
|
||||
await expect
|
||||
.poll(
|
||||
async () => {
|
||||
const asset = await prisma.asset.findFirst({ where: { name: fileName } })
|
||||
return asset?.status
|
||||
},
|
||||
{ timeout: 30_000 },
|
||||
)
|
||||
.toBe('processed')
|
||||
|
||||
// Verify that the file card shows the generic file icon and is not stuck in uploading state
|
||||
await expect(card.locator('svg.lucide-file')).toBeVisible({ timeout: 10_000 })
|
||||
})
|
||||
|
||||
@@ -0,0 +1,233 @@
|
||||
import { expect, test } from '../../fixtures'
|
||||
import { seedFile } from '../../helpers/assets'
|
||||
import { dragCard } from '../../helpers/dnd'
|
||||
import { apiAddAssetsToShare, apiCreateShare, fileCard } from '../../helpers/files'
|
||||
|
||||
test('owner manages versions: removes a version from a 3-version stack', async ({
|
||||
project,
|
||||
prisma,
|
||||
}) => {
|
||||
const { page, projectId, rootFolderId } = project
|
||||
|
||||
const fileA = await seedFile(prisma, projectId, rootFolderId, `e2e-mng-a-${Date.now()}`)
|
||||
const fileB = await seedFile(prisma, projectId, rootFolderId, `e2e-mng-b-${Date.now()}`)
|
||||
const fileC = await seedFile(prisma, projectId, rootFolderId, `e2e-mng-c-${Date.now()}`)
|
||||
|
||||
await page.goto(`/projects/${projectId}`)
|
||||
await expect(fileCard(page, fileA.name)).toBeVisible()
|
||||
await expect(fileCard(page, fileB.name)).toBeVisible()
|
||||
await expect(fileCard(page, fileC.name)).toBeVisible()
|
||||
|
||||
// 1. Create a 3-version stack: B on A -> stack (v2), then C on stack -> stack (v3)
|
||||
await dragCard(page, fileCard(page, fileB.name), fileCard(page, fileA.name))
|
||||
await expect(page.getByText('v2', { exact: true })).toBeVisible()
|
||||
|
||||
await dragCard(page, fileCard(page, fileC.name), fileCard(page, fileB.name))
|
||||
await expect(page.getByText('v3', { exact: true })).toBeVisible()
|
||||
|
||||
const stack = await prisma.asset.findFirstOrThrow({
|
||||
where: { projectId, parentId: rootFolderId, type: 'version_stack' },
|
||||
})
|
||||
expect(stack.fileCount).toBe(3)
|
||||
|
||||
// 2. Navigate to file viewer for the stack
|
||||
await page.goto(`/projects/${projectId}/files/${stack.id}`)
|
||||
|
||||
// 3. Open breadcrumb menu and click "Manage versions..."
|
||||
// Click on the asset name / badge dropdown trigger
|
||||
await page.getByRole('button', { name: new RegExp(fileC.name) }).click()
|
||||
// Hover or click on Versions sub-menu trigger
|
||||
await page.getByRole('menuitem', { name: 'Versions', exact: true }).hover()
|
||||
// Click "Manage versions..."
|
||||
await page.getByRole('button', { name: /manage versions$/i }).click()
|
||||
|
||||
// 4. Verify Manage versions dialog is visible with all 3 versions
|
||||
const dialog = page.getByRole('dialog')
|
||||
await expect(dialog).toBeVisible()
|
||||
await expect(dialog.getByText('Manage versions')).toBeVisible()
|
||||
await expect(dialog.getByText(fileA.name)).toBeVisible()
|
||||
await expect(dialog.getByText(fileB.name)).toBeVisible()
|
||||
await expect(dialog.getByText(fileC.name)).toBeVisible()
|
||||
|
||||
// 5. Remove fileB from stack: hover its row and click Remove from stack
|
||||
const rowB = dialog.locator('div.group', { hasText: fileB.name })
|
||||
await rowB.hover()
|
||||
const moreButton = rowB.getByRole('button', { name: 'More options' })
|
||||
await moreButton.click()
|
||||
await page.getByRole('menuitem', { name: /remove from stack/i }).click()
|
||||
|
||||
// 6. Verify toast and that fileB is removed from dialog
|
||||
await expect(page.getByText(/version removed from stack/i)).toBeVisible()
|
||||
await expect(dialog.getByText(fileB.name)).not.toBeVisible()
|
||||
await expect(dialog.getByText(fileA.name)).toBeVisible()
|
||||
await expect(dialog.getByText(fileC.name)).toBeVisible()
|
||||
|
||||
// DB: stack now has 2 versions (fileA and fileC), and fileB is standalone in root folder
|
||||
await expect
|
||||
.poll(async () => {
|
||||
const s = await prisma.asset.findUnique({ where: { id: stack.id } })
|
||||
return s?.fileCount
|
||||
})
|
||||
.toBe(2)
|
||||
|
||||
const updatedFileB = await prisma.asset.findUnique({ where: { id: fileB.id } })
|
||||
expect(updatedFileB?.parentId).toBe(rootFolderId)
|
||||
})
|
||||
|
||||
test('owner removes version from 2-version stack dissolving the stack into standalone files', async ({
|
||||
project,
|
||||
prisma,
|
||||
}) => {
|
||||
const { page, projectId, rootFolderId } = project
|
||||
|
||||
const fileA = await seedFile(prisma, projectId, rootFolderId, `e2e-dis-a-${Date.now()}`)
|
||||
const fileB = await seedFile(prisma, projectId, rootFolderId, `e2e-dis-b-${Date.now()}`)
|
||||
|
||||
await page.goto(`/projects/${projectId}`)
|
||||
await dragCard(page, fileCard(page, fileB.name), fileCard(page, fileA.name))
|
||||
await expect(page.getByText('v2', { exact: true })).toBeVisible()
|
||||
|
||||
const stack = await prisma.asset.findFirstOrThrow({
|
||||
where: { projectId, parentId: rootFolderId, type: 'version_stack' },
|
||||
})
|
||||
|
||||
// Open file view
|
||||
await page.goto(`/projects/${projectId}/files/${stack.id}`)
|
||||
|
||||
// Open breadcrumb menu and click "Manage versions..."
|
||||
await page.getByRole('button', { name: new RegExp(fileB.name) }).click()
|
||||
await page.getByRole('menuitem', { name: 'Versions', exact: true }).hover()
|
||||
await page.getByRole('button', { name: /manage versions$/i }).click()
|
||||
|
||||
const dialog = page.getByRole('dialog')
|
||||
await expect(dialog).toBeVisible()
|
||||
|
||||
// Remove fileB -> stack dissolves -> only fileA remains
|
||||
const rowB = dialog.locator('div.group', { hasText: fileB.name })
|
||||
await rowB.hover()
|
||||
const moreButton = rowB.getByRole('button', { name: 'More options' })
|
||||
await moreButton.click()
|
||||
await page.getByRole('menuitem', { name: /remove from stack/i }).click()
|
||||
|
||||
// Dialog should close automatically when stack dissolves
|
||||
await expect(dialog).not.toBeVisible()
|
||||
|
||||
// DB: stack asset is deleted
|
||||
await expect
|
||||
.poll(async () => {
|
||||
const s = await prisma.asset.findUnique({ where: { id: stack.id } })
|
||||
return s === null
|
||||
})
|
||||
.toBe(true)
|
||||
|
||||
// Both fileA and fileB are now standalone files in rootFolder
|
||||
const updatedFileA = await prisma.asset.findUnique({ where: { id: fileA.id } })
|
||||
const updatedFileB = await prisma.asset.findUnique({ where: { id: fileB.id } })
|
||||
expect(updatedFileA?.parentId).toBe(rootFolderId)
|
||||
expect(updatedFileB?.parentId).toBe(rootFolderId)
|
||||
})
|
||||
|
||||
test('dissolving a shared version stack renders the remaining standalone file name on the share page', async ({
|
||||
project,
|
||||
prisma,
|
||||
}) => {
|
||||
const { page, projectId, rootFolderId } = project
|
||||
|
||||
const fileA = await seedFile(prisma, projectId, rootFolderId, `e2e-shd-a-${Date.now()}`)
|
||||
const fileB = await seedFile(prisma, projectId, rootFolderId, `e2e-shd-b-${Date.now()}`)
|
||||
|
||||
await page.goto(`/projects/${projectId}`)
|
||||
await dragCard(page, fileCard(page, fileB.name), fileCard(page, fileA.name))
|
||||
await expect(page.getByText('v2', { exact: true })).toBeVisible()
|
||||
|
||||
const stack = await prisma.asset.findFirstOrThrow({
|
||||
where: { projectId, parentId: rootFolderId, type: 'version_stack' },
|
||||
})
|
||||
|
||||
// Share the version stack
|
||||
await fileCard(page, fileB.name).click({ button: 'right' })
|
||||
await page.getByRole('menuitem', { name: 'Create Share Link' }).click()
|
||||
const toast = page.locator('[data-sonner-toast]').filter({ hasText: 'Share link created' })
|
||||
await expect(toast).toBeVisible()
|
||||
|
||||
const share = await prisma.shareLink.findFirstOrThrow({
|
||||
where: { projectId },
|
||||
orderBy: { createdAt: 'desc' },
|
||||
})
|
||||
|
||||
// Open file viewer for the stack
|
||||
await page.goto(`/projects/${projectId}/files/${stack.id}`)
|
||||
|
||||
// Open breadcrumb menu and click "Manage versions"
|
||||
await page.getByRole('button', { name: new RegExp(fileB.name) }).click()
|
||||
await page.getByRole('menuitem', { name: 'Versions', exact: true }).hover()
|
||||
await page.getByRole('button', { name: /manage versions$/i }).click()
|
||||
|
||||
const dialog = page.getByRole('dialog')
|
||||
await expect(dialog).toBeVisible()
|
||||
|
||||
// Remove fileB -> stack dissolves -> only fileA remains
|
||||
const rowB = dialog.locator('div.group', { hasText: fileB.name })
|
||||
await rowB.hover()
|
||||
const moreButton = rowB.getByRole('button', { name: 'More options' })
|
||||
await moreButton.click()
|
||||
await page.getByRole('menuitem', { name: /remove from stack/i }).click()
|
||||
|
||||
await expect(dialog).not.toBeVisible()
|
||||
|
||||
// Navigate to public share page: verify fileA is displayed with its non-empty name
|
||||
await page.goto(`/share/${share.id}`)
|
||||
await expect(fileCard(page, fileA.name)).toBeVisible()
|
||||
await expect(fileCard(page, fileB.name)).not.toBeVisible()
|
||||
})
|
||||
|
||||
test('moving a shared file into a shared version stack leaves only 1 stack card on the share page', async ({
|
||||
project,
|
||||
prisma,
|
||||
}) => {
|
||||
const { page, projectId, rootFolderId } = project
|
||||
|
||||
const fileA = await seedFile(prisma, projectId, rootFolderId, `e2e-mvsh-a-${Date.now()}`)
|
||||
const fileB = await seedFile(prisma, projectId, rootFolderId, `e2e-mvsh-b-${Date.now()}`)
|
||||
const fileC = await seedFile(prisma, projectId, rootFolderId, `e2e-mvsh-c-${Date.now()}`)
|
||||
|
||||
await page.goto(`/projects/${projectId}`)
|
||||
|
||||
// 1. Create a version stack from file B and file A (stack has v2, displays file B)
|
||||
await dragCard(page, fileCard(page, fileB.name), fileCard(page, fileA.name))
|
||||
await expect(page.getByText('v2', { exact: true })).toBeVisible()
|
||||
|
||||
const stack = await prisma.asset.findFirstOrThrow({
|
||||
where: { projectId, parentId: rootFolderId, type: 'version_stack' },
|
||||
})
|
||||
|
||||
// 2. Create a share link and add both stack AB and file C to it
|
||||
const share = await apiCreateShare(project.context.request, projectId, `Test Share ${Date.now()}`)
|
||||
await apiAddAssetsToShare(project.context.request, share.id, [stack.id, fileC.id])
|
||||
|
||||
// Verify initial share page has both stack and file C
|
||||
await page.goto(`/share/${share.id}`)
|
||||
await expect(fileCard(page, fileB.name)).toBeVisible()
|
||||
await expect(fileCard(page, fileC.name)).toBeVisible()
|
||||
|
||||
// 3. In project page, drop file C onto stack card (displays file B)
|
||||
await page.goto(`/projects/${projectId}`)
|
||||
await dragCard(page, fileCard(page, fileC.name), fileCard(page, fileB.name))
|
||||
await expect(page.getByText('v3', { exact: true })).toBeVisible()
|
||||
|
||||
// 4. Return to public share page: now only 1 card exists (the stack showing file C with v3)
|
||||
await page.goto(`/share/${share.id}`)
|
||||
await expect(page.getByText('v3', { exact: true })).toBeVisible()
|
||||
await expect(fileCard(page, fileC.name)).toBeVisible()
|
||||
await expect(fileCard(page, fileB.name)).not.toBeVisible()
|
||||
|
||||
// DB: share rootFolder fileCount is 1 and exactly 1 symlink exists
|
||||
const symlinks = await prisma.asset.findMany({
|
||||
where: { parentId: share.rootFolderId, type: 'symlink' },
|
||||
})
|
||||
expect(symlinks).toHaveLength(1)
|
||||
expect(symlinks[0].targetId).toBe(stack.id)
|
||||
|
||||
const updatedShareRoot = await prisma.asset.findUnique({ where: { id: share.rootFolderId } })
|
||||
expect(updatedShareRoot?.fileCount).toBe(1)
|
||||
})
|
||||
@@ -0,0 +1,126 @@
|
||||
import { expect, test } from '../../fixtures'
|
||||
|
||||
test('owner manages resource quotas in settings and resets usage from the dashboard', async ({
|
||||
owner,
|
||||
prisma,
|
||||
}) => {
|
||||
const { page, teamId, email } = owner
|
||||
|
||||
// 1. Navigate to team settings
|
||||
await page.goto(`/teams/${teamId}/settings`)
|
||||
|
||||
// 2. Click the Quotas sidebar tab
|
||||
await page.getByRole('button', { name: /Quotas|配额/i }).click()
|
||||
|
||||
// Verify URL contains #quotas and remains after reload
|
||||
expect(page.url()).toContain('#quotas')
|
||||
await page.reload()
|
||||
expect(page.url()).toContain('#quotas')
|
||||
|
||||
// 3. Verify Quotas settings card is displayed with empty state
|
||||
await expect(page.getByRole('heading', { name: /^(Resource Quotas|资源配额)$/i })).toBeVisible()
|
||||
await expect(page.getByText(/No resource quotas configured|暂未配置资源配额/i)).toBeVisible()
|
||||
|
||||
// 4. Open Create Quota Dialog
|
||||
await page
|
||||
.getByRole('button', { name: /Add Quota|添加配额/i })
|
||||
.first()
|
||||
.click()
|
||||
await expect(page.getByText(/Create Quota Rule|创建配额规则/i)).toBeVisible()
|
||||
|
||||
// 5. Fill and submit new quota rule
|
||||
await page.fill('#quota-limit', '50000')
|
||||
await page.getByRole('button', { name: /^(Create|创建)$/i }).click()
|
||||
|
||||
// 6. Verify quota rule card appears in the list
|
||||
await expect(page.getByText(/50,000 tokens|50000 tokens/i)).toBeVisible()
|
||||
await expect(page.getByText(/Each Member|每个成员/i)).toBeVisible()
|
||||
|
||||
// Verify in database
|
||||
const createdRule = await prisma.quotaRule.findFirst({
|
||||
where: { teamId, limit: 50000 },
|
||||
})
|
||||
expect(createdRule).not.toBeNull()
|
||||
expect(createdRule?.enabled).toBe(true)
|
||||
|
||||
// 7. Usage is now monitored from the dashboard, not the settings rule card.
|
||||
await expect(page.getByRole('button', { name: /View Usage|查看使用量/i })).not.toBeVisible()
|
||||
|
||||
// 8. Toggle quota rule switch
|
||||
await page.getByRole('switch').click()
|
||||
await expect(page.getByRole('switch')).not.toBeChecked()
|
||||
const disabledRule = await prisma.quotaRule.findFirst({
|
||||
where: { id: createdRule?.id },
|
||||
})
|
||||
expect(disabledRule?.enabled).toBe(false)
|
||||
|
||||
// Toggle back on
|
||||
await page.getByRole('switch').click()
|
||||
await expect(page.getByRole('switch')).toBeChecked()
|
||||
|
||||
// 9. Open Edit Dialog by clicking the quota card
|
||||
await page.getByText(/50,000 tokens|50000 tokens/i).click()
|
||||
await expect(page.getByText(/Edit Quota Rule|编辑配额规则/i)).toBeVisible()
|
||||
await expect(page.getByRole('button', { name: /Each Member|每个成员/i })).toBeDisabled()
|
||||
await expect(page.locator('#quota-resource')).toBeDisabled()
|
||||
|
||||
// 10. Update limit
|
||||
await page.fill('#quota-limit', '75000')
|
||||
await page.getByRole('button', { name: /^(Save|保存)$/i }).click()
|
||||
|
||||
// Verify updated limit in UI and DB
|
||||
await expect(page.getByText(/75,000 tokens|75000 tokens/i)).toBeVisible()
|
||||
const updatedRule = await prisma.quotaRule.findFirst({
|
||||
where: { id: createdRule?.id },
|
||||
})
|
||||
expect(updatedRule?.limit).toBe(75000)
|
||||
|
||||
// 11. Verify quota usage and reset it from the dashboard
|
||||
const ownerUser = await prisma.user.findUnique({ where: { email } })
|
||||
expect(ownerUser).not.toBeNull()
|
||||
await prisma.quotaRecord.create({
|
||||
data: {
|
||||
ruleId: createdRule?.id as string,
|
||||
teamId,
|
||||
userId: ownerUser?.id,
|
||||
periodStart: new Date(),
|
||||
periodEnd: new Date(Date.now() + 24 * 60 * 60 * 1000),
|
||||
consumed: 100,
|
||||
},
|
||||
})
|
||||
await page.goto(`/teams/${teamId}/dashboard`)
|
||||
await page.getByRole('button', { name: /Quotas|配额/i }).click()
|
||||
await expect(
|
||||
page.getByText(/Monitor live quota usage|在仪表盘中监控实时配额使用情况/),
|
||||
).toBeVisible()
|
||||
|
||||
const quotaRuleButton = page.getByRole('button', { name: /Expand quota rule|展开配额规则/i })
|
||||
await quotaRuleButton.click()
|
||||
await expect(page.getByText(/^100 \/ 75,000 tokens$|^100 \/ 75000 tokens$/i)).toBeVisible()
|
||||
await page.getByRole('button', { name: /Reset Usage|重置使用量/i }).click()
|
||||
await expect(page.getByRole('alertdialog')).toBeVisible()
|
||||
await page.getByRole('button', { name: /Confirm|确认/i }).click()
|
||||
await expect(page.getByText(/^0 \/ 75,000 tokens$|^0 \/ 75000 tokens$/i)).toBeVisible()
|
||||
|
||||
const resetRecord = await prisma.quotaRecord.findFirst({
|
||||
where: { ruleId: createdRule?.id, userId: ownerUser?.id },
|
||||
})
|
||||
expect(resetRecord?.consumed).toBe(0)
|
||||
|
||||
// 12. Delete quota rule from settings
|
||||
await page.goto(`/teams/${teamId}/settings`)
|
||||
await page.getByRole('button', { name: /Quotas|配额/i }).click()
|
||||
await page.getByRole('button', { name: 'Quota actions' }).first().click()
|
||||
await page.getByRole('menuitem', { name: /Delete|删除/i }).click()
|
||||
await page
|
||||
.getByRole('button', { name: /Delete|删除/i })
|
||||
.last()
|
||||
.click()
|
||||
|
||||
// Verify empty state returns
|
||||
await expect(page.getByText(/No resource quotas configured|暂未配置资源配额/i)).toBeVisible()
|
||||
const deletedRule = await prisma.quotaRule.findFirst({
|
||||
where: { id: createdRule?.id },
|
||||
})
|
||||
expect(deletedRule).toBeNull()
|
||||
})
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@shumai/web-app",
|
||||
"version": "0.3.3",
|
||||
"version": "0.4.2",
|
||||
"private": true,
|
||||
"type": "module",
|
||||
"dependencies": {
|
||||
|
||||
@@ -13,12 +13,37 @@ import { initTranscodeWorkflows } from '@shumai/transcode'
|
||||
import { workflowService } from '@shumai/workflow-core'
|
||||
|
||||
import { handleDaemonCommands } from '@shumai/core/src/utils/daemon'
|
||||
import { authService } from '@shumai/core/src/auth/auth'
|
||||
|
||||
if (process.argv.includes('--check')) {
|
||||
console.log('✅ Web app evaluated successfully!')
|
||||
process.exit(0)
|
||||
}
|
||||
|
||||
const cliArgs = process.argv.slice(2)
|
||||
const resetCmdIndex = cliArgs.findIndex(
|
||||
(arg) => arg === 'reset-password' || arg === 'reset-passowrd',
|
||||
)
|
||||
|
||||
if (resetCmdIndex !== -1) {
|
||||
const email = cliArgs[resetCmdIndex + 1]
|
||||
if (!email || email.startsWith('-')) {
|
||||
console.error('Error: Please provide a valid email address.')
|
||||
console.error('Usage: shumai reset-password <email>')
|
||||
process.exit(1)
|
||||
}
|
||||
|
||||
try {
|
||||
const link = await authService.generatePasswordResetLink(email)
|
||||
console.log(link)
|
||||
process.exit(0)
|
||||
} catch (err: unknown) {
|
||||
const message = err instanceof Error ? err.message : 'Unknown error'
|
||||
console.error(`Error: ${message}`)
|
||||
process.exit(1)
|
||||
}
|
||||
}
|
||||
|
||||
async function run() {
|
||||
// Initialize workflows and activities for local executor mode
|
||||
initAgentWorkflows()
|
||||
|
||||
@@ -33,7 +33,7 @@
|
||||
},
|
||||
"apps/agent": {
|
||||
"name": "@shumai/agent-app",
|
||||
"version": "0.3.2",
|
||||
"version": "0.3.7",
|
||||
"bin": {
|
||||
"shumai-agent": "./src/index.ts",
|
||||
},
|
||||
@@ -45,7 +45,7 @@
|
||||
},
|
||||
"apps/cli": {
|
||||
"name": "@shumai/cli",
|
||||
"version": "0.3.2",
|
||||
"version": "0.3.7",
|
||||
"bin": {
|
||||
"shumai-cli": "./src/index.ts",
|
||||
},
|
||||
@@ -60,7 +60,7 @@
|
||||
},
|
||||
"apps/transcode": {
|
||||
"name": "@shumai/transcode-app",
|
||||
"version": "0.3.2",
|
||||
"version": "0.3.7",
|
||||
"bin": {
|
||||
"shumai-transcode": "./src/index.ts",
|
||||
},
|
||||
@@ -72,7 +72,7 @@
|
||||
},
|
||||
"apps/web": {
|
||||
"name": "@shumai/web-app",
|
||||
"version": "0.3.2",
|
||||
"version": "0.3.7",
|
||||
"dependencies": {
|
||||
"@shumai/agent": "workspace:*",
|
||||
"@shumai/api": "workspace:*",
|
||||
@@ -92,7 +92,7 @@
|
||||
},
|
||||
"packages/agent": {
|
||||
"name": "@shumai/agent",
|
||||
"version": "0.3.2",
|
||||
"version": "0.3.7",
|
||||
"dependencies": {
|
||||
"@anthropic-ai/sandbox-runtime": "0.0.66",
|
||||
"@earendil-works/pi-agent-core": "0.82.1",
|
||||
@@ -102,12 +102,12 @@
|
||||
"@shumai/db": "workspace:*",
|
||||
"@shumai/dtos": "workspace:*",
|
||||
"@shumai/workflow-core": "workspace:*",
|
||||
"@sinclair/typebox": "0.34.49",
|
||||
"@temporalio/activity": "1.17.2",
|
||||
"@temporalio/worker": "1.17.2",
|
||||
"@temporalio/workflow": "1.17.2",
|
||||
"adm-zip": "0.5.17",
|
||||
"jittered-fractional-indexing": "1.0.1",
|
||||
"typebox": "1.1.38",
|
||||
"ulid": "3.0.2",
|
||||
"zod": "4.4.3",
|
||||
},
|
||||
@@ -117,7 +117,7 @@
|
||||
},
|
||||
"packages/api": {
|
||||
"name": "@shumai/api",
|
||||
"version": "0.3.2",
|
||||
"version": "0.3.7",
|
||||
"dependencies": {
|
||||
"@hono/zod-validator": "0.7.6",
|
||||
"@shumai/core": "workspace:*",
|
||||
@@ -131,10 +131,11 @@
|
||||
},
|
||||
"packages/core": {
|
||||
"name": "@shumai/core",
|
||||
"version": "0.3.2",
|
||||
"version": "0.3.7",
|
||||
"dependencies": {
|
||||
"@earendil-works/pi-agent-core": "0.82.1",
|
||||
"@earendil-works/pi-ai": "0.82.1",
|
||||
"@modelcontextprotocol/client": "2.0.0",
|
||||
"@shumai/db": "workspace:*",
|
||||
"@shumai/dtos": "workspace:*",
|
||||
"@sinclair/typebox": "0.34.49",
|
||||
@@ -151,11 +152,13 @@
|
||||
"pino": "10.3.1",
|
||||
"sharp": "0.34.5",
|
||||
"tweetnacl": "1.0.3",
|
||||
"typebox": "1.1.38",
|
||||
"ulid": "3.0.2",
|
||||
"yaml": "2.9.0",
|
||||
"zod": "4.4.3",
|
||||
},
|
||||
"devDependencies": {
|
||||
"@modelcontextprotocol/server": "2.0.0",
|
||||
"@types/adm-zip": "0.5.8",
|
||||
"@types/extract-zip": "2.0.3",
|
||||
"@types/pdfkit": "0.17.6",
|
||||
@@ -163,7 +166,7 @@
|
||||
},
|
||||
"packages/db": {
|
||||
"name": "@shumai/db",
|
||||
"version": "0.3.2",
|
||||
"version": "0.3.7",
|
||||
"dependencies": {
|
||||
"@earendil-works/pi-agent-core": "0.82.1",
|
||||
"@prisma/adapter-pg": "7.8.0",
|
||||
@@ -179,7 +182,7 @@
|
||||
},
|
||||
"packages/dtos": {
|
||||
"name": "@shumai/dtos",
|
||||
"version": "0.3.2",
|
||||
"version": "0.3.7",
|
||||
"dependencies": {
|
||||
"@earendil-works/pi-agent-core": "0.82.1",
|
||||
"zod": "4.4.3",
|
||||
@@ -187,7 +190,7 @@
|
||||
},
|
||||
"packages/e2e": {
|
||||
"name": "@shumai/e2e",
|
||||
"version": "0.3.2",
|
||||
"version": "0.3.7",
|
||||
"dependencies": {
|
||||
"@earendil-works/pi-agent-core": "0.82.1",
|
||||
"@google/genai": "1.52.0",
|
||||
@@ -202,11 +205,11 @@
|
||||
},
|
||||
"packages/tableprinter": {
|
||||
"name": "@shumai/tableprinter",
|
||||
"version": "0.3.2",
|
||||
"version": "0.3.7",
|
||||
},
|
||||
"packages/transcode": {
|
||||
"name": "@shumai/transcode",
|
||||
"version": "0.3.2",
|
||||
"version": "0.3.7",
|
||||
"dependencies": {
|
||||
"@shumai/core": "workspace:*",
|
||||
"@shumai/db": "workspace:*",
|
||||
@@ -220,7 +223,7 @@
|
||||
},
|
||||
"packages/webui": {
|
||||
"name": "@shumai/webui",
|
||||
"version": "0.3.2",
|
||||
"version": "0.3.7",
|
||||
"dependencies": {
|
||||
"@base-ui/react": "1.5.0",
|
||||
"@dnd-kit/abstract": "0.4.0",
|
||||
@@ -318,7 +321,7 @@
|
||||
},
|
||||
"packages/workflow-core": {
|
||||
"name": "@shumai/workflow-core",
|
||||
"version": "0.3.2",
|
||||
"version": "0.3.7",
|
||||
"dependencies": {
|
||||
"@shumai/core": "workspace:*",
|
||||
"@shumai/db": "workspace:*",
|
||||
@@ -330,6 +333,9 @@
|
||||
},
|
||||
},
|
||||
},
|
||||
"patchedDependencies": {
|
||||
"@earendil-works/pi-ai@0.82.1": "patches/@earendil-works%2Fpi-ai@0.82.1.patch",
|
||||
},
|
||||
"packages": {
|
||||
"@alloc/quick-lru": ["@alloc/quick-lru@5.2.0", "", {}, "sha512-UrcABB+4bUrFABwbluTIBErXwvbsU/V7TZWfmbgJfbkwiBuziS9gxdODUyuiecfdGQ85jglMW6juS3+z5TsKLw=="],
|
||||
|
||||
@@ -735,6 +741,12 @@
|
||||
|
||||
"@mistralai/mistralai": ["@mistralai/mistralai@2.2.6", "", { "dependencies": { "@opentelemetry/semantic-conventions": "^1.40.0", "ws": "^8.18.0", "zod": "^3.25.0 || ^4.0.0", "zod-to-json-schema": "^3.25.0" }, "peerDependencies": { "@opentelemetry/api": "^1.9.0" }, "optionalPeers": ["@opentelemetry/api"] }, "sha512-W8pX7zHxjJvMIpw8JMxeJEleapXX0Q9NPszdNzqkM3MIEoIGPObdodujj+WHteXEvGfaP/AMwlNyRfEzSY6dQQ=="],
|
||||
|
||||
"@modelcontextprotocol/client": ["@modelcontextprotocol/client@2.0.0", "", { "dependencies": { "@modelcontextprotocol/core": "2.0.0", "cross-spawn": "^7.0.5", "eventsource": "^3.0.2", "eventsource-parser": "^3.0.0", "jose": "^6.1.3", "pkce-challenge": "^5.0.0", "zod": "^4.2.0" } }, "sha512-8f1OghQ2rjzIOfqgUCP+8GiUWqRs89njoWLNqAe8kWmDePv3s1fZXseej+QXemssEuuOvLLmLO/kqM3IQHtISw=="],
|
||||
|
||||
"@modelcontextprotocol/core": ["@modelcontextprotocol/core@2.0.0", "", { "dependencies": { "zod": "^4.2.0" } }, "sha512-pJCEwGG7Lfr/+PQp9ZTwKXNeO5wzbfKL7H3MYpCorM4oFBoQrdjnBgEoqG+RjhsvS1FKrDbKux+M1HhlnGWqcA=="],
|
||||
|
||||
"@modelcontextprotocol/server": ["@modelcontextprotocol/server@2.0.0", "", { "dependencies": { "@modelcontextprotocol/core": "2.0.0", "zod": "^4.2.0" } }, "sha512-YhHWdHfpFMQfd0prsEnxKeS3Qz3ytIGmsS0sth4KDjnacIT7hxk6hXHkJ9KysxlkvTM+WZAtQbbcUhdoP4Hvtw=="],
|
||||
|
||||
"@napi-rs/canvas": ["@napi-rs/canvas@1.0.2", "", { "optionalDependencies": { "@napi-rs/canvas-android-arm64": "1.0.2", "@napi-rs/canvas-darwin-arm64": "1.0.2", "@napi-rs/canvas-darwin-x64": "1.0.2", "@napi-rs/canvas-linux-arm-gnueabihf": "1.0.2", "@napi-rs/canvas-linux-arm64-gnu": "1.0.2", "@napi-rs/canvas-linux-arm64-musl": "1.0.2", "@napi-rs/canvas-linux-riscv64-gnu": "1.0.2", "@napi-rs/canvas-linux-x64-gnu": "1.0.2", "@napi-rs/canvas-linux-x64-musl": "1.0.2", "@napi-rs/canvas-win32-arm64-msvc": "1.0.2", "@napi-rs/canvas-win32-x64-msvc": "1.0.2" } }, "sha512-EYEqlMYaCbpZDz+IgDH5xp9MTd3ui4dmGqbQYryhMLnSRxrhHKq5KQWHHKxFUcEP4Hp8/BWgvqXocX4j7iSbOQ=="],
|
||||
|
||||
"@napi-rs/canvas-android-arm64": ["@napi-rs/canvas-android-arm64@1.0.2", "", { "os": "android", "cpu": "arm64" }, "sha512-IMXKVQod0ol4vt3gmClUfXz4JAgHYESGPCUqmH3lQxBoL0K/2greJaQE1HVBVxWWFKfLc4OLZVdxg7kXVyXv+g=="],
|
||||
@@ -1761,6 +1773,10 @@
|
||||
|
||||
"events-universal": ["events-universal@1.0.1", "", { "dependencies": { "bare-events": "^2.7.0" } }, "sha512-LUd5euvbMLpwOF8m6ivPCbhQeSiYVNb8Vs0fQ8QjXo0JTkEHpz8pxdQf0gStltaPpw0Cca8b39KxvK9cfKRiAw=="],
|
||||
|
||||
"eventsource": ["eventsource@3.0.7", "", { "dependencies": { "eventsource-parser": "^3.0.1" } }, "sha512-CRT1WTyuQoD771GW56XEZFQ/ZoSfWid1alKGDYMmkt2yl8UXrVR4pspqWNEcqKvVIzg6PAltWjxcSSPrboA4iA=="],
|
||||
|
||||
"eventsource-parser": ["eventsource-parser@3.1.0", "", {}, "sha512-kJezFj9YFAMLeORyi7aCLxLbD5/qWMQnoMVlVPyHIll7lgRJCc3JVln9Vgl9nwQi0YkMnhdGTMNn7CkRRAptMg=="],
|
||||
|
||||
"expect-type": ["expect-type@1.3.0", "", {}, "sha512-knvyeauYhqjOYvQ66MznSMs83wmHrCycNEN6Ao+2AeYEfxUIkuiVxdEa1qlGEPK+We3n0THiDciYSsCcgW/DoA=="],
|
||||
|
||||
"exsolve": ["exsolve@1.0.8", "", {}, "sha512-LmDxfWXwcTArk8fUEnOfSZpHOJ6zOMUJKOtFLFqJLoKJetuQG874Uc7/Kki7zFLzYybmZhp1M7+98pfMqeX8yA=="],
|
||||
@@ -2329,6 +2345,8 @@
|
||||
|
||||
"pino-std-serializers": ["pino-std-serializers@7.1.0", "", {}, "sha512-BndPH67/JxGExRgiX1dX0w1FvZck5Wa4aal9198SrRhZjH3GxKQUKIBnYJTdj2HDN3UQAS06HlfcSbQj2OHmaw=="],
|
||||
|
||||
"pkce-challenge": ["pkce-challenge@5.0.1", "", {}, "sha512-wQ0b/W4Fr01qtpHlqSqspcj3EhBvimsdh0KlHhH8HRZnMsEa0ea2fTULOXOS9ccQr3om+GcGRk4e+isrZWV8qQ=="],
|
||||
|
||||
"pkcs7": ["pkcs7@1.0.4", "", { "dependencies": { "@babel/runtime": "^7.5.5" }, "bin": { "pkcs7": "bin/cli.js" } }, "sha512-afRERtHn54AlwaF2/+LFszyAANTCggGilmcmILUzEjvs3XgFZT+xE6+QWQcAGmu4xajy+Xtj7acLOPdx5/eXWQ=="],
|
||||
|
||||
"pkg-types": ["pkg-types@2.3.1", "", { "dependencies": { "confbox": "^0.2.4", "exsolve": "^1.0.8", "pathe": "^2.0.3" } }, "sha512-y+ichcgc2LrADuhLNAx8DFjVfgz91pRxfZdI3UDhxHvcVEZsenLO+7XaU5vOp0u/7V/wZ+plyuQxtrDlZJ+yeg=="],
|
||||
|
||||
+10
-3
@@ -34,7 +34,8 @@
|
||||
"using-shumai/notifications",
|
||||
"using-shumai/metadata",
|
||||
"using-shumai/collections",
|
||||
"using-shumai/share-links"
|
||||
"using-shumai/share-links",
|
||||
"using-shumai/gotenberg"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -42,14 +43,20 @@
|
||||
"pages": [
|
||||
"using-shumai/agent-providers",
|
||||
"using-shumai/agents",
|
||||
"using-shumai/agents-md",
|
||||
"using-shumai/agent-skills",
|
||||
"using-shumai/agent-tools",
|
||||
"using-shumai/mcp-servers",
|
||||
"using-shumai/agent-sandbox"
|
||||
]
|
||||
},
|
||||
{
|
||||
"group": "Media Transcoding Settings",
|
||||
"pages": ["using-shumai/transcode-settings"]
|
||||
"group": "Team Settings",
|
||||
"pages": [
|
||||
"using-shumai/transcode-settings",
|
||||
"using-shumai/quotas-settings",
|
||||
"using-shumai/password-reset"
|
||||
]
|
||||
},
|
||||
{
|
||||
"group": "Configuration",
|
||||
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 309 KiB After Width: | Height: | Size: 131 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 45 KiB After Width: | Height: | Size: 82 KiB |
@@ -25,7 +25,7 @@ To protect your workspace environments and sensitive data, the sandbox enforces
|
||||
|
||||
## Domain Whitelisting
|
||||
|
||||
By default, sandboxed scripts cannot make network requests to the internet. Team Owners must explicitly authorize external APIs by managing domain access:
|
||||
By default, Network Sandbox is **disabled** (allowing all outbound network requests). Team Owners can toggle Network Sandbox **ON** in Sandbox Settings to enforce strict domain whitelisting:
|
||||
|
||||
### Allowed Domains
|
||||
|
||||
|
||||
@@ -30,36 +30,36 @@ The following tools can be individually toggled in the agent configuration dialo
|
||||
- **Description:** Allows the agent to load and read skill definitions to perform specialized actions.
|
||||
- **Why it matters:** Enables the agent to inspect the instructions/configurations of custom skills registered in your workspace before executing them.
|
||||
|
||||
### 3. Analyze Image (`analyze_image`)
|
||||
### 3. Read Asset (`read_asset`)
|
||||
|
||||
- **Description:** Allows the agent to view and analyze the visual contents of an image file.
|
||||
- **Why it matters:** Enables multimodal agents to "see" image assets uploaded to Shumai, allowing them to answer comments or write metadata about images.
|
||||
- **Description:** Allows the agent to inspect images, extract still frames from video files, render PDF document pages, and read text/markdown documents.
|
||||
- **Why it matters:** Enables multimodal agents to view visual media assets uploaded to Shumai, extract frame-by-frame video screenshots, inspect document layouts, and answer questions about uploaded creative assets.
|
||||
|
||||
### 4. Video Frame Extraction (`screenshot`)
|
||||
|
||||
- **Description:** Allows the agent to extract still image frames from video files for analysis.
|
||||
- **Why it matters:** Enables the agent to perform frame-by-frame analysis on videos (e.g. for comments, annotation, or search).
|
||||
|
||||
### 5. Browse Shumai (`list_assets`)
|
||||
### 4. Browse Shumai (`list_assets`)
|
||||
|
||||
- **Description:** Allows the agent to list folders and browse files in Shumai.
|
||||
- **Why it matters:** Gives the agent visual mapping of the project structure so it can search for other files or locate related assets.
|
||||
|
||||
### 6. Create Folder (`create_folder`)
|
||||
### 5. Create Folder (`create_folder`)
|
||||
|
||||
- **Description:** Allows the agent to create new folders in Shumai.
|
||||
- **Why it matters:** Needed if the agent organizes outputs or places files in custom subdirectory folders.
|
||||
|
||||
### 7. Create File (`create_file`)
|
||||
### 6. Create File (`create_file`)
|
||||
|
||||
- **Description:** Allows the agent to create and upload new files to Shumai.
|
||||
- **Why it matters:** Allows the agent to generate new assets (e.g. text logs, transcoded clips, reports) and save them directly back into your project.
|
||||
|
||||
### 8. Create Version (`create_version`)
|
||||
### 7. Create Version (`create_version`)
|
||||
|
||||
- **Description:** Allows the agent to upload and stack a new version of an existing file in Shumai.
|
||||
- **Why it matters:** Allows the agent to update files in a clean, non-destructive way by stacking revisions rather than creating duplicate files.
|
||||
|
||||
### 8. Download Asset (`download_asset`)
|
||||
|
||||
- **Description:** Allows the agent to download a workspace asset or specific storage S3 key to the local `.pi` directory for processing with local scripts or bash commands.
|
||||
- **Why it matters:** Enables agents executing custom skill scripts to fetch files or intermediate transcode artifacts to local disk.
|
||||
|
||||
---
|
||||
|
||||
## Restricting Tools
|
||||
|
||||
@@ -0,0 +1,53 @@
|
||||
---
|
||||
title: AGENTS.md Context & Instructions
|
||||
description: Provide hierarchical, folder-specific instructions and context to AI agents.
|
||||
---
|
||||
|
||||
In addition to global agent system prompts and skills, Shumai allows you to define project-level and folder-level instructions using **`AGENTS.md`**.
|
||||
|
||||
When an AI agent (such as a Chat Agent or Autofill Agent) operates within a project or folder, Shumai automatically loads the corresponding `AGENTS.md` files to provide context, operational rules, and project-specific knowledge.
|
||||
|
||||
---
|
||||
|
||||
## Hierarchical Traversal & Inheritance
|
||||
|
||||
Shumai uses a hierarchical context model for `AGENTS.md`:
|
||||
|
||||
- **Upward Traversal**: When an agent works on a file or folder, Shumai traverses the folder tree upwards from the current folder all the way to the **project root level**.
|
||||
- **Combined Context**: All `AGENTS.md` files found along this path are loaded into the agent's context in order (from the project root down to the current folder).
|
||||
- **Layered Rules**: This lets you define broad, project-wide rules and guidelines at the project root `AGENTS.md`, while adding specific rules, vocabulary, or autofill hints in nested subfolder `AGENTS.md` files.
|
||||
|
||||
---
|
||||
|
||||
## What to Include in AGENTS.md
|
||||
|
||||
You can use `AGENTS.md` to define any instructions you want the agent to follow when working in that folder or project:
|
||||
|
||||
- **Project & Folder Overview**: Describe what assets are stored in the folder and how they relate to the broader project.
|
||||
- **Agent Behavioral Rules**: Specify guardrails, tone, required formats, or things the agent should and shouldn't do when answering queries or leaving comments.
|
||||
- **Terminology & Domain Knowledge**: Define specialized vocabulary, acronyms, brand naming conventions, or project-specific jargon.
|
||||
- **Metadata & Autofill Instructions**: Guide the **Autofill Agent** on how to summarize assets, generate tags, or populate specific custom metadata fields for files in this folder.
|
||||
|
||||
---
|
||||
|
||||
## Accessing and Editing AGENTS.md
|
||||
|
||||
### Opening the Editor
|
||||
|
||||
To view or edit `AGENTS.md`:
|
||||
|
||||
1. Open any project or folder in the Shumai web application.
|
||||
2. Click the **`AGENTS.md`** button in the top navigation toolbar, or right-click any folder in the file browser and choose **AGENTS.md**.
|
||||
3. A dedicated WYSIWYG Markdown editor opens with full formatting support (headings, lists, code blocks, bold/italics, and links).
|
||||
|
||||
### Auto-Save
|
||||
|
||||
As you make changes in the editor, Shumai automatically saves your edits in the background with visual save status indicators (`Saving...`, `Saved`).
|
||||
|
||||
---
|
||||
|
||||
## Permissions & Read-Only Mode
|
||||
|
||||
- **Viewing**: All team members who have read access to the project can view `AGENTS.md`.
|
||||
- **Editing**: **Only Team Owners** are permitted to create, edit, or delete `AGENTS.md` files.
|
||||
- **Read-Only State**: Non-owner members will see a clear read-only indicator in the toolbar explaining that only team owners can edit instructions for the file.
|
||||
@@ -0,0 +1,82 @@
|
||||
---
|
||||
title: Document PDF Conversion with Gotenberg
|
||||
description: Convert Office documents, HTML, Markdown, CSV, and TXT files into high-fidelity PDF proxies for in-browser previewing.
|
||||
---
|
||||
|
||||
Office documents, HTML pages, Markdown files, spreadsheets, and plain-text files cannot be rendered natively in web browsers. Shumai uses [Gotenberg](https://gotenberg.dev), an open-source, Docker powered conversion API — to turn these files into PDF proxy assets for seamless in-browser previewing.
|
||||
|
||||
Gotenberg performs the conversion using:
|
||||
|
||||
- **LibreOffice** for Office documents, spreadsheets, and plain text.
|
||||
- **Headless Chromium** for HTML and Markdown files.
|
||||
|
||||
---
|
||||
|
||||
## Supported File Types
|
||||
|
||||
When Gotenberg is configured, Shumai automatically generates a PDF proxy for the following uploads:
|
||||
|
||||
| Category | Extensions | Converter |
|
||||
| ------------------ | ---------------------- | ----------- |
|
||||
| Word | `.doc`, `.docx` | LibreOffice |
|
||||
| Excel | `.xls`, `.xlsx` | LibreOffice |
|
||||
| PowerPoint | `.ppt`, `.pptx` | LibreOffice |
|
||||
| OpenDocument | `.odt`, `.ods`, `.odp` | LibreOffice |
|
||||
| Rich Text | `.rtf` | LibreOffice |
|
||||
| HTML | `.html`, `.htm` | Chromium |
|
||||
| Markdown | `.md`, `.markdown` | Chromium |
|
||||
| Spreadsheets / CSV | `.csv` | LibreOffice |
|
||||
| Plain text | `.txt` | LibreOffice |
|
||||
|
||||
---
|
||||
|
||||
## Configuration
|
||||
|
||||
Gotenberg support is opt-in and controlled by the following environment variables on the machine running the transcode workers:
|
||||
|
||||
| Variable | Required | Description |
|
||||
| ------------------------------- | --------------- | ---------------------------------------------------------------- |
|
||||
| `GOTENBERG_URL` | Yes (to enable) | Base URL of the Gotenberg service, e.g. `http://gotenberg:3000`. |
|
||||
| `GOTENBERG_BASIC_AUTH_USERNAME` | No | Username when Basic Authentication is enabled on Gotenberg. |
|
||||
| `GOTENBERG_BASIC_AUTH_PASSWORD` | No | Password when Basic Authentication is enabled on Gotenberg. |
|
||||
|
||||
### Docker Quickstart
|
||||
|
||||
You can start a Gotenberg container with a single command:
|
||||
|
||||
```bash
|
||||
docker run -d --name gotenberg -p 3000:3000 gotenberg/gotenberg:8
|
||||
```
|
||||
|
||||
If you wish to enable Basic Authentication:
|
||||
|
||||
```bash
|
||||
docker run -d --name gotenberg -p 3000:3000 gotenberg/gotenberg:8 gotenberg --gotenberg-basic-auth-username=admin --gotenberg-basic-auth-password=secret
|
||||
```
|
||||
|
||||
### Docker Compose Setup
|
||||
|
||||
Add a Gotenberg service to your `docker-compose.yaml`:
|
||||
|
||||
```yaml
|
||||
gotenberg:
|
||||
image: gotenberg/gotenberg:8
|
||||
restart: unless-stopped
|
||||
ports:
|
||||
- '3000:3000'
|
||||
```
|
||||
|
||||
Then point Shumai at it:
|
||||
|
||||
```bash
|
||||
GOTENBERG_URL=http://localhost:3000
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Behavior Without Gotenberg
|
||||
|
||||
If Gotenberg is not configured or unreachable, Shumai degrades gracefully:
|
||||
|
||||
- **Office documents and HTML**: the upload completes as `processed` without a PDF proxy.
|
||||
- **CSV, Markdown, and TXT**: a lightweight built-in PDF generator produces the proxy instead, with reduced fidelity.
|
||||
@@ -0,0 +1,115 @@
|
||||
---
|
||||
title: MCP Servers
|
||||
description: Connect your agents to external tools and APIs using Model Context Protocol.
|
||||
---
|
||||
|
||||
Model Context Protocol (MCP) is an open standard that enables AI models to safely interface with external tools, microservices, and APIs. In Shumai, you can register remote MCP servers using standard HTTP transports (`Streamable HTTP` or `SSE`) and assign them to your AI agents.
|
||||
|
||||
---
|
||||
|
||||
## How MCP Works in Shumai
|
||||
|
||||
Rather than overloading model context windows with dozens of complex parameter schemas, Shumai connects to MCP servers efficiently:
|
||||
|
||||
- **Automatic Discovery & Metadata Caching**: When you add an MCP server, Shumai records it in your team's settings and connects to the endpoint to discover available tools, server-reported usage instructions, and description metadata. Discovery runs when you refresh the server, complete an OAuth flow, or the first time an agent calls one of its tools. These schemas are cached in your database for fast retrieval.
|
||||
- **Context-Efficient Proxy Tool (`mcp`)**: Assigned MCP servers are multiplexed through a single unified `mcp` proxy tool injected into your Chat Agents. The agent can dynamically inspect server status, search tools, view parameter schemas, and invoke functions as needed without wasting LLM tokens.
|
||||
- **Direct Tools Option**: For high-frequency actions, you can optionally configure specific tools as **Direct Tools** to expose them directly to the agent as top-level LLM functions alongside the `mcp` proxy.
|
||||
|
||||
---
|
||||
|
||||
## Adding an MCP Server
|
||||
|
||||
To register a new MCP server in Shumai:
|
||||
|
||||
1. Navigate to **Team Settings** and click the **MCP** tab.
|
||||
2. Click **Add MCP Server**.
|
||||
3. In the dialog box, enter your **Server Endpoint URL** (e.g. `https://mcp.example.com/sse` or `http://localhost:8080/mcp`).
|
||||
4. Click **Create**.
|
||||
|
||||
> **Note:** Only the **Server Endpoint URL** is required. Shumai derives a placeholder server name from the URL immediately; the server's actual name, status, instructions, and tool inventory are discovered the first time the server is connected (via the Refresh button in the edit dialog or the first tool call by an agent).
|
||||
|
||||
### Optional Server Configuration
|
||||
|
||||
After creating a server (the create dialog only requires a URL), open its edit dialog to configure advanced settings:
|
||||
|
||||
- **Transport**: Choose between `Streamable HTTP` (default) or `Server-Sent Events (SSE)`.
|
||||
- **Auth Strategy**: Select `Auto-detect` (default), `None`, `Bearer Token`, or `OAuth 2.0`.
|
||||
- **Minimum Permission Role**: Set the minimum team role required to invoke tools on this server (`Reviewer`, `Editor`, or `Owner`).
|
||||
- **Direct Tools**: Specify a list of tool names that should be exposed directly to agents as native LLM tools.
|
||||
|
||||
---
|
||||
|
||||
## Understanding Tool Configuration
|
||||
|
||||
In the server's edit dialog, the **Tools** section lists every discovered tool with a three-state toggle (plus **All Off** / **All Proxy** / **All Direct** bulk actions):
|
||||
|
||||
- **Off**: The tool is excluded and completely invisible to agents — it cannot be listed, searched, or called through the proxy, nor registered as a direct tool. Use this to hide noisy or dangerous tools.
|
||||
- **Proxy** (default): The tool is available through the single `mcp` proxy tool.
|
||||
- **Direct**: The tool is exposed to agents as a native top-level function with a `{server}_{tool}` prefixed name.
|
||||
|
||||
### The `mcp` Proxy Tool
|
||||
|
||||
The `mcp` proxy tool is a single function injected into an agent's context that multiplexes every MCP server assigned to that agent. Instead of loading each tool's full parameter schema up front, the agent interacts with servers on demand:
|
||||
|
||||
- `mcp({})` — connection and auth status of all assigned servers
|
||||
- `mcp({ server: "name" })` — list a server's tools
|
||||
- `mcp({ search: "query" })` — search for tools across servers (schemas included by default)
|
||||
- `mcp({ describe: "tool" })` — view one tool's full parameter schema
|
||||
- `mcp({ instructions: "name" })` — view a server's usage instructions
|
||||
- `mcp({ server: "name", tool: "tool_name", args: {...} })` — call a tool (pass either the `{server}_{tool}` prefixed name or the original name)
|
||||
- `mcp({ action: "auth-start", server: "name" })` — start OAuth for a server
|
||||
|
||||
Because only one compact tool (plus a short server/tool listing) occupies the context window, the proxy keeps token usage low even when a server exposes dozens of tools. The trade-off is an extra discovery round trip: the agent typically lists or searches tools first, then calls them.
|
||||
|
||||
### Direct Tools
|
||||
|
||||
Direct tools flip the trade-off in the other direction. A tool configured as **Direct** is registered as a native top-level function (e.g. `tavily_mcp_tavily_search`) that the agent can invoke immediately, exactly like any built-in tool.
|
||||
|
||||
Why use direct tools:
|
||||
|
||||
- **Faster, more reliable calls** for high-frequency actions: the full parameter schema is always in the context window, so the agent can call the tool in a single step without first discovering it through the proxy.
|
||||
- **Better tool discovery**: the model sees the tool and its description up front and is more likely to reach for it at the right moment.
|
||||
|
||||
The cost: every direct tool permanently consumes context tokens for its schema, so reserve **Direct** for frequently used or critical tools and keep large MCP servers on **Proxy** to avoid unnecessary context overhead. Direct tools are still subject to the same role-based permission checks as proxy calls, and the `mcp` proxy tool remains available for discovery, auth, and status.
|
||||
|
||||
---
|
||||
|
||||
## Authentication Modes
|
||||
|
||||
Shumai supports several authentication strategies for securing access to MCP endpoints:
|
||||
|
||||
### 1. No Auth (`none`)
|
||||
|
||||
Used for public or local MCP servers that do not require credentials.
|
||||
|
||||
### 2. Bearer Token (`bearer`)
|
||||
|
||||
Provide a static API token or key. Shumai attaches this token in the `Authorization: Bearer <token>` header for all transport requests.
|
||||
|
||||
### 3. OAuth 2.0 (`oauth`)
|
||||
|
||||
For MCP endpoints protected by OAuth identity providers:
|
||||
|
||||
- **Authorization Code + PKCE**: Click **Connect** on the server card in Team Settings. Shumai opens a secure OAuth popup window directing you to the identity provider. After approving permissions, the browser automatically redirects back to Shumai, completes token exchange, and refreshes server tools.
|
||||
- **Client Credentials**: Provide a `Client ID` and `Client Secret` for automated server-to-server token acquisition.
|
||||
|
||||
---
|
||||
|
||||
## Assigning MCP Servers to Agents
|
||||
|
||||
By default, newly added MCP servers are **not assigned to any agent**. To give an agent access to an MCP server:
|
||||
|
||||
1. Navigate to **Team Settings** > **Agents**.
|
||||
2. Click on the target agent to open its configuration dialog.
|
||||
3. Scroll down to the **MCP Servers** section.
|
||||
4. Toggle the switch next to the MCP server(s) you want to authorize for this agent.
|
||||
5. Click **Save Changes**.
|
||||
|
||||
---
|
||||
|
||||
## Role-Based Access Control
|
||||
|
||||
Each MCP server has a **Minimum Required Role** setting (`Reviewer`, `Editor`, or `Owner`):
|
||||
|
||||
- When an agent attempts to call a tool on an MCP server, Shumai verifies the role of the user interacting with the agent.
|
||||
- If the user's role does not meet the minimum requirement, tool execution is blocked with a permission error message, preventing unauthorized actions.
|
||||
@@ -0,0 +1,60 @@
|
||||
---
|
||||
title: Password Reset
|
||||
description: How administrators generate secure password reset links for team members.
|
||||
---
|
||||
|
||||
Because Shumai does not require an external email delivery service (SMTP) to be configured for standard self-hosted deployments, password resets are initiated securely by an administrator using the Shumai CLI.
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
When a user forgets their password, an administrator can generate a one-time password reset link directly from the command line.
|
||||
|
||||
- **Link Expiration**: The generated password reset link is valid for **1 hour** (`3600 seconds`).
|
||||
- **One-Time Use**: Once used, the token is permanently invalidated.
|
||||
- **Session Revocation**: When a user resets their password, all existing active sessions for that account are automatically revoked across all devices.
|
||||
- **Latest Link Validity**: Generating a new reset link for a user immediately supersedes any previously generated pending links.
|
||||
|
||||
---
|
||||
|
||||
## Generating a Password Reset Link
|
||||
|
||||
### Running on Local Host / Server
|
||||
|
||||
Run the `reset-password` subcommand from your Shumai installation directory:
|
||||
|
||||
```bash
|
||||
shumai reset-password <user-email>
|
||||
```
|
||||
|
||||
_(Alternatively, `bun apps/web/src/index.ts reset-password <user-email>`)_
|
||||
|
||||
**Example Output:**
|
||||
|
||||
```text
|
||||
http://localhost:3000/reset-password?token=bb3xg4uO3cwN0FQv4cgUK6Hh
|
||||
```
|
||||
|
||||
### Running inside Docker
|
||||
|
||||
If Shumai is running inside a Docker container, execute the command using `docker exec`:
|
||||
|
||||
```bash
|
||||
docker exec -it <container-name-or-id> shumai reset-password <user-email>
|
||||
```
|
||||
|
||||
> [!TIP]
|
||||
> Both `shumai` and the common alias `shuami` (e.g. `shuami reset-password <user-email>`) are supported.
|
||||
|
||||
> [!NOTE]
|
||||
> For remote servers or production deployments, ensure `BETTER_AUTH_URL` is set in your environment (e.g., `BETTER_AUTH_URL=https://shumai.example.com`) so the CLI generates the reset link with your public domain instead of `localhost`.
|
||||
|
||||
---
|
||||
|
||||
## Member Reset Experience
|
||||
|
||||
1. The administrator sends the generated URL to the team member via their preferred secure communication channel.
|
||||
2. The user opens the link in their browser.
|
||||
3. The user inputs their **New Password** and **Confirm Password** (minimum 3 characters).
|
||||
4. Upon clicking **Reset Password**, the password is securely updated, all previous active sessions are invalidated, and the user is redirected to `/login` to sign in.
|
||||
@@ -0,0 +1,121 @@
|
||||
---
|
||||
title: Resource Quotas
|
||||
description: Configure team resource quotas, monitor live usage, and reset quota windows from the dashboard.
|
||||
---
|
||||
|
||||
AI workflows and media processing tools can consume significant compute and API credits. Shumai provides a **Resource Quotas** system that allows Team Owners to set granular rate limits, govern budgets, and monitor real-time usage across team members and roles.
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
Resource Quotas allow you to define maximum usage limits across specific time windows (e.g., hourly, daily, or weekly). When a member or team reaches their assigned quota, further actions for that resource are safely blocked until the quota period resets.
|
||||
|
||||
Quota configuration and usage monitoring are separate parts of the team experience:
|
||||
|
||||
- To create and manage quota rules, open **Team Settings** and navigate to the **Quotas** tab.
|
||||
- To monitor live usage, open the **Team Dashboard** and select **Quotas** under the **TEAM** section.
|
||||
|
||||
The quota dashboard is available to Team Owners.
|
||||
|
||||
---
|
||||
|
||||
## Scope Modes
|
||||
|
||||
When creating or editing a quota rule, you can define how the limit is applied:
|
||||
|
||||
### 1. Each Member
|
||||
|
||||
- **Behavior**: Every member in the scope receives their own independent limit. Usage by one member does not affect the remaining quota of others.
|
||||
- **Optional Role Filter**: You can restrict the quota to members with a specific role (e.g. only **Editors** or **Reviewers**), or apply it to the entire team.
|
||||
- **Use Case**: Give each editor a daily budget of 100,000 tokens.
|
||||
|
||||
### 2. All Members (Shared Pool)
|
||||
|
||||
- **Behavior**: The quota limit is shared as a collective pool across all matching members. Every member's consumption draws from the same total.
|
||||
- **Optional Role Filter**: Apply the shared pool to all team members or restrict it to a specific role.
|
||||
- **Use Case**: Cap the total team spending on AI models to $50 per day.
|
||||
|
||||
### 3. Selected Members
|
||||
|
||||
- **Behavior**: Assign individual limits to specific chosen team members.
|
||||
- **Use Case**: Grant higher limits to senior artists or technical directors while keeping standard limits for others.
|
||||
|
||||
---
|
||||
|
||||
## Supported Resource Types
|
||||
|
||||
Shumai supports quota enforcement across multiple layers of the AI and agent architecture:
|
||||
|
||||
| Resource Type | Description | Target Specification |
|
||||
| :-------------------------- | :-------------------------------------------------------------------------------------- | :----------------------------------- |
|
||||
| **Total Tokens** | Total LLM input and output tokens consumed in chat, comments, and autofill. | Team, Role, or Members |
|
||||
| **AI Cost ($)** | Dollar expenditure accrued from AI model providers. | Team, Role, or Members |
|
||||
| **MCP Server Calls** | Number of tool invocations directed to a connected Model Context Protocol (MCP) server. | Target MCP Server ID |
|
||||
| **Sandboxed Bash Commands** | Shell commands executed by the agent inside the isolated sandbox. | Wildcard pattern (e.g. `npm *`, `*`) |
|
||||
| **Agent Tool Calls** | Calls to specific native tools (e.g. `read_asset`, `download_asset`, `create_file`). | Tool name |
|
||||
|
||||
### Bash Command Wildcard Matching
|
||||
|
||||
For sandboxed bash execution, you can restrict specific command patterns using wildcards (`*` and `?`):
|
||||
|
||||
- `*`: Matches any bash command execution.
|
||||
- `npm *`: Matches any npm command (e.g., `npm install`, `npm test`).
|
||||
- `git commit*`: Matches git commit invocations.
|
||||
|
||||
---
|
||||
|
||||
## Time Periods & Rollover
|
||||
|
||||
Quotas can be configured with the following reset periods:
|
||||
|
||||
- **1 Hour** (`1hour`)
|
||||
- **5 Hours** (`5hour`)
|
||||
- **1 Day** (`1day`)
|
||||
- **7 Days** (`7day`)
|
||||
|
||||
### Lazy Reset Mechanism
|
||||
|
||||
Shumai tracks usage windows automatically. When a period window expires, the system resets the quota upon the member's next request, seamlessly starting a fresh window without requiring background maintenance tasks.
|
||||
|
||||
---
|
||||
|
||||
## Monitoring Live Usage
|
||||
|
||||
Team Owners can inspect live consumption from the team dashboard:
|
||||
|
||||
1. Open the **Team Dashboard**.
|
||||
2. Select **Quotas** under the **TEAM** section.
|
||||
3. Quota rules are shown as first-level collapsible entries.
|
||||
4. Expand a rule to view its usage records.
|
||||
|
||||
Each usage record displays:
|
||||
|
||||
- **Consumption Status**: Progress bar showing consumed units versus the total limit.
|
||||
- **Remaining Allowance**: Percentage and numerical amount remaining.
|
||||
- **Refresh Countdown**: Remaining time until the active window resets (e.g., _"Refreshes in 45m"_).
|
||||
- **Target**: The team shared pool, role pool, or individual member associated with the record.
|
||||
- **Member Search**: For member-scoped rules, search the usage records by member name or email.
|
||||
|
||||
Usage records are loaded when a rule is expanded and refresh automatically while the rule is open.
|
||||
|
||||
### Manually Resetting a Usage Record
|
||||
|
||||
Each usage record includes a **Reset Usage** action. After confirming the action:
|
||||
|
||||
- Consumption is set to zero.
|
||||
- The quota period starts immediately.
|
||||
- The period ends after the configured quota duration.
|
||||
- For example, resetting a one-day quota at 10:00 starts a new window from 10:00 until 10:00 the following day.
|
||||
|
||||
A reset can also initialize a zero-consumption record for a member or shared pool that has not received usage yet. Resets are recorded in the team audit log.
|
||||
|
||||
---
|
||||
|
||||
## Managing Quota Rules
|
||||
|
||||
- **Enable / Disable**: Toggle the switch on any quota card in Team Settings to temporarily pause or resume enforcement without deleting the rule.
|
||||
- **Edit Rules**: Click any quota card in Team Settings to update limits, change reset periods, or adjust member selections.
|
||||
- **Delete Rules**: Open the card action menu (`⋮`) in Team Settings and select **Delete** to remove the quota rule.
|
||||
|
||||
Quota usage is monitored and reset from the Team Dashboard rather than from the settings rule cards.
|
||||
@@ -14,6 +14,8 @@ Shumai allows you to collaborate with external stakeholders who do not have acco
|
||||
3. Configure the share link in the right sidebar. You can:
|
||||
- Add password protection
|
||||
- Set an expiration date
|
||||
- Allow or disallow downloads
|
||||
- Add a watermark to previews
|
||||
- Configure which metadata fields are visible to recipients
|
||||
4. Click **Copy Link** at the bottom of the sidebar, then send the link to your client or stakeholder.
|
||||
|
||||
@@ -41,6 +43,30 @@ Set an optional date and time after which the link becomes inactive. Once the da
|
||||
|
||||
Secure sensitive work by adding a password. External users visiting the link will be prompted to enter the correct password before they can view the assets.
|
||||
|
||||
### Allow Download
|
||||
|
||||
Control whether visitors can download the shared files. When **Allow download** is turned off:
|
||||
|
||||
- All download buttons are hidden on the public share page (file cards, selection bar, viewer control bars, and the top navigation).
|
||||
|
||||
Guests can still preview the files; only downloading is blocked. This is often combined with a watermark so previews remain viewable but protected.
|
||||
|
||||
### Watermark
|
||||
|
||||
Overlay a watermark (e.g. a "CONFIDENTIAL" text label or a logo image) on every preview shown through the share link. Open the watermark editor, arrange the blocks, and save.
|
||||
|
||||
Watermarking is **lazy and per-share-link** to keep storage costs low:
|
||||
|
||||
- The watermark transcode is only triggered when you **enable the watermark on a share link** — Shumai does **not** pre-generate watermark copies for every file in your workspace.
|
||||
- All video and image assets already in the share are transcoded at that moment (the sidebar shows a _processing_ status until it finishes).
|
||||
- Files and folders **added to the share link later are automatically transcoded too**, so the watermark always covers the full share without any manual steps.
|
||||
- Since watermark copies are only produced for assets that are actually shared through a watermarked link, files that are never shared (or shared through non-watermarked links) never consume extra storage for watermark proxies. This can save a very large amount of storage on big libraries.
|
||||
|
||||
Notes:
|
||||
|
||||
- Only **video and image** proxies are watermarked; other media types (PDF, audio, ...) are not affected.
|
||||
- While the watermark is still processing, previews are hidden rather than exposing the original, unwatermarked proxy.
|
||||
|
||||
### Default Sort Order
|
||||
|
||||
Set a default sorting rule for the shared page (e.g. sorting by name or version) to ensure the client views the files in the intended order.
|
||||
|
||||
@@ -74,6 +74,7 @@ export default tseslint.config(
|
||||
'**/packages/db/src/generated/**',
|
||||
'**/packages/core/src/generated/**',
|
||||
'**/data/**',
|
||||
'**/packages/core/src/provider/generator/**',
|
||||
'**/packages/webui/components/ui/**',
|
||||
'**/packages/webui/paraglide/**',
|
||||
'**/packages/webui/public/**',
|
||||
|
||||
+6
-4
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "shumai",
|
||||
"version": "0.3.3",
|
||||
"version": "0.4.2",
|
||||
"private": true,
|
||||
"type": "module",
|
||||
"repository": {
|
||||
@@ -18,11 +18,10 @@
|
||||
"typecheck": "tsc --noEmit",
|
||||
"lint": "eslint . --ext ts,tsx --report-unused-disable-directives --max-warnings 0",
|
||||
"test": "bun --bun vitest run",
|
||||
"test:e2e": "playwright test --project=harness-chromium --project=app-chromium",
|
||||
"test:e2e:app": "playwright test --project=app-chromium",
|
||||
"test:e2e:webui": "E2E_SKIP_APP_SERVER=true playwright test --project=harness-chromium",
|
||||
"test:e2e:all": "playwright test",
|
||||
"test:e2e:workflow": "bun --bun vitest run -c packages/e2e/vitest.config.ts",
|
||||
"test:e2e:ui": "playwright test --ui --project=harness-chromium --project=app-chromium",
|
||||
"test:e2e:report": "playwright show-report",
|
||||
"test:e2e:install": "playwright install --with-deps",
|
||||
"harness:dev": "bun run packages/webui/e2e/harness/serve.ts",
|
||||
"format": "prettier --write .",
|
||||
@@ -66,5 +65,8 @@
|
||||
"typescript-eslint": "8.60.1",
|
||||
"vite-tsconfig-paths": "6.1.1",
|
||||
"vitest": "4.1.8"
|
||||
},
|
||||
"patchedDependencies": {
|
||||
"@earendil-works/pi-ai@0.82.1": "patches/@earendil-works%2Fpi-ai@0.82.1.patch"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@shumai/agent",
|
||||
"version": "0.3.3",
|
||||
"version": "0.4.2",
|
||||
"private": true,
|
||||
"type": "module",
|
||||
"main": "./src/index.ts",
|
||||
@@ -14,12 +14,12 @@
|
||||
"@shumai/db": "workspace:*",
|
||||
"@shumai/dtos": "workspace:*",
|
||||
"@shumai/workflow-core": "workspace:*",
|
||||
"@sinclair/typebox": "0.34.49",
|
||||
"@temporalio/activity": "1.17.2",
|
||||
"@temporalio/worker": "1.17.2",
|
||||
"@temporalio/workflow": "1.17.2",
|
||||
"adm-zip": "0.5.17",
|
||||
"jittered-fractional-indexing": "1.0.1",
|
||||
"typebox": "1.1.38",
|
||||
"ulid": "3.0.2",
|
||||
"zod": "4.4.3"
|
||||
},
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,354 @@
|
||||
import { describe, it, expect } from 'vitest'
|
||||
import { escapeXmlAttr, serializeContextToXml } from './serialize-context'
|
||||
import type { ShumaiMessageContext } from '@shumai/dtos'
|
||||
|
||||
describe('serializeContextToXml', () => {
|
||||
describe('escapeXmlAttr', () => {
|
||||
it('escapes &, <, >, ", and \' characters correctly', () => {
|
||||
expect(escapeXmlAttr('Alice & Bob <Admin> "v1" \'test\'')).toBe(
|
||||
'Alice & Bob <Admin> "v1" 'test'',
|
||||
)
|
||||
})
|
||||
|
||||
it('handles clean strings without modification', () => {
|
||||
expect(escapeXmlAttr('normal-string_123.mp4')).toBe('normal-string_123.mp4')
|
||||
})
|
||||
})
|
||||
|
||||
describe('Tag Serialization', () => {
|
||||
it('returns empty string for null, undefined, or empty context', () => {
|
||||
expect(serializeContextToXml(null)).toBe('')
|
||||
expect(serializeContextToXml(undefined)).toBe('')
|
||||
expect(serializeContextToXml({})).toBe('')
|
||||
})
|
||||
|
||||
it('serializes minimal context with only user', () => {
|
||||
const context: ShumaiMessageContext = {
|
||||
user: { id: 'usr_1', name: 'Alice', role: 'editor' },
|
||||
}
|
||||
expect(serializeContextToXml(context)).toBe(
|
||||
'<context>\n <user id="usr_1" name="Alice" role="editor" />\n</context>',
|
||||
)
|
||||
})
|
||||
|
||||
it('serializes context with user and thread tag with reply_count', () => {
|
||||
const context: ShumaiMessageContext = {
|
||||
user: { id: 'usr_1', name: 'Alice', role: 'editor' },
|
||||
thread: { id: 'th_01JXYZ', replyCount: 3 },
|
||||
}
|
||||
expect(serializeContextToXml(context)).toBe(
|
||||
'<context>\n <user id="usr_1" name="Alice" role="editor" />\n <thread id="th_01JXYZ" reply_count="3" />\n</context>',
|
||||
)
|
||||
})
|
||||
|
||||
it('serializes context with thread tag without reply_count', () => {
|
||||
const context: ShumaiMessageContext = {
|
||||
thread: { id: 'th_01JXYZ' },
|
||||
}
|
||||
expect(serializeContextToXml(context)).toBe(
|
||||
'<context>\n <thread id="th_01JXYZ" />\n</context>',
|
||||
)
|
||||
})
|
||||
|
||||
it('serializes minimal context with only currentAsset (without ancestors)', () => {
|
||||
const context: ShumaiMessageContext = {
|
||||
currentAsset: {
|
||||
id: 'ast_1',
|
||||
name: 'clip.mp4',
|
||||
type: 'file',
|
||||
mediaType: 'video',
|
||||
path: 'clip.mp4',
|
||||
},
|
||||
}
|
||||
expect(serializeContextToXml(context)).toBe(
|
||||
'<context>\n <current_asset id="ast_1" name="clip.mp4" type="file" media_type="video" path="clip.mp4" />\n</context>',
|
||||
)
|
||||
})
|
||||
|
||||
it('serializes full video context with duration, timestamp, annotation, attached files, and referenced assets', () => {
|
||||
const context: ShumaiMessageContext = {
|
||||
user: { id: 'usr_01', name: 'Alice Chen', role: 'editor' },
|
||||
currentAsset: {
|
||||
id: 'ast_01JC04_CURRENT',
|
||||
name: 'product_launch_v2.mp4',
|
||||
type: 'file',
|
||||
mediaType: 'video',
|
||||
parentId: 'ast_01JC03_PARENT',
|
||||
path: 'Marketing/2026_Launch/Footage/product_launch_v2.mp4',
|
||||
durationSeconds: 85.4,
|
||||
ancestors: [
|
||||
{ id: 'ast_01JC01_ROOT', name: 'Marketing' },
|
||||
{ id: 'ast_01JC02_SUB', name: '2026_Launch' },
|
||||
{ id: 'ast_01JC03_PARENT', name: 'Footage' },
|
||||
],
|
||||
},
|
||||
position: { type: 'time', seconds: 14.25 },
|
||||
annotation: true,
|
||||
attachedFiles: [
|
||||
{
|
||||
id: 'ast_01JC05_ATT1',
|
||||
name: 'brand_guidelines_2026.pdf',
|
||||
type: 'file',
|
||||
mediaType: 'pdf',
|
||||
path: 'Brand/brand_guidelines_2026.pdf',
|
||||
},
|
||||
],
|
||||
referencedAssets: [
|
||||
{
|
||||
id: 'ast_01JC07_REF2',
|
||||
name: 'Color_LUTs',
|
||||
type: 'folder',
|
||||
path: 'Assets/Color_LUTs',
|
||||
},
|
||||
{
|
||||
id: 'ast_01JC06_REF1',
|
||||
name: 'logo_white.png',
|
||||
type: 'file',
|
||||
mediaType: 'image',
|
||||
path: 'Brand/Logos/logo_white.png',
|
||||
},
|
||||
],
|
||||
}
|
||||
|
||||
const expected = `<context>
|
||||
<user id="usr_01" name="Alice Chen" role="editor" />
|
||||
<current_asset id="ast_01JC04_CURRENT" name="product_launch_v2.mp4" type="file" media_type="video" parent_id="ast_01JC03_PARENT" path="Marketing/2026_Launch/Footage/product_launch_v2.mp4" duration_seconds="85.40">
|
||||
<ancestors>
|
||||
<folder id="ast_01JC01_ROOT" name="Marketing" />
|
||||
<folder id="ast_01JC02_SUB" name="2026_Launch" />
|
||||
<folder id="ast_01JC03_PARENT" name="Footage" />
|
||||
</ancestors>
|
||||
</current_asset>
|
||||
<position type="time" seconds="14.2500" />
|
||||
<annotation />
|
||||
<attached_files>
|
||||
<file id="ast_01JC05_ATT1" name="brand_guidelines_2026.pdf" type="file" media_type="pdf" path="Brand/brand_guidelines_2026.pdf" />
|
||||
</attached_files>
|
||||
<referenced_assets>
|
||||
<asset id="ast_01JC06_REF1" name="logo_white.png" type="file" media_type="image" path="Brand/Logos/logo_white.png" />
|
||||
<folder id="ast_01JC07_REF2" name="Color_LUTs" path="Assets/Color_LUTs" />
|
||||
</referenced_assets>
|
||||
</context>`
|
||||
|
||||
expect(serializeContextToXml(context)).toBe(expected)
|
||||
})
|
||||
|
||||
it('serializes PDF document context with total_pages and position.type === "page"', () => {
|
||||
const context: ShumaiMessageContext = {
|
||||
currentAsset: {
|
||||
id: 'pdf_1',
|
||||
name: 'report.pdf',
|
||||
type: 'file',
|
||||
mediaType: 'pdf',
|
||||
totalPages: 12,
|
||||
},
|
||||
position: { type: 'page', page: 3 },
|
||||
}
|
||||
|
||||
const expected = `<context>
|
||||
<current_asset id="pdf_1" name="report.pdf" type="file" media_type="pdf" total_pages="12" />
|
||||
<position type="page" page="3" />
|
||||
</context>`
|
||||
|
||||
expect(serializeContextToXml(context)).toBe(expected)
|
||||
})
|
||||
|
||||
it('serializes Video context with total_frames and duration_seconds', () => {
|
||||
const context: ShumaiMessageContext = {
|
||||
currentAsset: {
|
||||
id: 'vid_1',
|
||||
name: 'clip.mp4',
|
||||
type: 'file',
|
||||
mediaType: 'video',
|
||||
mimeType: 'video/mp4',
|
||||
durationSeconds: 9,
|
||||
totalFrames: 268,
|
||||
},
|
||||
}
|
||||
|
||||
const expected = `<context>
|
||||
<current_asset id="vid_1" name="clip.mp4" type="file" media_type="video" mime_type="video/mp4" duration_seconds="9.00" total_frames="268" />
|
||||
</context>`
|
||||
|
||||
expect(serializeContextToXml(context)).toBe(expected)
|
||||
})
|
||||
|
||||
it('serializes navigation context with navigated="true" and ancestors hierarchy', () => {
|
||||
const context: ShumaiMessageContext = {
|
||||
currentAsset: {
|
||||
id: 'f_sub',
|
||||
name: 'Subfolder',
|
||||
type: 'folder',
|
||||
navigated: true,
|
||||
ancestors: [{ id: 'f_root', name: 'Root' }],
|
||||
},
|
||||
}
|
||||
|
||||
const expected = `<context>
|
||||
<current_asset id="f_sub" name="Subfolder" type="folder" navigated="true">
|
||||
<ancestors>
|
||||
<folder id="f_root" name="Root" />
|
||||
</ancestors>
|
||||
</current_asset>
|
||||
</context>`
|
||||
|
||||
expect(serializeContextToXml(context)).toBe(expected)
|
||||
})
|
||||
|
||||
it('serializes mime_type alongside media_type for current asset and attached files', () => {
|
||||
const context: ShumaiMessageContext = {
|
||||
currentAsset: {
|
||||
id: 'img_1',
|
||||
name: 'photo.png',
|
||||
type: 'file',
|
||||
mediaType: 'image',
|
||||
mimeType: 'image/png',
|
||||
},
|
||||
attachedFiles: [
|
||||
{
|
||||
id: 'doc_1',
|
||||
name: 'spec.pdf',
|
||||
type: 'file',
|
||||
mediaType: 'pdf',
|
||||
mimeType: 'application/pdf',
|
||||
},
|
||||
],
|
||||
}
|
||||
|
||||
const expected = `<context>
|
||||
<current_asset id="img_1" name="photo.png" type="file" media_type="image" mime_type="image/png" />
|
||||
<attached_files>
|
||||
<file id="doc_1" name="spec.pdf" type="file" media_type="pdf" mime_type="application/pdf" />
|
||||
</attached_files>
|
||||
</context>`
|
||||
|
||||
expect(serializeContextToXml(context)).toBe(expected)
|
||||
})
|
||||
})
|
||||
|
||||
describe('XML Escaping & Security', () => {
|
||||
it('escapes user names, asset names, and paths with special characters', () => {
|
||||
const context: ShumaiMessageContext = {
|
||||
user: {
|
||||
id: 'u_1',
|
||||
name: 'Alice & Bob <Admin>',
|
||||
role: 'reviewer "lead"',
|
||||
},
|
||||
currentAsset: {
|
||||
id: 'ast_1',
|
||||
name: 'Final <Cut> "v2" & Test.mp4',
|
||||
type: 'file',
|
||||
path: 'Folder A > Folder B & C/clip.mp4',
|
||||
ancestors: [{ id: 'anc_1', name: 'Folder B & C' }],
|
||||
},
|
||||
attachedFiles: [
|
||||
{
|
||||
id: 'att_1',
|
||||
name: "Don't <Touch> & Go.pdf",
|
||||
type: 'file',
|
||||
path: "Path 'A' & 'B'/doc.pdf",
|
||||
},
|
||||
],
|
||||
}
|
||||
|
||||
const xml = serializeContextToXml(context)
|
||||
expect(xml).toContain('name="Alice & Bob <Admin>"')
|
||||
expect(xml).toContain('role="reviewer "lead""')
|
||||
expect(xml).toContain('name="Final <Cut> "v2" & Test.mp4"')
|
||||
expect(xml).toContain('path="Folder A > Folder B & C/clip.mp4"')
|
||||
expect(xml).toContain('name="Folder B & C"')
|
||||
expect(xml).toContain('name="Don't <Touch> & Go.pdf"')
|
||||
expect(xml).toContain('path="Path 'A' & 'B'/doc.pdf"')
|
||||
|
||||
// Verify no unescaped dangerous characters exist inside attribute quotes
|
||||
const attrMatch = xml.match(/\w+="([^"]*)"/g)
|
||||
expect(attrMatch).not.toBeNull()
|
||||
})
|
||||
})
|
||||
|
||||
describe('Order Stability & Prompt Caching Invariants', () => {
|
||||
it('produces identical XML regardless of object key order', () => {
|
||||
const contextA: ShumaiMessageContext = {
|
||||
user: { role: 'editor', name: 'Alice', id: 'u_1' },
|
||||
currentAsset: {
|
||||
name: 'video.mp4',
|
||||
type: 'file',
|
||||
id: 'ast_1',
|
||||
mediaType: 'video',
|
||||
},
|
||||
position: { seconds: 12.345, type: 'time' },
|
||||
}
|
||||
|
||||
const contextB: ShumaiMessageContext = {
|
||||
position: { type: 'time', seconds: 12.345 },
|
||||
currentAsset: {
|
||||
id: 'ast_1',
|
||||
mediaType: 'video',
|
||||
type: 'file',
|
||||
name: 'video.mp4',
|
||||
},
|
||||
user: { id: 'u_1', name: 'Alice', role: 'editor' },
|
||||
}
|
||||
|
||||
expect(serializeContextToXml(contextA)).toBe(serializeContextToXml(contextB))
|
||||
})
|
||||
|
||||
it('sorts attachedFiles and referencedAssets by id ascending', () => {
|
||||
const context: ShumaiMessageContext = {
|
||||
attachedFiles: [
|
||||
{ id: 'z_file', name: 'Z', type: 'file' },
|
||||
{ id: 'a_file', name: 'A', type: 'file' },
|
||||
{ id: 'm_file', name: 'M', type: 'file' },
|
||||
],
|
||||
referencedAssets: [
|
||||
{ id: 'z_asset', name: 'Z', type: 'file' },
|
||||
{ id: 'a_asset', name: 'A', type: 'folder' },
|
||||
{ id: 'm_asset', name: 'M', type: 'file' },
|
||||
],
|
||||
}
|
||||
|
||||
const xml = serializeContextToXml(context)
|
||||
const fileOrder = [...xml.matchAll(/<file id="([^"]+)"/g)].map((m) => m[1])
|
||||
const refOrder = [...xml.matchAll(/<(?:asset|folder) id="([^"]+)"/g)].map((m) => m[1])
|
||||
|
||||
expect(fileOrder).toEqual(['a_file', 'm_file', 'z_file'])
|
||||
expect(refOrder).toEqual(['a_asset', 'm_asset', 'z_asset'])
|
||||
})
|
||||
|
||||
it('normalizes float formatting with fixed precision (toFixed(4) for position, toFixed(2) for duration)', () => {
|
||||
const context1: ShumaiMessageContext = {
|
||||
currentAsset: { id: '1', name: 'a', type: 'file', durationSeconds: 14 },
|
||||
position: { type: 'time', seconds: 5.5 },
|
||||
}
|
||||
const context2: ShumaiMessageContext = {
|
||||
currentAsset: { id: '1', name: 'a', type: 'file', durationSeconds: 14.0001 },
|
||||
position: { type: 'time', seconds: 5.50002 },
|
||||
}
|
||||
|
||||
expect(serializeContextToXml(context1)).toContain('duration_seconds="14.00"')
|
||||
expect(serializeContextToXml(context1)).toContain('seconds="5.5000"')
|
||||
expect(serializeContextToXml(context2)).toContain('duration_seconds="14.00"')
|
||||
expect(serializeContextToXml(context2)).toContain('seconds="5.5000"')
|
||||
})
|
||||
|
||||
it('serializes annotation tag with id when context.id is provided', () => {
|
||||
const context: ShumaiMessageContext = {
|
||||
id: '01JABCDEF1234567890',
|
||||
annotation: true,
|
||||
}
|
||||
expect(serializeContextToXml(context)).toBe(
|
||||
'<context>\n <annotation id="01JABCDEF1234567890" />\n</context>',
|
||||
)
|
||||
})
|
||||
|
||||
it('escapes special XML characters in annotation id', () => {
|
||||
const context: ShumaiMessageContext = {
|
||||
id: 'test<id>&"123"',
|
||||
annotation: true,
|
||||
}
|
||||
expect(serializeContextToXml(context)).toBe(
|
||||
'<context>\n <annotation id="test<id>&"123"" />\n</context>',
|
||||
)
|
||||
})
|
||||
})
|
||||
})
|
||||
@@ -0,0 +1 @@
|
||||
export { escapeXmlAttr, serializeContextToXml } from '@shumai/dtos'
|
||||
@@ -7,8 +7,7 @@ import { DatabaseSessionStorage } from './database-session-storage'
|
||||
import { agentService } from '@shumai/core/src/agent/agent'
|
||||
import { createAgentSession, type DbProviderInfo } from './index'
|
||||
import * as sandboxedBashModule from './tools/sandboxed-bash'
|
||||
import * as analyzeImageModule from './tools/analyze-image'
|
||||
import * as screenshotModule from './tools/screenshot'
|
||||
import * as readAssetModule from './tools/read-asset'
|
||||
|
||||
describe('DatabaseSessionStorage', () => {
|
||||
setupTestDbHooks()
|
||||
@@ -451,9 +450,8 @@ describe('DatabaseSessionStorage', () => {
|
||||
})
|
||||
const sessionId = initialStorage.sessionId
|
||||
|
||||
// 2. Spy on media tools constructors
|
||||
const createAnalyzeImageToolSpy = vi.spyOn(analyzeImageModule, 'createAnalyzeImageTool')
|
||||
const createScreenshotToolSpy = vi.spyOn(screenshotModule, 'createScreenshotTool')
|
||||
// 2. Spy on media tool constructor
|
||||
const createReadAssetToolSpy = vi.spyOn(readAssetModule, 'createReadAssetTool')
|
||||
|
||||
// 3. Resume the session via createAgentSession with a NEW comment ID
|
||||
await createAgentSession({
|
||||
@@ -470,12 +468,11 @@ describe('DatabaseSessionStorage', () => {
|
||||
providers: mockProviders,
|
||||
})
|
||||
|
||||
// 4. Assert that the tools were instantiated using the new comment ID and user ID
|
||||
expect(createAnalyzeImageToolSpy).toHaveBeenCalledWith(user.id, 'new-comment-456')
|
||||
expect(createScreenshotToolSpy).toHaveBeenCalledWith(user.id, 'new-comment-456')
|
||||
// 4. Assert that the tool was instantiated using user ID
|
||||
expect(createReadAssetToolSpy).toHaveBeenCalledWith(user.id)
|
||||
})
|
||||
|
||||
it('should use the current comment ID for media tools in subsequent turns (video)', async () => {
|
||||
it('should instantiate media tools with user ID in subsequent turns (video)', async () => {
|
||||
const { agent, user, team } = await setupTestData()
|
||||
|
||||
// Create a project and asset to satisfy FK constraints
|
||||
@@ -505,9 +502,8 @@ describe('DatabaseSessionStorage', () => {
|
||||
})
|
||||
const sessionId = initialStorage.sessionId
|
||||
|
||||
// 2. Spy on media tools constructors
|
||||
const createAnalyzeImageToolSpy = vi.spyOn(analyzeImageModule, 'createAnalyzeImageTool')
|
||||
const createScreenshotToolSpy = vi.spyOn(screenshotModule, 'createScreenshotTool')
|
||||
// 2. Spy on media tool constructor
|
||||
const createReadAssetToolSpy = vi.spyOn(readAssetModule, 'createReadAssetTool')
|
||||
|
||||
// 3. Resume the session via createAgentSession with a NEW comment ID
|
||||
await createAgentSession({
|
||||
@@ -524,9 +520,8 @@ describe('DatabaseSessionStorage', () => {
|
||||
providers: mockProviders,
|
||||
})
|
||||
|
||||
// 4. Assert that the tools were instantiated using the new comment ID and user ID
|
||||
expect(createScreenshotToolSpy).toHaveBeenCalledWith(user.id, 'new-comment-456')
|
||||
expect(createAnalyzeImageToolSpy).toHaveBeenCalledWith(user.id, 'new-comment-456')
|
||||
// 4. Assert that the tool was instantiated using user ID
|
||||
expect(createReadAssetToolSpy).toHaveBeenCalledWith(user.id)
|
||||
})
|
||||
|
||||
describe('P1 Bug Reproductions', () => {
|
||||
@@ -662,5 +657,158 @@ describe('DatabaseSessionStorage', () => {
|
||||
expect(stats.totalTokens).toBe(170)
|
||||
expect(stats.costTotal).toBeCloseTo(0.032)
|
||||
})
|
||||
|
||||
it('should save user message turn as custom_message (shumai_message) in DB when currentMessageContext is set', async () => {
|
||||
const { agent, user } = await setupTestData()
|
||||
const storage = await DatabaseSessionStorage.create({ agentId: agent.id, userId: user.id })
|
||||
|
||||
storage.currentMessageContext = {
|
||||
user: { id: user.id, name: user.name, role: 'owner' },
|
||||
currentAsset: { id: 'asset-123', name: 'video.mp4', type: 'file' },
|
||||
}
|
||||
|
||||
const userEntry: SessionTreeEntry = {
|
||||
type: 'message',
|
||||
id: 'msg-user-1',
|
||||
parentId: null,
|
||||
timestamp: new Date().toISOString(),
|
||||
message: {
|
||||
role: 'user',
|
||||
content: 'Hello, help me analyze this video',
|
||||
timestamp: Date.now(),
|
||||
},
|
||||
}
|
||||
|
||||
await storage.appendEntry(userEntry)
|
||||
|
||||
// 1. Verify DB record type is 'custom_message', not 'message'
|
||||
const record = await prisma.agentSessionEntry.findUnique({
|
||||
where: { id: 'msg-user-1' },
|
||||
})
|
||||
expect(record).toBeDefined()
|
||||
expect(record?.type).toBe('custom_message')
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const data = record?.data as any
|
||||
expect(data.customType).toBe('shumai_message')
|
||||
expect(data.content).toBe('Hello, help me analyze this video')
|
||||
expect(data.details?.user?.id).toBe(user.id)
|
||||
expect(data.details?.currentAsset?.id).toBe('asset-123')
|
||||
|
||||
// 2. Verify getEntries() and getPathToRoot() do not throw and return proper custom_message
|
||||
const entries = await storage.getEntries()
|
||||
expect(entries).toHaveLength(1)
|
||||
expect(entries[0].type).toBe('custom_message')
|
||||
|
||||
const pathEntries = await storage.getPathToRoot('msg-user-1')
|
||||
expect(pathEntries).toHaveLength(1)
|
||||
expect(pathEntries[0].type).toBe('custom_message')
|
||||
|
||||
const stats = await storage.getSessionStats()
|
||||
expect(stats.messageCount).toBe(1)
|
||||
})
|
||||
|
||||
it('should safely handle legacy records where type was message but data was shumai_message', async () => {
|
||||
const { agent } = await setupTestData()
|
||||
const storage = await DatabaseSessionStorage.create({ agentId: agent.id })
|
||||
|
||||
await prisma.agentSessionEntry.create({
|
||||
data: {
|
||||
id: 'legacy-corrupted-entry',
|
||||
sessionId: storage.sessionId,
|
||||
type: 'message',
|
||||
data: {
|
||||
customType: 'shumai_message',
|
||||
content: 'Legacy prompt',
|
||||
display: true,
|
||||
details: { user: { id: 'u1', name: 'User 1' } },
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
// Must not throw in getEntries(), getPathToRoot(), or getSessionStats()
|
||||
const entries = await storage.getEntries()
|
||||
expect(entries).toHaveLength(1)
|
||||
expect(entries[0].type).toBe('custom_message')
|
||||
|
||||
const path = await storage.getPathToRoot('legacy-corrupted-entry')
|
||||
expect(path).toHaveLength(1)
|
||||
expect(path[0].type).toBe('custom_message')
|
||||
|
||||
const stats = await storage.getSessionStats()
|
||||
expect(stats.messageCount).toBe(1)
|
||||
})
|
||||
|
||||
it('should dynamically inject thread metadata into details.thread in getPathToRoot when replies exist', async () => {
|
||||
const { agent, user } = await setupTestData()
|
||||
const project = await prisma.project.create({
|
||||
data: { name: 'Test Project', teamId: agent.teamId },
|
||||
})
|
||||
const asset = await prisma.asset.create({
|
||||
data: {
|
||||
name: 'Test Asset',
|
||||
type: 'file',
|
||||
status: 'uploaded',
|
||||
projectId: project.id,
|
||||
},
|
||||
})
|
||||
const storage = await DatabaseSessionStorage.create({ agentId: agent.id, assetId: asset.id })
|
||||
|
||||
const rootComment = await prisma.assetComment.create({
|
||||
data: {
|
||||
id: 'comment-root-1',
|
||||
assetId: asset.id,
|
||||
message: 'Top-level question',
|
||||
creatorId: user.id,
|
||||
},
|
||||
})
|
||||
|
||||
// Add a reply
|
||||
await prisma.assetComment.create({
|
||||
data: {
|
||||
id: 'comment-reply-1',
|
||||
assetId: asset.id,
|
||||
message: 'Reply 1',
|
||||
creatorId: user.id,
|
||||
replyToId: rootComment.id,
|
||||
},
|
||||
})
|
||||
|
||||
// Create session entry for root comment
|
||||
await prisma.agentSessionEntry.create({
|
||||
data: {
|
||||
id: rootComment.id,
|
||||
sessionId: storage.sessionId,
|
||||
assetId: asset.id,
|
||||
type: 'custom_message',
|
||||
data: {
|
||||
customType: 'shumai_message',
|
||||
content: 'Top-level question',
|
||||
display: true,
|
||||
details: { user: { id: user.id, name: user.name } },
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
const path = await storage.getPathToRoot(rootComment.id)
|
||||
expect(path).toHaveLength(1)
|
||||
expect(path[0].type).toBe('custom_message')
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const details = (path[0] as any).details
|
||||
expect(details.thread).toEqual({
|
||||
id: rootComment.id,
|
||||
replyCount: 1,
|
||||
})
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
expect((path[0] as any).content).toBe('Top-level question')
|
||||
|
||||
const entries = await storage.getEntries()
|
||||
expect(entries).toHaveLength(1)
|
||||
expect(entries[0].type).toBe('custom_message')
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
expect((entries[0] as any).details?.thread).toEqual({
|
||||
id: rootComment.id,
|
||||
replyCount: 1,
|
||||
})
|
||||
})
|
||||
})
|
||||
})
|
||||
|
||||
@@ -8,6 +8,7 @@ import {
|
||||
type SessionTreeEntry,
|
||||
} from '@earendil-works/pi-agent-core'
|
||||
import { agentService } from '@shumai/core/src/agent/agent'
|
||||
import type { ShumaiMessageContext } from '@shumai/dtos'
|
||||
|
||||
export interface DatabaseSessionMetadata extends SessionMetadata {
|
||||
agentId: string
|
||||
@@ -72,6 +73,7 @@ export class DatabaseSessionStorage implements SessionStorage<DatabaseSessionMet
|
||||
}
|
||||
|
||||
nextEntryId?: string | null
|
||||
currentMessageContext?: PrismaJson.ShumaiMessageContext
|
||||
|
||||
async createEntryId(): Promise<string> {
|
||||
if (this.nextEntryId) {
|
||||
@@ -90,9 +92,13 @@ export class DatabaseSessionStorage implements SessionStorage<DatabaseSessionMet
|
||||
data: unknown
|
||||
}): SessionTreeEntry {
|
||||
const payload = (record.data as Record<string, unknown>) || {}
|
||||
let type = (record.type || 'message') as SessionTreeEntry['type']
|
||||
if (type === 'message' && payload.customType === 'shumai_message') {
|
||||
type = 'custom_message'
|
||||
}
|
||||
return {
|
||||
id: record.id,
|
||||
type: (record.type || 'message') as SessionTreeEntry['type'],
|
||||
type,
|
||||
parentId: record.parentId,
|
||||
timestamp: record.createdAt.toISOString(),
|
||||
...payload,
|
||||
@@ -100,10 +106,44 @@ export class DatabaseSessionStorage implements SessionStorage<DatabaseSessionMet
|
||||
}
|
||||
|
||||
async appendEntry(entry: SessionTreeEntry): Promise<void> {
|
||||
const strippedEntry = structuredClone(entry)
|
||||
let entryToProcess = entry
|
||||
if (
|
||||
entryToProcess.type === 'message' &&
|
||||
entryToProcess.message &&
|
||||
entryToProcess.message.role === 'user' &&
|
||||
this.currentMessageContext
|
||||
) {
|
||||
let contentText = ''
|
||||
if (typeof entryToProcess.message.content === 'string') {
|
||||
contentText = entryToProcess.message.content
|
||||
} else if (Array.isArray(entryToProcess.message.content)) {
|
||||
contentText = entryToProcess.message.content
|
||||
.map((c) =>
|
||||
typeof c === 'object' && c && 'text' in c && typeof c.text === 'string' ? c.text : '',
|
||||
)
|
||||
.join('')
|
||||
}
|
||||
|
||||
entryToProcess = {
|
||||
type: 'custom_message',
|
||||
id: entryToProcess.id,
|
||||
parentId: entryToProcess.parentId,
|
||||
timestamp: entryToProcess.timestamp,
|
||||
customType: 'shumai_message',
|
||||
content: contentText,
|
||||
display: true,
|
||||
details: {
|
||||
...this.currentMessageContext,
|
||||
id: entryToProcess.id,
|
||||
},
|
||||
} as unknown as SessionTreeEntry
|
||||
this.currentMessageContext = undefined
|
||||
}
|
||||
|
||||
const strippedEntry = structuredClone(entryToProcess)
|
||||
|
||||
// Strip image data and skill content before saving to DB
|
||||
if (strippedEntry.type === 'message') {
|
||||
if (strippedEntry.type === 'message' && strippedEntry.message) {
|
||||
const msg = strippedEntry.message
|
||||
if (msg.role === 'toolResult') {
|
||||
const details = msg.details as { sourceKeys?: string[]; skillId?: string } | undefined
|
||||
@@ -139,7 +179,10 @@ export class DatabaseSessionStorage implements SessionStorage<DatabaseSessionMet
|
||||
}
|
||||
}
|
||||
|
||||
const targetLeafId = entry.type === 'leaf' ? entry.targetId : entry.id
|
||||
const targetLeafId =
|
||||
strippedEntry.type === 'leaf'
|
||||
? (strippedEntry as unknown as { targetId?: string }).targetId || strippedEntry.id
|
||||
: strippedEntry.id
|
||||
|
||||
// Extract base fields and store type-specific properties in data payload
|
||||
const payload = { ...strippedEntry } as Record<string, unknown>
|
||||
@@ -155,17 +198,18 @@ export class DatabaseSessionStorage implements SessionStorage<DatabaseSessionMet
|
||||
|
||||
await prisma.$transaction([
|
||||
prisma.agentSessionEntry.upsert({
|
||||
where: { id: entry.id },
|
||||
where: { id: strippedEntry.id },
|
||||
create: {
|
||||
id: entry.id,
|
||||
id: strippedEntry.id,
|
||||
sessionId: this.sessionId,
|
||||
assetId: session?.assetId || null,
|
||||
type: entry.type,
|
||||
parentId: entry.parentId || null,
|
||||
createdAt: entry.timestamp ? new Date(entry.timestamp) : new Date(),
|
||||
type: strippedEntry.type,
|
||||
parentId: strippedEntry.parentId || null,
|
||||
createdAt: strippedEntry.timestamp ? new Date(strippedEntry.timestamp) : new Date(),
|
||||
data: payload as PrismaJson.PiSessionEntryData,
|
||||
},
|
||||
update: {
|
||||
type: strippedEntry.type,
|
||||
data: payload as PrismaJson.PiSessionEntryData,
|
||||
},
|
||||
}),
|
||||
@@ -236,7 +280,9 @@ export class DatabaseSessionStorage implements SessionStorage<DatabaseSessionMet
|
||||
let costTotal = 0
|
||||
|
||||
for (const entry of entries) {
|
||||
if (entry.type === 'message') {
|
||||
if (entry.type === 'custom_message' && entry.customType === 'shumai_message') {
|
||||
messageCount++
|
||||
} else if (entry.type === 'message' && entry.message) {
|
||||
const msg = entry.message
|
||||
if (msg.role === 'user' || msg.role === 'assistant') {
|
||||
messageCount++
|
||||
@@ -324,48 +370,7 @@ export class DatabaseSessionStorage implements SessionStorage<DatabaseSessionMet
|
||||
await this.reinjectSkillContentAsync(entry)
|
||||
}
|
||||
|
||||
// Dynamically tag comments that currently have reply threads
|
||||
const entryIds = pathEntries.map((e) => e.id)
|
||||
if (entryIds.length > 0) {
|
||||
const threadCounts = await prisma.assetComment.groupBy({
|
||||
by: ['replyToId'],
|
||||
where: {
|
||||
replyToId: { in: entryIds },
|
||||
message: { not: '__CHAT__' },
|
||||
},
|
||||
_count: {
|
||||
id: true,
|
||||
},
|
||||
})
|
||||
const threadReplyCountMap = new Map<string, number>()
|
||||
for (const tc of threadCounts) {
|
||||
if (tc.replyToId) {
|
||||
threadReplyCountMap.set(tc.replyToId, tc._count.id)
|
||||
}
|
||||
}
|
||||
|
||||
if (threadReplyCountMap.size > 0) {
|
||||
for (let i = 0; i < pathEntries.length; i++) {
|
||||
const entry = pathEntries[i]
|
||||
const count = threadReplyCountMap.get(entry.id)
|
||||
if (count !== undefined && count > 0 && entry.type === 'message') {
|
||||
const cloned = structuredClone(entry)
|
||||
const msg = cloned.message as unknown as {
|
||||
content?: Array<{ type: string; text: string }>
|
||||
}
|
||||
if (Array.isArray(msg.content) && msg.content[0] && msg.content[0].type === 'text') {
|
||||
const threadTag = `[Thread ID: ${entry.id}] [Replies: ${count}]`
|
||||
if (!msg.content[0].text.includes(`[Thread ID: ${entry.id}]`)) {
|
||||
msg.content[0].text = `${threadTag} ${msg.content[0].text}`
|
||||
}
|
||||
}
|
||||
pathEntries[i] = cloned
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return pathEntries
|
||||
return this.injectThreadMetadataAsync(pathEntries)
|
||||
}
|
||||
|
||||
async getEntries(): Promise<SessionTreeEntry[]> {
|
||||
@@ -378,11 +383,61 @@ export class DatabaseSessionStorage implements SessionStorage<DatabaseSessionMet
|
||||
await this.reinjectImageDataAsync(entry)
|
||||
await this.reinjectSkillContentAsync(entry)
|
||||
}
|
||||
return this.injectThreadMetadataAsync(entries)
|
||||
}
|
||||
|
||||
private async injectThreadMetadataAsync(
|
||||
entries: SessionTreeEntry[],
|
||||
): Promise<SessionTreeEntry[]> {
|
||||
const entryIds = entries.map((e) => e.id)
|
||||
if (entryIds.length === 0) {
|
||||
return entries
|
||||
}
|
||||
|
||||
const threadCounts = await prisma.assetComment.groupBy({
|
||||
by: ['replyToId'],
|
||||
where: {
|
||||
replyToId: { in: entryIds },
|
||||
message: { not: '__CHAT__' },
|
||||
},
|
||||
_count: {
|
||||
id: true,
|
||||
},
|
||||
})
|
||||
const threadReplyCountMap = new Map<string, number>()
|
||||
for (const tc of threadCounts) {
|
||||
if (tc.replyToId) {
|
||||
threadReplyCountMap.set(tc.replyToId, tc._count.id)
|
||||
}
|
||||
}
|
||||
|
||||
if (threadReplyCountMap.size > 0) {
|
||||
for (let i = 0; i < entries.length; i++) {
|
||||
const entry = entries[i]
|
||||
const count = threadReplyCountMap.get(entry.id)
|
||||
if (count !== undefined && count > 0) {
|
||||
if (entry.type === 'custom_message') {
|
||||
const cloned = structuredClone(entry)
|
||||
const existingDetails = ((cloned as unknown as { details?: ShumaiMessageContext })
|
||||
.details || {}) as ShumaiMessageContext
|
||||
;(cloned as unknown as { details: ShumaiMessageContext }).details = {
|
||||
...existingDetails,
|
||||
thread: {
|
||||
id: entry.id,
|
||||
replyCount: count,
|
||||
},
|
||||
}
|
||||
entries[i] = cloned
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return entries
|
||||
}
|
||||
|
||||
private async reinjectImageDataAsync(entry: SessionTreeEntry) {
|
||||
if (entry.type === 'message') {
|
||||
if (entry.type === 'message' && entry.message) {
|
||||
const msg = entry.message as AgentMessage
|
||||
if (msg.role === 'toolResult') {
|
||||
const details = msg.details as { sourceKeys?: string[] } | undefined
|
||||
@@ -407,7 +462,7 @@ export class DatabaseSessionStorage implements SessionStorage<DatabaseSessionMet
|
||||
}
|
||||
|
||||
private async reinjectSkillContentAsync(entry: SessionTreeEntry) {
|
||||
if (entry.type === 'message') {
|
||||
if (entry.type === 'message' && entry.message) {
|
||||
const msg = entry.message as AgentMessage
|
||||
if (msg.role === 'toolResult' && msg.toolName === 'read_skill') {
|
||||
const details = msg.details as { skillId?: string } | undefined
|
||||
|
||||
@@ -8,8 +8,11 @@ import {
|
||||
} from './index'
|
||||
import { createSandboxedBashTool } from './tools/sandboxed-bash'
|
||||
import { SandboxManager, type SandboxAskCallback } from '@anthropic-ai/sandbox-runtime'
|
||||
import { quotaService } from '@shumai/core/src/quota/quota-service'
|
||||
import { prisma } from '@shumai/db'
|
||||
import { setupTestDbHooks } from '@shumai/db/test'
|
||||
import { type TSchema } from 'typebox'
|
||||
import { Value } from 'typebox/value'
|
||||
import * as path from 'path'
|
||||
import * as childProcess from 'node:child_process'
|
||||
import * as fs from 'fs'
|
||||
@@ -89,10 +92,16 @@ describe('Sandbox Network isolation integration', () => {
|
||||
setupTestDbHooks()
|
||||
|
||||
it('should register callback that pushes blocked hosts to database and propagates to bash tool', async () => {
|
||||
// 1. Create a team
|
||||
// 1. Create a team and enabled sandbox
|
||||
const team = await prisma.team.create({
|
||||
data: { name: 'Test Sandbox Team' },
|
||||
})
|
||||
await prisma.sandbox.create({
|
||||
data: {
|
||||
teamId: team.id,
|
||||
networkSandboxEnabled: true,
|
||||
},
|
||||
})
|
||||
|
||||
// Ensure agent user and agent exist in database to avoid foreign key violation
|
||||
await prisma.user.create({
|
||||
@@ -198,6 +207,12 @@ describe('Sandbox Network isolation integration', () => {
|
||||
const team2 = await prisma.team.create({
|
||||
data: { name: 'Team 2' },
|
||||
})
|
||||
await prisma.sandbox.create({
|
||||
data: { teamId: team1.id, networkSandboxEnabled: true },
|
||||
})
|
||||
await prisma.sandbox.create({
|
||||
data: { teamId: team2.id, networkSandboxEnabled: true },
|
||||
})
|
||||
|
||||
// Ensure agent user and agents exist in database
|
||||
await prisma.user.create({
|
||||
@@ -290,6 +305,64 @@ describe('Sandbox Network isolation integration', () => {
|
||||
}
|
||||
})
|
||||
|
||||
it('should bypass domain blocking and pending domain recording when networkSandboxEnabled is false', async () => {
|
||||
const team = await prisma.team.create({
|
||||
data: { name: 'Disabled Sandbox Team' },
|
||||
})
|
||||
await prisma.sandbox.create({
|
||||
data: { teamId: team.id, networkSandboxEnabled: false },
|
||||
})
|
||||
|
||||
await prisma.user.create({
|
||||
data: {
|
||||
id: 'agent-disabled',
|
||||
name: 'Ai Agent Disabled',
|
||||
email: 'disabled@shumai.ai',
|
||||
type: 'agent',
|
||||
},
|
||||
})
|
||||
await prisma.agent.create({
|
||||
data: {
|
||||
id: 'agent-disabled',
|
||||
teamId: team.id,
|
||||
type: 'chat',
|
||||
config: { provider: 'openai', model: 'gpt-4' },
|
||||
},
|
||||
})
|
||||
|
||||
const initializeSpy = vi.spyOn(SandboxManager, 'initialize').mockResolvedValue()
|
||||
vi.spyOn(SandboxManager, 'wrapWithSandbox').mockImplementation(async (cmd) => cmd)
|
||||
|
||||
await createAgentSession({
|
||||
teamId: team.id,
|
||||
agentId: 'agent-disabled',
|
||||
providerName: 'google',
|
||||
modelId: 'gemini',
|
||||
systemPrompt: 'prompt',
|
||||
teamSkills: [],
|
||||
allowedDomains: ['*'],
|
||||
providers: mockProviders,
|
||||
})
|
||||
|
||||
expect(initializeSpy).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
network: expect.objectContaining({
|
||||
allowedDomains: ['*'],
|
||||
}),
|
||||
}),
|
||||
expect.any(Function),
|
||||
)
|
||||
|
||||
const callback = initializeSpy.mock.calls[0][1]
|
||||
const res = await callback!({ host: 'any-external-domain.com', port: 443 })
|
||||
expect(res).toBe(true)
|
||||
|
||||
const sandbox = await prisma.sandbox.findUnique({
|
||||
where: { teamId: team.id },
|
||||
})
|
||||
expect(sandbox?.pendingDomains).toEqual([])
|
||||
})
|
||||
|
||||
it('should pass thinkingLevel to AgentHarness and default to off', async () => {
|
||||
const team = await prisma.team.create({
|
||||
data: { name: 'Test Team' },
|
||||
@@ -813,3 +886,402 @@ describe('createAgentSession bash restriction for non-owner users', () => {
|
||||
expect(prompt).not.toContain('# Restricted User Context')
|
||||
})
|
||||
})
|
||||
|
||||
describe('createAgentSession typed metadata schema', () => {
|
||||
setupTestDbHooks()
|
||||
|
||||
afterEach(() => {
|
||||
vi.restoreAllMocks()
|
||||
})
|
||||
|
||||
async function setupSessionWithProject(opts: { withCreationFields: boolean }) {
|
||||
const team = await prisma.team.create({ data: { name: 'Typed Metadata Team' } })
|
||||
const project = await prisma.project.create({
|
||||
data: { name: 'Typed Metadata Project', teamId: team.id },
|
||||
})
|
||||
const user = await prisma.user.create({
|
||||
data: { name: 'Typed Metadata User', email: 'typed-metadata@shumai.ai' },
|
||||
})
|
||||
await prisma.teamMember.create({
|
||||
data: { teamId: team.id, userId: user.id, role: 'owner' },
|
||||
})
|
||||
await prisma.user.create({
|
||||
data: {
|
||||
id: 'typed-metadata-agent',
|
||||
name: 'Ai Agent Typed Metadata',
|
||||
email: 'typed-metadata-agent@shumai.ai',
|
||||
type: 'agent',
|
||||
},
|
||||
})
|
||||
await prisma.agent.create({
|
||||
data: {
|
||||
id: 'typed-metadata-agent',
|
||||
teamId: team.id,
|
||||
type: 'chat',
|
||||
config: { provider: 'google', model: 'gemini' },
|
||||
},
|
||||
})
|
||||
|
||||
if (opts.withCreationFields) {
|
||||
await prisma.metadataField.create({
|
||||
data: {
|
||||
key: 'prompt',
|
||||
scope: 'PROJECT',
|
||||
projectId: project.id,
|
||||
teamId: team.id,
|
||||
config: { name: 'Prompt', type: 'text', autofillSource: 'CREATION_CONTEXT' },
|
||||
},
|
||||
})
|
||||
await prisma.metadataField.create({
|
||||
data: {
|
||||
key: 'source',
|
||||
scope: 'PROJECT',
|
||||
projectId: project.id,
|
||||
teamId: team.id,
|
||||
config: {
|
||||
name: 'Source',
|
||||
type: 'select',
|
||||
autofillSource: 'CREATION_CONTEXT',
|
||||
select: {
|
||||
options: [{ id: 'gemini', displayName: 'Gemini', color: '#ffffff' }],
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
await prisma.metadataField.create({
|
||||
data: {
|
||||
key: 'manualNotes',
|
||||
scope: 'PROJECT',
|
||||
projectId: project.id,
|
||||
teamId: team.id,
|
||||
config: { name: 'Manual Notes', type: 'text', autofillSource: 'NONE' },
|
||||
},
|
||||
})
|
||||
}
|
||||
|
||||
const initializeSpy = vi.spyOn(SandboxManager, 'initialize').mockResolvedValue()
|
||||
try {
|
||||
const { harness } = await createAgentSession({
|
||||
teamId: team.id,
|
||||
agentId: 'typed-metadata-agent',
|
||||
providerName: 'google',
|
||||
modelId: 'gemini',
|
||||
systemPrompt: 'prompt',
|
||||
teamSkills: [],
|
||||
allowedDomains: [],
|
||||
providers: mockProviders,
|
||||
userId: user.id,
|
||||
projectId: project.id,
|
||||
})
|
||||
return { harness }
|
||||
} finally {
|
||||
initializeSpy.mockRestore()
|
||||
}
|
||||
}
|
||||
|
||||
it('should build create_file/create_version with the project CREATION_CONTEXT fields', async () => {
|
||||
const { harness } = await setupSessionWithProject({ withCreationFields: true })
|
||||
const tools = harness.getTools()
|
||||
|
||||
expect(tools.some((t) => t.name === 'list_autofill_fields')).toBe(false)
|
||||
|
||||
const createFile = tools.find((t) => t.name === 'create_file')
|
||||
const createVersion = tools.find((t) => t.name === 'create_version')
|
||||
expect(createFile).toBeDefined()
|
||||
expect(createVersion).toBeDefined()
|
||||
|
||||
const checkFile = (args: Record<string, unknown>) =>
|
||||
Value.Check(createFile!.parameters as unknown as TSchema, {
|
||||
parent: 'f1',
|
||||
path: '/tmp/x.md',
|
||||
data: null,
|
||||
...args,
|
||||
})
|
||||
const checkVersion = (args: Record<string, unknown>) =>
|
||||
Value.Check(createVersion!.parameters as unknown as TSchema, {
|
||||
parent: 'f1',
|
||||
path: '/tmp/x.md',
|
||||
...args,
|
||||
})
|
||||
|
||||
for (const check of [checkFile, checkVersion]) {
|
||||
// Declared CREATION_CONTEXT fields (all-required, nullable) validate; other keys do not
|
||||
expect(check({ metadata: { prompt: 'hello', source: null } })).toBe(true)
|
||||
expect(check({ metadata: { prompt: null, source: 'gemini' } })).toBe(true)
|
||||
expect(check({ metadata: null })).toBe(true)
|
||||
expect(check({ metadata: { prompt: null, source: null, manualNotes: 'no' } })).toBe(false)
|
||||
expect(check({ metadata: { prompt: null, source: null, bogus: 1 } })).toBe(false)
|
||||
expect(check({ metadata: { prompt: 'hello' } })).toBe(false)
|
||||
}
|
||||
})
|
||||
|
||||
it('should omit the metadata parameter when the project has no CREATION_CONTEXT fields', async () => {
|
||||
const { harness } = await setupSessionWithProject({ withCreationFields: false })
|
||||
const createFile = harness.getTools().find((t) => t.name === 'create_file')
|
||||
const createVersion = harness.getTools().find((t) => t.name === 'create_version')
|
||||
expect(createFile).toBeDefined()
|
||||
expect(createVersion).toBeDefined()
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any -- inspecting the runtime schema shape of the dynamically-built tool
|
||||
const fileProps = (createFile!.parameters as any).properties
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any -- inspecting the runtime schema shape of the dynamically-built tool
|
||||
const versionProps = (createVersion!.parameters as any).properties
|
||||
expect('metadata' in fileProps).toBe(false)
|
||||
expect('metadata' in versionProps).toBe(false)
|
||||
})
|
||||
})
|
||||
|
||||
describe('createAgentSession enabled skill filtering', () => {
|
||||
setupTestDbHooks()
|
||||
|
||||
afterEach(() => {
|
||||
vi.restoreAllMocks()
|
||||
})
|
||||
|
||||
it('should only advertise and allow reading skills enabled for the agent', async () => {
|
||||
const team = await prisma.team.create({ data: { name: 'Skill Filter Team' } })
|
||||
|
||||
const enabledSkill = await prisma.skill.create({
|
||||
data: {
|
||||
name: 'Enabled Skill',
|
||||
assetId: 'asset-enabled',
|
||||
hash: 'enabled-hash',
|
||||
teamId: team.id,
|
||||
},
|
||||
})
|
||||
const disabledSkill = await prisma.skill.create({
|
||||
data: {
|
||||
name: 'Disabled Skill',
|
||||
assetId: 'asset-disabled',
|
||||
hash: 'disabled-hash',
|
||||
teamId: team.id,
|
||||
},
|
||||
})
|
||||
|
||||
await prisma.user.create({
|
||||
data: {
|
||||
id: 'skill-filter-agent',
|
||||
name: 'Ai Agent Skill Filter',
|
||||
email: 'skill-filter-agent@shumai.ai',
|
||||
type: 'agent',
|
||||
},
|
||||
})
|
||||
await prisma.agent.create({
|
||||
data: {
|
||||
id: 'skill-filter-agent',
|
||||
teamId: team.id,
|
||||
type: 'chat',
|
||||
config: { provider: 'google', model: 'gemini' },
|
||||
skills: {
|
||||
create: [{ skillId: enabledSkill.id }],
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
const initializeSpy = vi.spyOn(SandboxManager, 'initialize').mockResolvedValue()
|
||||
try {
|
||||
const { harness } = await createAgentSession({
|
||||
teamId: team.id,
|
||||
agentId: 'skill-filter-agent',
|
||||
providerName: 'google',
|
||||
modelId: 'gemini',
|
||||
systemPrompt: 'prompt',
|
||||
teamSkills: [{ id: enabledSkill.id, name: enabledSkill.name }],
|
||||
enabledSkillIds: [enabledSkill.id],
|
||||
allowedDomains: [],
|
||||
providers: mockProviders,
|
||||
})
|
||||
|
||||
// The disabled skill must not be advertised in the available skills list
|
||||
// @ts-expect-error accessing private property for verification
|
||||
const prompt = await harness.systemPrompt()
|
||||
expect(prompt).toContain(enabledSkill.id)
|
||||
expect(prompt).not.toContain(disabledSkill.id)
|
||||
|
||||
// read_skill must reject the disabled skill id
|
||||
const readSkillTool = harness.getTools().find((t) => t.name === 'read_skill')
|
||||
expect(readSkillTool).toBeDefined()
|
||||
|
||||
vi.spyOn(fs, 'existsSync').mockReturnValue(true)
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any -- mocking node fs readFileSync which has complex overloaded signatures
|
||||
vi.spyOn(fs, 'readFileSync').mockImplementation((p: any) => {
|
||||
if (p.toString().endsWith('.hash')) return 'enabled-hash'
|
||||
if (p.toString().endsWith('SKILL.md')) return '# Enabled Skill'
|
||||
return ''
|
||||
})
|
||||
|
||||
await expect(
|
||||
readSkillTool!.execute('1', { skillId: disabledSkill.id }, undefined, undefined, undefined),
|
||||
).rejects.toThrow('not enabled for this agent')
|
||||
|
||||
const result = await readSkillTool!.execute(
|
||||
'1',
|
||||
{ skillId: enabledSkill.id },
|
||||
undefined,
|
||||
undefined,
|
||||
undefined,
|
||||
)
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
expect((result.content[0] as any).text).toBe('# Enabled Skill')
|
||||
} finally {
|
||||
initializeSpy.mockRestore()
|
||||
}
|
||||
})
|
||||
|
||||
it('should reject all read_skill calls when no skills are enabled for the agent', async () => {
|
||||
const team = await prisma.team.create({ data: { name: 'Skill None Team' } })
|
||||
const skill = await prisma.skill.create({
|
||||
data: { name: 'Unassigned Skill', assetId: 'asset-none', hash: 'none-hash', teamId: team.id },
|
||||
})
|
||||
|
||||
await prisma.user.create({
|
||||
data: {
|
||||
id: 'skill-none-agent',
|
||||
name: 'Ai Agent Skill None',
|
||||
email: 'skill-none-agent@shumai.ai',
|
||||
type: 'agent',
|
||||
},
|
||||
})
|
||||
await prisma.agent.create({
|
||||
data: {
|
||||
id: 'skill-none-agent',
|
||||
teamId: team.id,
|
||||
type: 'chat',
|
||||
config: { provider: 'google', model: 'gemini' },
|
||||
},
|
||||
})
|
||||
|
||||
const initializeSpy = vi.spyOn(SandboxManager, 'initialize').mockResolvedValue()
|
||||
try {
|
||||
const { harness } = await createAgentSession({
|
||||
teamId: team.id,
|
||||
agentId: 'skill-none-agent',
|
||||
providerName: 'google',
|
||||
modelId: 'gemini',
|
||||
systemPrompt: 'prompt',
|
||||
teamSkills: [],
|
||||
enabledSkillIds: [],
|
||||
allowedDomains: [],
|
||||
providers: mockProviders,
|
||||
})
|
||||
|
||||
const readSkillTool = harness.getTools().find((t) => t.name === 'read_skill')
|
||||
expect(readSkillTool).toBeDefined()
|
||||
|
||||
await expect(
|
||||
readSkillTool!.execute('1', { skillId: skill.id }, undefined, undefined, undefined),
|
||||
).rejects.toThrow('not enabled for this agent')
|
||||
} finally {
|
||||
initializeSpy.mockRestore()
|
||||
}
|
||||
})
|
||||
|
||||
it('enforces agent tool call count quota on tool execution', async () => {
|
||||
const team = await prisma.team.create({ data: { name: 'Tool Quota Enforcement Team' } })
|
||||
const user = await prisma.user.create({
|
||||
data: { name: 'Member User', email: 'member-tool-quota@shumai.ai', password: 'pw' },
|
||||
})
|
||||
await prisma.teamMember.create({
|
||||
data: { teamId: team.id, userId: user.id, role: 'editor' },
|
||||
})
|
||||
await prisma.user.create({
|
||||
data: {
|
||||
id: 'tool-quota-agent',
|
||||
name: 'Tool Quota Agent',
|
||||
email: 'tool-quota-agent@shumai.ai',
|
||||
type: 'agent',
|
||||
},
|
||||
})
|
||||
await prisma.agent.create({
|
||||
data: {
|
||||
id: 'tool-quota-agent',
|
||||
teamId: team.id,
|
||||
type: 'chat',
|
||||
config: { provider: 'google', model: 'gemini' },
|
||||
},
|
||||
})
|
||||
|
||||
await quotaService.createRule(team.id, {
|
||||
scopeMode: 'all_members',
|
||||
resource: 'agent_tool_call_count',
|
||||
resourceData: { name: 'read_thread' },
|
||||
limit: 1,
|
||||
period: '1hour',
|
||||
enabled: true,
|
||||
})
|
||||
|
||||
const initializeSpy = vi.spyOn(SandboxManager, 'initialize').mockResolvedValue()
|
||||
try {
|
||||
const { harness } = await createAgentSession({
|
||||
teamId: team.id,
|
||||
userId: user.id,
|
||||
agentId: 'tool-quota-agent',
|
||||
providerName: 'google',
|
||||
modelId: 'gemini',
|
||||
systemPrompt: 'prompt',
|
||||
teamSkills: [],
|
||||
enabledSkillIds: [],
|
||||
allowedDomains: [],
|
||||
providers: mockProviders,
|
||||
})
|
||||
|
||||
const readThreadTool = harness.getTools().find((t) => t.name === 'read_thread')
|
||||
expect(readThreadTool).toBeDefined()
|
||||
|
||||
// First call executes and consumes quota
|
||||
const res1 = await readThreadTool!.execute(
|
||||
'call-1',
|
||||
{ threadId: 'non-existent' },
|
||||
undefined,
|
||||
undefined,
|
||||
undefined,
|
||||
)
|
||||
expect(res1).toBeDefined()
|
||||
|
||||
// Second call exceeds quota and returns error
|
||||
const res2 = await readThreadTool!.execute(
|
||||
'call-2',
|
||||
{ threadId: 'non-existent' },
|
||||
undefined,
|
||||
undefined,
|
||||
undefined,
|
||||
)
|
||||
expect(res2).toBeDefined()
|
||||
const textContent = res2.content[0]
|
||||
if (textContent && textContent.type === 'text') {
|
||||
expect(textContent.text).toContain('Quota exceeded')
|
||||
} else {
|
||||
expect.unreachable('Expected text content')
|
||||
}
|
||||
} finally {
|
||||
initializeSpy.mockRestore()
|
||||
}
|
||||
})
|
||||
})
|
||||
|
||||
describe('getModelFromDb', () => {
|
||||
it('should prioritize provider active api protocol over model config api', () => {
|
||||
const providers: DbProviderInfo[] = [
|
||||
{
|
||||
name: 'custom-provider',
|
||||
config: { api: 'anthropic-messages', apiKey: 'KEY' },
|
||||
models: [
|
||||
{
|
||||
modelId: 'my-model',
|
||||
name: 'My Model',
|
||||
config: {
|
||||
api: 'openai-responses', // stale model config
|
||||
reasoning: false,
|
||||
input: ['text'],
|
||||
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
|
||||
contextWindow: 128000,
|
||||
maxTokens: 4096,
|
||||
},
|
||||
},
|
||||
],
|
||||
},
|
||||
]
|
||||
|
||||
const model = getModelFromDb(providers, 'custom-provider', 'my-model')
|
||||
expect(model.api).toBe('anthropic-messages')
|
||||
})
|
||||
})
|
||||
|
||||
+192
-68
@@ -9,24 +9,27 @@ import type { Api, Model } from '@earendil-works/pi-ai'
|
||||
import { createModels, InMemoryCredentialStore } from '@earendil-works/pi-ai'
|
||||
import { builtinProviders } from '@earendil-works/pi-ai/providers/all'
|
||||
import { agentService } from '@shumai/core/src/agent/agent'
|
||||
import { prisma, type TeamMemberRole } from '@shumai/db'
|
||||
import { Type, type TSchema } from '@sinclair/typebox'
|
||||
import { resolveEffectiveRole } from '@shumai/core/src/authz/authz'
|
||||
import { quotaService, QuotaExceededError } from '@shumai/core/src/quota/quota-service'
|
||||
import { logger } from '@shumai/core/src/logger'
|
||||
import { prisma } from '@shumai/db'
|
||||
import { Type, type TSchema } from 'typebox'
|
||||
import * as fs from 'fs'
|
||||
import * as os from 'os'
|
||||
import * as path from 'path'
|
||||
import { DatabaseSessionStorage } from './database-session-storage'
|
||||
import { createAnalyzeImageTool } from './tools/analyze-image'
|
||||
import { metadataService } from '@shumai/core/src/metadata/metadata'
|
||||
import { createCreateFileTool } from './tools/create-file'
|
||||
import { createListAutofillFieldsTool } from './tools/list-autofill-fields'
|
||||
import { createCreateFolderTool } from './tools/create-folder'
|
||||
import { createCreateVersionTool } from './tools/create-version'
|
||||
import { createDownloadAssetTool } from './tools/download-asset'
|
||||
import { createListAssetsTool } from './tools/list-assets'
|
||||
import { createReadPdfPagesTool } from './tools/read-pdf-pages'
|
||||
import { createReadAssetTool } from './tools/read-asset'
|
||||
import { createReadSkillTool } from './tools/read-skill'
|
||||
import { createReadThreadTool } from './tools/read-thread'
|
||||
import { createSandboxedBashTool } from './tools/sandboxed-bash'
|
||||
import { createScreenshotTool } from './tools/screenshot'
|
||||
import { serializeContextToXml } from './context/serialize-context'
|
||||
import type { ShumaiMessageContext } from '@shumai/dtos'
|
||||
|
||||
export interface DbModelInfo {
|
||||
modelId: string
|
||||
@@ -67,10 +70,10 @@ export function getModelFromDb(providers: DbProviderInfo[], providerName: string
|
||||
if (dbProvider.config.baseUrl) {
|
||||
m.baseUrl = dbProvider.config.baseUrl
|
||||
}
|
||||
Object.assign(m, dbModel.config)
|
||||
if (dbProvider.config.api) {
|
||||
m.api = dbProvider.config.api
|
||||
}
|
||||
Object.assign(m, dbModel.config)
|
||||
if (dbModel.name) {
|
||||
m.name = dbModel.name
|
||||
}
|
||||
@@ -98,9 +101,11 @@ export interface CreateAgentSessionParams {
|
||||
modelId: string
|
||||
systemPrompt: string
|
||||
teamSkills: Array<{ id: string; name: string; description?: string | null }>
|
||||
enabledSkillIds?: string[]
|
||||
allowedDomains: string[]
|
||||
sessionId?: string
|
||||
userId?: string
|
||||
projectId?: string
|
||||
userCommentId?: string | null
|
||||
customTools?: AgentTool[]
|
||||
thinkingLevel?: string
|
||||
@@ -110,18 +115,6 @@ export interface CreateAgentSessionParams {
|
||||
baseDelayMs?: number
|
||||
}
|
||||
|
||||
async function resolveTeamMemberRole(
|
||||
teamId: string,
|
||||
userId?: string,
|
||||
): Promise<TeamMemberRole | undefined> {
|
||||
if (!userId) return undefined
|
||||
const member = await prisma.teamMember.findUnique({
|
||||
where: { teamIdUserId: { teamId, userId } },
|
||||
select: { role: true },
|
||||
})
|
||||
return member?.role
|
||||
}
|
||||
|
||||
/**
|
||||
* Security instructions appended to the system prompt when the requesting user is not a team
|
||||
* owner (i.e. editor/reviewer). These complement the hard enforcement in the bash tool itself
|
||||
@@ -145,9 +138,11 @@ export async function createAgentSession(params: CreateAgentSessionParams) {
|
||||
modelId,
|
||||
systemPrompt,
|
||||
teamSkills,
|
||||
enabledSkillIds,
|
||||
allowedDomains,
|
||||
sessionId,
|
||||
userId,
|
||||
projectId,
|
||||
userCommentId: passedUserCommentId,
|
||||
customTools = [],
|
||||
thinkingLevel,
|
||||
@@ -181,11 +176,17 @@ export async function createAgentSession(params: CreateAgentSessionParams) {
|
||||
blockedHost: '',
|
||||
}
|
||||
|
||||
const role = userId ? await resolveEffectiveRole(teamId, projectId, userId) : undefined
|
||||
const isOwner = !userId || role === 'owner'
|
||||
const restricted = !isOwner
|
||||
const sandboxAskCallback = async ({ host }: { host: string; port?: number }) => {
|
||||
try {
|
||||
const sandbox = await prisma.sandbox.findUnique({
|
||||
where: { teamId },
|
||||
})
|
||||
if (sandbox && !sandbox.networkSandboxEnabled) {
|
||||
return true
|
||||
}
|
||||
const pendingDomains = sandbox?.pendingDomains || []
|
||||
if (!pendingDomains.includes(host)) {
|
||||
await prisma.sandbox.upsert({
|
||||
@@ -210,6 +211,54 @@ export async function createAgentSession(params: CreateAgentSessionParams) {
|
||||
return false
|
||||
}
|
||||
|
||||
const wrapToolWithQuota = (tool: AgentTool): AgentTool => {
|
||||
const originalExecute = tool.execute
|
||||
return {
|
||||
...tool,
|
||||
execute: async (toolCallId, args, signal, onUpdate) => {
|
||||
try {
|
||||
await quotaService.checkQuota(
|
||||
{
|
||||
teamId,
|
||||
userId,
|
||||
role,
|
||||
resource: 'agent_tool_call_count',
|
||||
resourceData: { name: tool.name, toolName: tool.name },
|
||||
},
|
||||
1,
|
||||
)
|
||||
} catch (err) {
|
||||
if (err instanceof QuotaExceededError) {
|
||||
return {
|
||||
content: [{ type: 'text', text: `Quota exceeded: ${err.message}` }],
|
||||
details: { error: err.message },
|
||||
}
|
||||
}
|
||||
throw err
|
||||
}
|
||||
|
||||
const result = await originalExecute(toolCallId, args, signal, onUpdate)
|
||||
|
||||
try {
|
||||
await quotaService.consumeQuota(
|
||||
{
|
||||
teamId,
|
||||
userId,
|
||||
role,
|
||||
resource: 'agent_tool_call_count',
|
||||
resourceData: { name: tool.name, toolName: tool.name },
|
||||
},
|
||||
1,
|
||||
)
|
||||
} catch (err) {
|
||||
logger.error({ err }, 'Failed to record quota usage for agent tool call')
|
||||
}
|
||||
|
||||
return result
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
// SandboxManager.initialize is a global operation that applies to the entire process.
|
||||
// We reset it first to ensure any previous process-global SOCKS/HTTP proxy servers
|
||||
// and callbacks are cleaned up, allowing the new callback and allowedDomains to take effect.
|
||||
@@ -235,13 +284,6 @@ export async function createAgentSession(params: CreateAgentSessionParams) {
|
||||
Object.assign(skillEnvs, envs)
|
||||
}
|
||||
|
||||
// Resolve the requesting user's team role to enforce owner-only bash privileges.
|
||||
// A user who is not a member of the team is treated as restricted (fail-closed),
|
||||
// while flows without a user context (e.g. autofill) remain unrestricted.
|
||||
const role = await resolveTeamMemberRole(teamId, userId)
|
||||
const isOwner = !userId || role === 'owner'
|
||||
const restricted = !isOwner
|
||||
|
||||
// Restore env variables from previously loaded skills in this session
|
||||
let skillLoadedInSession = false
|
||||
if (sessionId) {
|
||||
@@ -250,6 +292,7 @@ export async function createAgentSession(params: CreateAgentSessionParams) {
|
||||
for (const entry of entries) {
|
||||
if (
|
||||
entry.type === 'message' &&
|
||||
entry.message &&
|
||||
entry.message.role === 'toolResult' &&
|
||||
entry.message.toolName === 'read_skill' &&
|
||||
!entry.message.isError
|
||||
@@ -267,17 +310,9 @@ export async function createAgentSession(params: CreateAgentSessionParams) {
|
||||
}
|
||||
}
|
||||
|
||||
const metadata = await storage.getMetadata()
|
||||
const userCommentId =
|
||||
passedUserCommentId !== undefined ? passedUserCommentId : metadata.userCommentId
|
||||
|
||||
const mediaTools: AgentTool[] = []
|
||||
if (userId) {
|
||||
mediaTools.push(
|
||||
createAnalyzeImageTool(userId, userCommentId),
|
||||
createScreenshotTool(userId, userCommentId),
|
||||
createReadPdfPagesTool(userId, userCommentId),
|
||||
)
|
||||
mediaTools.push(createReadAssetTool(userId))
|
||||
}
|
||||
|
||||
const agent = await prisma.agent.findUnique({
|
||||
@@ -287,6 +322,9 @@ export async function createAgentSession(params: CreateAgentSessionParams) {
|
||||
const deniedTools = agentConfig?.deniedTools || []
|
||||
|
||||
const sandboxedBash = createSandboxedBashTool(process.cwd(), skillEnvs, {
|
||||
teamId,
|
||||
userId,
|
||||
role,
|
||||
getBlockedHost: () => sandboxState.blockedHost,
|
||||
clearBlockedHost: () => {
|
||||
sandboxState.blockedHost = ''
|
||||
@@ -307,28 +345,34 @@ export async function createAgentSession(params: CreateAgentSessionParams) {
|
||||
bashInjected = true
|
||||
// Pass the full post-update tool list as activeToolNames: setTools only updates the
|
||||
// registry otherwise, and the model would never see the bash tool on the next turn.
|
||||
const next = [...harness.getTools(), sandboxedBash]
|
||||
const next = [...harness.getTools(), wrapToolWithQuota(sandboxedBash)]
|
||||
await harness.setTools(
|
||||
next,
|
||||
next.map((t) => t.name),
|
||||
)
|
||||
}
|
||||
const readSkill = createReadSkillTool(userId, onEnvsAdded, restricted ? onSkillLoaded : undefined)
|
||||
const readSkill = createReadSkillTool(
|
||||
userId,
|
||||
onEnvsAdded,
|
||||
restricted ? onSkillLoaded : undefined,
|
||||
enabledSkillIds,
|
||||
projectId,
|
||||
)
|
||||
|
||||
const systemTools: AgentTool[] = []
|
||||
if (userId) {
|
||||
const metadataSchema = await buildProjectMetadataSchema(projectId)
|
||||
systemTools.push(
|
||||
createListAssetsTool(userId),
|
||||
createCreateFolderTool(userId),
|
||||
createCreateFileTool(userId),
|
||||
createCreateVersionTool(userId),
|
||||
createCreateFileTool(userId, metadataSchema),
|
||||
createCreateVersionTool(userId, metadataSchema),
|
||||
createDownloadAssetTool(userId),
|
||||
createListAutofillFieldsTool(userId),
|
||||
)
|
||||
}
|
||||
|
||||
const readThread = createReadThreadTool()
|
||||
const allTools = [
|
||||
const rawTools = [
|
||||
...mediaTools,
|
||||
readSkill,
|
||||
readThread,
|
||||
@@ -336,6 +380,7 @@ export async function createAgentSession(params: CreateAgentSessionParams) {
|
||||
...systemTools,
|
||||
...customTools,
|
||||
]
|
||||
const allTools = rawTools.map((tool) => wrapToolWithQuota(tool))
|
||||
const enabledTools = disableTools
|
||||
? []
|
||||
: allTools.filter((tool) => !deniedTools.includes(tool.name))
|
||||
@@ -393,6 +438,29 @@ export async function createAgentSession(params: CreateAgentSessionParams) {
|
||||
tools: enabledTools,
|
||||
})
|
||||
|
||||
harness.on('context', async ({ messages }) => {
|
||||
return {
|
||||
messages: messages.map((msg) => {
|
||||
if (
|
||||
msg.role === 'custom' &&
|
||||
msg.customType === 'shumai_message' &&
|
||||
msg.details &&
|
||||
typeof msg.details === 'object'
|
||||
) {
|
||||
const context = msg.details as ShumaiMessageContext
|
||||
const xml = serializeContextToXml(context)
|
||||
const text = typeof msg.content === 'string' ? msg.content : ''
|
||||
const fullContent = xml ? `${text}\n\n${xml}`.trim() : text
|
||||
return {
|
||||
...msg,
|
||||
content: fullContent,
|
||||
}
|
||||
}
|
||||
return msg
|
||||
}),
|
||||
}
|
||||
})
|
||||
|
||||
return { session, harness }
|
||||
}
|
||||
|
||||
@@ -403,58 +471,116 @@ export interface AutofillField {
|
||||
}
|
||||
|
||||
export function fieldsToTypeBoxSchema(fields: AutofillField[]) {
|
||||
const newOptionSchema = Type.Object(
|
||||
{
|
||||
newOption: Type.Object(
|
||||
{
|
||||
value: Type.String({
|
||||
minLength: 1,
|
||||
description:
|
||||
'The new option display name/value to create and select if none of the existing options match.',
|
||||
}),
|
||||
},
|
||||
{ additionalProperties: false },
|
||||
),
|
||||
},
|
||||
{ additionalProperties: false },
|
||||
)
|
||||
|
||||
const properties: Record<string, TSchema> = {}
|
||||
for (const f of fields) {
|
||||
let schema: TSchema
|
||||
const fieldName = f.config.name
|
||||
const fieldDesc = f.description || fieldName
|
||||
const baseDescription = `The field '${fieldName}' represents ${fieldDesc}.`
|
||||
switch (f.config.type) {
|
||||
case 'text':
|
||||
case 'longText':
|
||||
schema = Type.String()
|
||||
schema = Type.String({ description: baseDescription })
|
||||
break
|
||||
case 'number':
|
||||
case 'rating':
|
||||
schema = Type.Number()
|
||||
schema = Type.Number({ description: baseDescription })
|
||||
break
|
||||
case 'toggle':
|
||||
schema = Type.Boolean()
|
||||
schema = Type.Boolean({ description: baseDescription })
|
||||
break
|
||||
case 'select': {
|
||||
const options = f.config.select?.options || []
|
||||
schema = Type.String({
|
||||
enum: options.map((o) => o.id),
|
||||
})
|
||||
const description =
|
||||
options.length > 0
|
||||
? `${baseDescription}\nSelect one existing option ID or provide {"newOption": {"value": "..."}} to create a new option.\n\nAvailable options:\n${options.map((o) => `- ${o.displayName} => ${o.id}`).join('\n')}`
|
||||
: `${baseDescription}\nProvide {"newOption": {"value": "..."}} with the desired option name.`
|
||||
if (options.length > 0) {
|
||||
const optionLines = options.map((o) => `- ${o.displayName} => ${o.id}`).join('\n')
|
||||
schema.description = `The field '${fieldName}' represents ${fieldDesc}.\nSelect one option and return the option ID as the value.\n\nAvailable options:\n${optionLines}`
|
||||
schema = Type.Union(
|
||||
[
|
||||
Type.String({
|
||||
enum: options.map((o) => o.id),
|
||||
}),
|
||||
newOptionSchema,
|
||||
],
|
||||
{ description },
|
||||
)
|
||||
} else {
|
||||
schema = Type.Object(newOptionSchema.properties, {
|
||||
additionalProperties: false,
|
||||
description,
|
||||
})
|
||||
}
|
||||
break
|
||||
}
|
||||
case 'selectMulti': {
|
||||
const options = f.config.selectMulti?.options || []
|
||||
schema = Type.Array(
|
||||
Type.String({
|
||||
enum: options.map((o) => o.id),
|
||||
}),
|
||||
)
|
||||
if (options.length > 0) {
|
||||
const optionLines = options.map((o) => `- ${o.displayName} => ${o.id}`).join('\n')
|
||||
schema.description = `The field '${fieldName}' represents ${fieldDesc}.\nSelect applicable options and return the option IDs as the value.\n\nAvailable options:\n${optionLines}`
|
||||
}
|
||||
const description =
|
||||
options.length > 0
|
||||
? `${baseDescription}\nSelect applicable option IDs or provide {"newOption": {"value": "..."}} objects for new options (e.g. ["opt1", {"newOption": {"value": "new_name"}}]).\n\nAvailable options:\n${options.map((o) => `- ${o.displayName} => ${o.id}`).join('\n')}`
|
||||
: `${baseDescription}\nProvide an array of {"newOption": {"value": "..."}} objects for new options.`
|
||||
const itemSchema =
|
||||
options.length > 0
|
||||
? Type.Union([
|
||||
Type.String({
|
||||
enum: options.map((o) => o.id),
|
||||
}),
|
||||
newOptionSchema,
|
||||
])
|
||||
: newOptionSchema
|
||||
schema = Type.Array(itemSchema, { description })
|
||||
break
|
||||
}
|
||||
default:
|
||||
schema = Type.String()
|
||||
schema = Type.String({ description: baseDescription })
|
||||
}
|
||||
|
||||
if (!schema.description) {
|
||||
schema.description = `The field '${fieldName}' represents ${fieldDesc}.`
|
||||
}
|
||||
properties[f.id] = schema
|
||||
// Every field is required but nullable: the agent must return each field key,
|
||||
// using `null` for values it does not know. Nulls are skipped when persisting.
|
||||
// This matches the OpenAI structured-outputs strict-mode convention (all
|
||||
// properties required, optionality expressed via `null`).
|
||||
properties[f.id] = Type.Union([schema, Type.Null()])
|
||||
}
|
||||
|
||||
return Type.Object(properties)
|
||||
return Type.Object(properties, { additionalProperties: false })
|
||||
}
|
||||
|
||||
/**
|
||||
* Builds the strict, all-optional metadata schema for the project's CREATION_CONTEXT
|
||||
* fields (the same field set the agent may attach when creating files/versions).
|
||||
* Returns undefined when no project is known or the project defines no fields, in
|
||||
* which case the `metadata` parameter is omitted from the tools entirely.
|
||||
*/
|
||||
async function buildProjectMetadataSchema(projectId?: string): Promise<TSchema | undefined> {
|
||||
if (!projectId) return undefined
|
||||
const fields = await metadataService.listProjectFields('', projectId)
|
||||
const creationFields: AutofillField[] = []
|
||||
for (const f of fields) {
|
||||
const config = f.field.config
|
||||
if (!config || config.autofillSource !== 'CREATION_CONTEXT') continue
|
||||
creationFields.push({
|
||||
id: f.field.key,
|
||||
config,
|
||||
description: f.field.description,
|
||||
})
|
||||
}
|
||||
if (creationFields.length === 0) return undefined
|
||||
return fieldsToTypeBoxSchema(creationFields)
|
||||
}
|
||||
|
||||
function escapeXml(str: string): string {
|
||||
@@ -503,7 +629,6 @@ import * as aiActivities from './activities/ai'
|
||||
import { agentAutofillMedia } from './workflows/agent-autofill'
|
||||
import { agentChat } from './workflows/agent-chat'
|
||||
import { agentEmbeddingMedia } from './workflows/agent-embedding'
|
||||
import { agentToolCall } from './workflows/agent-tool-call'
|
||||
import { queryEmbeddingForSearch } from './workflows/query-embedding-for-search'
|
||||
|
||||
export function initAgentWorkflows() {
|
||||
@@ -511,7 +636,6 @@ export function initAgentWorkflows() {
|
||||
registerWorkflow(WorkflowTaskType.query_embedding_for_search, queryEmbeddingForSearch)
|
||||
registerWorkflow(WorkflowTaskType.ai_metadata_autofill, agentAutofillMedia)
|
||||
registerWorkflow(WorkflowTaskType.chat, agentChat)
|
||||
registerWorkflow(WorkflowTaskType.agent_tool_call, agentToolCall)
|
||||
|
||||
registerActivities(agentActivities)
|
||||
registerActivities(aiActivities)
|
||||
@@ -530,8 +654,8 @@ export {
|
||||
type GenerateTextEmbeddingParams,
|
||||
} from './activities/ai'
|
||||
export * from './database-session-storage'
|
||||
export * from './context/serialize-context'
|
||||
export * from './workflows/agent-autofill'
|
||||
export * from './workflows/agent-chat'
|
||||
export * from './workflows/agent-embedding'
|
||||
export * from './workflows/agent-tool-call'
|
||||
export * from './workflows/query-embedding-for-search'
|
||||
|
||||
@@ -0,0 +1,117 @@
|
||||
import { describe, it, expect, vi, beforeEach } from 'vitest'
|
||||
import { validateToolArguments } from '@earendil-works/pi-ai'
|
||||
import { createCreateFileTool } from './tools/create-file'
|
||||
import { fieldsToTypeBoxSchema } from './index'
|
||||
import { s3Service } from '@shumai/core/src/s3/s3'
|
||||
import { assetService } from '@shumai/core/src/asset/asset'
|
||||
import { authzService } from '@shumai/core/src/authz/authz'
|
||||
|
||||
vi.mock('@shumai/core/src/s3/s3', () => ({
|
||||
s3Service: {
|
||||
uploadFileToKey: vi.fn(),
|
||||
putObject: vi.fn(),
|
||||
},
|
||||
}))
|
||||
|
||||
vi.mock('@shumai/core/src/authz/authz', () => ({
|
||||
authzService: {
|
||||
hasPermission: vi.fn().mockResolvedValue(undefined),
|
||||
},
|
||||
Permission: { Edit: 'edit', Read: 'read' },
|
||||
ResourceType: { Asset: 'asset' },
|
||||
}))
|
||||
|
||||
vi.mock('@shumai/core/src/asset/asset', () => ({
|
||||
assetService: {
|
||||
createFile: vi
|
||||
.fn()
|
||||
.mockResolvedValue({ id: 'file-1', name: 'test', type: 'file', sizeByte: 100 }),
|
||||
},
|
||||
}))
|
||||
|
||||
/**
|
||||
* Reproduce: pi-ai <= 0.82.1 runs its lenient coercion on typebox v1 schemas and
|
||||
* converts `null` in a `[string, null]` union into `""` (see
|
||||
* coerceWithUnionSchema in @earendil-works/pi-ai/dist/utils/validation.js).
|
||||
*
|
||||
* When the agent calls create_file with `path: null, data: {...}`, the harness
|
||||
* validates first: the `null` path becomes `""`, so the tool's
|
||||
* assertExactlyOneSource believes BOTH path and data were provided and throws
|
||||
* "Provide exactly one of ..." even though the call is valid.
|
||||
*
|
||||
* Fixed upstream in pi-ai 0.84.0 (#7328): values that already match a union arm
|
||||
* are preserved before coercion. This test should pass once @earendil-works/pi-ai
|
||||
* is upgraded to >= 0.84.0.
|
||||
*/
|
||||
describe('reproduce null coercion in harness tool validation', () => {
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks()
|
||||
})
|
||||
|
||||
it('keeps path: null when data is provided (no false "exactly one" error)', async () => {
|
||||
const tool = createCreateFileTool('user-1')
|
||||
|
||||
const validated = validateToolArguments(
|
||||
{
|
||||
name: 'create_file',
|
||||
description: '',
|
||||
parameters: tool.parameters,
|
||||
} as Parameters<typeof validateToolArguments>[0],
|
||||
{
|
||||
type: 'toolCall',
|
||||
id: 'call-1',
|
||||
name: 'create_file',
|
||||
arguments: {
|
||||
parent: '01KYKNP52YERGJ6Q4GTPF5FRQF',
|
||||
path: null,
|
||||
data: { name: 'random_text.txt', content: 'hello' },
|
||||
},
|
||||
} as Parameters<typeof validateToolArguments>[1],
|
||||
) as { path?: unknown; data?: unknown }
|
||||
|
||||
// The `null` path must survive validation untouched; coercion to "" makes
|
||||
// the tool think both path and data were provided.
|
||||
expect(validated.path).toBeNull()
|
||||
expect(validated.data).toEqual({ name: 'random_text.txt', content: 'hello' })
|
||||
|
||||
// execute must accept the valid call (data-only) without throwing
|
||||
const result = await tool.execute('call-1', validated as never)
|
||||
expect(result.details).toEqual({})
|
||||
expect(JSON.parse((result.content[0] as { text: string }).text)).toEqual({
|
||||
id: 'file-1',
|
||||
name: 'test',
|
||||
type: 'file',
|
||||
size: 100,
|
||||
})
|
||||
expect(s3Service.putObject).toHaveBeenCalledTimes(1)
|
||||
expect(authzService.hasPermission).toHaveBeenCalledTimes(1)
|
||||
expect(assetService.createFile).toHaveBeenCalledTimes(1)
|
||||
})
|
||||
|
||||
it('keeps null metadata values (the "unknown" sentinel) through validation', () => {
|
||||
const tool = createCreateFileTool(
|
||||
'user-1',
|
||||
fieldsToTypeBoxSchema([{ id: 'prompt', config: { name: 'Prompt', type: 'text' } }]),
|
||||
)
|
||||
const validated = validateToolArguments(
|
||||
{
|
||||
name: 'create_file',
|
||||
description: '',
|
||||
parameters: tool.parameters,
|
||||
} as Parameters<typeof validateToolArguments>[0],
|
||||
{
|
||||
type: 'toolCall',
|
||||
id: 'call-1',
|
||||
name: 'create_file',
|
||||
arguments: {
|
||||
parent: 'folder-1',
|
||||
path: null,
|
||||
data: { name: 'a.md', content: 'x' },
|
||||
metadata: { prompt: null },
|
||||
},
|
||||
} as Parameters<typeof validateToolArguments>[1],
|
||||
) as { metadata?: Record<string, unknown> }
|
||||
|
||||
expect(validated.metadata).toEqual({ prompt: null })
|
||||
})
|
||||
})
|
||||
@@ -1,6 +1,22 @@
|
||||
import { describe, it, expect } from 'vitest'
|
||||
import { type TSchema } from 'typebox'
|
||||
import { Value } from 'typebox/value'
|
||||
import { fieldsToTypeBoxSchema, type AutofillField } from './index'
|
||||
|
||||
interface AnyOfFieldSchema {
|
||||
type?: string
|
||||
enum?: string[]
|
||||
const?: string
|
||||
description?: string
|
||||
items?: { enum?: string[]; type?: string }
|
||||
anyOf?: AnyOfFieldSchema[]
|
||||
}
|
||||
|
||||
function propsOf(schema: TSchema): Record<string, { anyOf?: AnyOfFieldSchema[] }> {
|
||||
return (schema as unknown as { properties: Record<string, { anyOf?: AnyOfFieldSchema[] }> })
|
||||
.properties
|
||||
}
|
||||
|
||||
describe('fieldsToTypeBoxSchema', () => {
|
||||
it('converts text fields', () => {
|
||||
const fields: AutofillField[] = [
|
||||
@@ -8,10 +24,12 @@ describe('fieldsToTypeBoxSchema', () => {
|
||||
{ id: 'f2', config: { name: 'Desc', type: 'longText' } },
|
||||
]
|
||||
const schema = fieldsToTypeBoxSchema(fields)
|
||||
expect(schema.properties.f1.type).toBe('string')
|
||||
expect(schema.properties.f1.description).toBe("The field 'Title' represents The title.")
|
||||
expect(schema.properties.f2.type).toBe('string')
|
||||
expect(schema.properties.f2.description).toBe("The field 'Desc' represents Desc.")
|
||||
const props = propsOf(schema)
|
||||
expect(props.f1.anyOf![0].type).toBe('string')
|
||||
expect(props.f1.anyOf![1].type).toBe('null')
|
||||
expect(props.f1.anyOf![0].description).toBe("The field 'Title' represents The title.")
|
||||
expect(props.f2.anyOf![0].type).toBe('string')
|
||||
expect(props.f2.anyOf![0].description).toBe("The field 'Desc' represents Desc.")
|
||||
})
|
||||
|
||||
it('converts numeric fields', () => {
|
||||
@@ -20,17 +38,18 @@ describe('fieldsToTypeBoxSchema', () => {
|
||||
{ id: 'f2', config: { name: 'Rating', type: 'rating' } },
|
||||
]
|
||||
const schema = fieldsToTypeBoxSchema(fields)
|
||||
expect(schema.properties.f1.type).toBe('number')
|
||||
expect(schema.properties.f2.type).toBe('number')
|
||||
const props = propsOf(schema)
|
||||
expect(props.f1.anyOf![0].type).toBe('number')
|
||||
expect(props.f2.anyOf![0].type).toBe('number')
|
||||
})
|
||||
|
||||
it('converts toggle fields', () => {
|
||||
const fields: AutofillField[] = [{ id: 'f1', config: { name: 'Active', type: 'toggle' } }]
|
||||
const schema = fieldsToTypeBoxSchema(fields)
|
||||
expect(schema.properties.f1.type).toBe('boolean')
|
||||
expect(propsOf(schema).f1.anyOf![0].type).toBe('boolean')
|
||||
})
|
||||
|
||||
it('converts select fields with enums and option descriptions', () => {
|
||||
it('converts select fields with enums, newOption support and option descriptions', () => {
|
||||
const fields: AutofillField[] = [
|
||||
{
|
||||
id: 'f1',
|
||||
@@ -48,14 +67,41 @@ describe('fieldsToTypeBoxSchema', () => {
|
||||
},
|
||||
]
|
||||
const schema = fieldsToTypeBoxSchema(fields)
|
||||
expect(schema.properties.f1.type).toBe('string')
|
||||
expect(schema.properties.f1.enum).toEqual(['opt1', 'opt2'])
|
||||
expect(schema.properties.f1.description).toBe(
|
||||
"The field 'Species' represents Species of animal.\nSelect one option and return the option ID as the value.\n\nAvailable options:\n- Option 1 => opt1\n- Option 2 => opt2",
|
||||
const selectSchema = propsOf(schema).f1.anyOf![0]
|
||||
expect(selectSchema.anyOf![0].type).toBe('string')
|
||||
expect(selectSchema.anyOf![0].enum).toEqual(['opt1', 'opt2'])
|
||||
expect(selectSchema.anyOf![1].type).toBe('object')
|
||||
expect(selectSchema.description).toBe(
|
||||
'The field \'Species\' represents Species of animal.\nSelect one existing option ID or provide {"newOption": {"value": "..."}} to create a new option.\n\nAvailable options:\n- Option 1 => opt1\n- Option 2 => opt2',
|
||||
)
|
||||
// Declared option IDs, newOption objects, and null are valid
|
||||
expect(Value.Check(schema, { f1: 'opt1' })).toBe(true)
|
||||
expect(Value.Check(schema, { f1: 'opt2' })).toBe(true)
|
||||
expect(Value.Check(schema, { f1: { newOption: { value: 'kling' } } })).toBe(true)
|
||||
expect(Value.Check(schema, { f1: null })).toBe(true)
|
||||
// Arbitrary strings or invalid objects are rejected
|
||||
expect(Value.Check(schema, { f1: 'not-an-option' })).toBe(false)
|
||||
expect(Value.Check(schema, { f1: { newOption: { foo: 'bar' } } })).toBe(false)
|
||||
})
|
||||
|
||||
it('converts selectMulti fields with array enums and option descriptions', () => {
|
||||
it('converts select fields with empty options to newOption schema only', () => {
|
||||
const fields: AutofillField[] = [
|
||||
{
|
||||
id: 'f1',
|
||||
config: {
|
||||
name: 'Provider',
|
||||
type: 'select',
|
||||
select: { options: [] },
|
||||
},
|
||||
},
|
||||
]
|
||||
const schema = fieldsToTypeBoxSchema(fields)
|
||||
expect(Value.Check(schema, { f1: { newOption: { value: 'kling' } } })).toBe(true)
|
||||
expect(Value.Check(schema, { f1: null })).toBe(true)
|
||||
expect(Value.Check(schema, { f1: 'any-string' })).toBe(false)
|
||||
})
|
||||
|
||||
it('converts selectMulti fields with array enums, newOption support and option descriptions', () => {
|
||||
const fields: AutofillField[] = [
|
||||
{
|
||||
id: 'f1',
|
||||
@@ -72,11 +118,35 @@ describe('fieldsToTypeBoxSchema', () => {
|
||||
},
|
||||
]
|
||||
const schema = fieldsToTypeBoxSchema(fields)
|
||||
expect(schema.properties.f1.type).toBe('array')
|
||||
expect(schema.properties.f1.items.enum).toEqual(['opt1', 'opt2'])
|
||||
expect(schema.properties.f1.description).toBe(
|
||||
"The field 'Tags' represents Tags.\nSelect applicable options and return the option IDs as the value.\n\nAvailable options:\n- Tag 1 => opt1\n- Tag 2 => opt2",
|
||||
const selectMultiSchema = propsOf(schema).f1.anyOf![0]
|
||||
expect(selectMultiSchema.type).toBe('array')
|
||||
expect(selectMultiSchema.description).toBe(
|
||||
'The field \'Tags\' represents Tags.\nSelect applicable option IDs or provide {"newOption": {"value": "..."}} objects for new options (e.g. ["opt1", {"newOption": {"value": "new_name"}}]).\n\nAvailable options:\n- Tag 1 => opt1\n- Tag 2 => opt2',
|
||||
)
|
||||
expect(Value.Check(schema, { f1: ['opt1', 'opt2'] })).toBe(true)
|
||||
expect(Value.Check(schema, { f1: [{ newOption: { value: 'Tag 3' } }] })).toBe(true)
|
||||
expect(Value.Check(schema, { f1: ['opt1', { newOption: { value: 'Tag 3' } }] })).toBe(true)
|
||||
expect(Value.Check(schema, { f1: null })).toBe(true)
|
||||
expect(Value.Check(schema, { f1: ['opt1', 'bad'] })).toBe(false)
|
||||
expect(Value.Check(schema, { f1: ['opt1', { newOption: { bad: 'value' } }] })).toBe(false)
|
||||
})
|
||||
|
||||
it('converts selectMulti fields with empty options to array of newOption schema', () => {
|
||||
const fields: AutofillField[] = [
|
||||
{
|
||||
id: 'f1',
|
||||
config: {
|
||||
name: 'Tags',
|
||||
type: 'selectMulti',
|
||||
selectMulti: { options: [] },
|
||||
},
|
||||
},
|
||||
]
|
||||
const schema = fieldsToTypeBoxSchema(fields)
|
||||
expect(Value.Check(schema, { f1: [{ newOption: { value: 'Tag 1' } }] })).toBe(true)
|
||||
expect(Value.Check(schema, { f1: [] })).toBe(true)
|
||||
expect(Value.Check(schema, { f1: null })).toBe(true)
|
||||
expect(Value.Check(schema, { f1: ['tag1'] })).toBe(false)
|
||||
})
|
||||
|
||||
it('defaults to string for unknown types', () => {
|
||||
@@ -85,6 +155,22 @@ describe('fieldsToTypeBoxSchema', () => {
|
||||
{ id: 'f1', config: { name: 'Unknown', type: 'invalid' } },
|
||||
]
|
||||
const schema = fieldsToTypeBoxSchema(fields)
|
||||
expect(schema.properties.f1.type).toBe('string')
|
||||
expect(propsOf(schema).f1.anyOf![0].type).toBe('string')
|
||||
})
|
||||
|
||||
it('marks every property required (nullable) and rejects unknown keys', () => {
|
||||
const fields: AutofillField[] = [
|
||||
{ id: 'f1', config: { name: 'Title', type: 'text' } },
|
||||
{ id: 'f2', config: { name: 'Rating', type: 'rating' } },
|
||||
]
|
||||
const schema = fieldsToTypeBoxSchema(fields)
|
||||
const props = propsOf(schema)
|
||||
// typebox v1 objects are strict by default: unknown keys are rejected
|
||||
expect(props.f1.anyOf![0].type).toBe('string')
|
||||
expect(props.f1.anyOf![1].type).toBe('null')
|
||||
expect(Value.Check(schema, { f1: 'x', f2: null })).toBe(true)
|
||||
expect(Value.Check(schema, { f1: null, f2: 3 })).toBe(true)
|
||||
expect(Value.Check(schema, { f1: 'x' })).toBe(false)
|
||||
expect(Value.Check(schema, { f1: 'x', f2: null, extra: 1 })).toBe(false)
|
||||
})
|
||||
})
|
||||
|
||||
@@ -1,175 +0,0 @@
|
||||
import { describe, it, expect, vi, beforeEach } from 'vitest'
|
||||
import { createAnalyzeImageTool } from './analyze-image'
|
||||
import {
|
||||
prisma,
|
||||
WorkflowTaskStatus,
|
||||
type Asset,
|
||||
type AssetComment,
|
||||
type User,
|
||||
type WorkflowTask,
|
||||
} from '@shumai/db'
|
||||
import { s3Service } from '@shumai/core/src/s3/s3'
|
||||
import { workflowService } from '@shumai/workflow-core'
|
||||
import { authzService } from '@shumai/core/src/authz/authz'
|
||||
|
||||
vi.mock('@shumai/db', async (importOriginal) => {
|
||||
const actual = await importOriginal<typeof import('@shumai/db')>()
|
||||
return {
|
||||
...actual,
|
||||
prisma: {
|
||||
user: {
|
||||
findUnique: vi.fn(),
|
||||
},
|
||||
asset: {
|
||||
findUnique: vi.fn(),
|
||||
},
|
||||
assetComment: {
|
||||
findUnique: vi.fn(),
|
||||
},
|
||||
workflowTask: {
|
||||
create: vi.fn(),
|
||||
},
|
||||
},
|
||||
}
|
||||
})
|
||||
|
||||
vi.mock('@shumai/core/src/s3/s3', () => ({
|
||||
s3Service: {
|
||||
getObject: vi.fn(),
|
||||
},
|
||||
}))
|
||||
|
||||
vi.mock('@shumai/workflow-core', () => ({
|
||||
workflowService: {
|
||||
executeWait: vi.fn(),
|
||||
},
|
||||
}))
|
||||
|
||||
vi.mock('@shumai/core/src/authz/authz', () => ({
|
||||
authzService: {
|
||||
hasPermission: vi.fn(),
|
||||
},
|
||||
Permission: { Read: 'Read' },
|
||||
ResourceType: { Asset: 'asset' },
|
||||
}))
|
||||
|
||||
describe('analyzeImageTool', () => {
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks()
|
||||
})
|
||||
|
||||
it('should check user permissions and fetch the image from S3 when comment has no annotations', async () => {
|
||||
vi.mocked(prisma.user.findUnique).mockResolvedValue({ id: 'user-1' } as User)
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'asset-1',
|
||||
projectId: 'project-1',
|
||||
storageKey: { key: 'raw-image.png' },
|
||||
media: null,
|
||||
} as unknown as Asset)
|
||||
|
||||
vi.mocked(prisma.assetComment.findUnique).mockResolvedValue({
|
||||
id: 'comment-1',
|
||||
assetId: 'asset-1',
|
||||
annotation: null,
|
||||
} as unknown as AssetComment)
|
||||
|
||||
vi.mocked(s3Service.getObject).mockResolvedValue({
|
||||
buffer: Buffer.from('fake-image-bytes'),
|
||||
contentType: 'image/png',
|
||||
} as unknown as { buffer: Buffer; contentType: string })
|
||||
|
||||
const tool = createAnalyzeImageTool('user-1', 'comment-1')
|
||||
const result = await tool.execute('call-1', { assetId: 'asset-1' })
|
||||
|
||||
expect(authzService.hasPermission).toHaveBeenCalledWith({
|
||||
user: { id: 'user-1' },
|
||||
permission: 'Read',
|
||||
type: 'asset',
|
||||
id: 'asset-1',
|
||||
})
|
||||
|
||||
expect(result.content[0].type).toBe('image')
|
||||
expect((result.content[0] as unknown as { data: string }).data).toBe(
|
||||
Buffer.from('fake-image-bytes').toString('base64'),
|
||||
)
|
||||
expect(result.details.sourceKeys).toEqual(['raw-image.png'])
|
||||
|
||||
expect(prisma.workflowTask.create).not.toHaveBeenCalled()
|
||||
})
|
||||
|
||||
it('should trigger overlay transcode workflow when comment has annotations', async () => {
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'asset-1',
|
||||
projectId: 'project-1',
|
||||
storageKey: { key: 'raw-image.png' },
|
||||
media: {
|
||||
imageTranscodes: [{ key: 'transcoded-image.webp' }],
|
||||
},
|
||||
} as unknown as Asset)
|
||||
|
||||
vi.mocked(prisma.assetComment.findUnique).mockResolvedValue({
|
||||
id: 'comment-1',
|
||||
assetId: 'asset-1',
|
||||
annotation: [
|
||||
{
|
||||
type: 'box',
|
||||
color: '#ff0000',
|
||||
points: [
|
||||
[0, 0],
|
||||
[1, 1],
|
||||
],
|
||||
},
|
||||
],
|
||||
} as unknown as AssetComment)
|
||||
|
||||
vi.mocked(prisma.workflowTask.create).mockResolvedValue({
|
||||
id: 'task-1',
|
||||
} as unknown as WorkflowTask)
|
||||
|
||||
vi.mocked(workflowService.executeWait).mockResolvedValue({
|
||||
id: 'task-1',
|
||||
status: WorkflowTaskStatus.completed,
|
||||
output: { key: 'annotated-image.webp' },
|
||||
} as unknown as WorkflowTask)
|
||||
|
||||
vi.mocked(s3Service.getObject).mockResolvedValue({
|
||||
buffer: Buffer.from('fake-annotated-image-bytes'),
|
||||
contentType: 'image/webp',
|
||||
} as unknown as { buffer: Buffer; contentType: string })
|
||||
|
||||
const tool = createAnalyzeImageTool('user-1', 'comment-1')
|
||||
const result = await tool.execute('call-1', { assetId: 'asset-1' })
|
||||
|
||||
expect(prisma.workflowTask.create).toHaveBeenCalledWith({
|
||||
data: {
|
||||
assetId: 'asset-1',
|
||||
projectId: 'project-1',
|
||||
type: 'transcode_image_annotation',
|
||||
status: 'pending',
|
||||
payload: {
|
||||
projectId: 'project-1',
|
||||
imageAnnotation: {
|
||||
annotations: [
|
||||
{
|
||||
type: 'box',
|
||||
color: '#ff0000',
|
||||
points: [
|
||||
[0, 0],
|
||||
[1, 1],
|
||||
],
|
||||
},
|
||||
],
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
expect(result.content[0].type).toBe('image')
|
||||
expect((result.content[0] as unknown as { data: string }).data).toBe(
|
||||
Buffer.from('fake-annotated-image-bytes').toString('base64'),
|
||||
)
|
||||
expect(result.details.sourceKeys).toEqual(['annotated-image.webp'])
|
||||
})
|
||||
})
|
||||
@@ -1,128 +0,0 @@
|
||||
import { Type } from '@sinclair/typebox'
|
||||
import { type AgentTool } from '@earendil-works/pi-agent-core'
|
||||
import { type ImageContent } from '@earendil-works/pi-ai'
|
||||
import { prisma, WorkflowTaskType, WorkflowTaskStatus, type User } from '@shumai/db'
|
||||
import { s3Service } from '@shumai/core/src/s3/s3'
|
||||
import { workflowService } from '@shumai/workflow-core'
|
||||
import { authzService, Permission, ResourceType } from '@shumai/core/src/authz/authz'
|
||||
|
||||
const analyzeImageSchema = Type.Object({
|
||||
assetId: Type.String({
|
||||
description: 'The asset ID of the image to analyze. This parameter is required.',
|
||||
}),
|
||||
})
|
||||
|
||||
export function createAnalyzeImageTool(
|
||||
userId: string,
|
||||
userCommentId?: string | null,
|
||||
): AgentTool<typeof analyzeImageSchema> {
|
||||
return {
|
||||
name: 'analyze_image',
|
||||
label: 'Analyze Image',
|
||||
description:
|
||||
'Retrieves and views the image content. Call this tool if you need to analyze the image.',
|
||||
parameters: analyzeImageSchema,
|
||||
execute: async (_toolCallId, params) => {
|
||||
const assetId = params.assetId
|
||||
|
||||
if (!userId) {
|
||||
throw new Error('User ID is required for authorization.')
|
||||
}
|
||||
|
||||
await authzService.hasPermission({
|
||||
user: { id: userId } as User,
|
||||
permission: Permission.Read,
|
||||
type: ResourceType.Asset,
|
||||
id: assetId,
|
||||
})
|
||||
|
||||
const asset = await prisma.asset.findUnique({
|
||||
where: { id: assetId },
|
||||
include: { storageKey: true },
|
||||
})
|
||||
|
||||
if (!asset) {
|
||||
throw new Error(`Asset with ID ${assetId} not found.`)
|
||||
}
|
||||
|
||||
// Get default media key
|
||||
let mediaKey = asset.storageKey?.key
|
||||
if (asset.media) {
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const mediaInfo = asset.media as any
|
||||
if (mediaInfo.imageTranscodes && mediaInfo.imageTranscodes.length > 0) {
|
||||
mediaKey = mediaInfo.imageTranscodes[0].key || mediaKey
|
||||
}
|
||||
}
|
||||
|
||||
if (!mediaKey) {
|
||||
throw new Error('No media content found for this asset.')
|
||||
}
|
||||
|
||||
// Check if trigger comment has draw annotations for this asset
|
||||
let annotations: unknown = null
|
||||
if (userCommentId) {
|
||||
const comment = await prisma.assetComment.findUnique({
|
||||
where: { id: userCommentId },
|
||||
})
|
||||
if (comment && comment.assetId === assetId && comment.annotation) {
|
||||
const list = comment.annotation
|
||||
if (Array.isArray(list) && list.length > 0) {
|
||||
annotations = list
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
let keyToUse = mediaKey
|
||||
|
||||
if (annotations) {
|
||||
// Trigger transcode workflow to draw annotation
|
||||
const task = await prisma.workflowTask.create({
|
||||
data: {
|
||||
assetId,
|
||||
projectId: asset.projectId || 'none',
|
||||
type: WorkflowTaskType.transcode_image_annotation,
|
||||
status: WorkflowTaskStatus.pending,
|
||||
payload: {
|
||||
projectId: asset.projectId || 'none',
|
||||
imageAnnotation: {
|
||||
annotations: annotations as PrismaJson.AnnotationList,
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
const completedTask = await workflowService.executeWait(task)
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const output = completedTask.output as any
|
||||
if (output?.key) {
|
||||
keyToUse = output.key
|
||||
} else {
|
||||
throw new Error('Image annotation transcode workflow failed to output S3 key.')
|
||||
}
|
||||
}
|
||||
|
||||
// Retrieve the image content from S3
|
||||
const bucket = process.env.S3_BUCKET || 'shumai'
|
||||
const { buffer, contentType } = await s3Service.getObject(bucket, keyToUse)
|
||||
|
||||
const mimeType =
|
||||
contentType && contentType !== 'application/octet-stream' ? contentType : 'image/webp'
|
||||
|
||||
const content: ImageContent[] = [
|
||||
{
|
||||
type: 'image',
|
||||
data: buffer.toString('base64'),
|
||||
mimeType,
|
||||
},
|
||||
]
|
||||
|
||||
return {
|
||||
content,
|
||||
details: {
|
||||
sourceKeys: [keyToUse],
|
||||
},
|
||||
}
|
||||
},
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,270 @@
|
||||
import { describe, it, expect, beforeEach } from 'vitest'
|
||||
import { prisma } from '@shumai/db'
|
||||
import { setupTestDbHooks } from '@shumai/db/test'
|
||||
import { resolveAnnotationsById } from './annotation-resolver'
|
||||
import { DatabaseSessionStorage } from '../database-session-storage'
|
||||
import type { SessionTreeEntry } from '@earendil-works/pi-agent-core'
|
||||
|
||||
describe('resolveAnnotationsById', () => {
|
||||
setupTestDbHooks()
|
||||
|
||||
beforeEach(() => {
|
||||
// DB hooks automatically manage transactions
|
||||
})
|
||||
|
||||
it('returns null annotations and null timestamp when annotationId is undefined or empty', async () => {
|
||||
const result1 = await resolveAnnotationsById('asset-1', undefined)
|
||||
expect(result1).toEqual({ annotations: null, timestamp: null })
|
||||
|
||||
const result2 = await resolveAnnotationsById('asset-1', '')
|
||||
expect(result2).toEqual({ annotations: null, timestamp: null })
|
||||
})
|
||||
|
||||
it('resolves annotations and timestamp from AssetComment (Comments Mode)', async () => {
|
||||
const user = await prisma.user.create({
|
||||
data: { name: 'Comment Author', email: 'author@test.com', password: 'pw' },
|
||||
})
|
||||
const team = await prisma.team.create({
|
||||
data: { name: 'Test Team' },
|
||||
})
|
||||
const project = await prisma.project.create({
|
||||
data: { name: 'Test Project', teamId: team.id },
|
||||
})
|
||||
const asset = await prisma.asset.create({
|
||||
data: {
|
||||
name: 'video.mp4',
|
||||
type: 'file',
|
||||
projectId: project.id,
|
||||
status: 'uploaded',
|
||||
},
|
||||
})
|
||||
|
||||
const comment = await prisma.assetComment.create({
|
||||
data: {
|
||||
assetId: asset.id,
|
||||
creatorId: user.id,
|
||||
message: 'Look at the highlighted area',
|
||||
second: 18.5,
|
||||
annotation: [
|
||||
{
|
||||
type: 'line',
|
||||
color: '#ff0000',
|
||||
points: [
|
||||
[10, 10],
|
||||
[50, 50],
|
||||
],
|
||||
},
|
||||
],
|
||||
},
|
||||
})
|
||||
|
||||
const result = await resolveAnnotationsById(asset.id, comment.id)
|
||||
expect(result.timestamp).toBe(18.5)
|
||||
expect(result.annotations).toEqual([
|
||||
{
|
||||
type: 'line',
|
||||
color: '#ff0000',
|
||||
points: [
|
||||
[10, 10],
|
||||
[50, 50],
|
||||
],
|
||||
},
|
||||
])
|
||||
})
|
||||
|
||||
it('throws an error when AssetComment belongs to a different asset', async () => {
|
||||
const user = await prisma.user.create({
|
||||
data: { name: 'Author', email: 'author2@test.com', password: 'pw' },
|
||||
})
|
||||
const team = await prisma.team.create({
|
||||
data: { name: 'Team' },
|
||||
})
|
||||
const project = await prisma.project.create({
|
||||
data: { name: 'Project', teamId: team.id },
|
||||
})
|
||||
const assetA = await prisma.asset.create({
|
||||
data: { name: 'videoA.mp4', type: 'file', projectId: project.id, status: 'uploaded' },
|
||||
})
|
||||
const assetB = await prisma.asset.create({
|
||||
data: { name: 'videoB.mp4', type: 'file', projectId: project.id, status: 'uploaded' },
|
||||
})
|
||||
|
||||
const commentB = await prisma.assetComment.create({
|
||||
data: {
|
||||
assetId: assetB.id,
|
||||
creatorId: user.id,
|
||||
message: 'Comment on B',
|
||||
annotation: [
|
||||
{
|
||||
type: 'box',
|
||||
color: '#ff0000',
|
||||
points: [
|
||||
[0, 0],
|
||||
[10, 10],
|
||||
],
|
||||
},
|
||||
],
|
||||
},
|
||||
})
|
||||
|
||||
await expect(resolveAnnotationsById(assetA.id, commentB.id)).rejects.toThrow(
|
||||
`Annotation "${commentB.id}" belongs to asset "${assetB.id}", not target asset "${assetA.id}".`,
|
||||
)
|
||||
})
|
||||
|
||||
it('resolves annotations and timestamp from AgentSessionEntry (1-on-1 Chat Mode)', async () => {
|
||||
const user = await prisma.user.create({
|
||||
data: { name: 'Chat User', email: 'chatuser@test.com', password: 'pw' },
|
||||
})
|
||||
const team = await prisma.team.create({
|
||||
data: { name: 'Chat Team' },
|
||||
})
|
||||
const project = await prisma.project.create({
|
||||
data: { name: 'Chat Project', teamId: team.id },
|
||||
})
|
||||
const asset = await prisma.asset.create({
|
||||
data: {
|
||||
name: 'chat-video.mp4',
|
||||
type: 'file',
|
||||
projectId: project.id,
|
||||
status: 'uploaded',
|
||||
},
|
||||
})
|
||||
const agentUser = await prisma.user.create({
|
||||
data: { name: 'Chat Bot User', email: 'bot@example.com', type: 'agent' },
|
||||
})
|
||||
const agent = await prisma.agent.create({
|
||||
data: {
|
||||
id: agentUser.id,
|
||||
teamId: team.id,
|
||||
type: 'chat',
|
||||
config: { provider: 'test-provider', model: 'test-model' },
|
||||
},
|
||||
})
|
||||
|
||||
// Create session storage
|
||||
const storage = await DatabaseSessionStorage.create({
|
||||
agentId: agent.id,
|
||||
userId: user.id,
|
||||
assetId: asset.id,
|
||||
})
|
||||
|
||||
// Set active message context with markup annotations and position
|
||||
storage.currentMessageContext = {
|
||||
currentAsset: {
|
||||
id: asset.id,
|
||||
name: asset.name,
|
||||
type: 'file',
|
||||
path: asset.name,
|
||||
},
|
||||
position: { type: 'time', seconds: 12.34 },
|
||||
annotation: true,
|
||||
annotations: [
|
||||
{
|
||||
type: 'rectangle',
|
||||
x: 100,
|
||||
y: 200,
|
||||
width: 50,
|
||||
height: 50,
|
||||
},
|
||||
],
|
||||
}
|
||||
|
||||
// User sends a message -> DatabaseSessionStorage.appendEntry is called
|
||||
const userEntry: SessionTreeEntry = {
|
||||
type: 'message',
|
||||
id: '01JTESTENTRY1234567890',
|
||||
parentId: null,
|
||||
timestamp: new Date().toISOString(),
|
||||
message: {
|
||||
role: 'user',
|
||||
content: 'Check this rectangle markup on video',
|
||||
timestamp: Date.now(),
|
||||
},
|
||||
}
|
||||
|
||||
await storage.appendEntry(userEntry)
|
||||
|
||||
// Verify DatabaseSessionStorage persisted entry with details.id = entry.id
|
||||
const dbEntry = await prisma.agentSessionEntry.findUnique({
|
||||
where: { id: '01JTESTENTRY1234567890' },
|
||||
})
|
||||
expect(dbEntry).toBeDefined()
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const details = (dbEntry?.data as any)?.details
|
||||
expect(details.id).toBe('01JTESTENTRY1234567890')
|
||||
expect(details.position).toEqual({ type: 'time', seconds: 12.34 })
|
||||
expect(details.annotations).toHaveLength(1)
|
||||
|
||||
// Now resolveAnnotationsById directly with the entry id and matching asset.id
|
||||
const result = await resolveAnnotationsById(asset.id, '01JTESTENTRY1234567890')
|
||||
expect(result.timestamp).toBe(12.34)
|
||||
expect(result.annotations).toEqual([
|
||||
{
|
||||
type: 'rectangle',
|
||||
x: 100,
|
||||
y: 200,
|
||||
width: 50,
|
||||
height: 50,
|
||||
},
|
||||
])
|
||||
})
|
||||
|
||||
it('throws an error when AgentSessionEntry belongs to a different asset', async () => {
|
||||
const user = await prisma.user.create({
|
||||
data: { name: 'User', email: 'user3@test.com', password: 'pw' },
|
||||
})
|
||||
const team = await prisma.team.create({
|
||||
data: { name: 'Team' },
|
||||
})
|
||||
const project = await prisma.project.create({
|
||||
data: { name: 'Project', teamId: team.id },
|
||||
})
|
||||
const assetA = await prisma.asset.create({
|
||||
data: { name: 'chatA.mp4', type: 'file', projectId: project.id, status: 'uploaded' },
|
||||
})
|
||||
const assetB = await prisma.asset.create({
|
||||
data: { name: 'chatB.mp4', type: 'file', projectId: project.id, status: 'uploaded' },
|
||||
})
|
||||
const agentUser = await prisma.user.create({
|
||||
data: { name: 'Bot User', email: 'bot2@example.com', type: 'agent' },
|
||||
})
|
||||
const agent = await prisma.agent.create({
|
||||
data: {
|
||||
id: agentUser.id,
|
||||
teamId: team.id,
|
||||
type: 'chat',
|
||||
config: { provider: 'test-provider', model: 'test-model' },
|
||||
},
|
||||
})
|
||||
|
||||
const storage = await DatabaseSessionStorage.create({
|
||||
agentId: agent.id,
|
||||
userId: user.id,
|
||||
assetId: assetB.id,
|
||||
})
|
||||
storage.currentMessageContext = {
|
||||
currentAsset: { id: assetB.id, name: assetB.name, type: 'file', path: assetB.name },
|
||||
annotation: true,
|
||||
annotations: [{ type: 'box' }],
|
||||
}
|
||||
const userEntry: SessionTreeEntry = {
|
||||
type: 'message',
|
||||
id: '01JENTRYONASSETB123456',
|
||||
parentId: null,
|
||||
timestamp: new Date().toISOString(),
|
||||
message: { role: 'user', content: 'Markup on B', timestamp: Date.now() },
|
||||
}
|
||||
await storage.appendEntry(userEntry)
|
||||
|
||||
await expect(resolveAnnotationsById(assetA.id, '01JENTRYONASSETB123456')).rejects.toThrow(
|
||||
`Annotation "01JENTRYONASSETB123456" belongs to asset "${assetB.id}", not target asset "${assetA.id}".`,
|
||||
)
|
||||
})
|
||||
|
||||
it('throws an error if annotationId does not match any record', async () => {
|
||||
await expect(resolveAnnotationsById('asset-1', 'non_existent_id')).rejects.toThrow(
|
||||
'Annotation with ID "non_existent_id" not found.',
|
||||
)
|
||||
})
|
||||
})
|
||||
@@ -0,0 +1,52 @@
|
||||
import { prisma } from '@shumai/db'
|
||||
import type { ShumaiMessageContext } from '@shumai/dtos'
|
||||
|
||||
export async function resolveAnnotationsById(
|
||||
assetId: string,
|
||||
annotationId?: string | null,
|
||||
): Promise<{ annotations: PrismaJson.AnnotationList | null; timestamp: number | null }> {
|
||||
if (!annotationId) {
|
||||
return { annotations: null, timestamp: null }
|
||||
}
|
||||
|
||||
// 1. Check AssetComment table (Comments Mode)
|
||||
const comment = await prisma.assetComment.findUnique({
|
||||
where: { id: annotationId },
|
||||
select: { assetId: true, annotation: true, second: true },
|
||||
})
|
||||
if (comment) {
|
||||
if (comment.assetId !== assetId) {
|
||||
throw new Error(
|
||||
`Annotation "${annotationId}" belongs to asset "${comment.assetId}", not target asset "${assetId}".`,
|
||||
)
|
||||
}
|
||||
const list = comment.annotation
|
||||
const annotations =
|
||||
Array.isArray(list) && list.length > 0 ? (list as PrismaJson.AnnotationList) : null
|
||||
return { annotations, timestamp: comment.second }
|
||||
}
|
||||
|
||||
// 2. Check AgentSessionEntry table (1-on-1 Chat Mode)
|
||||
const entry = await prisma.agentSessionEntry.findUnique({
|
||||
where: { id: annotationId },
|
||||
select: { assetId: true, data: true },
|
||||
})
|
||||
if (entry) {
|
||||
const details = (entry.data as Record<string, unknown> | null)?.details as
|
||||
| ShumaiMessageContext
|
||||
| undefined
|
||||
const entryAssetId = entry.assetId || details?.currentAsset?.id
|
||||
if (entryAssetId && entryAssetId !== assetId) {
|
||||
throw new Error(
|
||||
`Annotation "${annotationId}" belongs to asset "${entryAssetId}", not target asset "${assetId}".`,
|
||||
)
|
||||
}
|
||||
const list = details?.annotations
|
||||
const annotations =
|
||||
Array.isArray(list) && list.length > 0 ? (list as unknown as PrismaJson.AnnotationList) : null
|
||||
const timestamp = details?.position?.type === 'time' ? details.position.seconds : null
|
||||
return { annotations, timestamp }
|
||||
}
|
||||
|
||||
throw new Error(`Annotation with ID "${annotationId}" not found.`)
|
||||
}
|
||||
@@ -1,7 +1,10 @@
|
||||
import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest'
|
||||
import { createCreateFileTool } from './create-file'
|
||||
import { fieldsToTypeBoxSchema } from '../index'
|
||||
import { s3Service } from '@shumai/core/src/s3/s3'
|
||||
import { executeAgentToolWorkflow } from './utils'
|
||||
import { assetService } from '@shumai/core/src/asset/asset'
|
||||
import { authzService } from '@shumai/core/src/authz/authz'
|
||||
import { Value } from 'typebox/value'
|
||||
import * as fs from 'fs'
|
||||
import * as os from 'os'
|
||||
import * as path from 'path'
|
||||
@@ -13,8 +16,20 @@ vi.mock('@shumai/core/src/s3/s3', () => ({
|
||||
},
|
||||
}))
|
||||
|
||||
vi.mock('./utils', () => ({
|
||||
executeAgentToolWorkflow: vi.fn().mockResolvedValue({ id: 'file-1', name: 'test', type: 'file' }),
|
||||
vi.mock('@shumai/core/src/authz/authz', () => ({
|
||||
authzService: {
|
||||
hasPermission: vi.fn().mockResolvedValue(undefined),
|
||||
},
|
||||
Permission: { Edit: 'edit', Read: 'read' },
|
||||
ResourceType: { Asset: 'asset' },
|
||||
}))
|
||||
|
||||
vi.mock('@shumai/core/src/asset/asset', () => ({
|
||||
assetService: {
|
||||
createFile: vi
|
||||
.fn()
|
||||
.mockResolvedValue({ id: 'file-1', name: 'test', type: 'file', sizeByte: 100 }),
|
||||
},
|
||||
}))
|
||||
|
||||
describe('createCreateFileTool', () => {
|
||||
@@ -44,7 +59,7 @@ describe('createCreateFileTool', () => {
|
||||
const filePath = createTempFile('# Hello from disk', 'create-file-test.md')
|
||||
|
||||
const tool = createCreateFileTool('user-1')
|
||||
const result = await tool.execute('call-1', { parent: 'folder-1', path: filePath })
|
||||
const result = await tool.execute('call-1', { parent: 'folder-1', path: filePath, data: null })
|
||||
|
||||
expect(s3Service.uploadFileToKey).toHaveBeenCalledTimes(1)
|
||||
expect(s3Service.putObject).not.toHaveBeenCalled()
|
||||
@@ -54,62 +69,127 @@ describe('createCreateFileTool', () => {
|
||||
expect(s3Key).toMatch(/^files\/.+\.md$/)
|
||||
expect(uploadArgs[2]).toBe('text/markdown')
|
||||
|
||||
expect(executeAgentToolWorkflow).toHaveBeenCalledWith({
|
||||
toolName: 'create_file',
|
||||
args: {
|
||||
parent: 'folder-1',
|
||||
s3Key,
|
||||
name: 'create-file-test.md',
|
||||
size: Buffer.byteLength('# Hello from disk', 'utf-8'),
|
||||
contentType: 'text/markdown',
|
||||
},
|
||||
userId: 'user-1',
|
||||
assetId: 'folder-1',
|
||||
expect(authzService.hasPermission).toHaveBeenCalledWith({
|
||||
user: { id: 'user-1' },
|
||||
permission: 'edit',
|
||||
type: 'asset',
|
||||
id: 'folder-1',
|
||||
})
|
||||
|
||||
expect(result.details).toEqual({ id: 'file-1', name: 'test', type: 'file' })
|
||||
expect(assetService.createFile).toHaveBeenCalledWith({
|
||||
parentId: 'folder-1',
|
||||
name: 'create-file-test.md',
|
||||
key: s3Key,
|
||||
sizeByte: Buffer.byteLength('# Hello from disk', 'utf-8'),
|
||||
contentType: 'text/markdown',
|
||||
creatorId: 'user-1',
|
||||
metadata: undefined,
|
||||
})
|
||||
|
||||
expect(result.details).toEqual({})
|
||||
expect(JSON.parse((result.content[0] as { text: string }).text)).toEqual({
|
||||
id: 'file-1',
|
||||
name: 'test',
|
||||
type: 'file',
|
||||
size: 100,
|
||||
})
|
||||
})
|
||||
|
||||
it('should forward the optional context to the agent tool workflow when provided', async () => {
|
||||
const filePath = createTempFile('# Hello from disk', 'create-file-context.md')
|
||||
it('should forward the metadata to assetService.createFile when provided', async () => {
|
||||
const filePath = createTempFile('# Hello from disk', 'create-file-metadata.md')
|
||||
const metadataSchema = fieldsToTypeBoxSchema([
|
||||
{ id: 'prompt', config: { name: 'Prompt', type: 'text' } },
|
||||
])
|
||||
|
||||
const tool = createCreateFileTool('user-1')
|
||||
const tool = createCreateFileTool('user-1', metadataSchema)
|
||||
await tool.execute('call-1', {
|
||||
parent: 'folder-1',
|
||||
path: filePath,
|
||||
context: 'Generated using gemini',
|
||||
data: null,
|
||||
metadata: { prompt: 'Generated using gemini' },
|
||||
})
|
||||
|
||||
expect(executeAgentToolWorkflow).toHaveBeenCalledWith(
|
||||
expect(assetService.createFile).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
args: expect.objectContaining({ context: 'Generated using gemini' }),
|
||||
metadata: { prompt: 'Generated using gemini' },
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
||||
it('should not include context in args when not provided', async () => {
|
||||
const filePath = createTempFile('# Hello from disk', 'create-file-no-context.md')
|
||||
it('should forward select and selectMulti newOption metadata', async () => {
|
||||
const filePath = createTempFile('# Hello from disk', 'create-file-new-option.md')
|
||||
const metadataSchema = fieldsToTypeBoxSchema([
|
||||
{
|
||||
id: 'provider',
|
||||
config: {
|
||||
name: 'Provider',
|
||||
type: 'select',
|
||||
select: { options: [{ id: 'openai', displayName: 'OpenAI', color: '#f43f5e' }] },
|
||||
},
|
||||
},
|
||||
{
|
||||
id: 'tags',
|
||||
config: {
|
||||
name: 'Tags',
|
||||
type: 'selectMulti',
|
||||
selectMulti: { options: [{ id: 'tag1', displayName: 'Tag 1', color: '#3b82f6' }] },
|
||||
},
|
||||
},
|
||||
])
|
||||
|
||||
const tool = createCreateFileTool('user-1')
|
||||
await tool.execute('call-1', { parent: 'folder-1', path: filePath })
|
||||
const tool = createCreateFileTool('user-1', metadataSchema)
|
||||
await tool.execute('call-1', {
|
||||
parent: 'folder-1',
|
||||
path: filePath,
|
||||
data: null,
|
||||
metadata: {
|
||||
provider: { newOption: { value: 'Kling' } },
|
||||
tags: ['tag1', { newOption: { value: 'Tag 2' } }],
|
||||
},
|
||||
})
|
||||
|
||||
const callArgs = vi.mocked(executeAgentToolWorkflow).mock.calls[0][0].args
|
||||
expect(callArgs).not.toHaveProperty('context')
|
||||
expect(assetService.createFile).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
metadata: {
|
||||
provider: { newOption: { value: 'Kling' } },
|
||||
tags: ['tag1', { newOption: { value: 'Tag 2' } }],
|
||||
},
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
||||
it('should not include metadata when metadata is null', async () => {
|
||||
const filePath = createTempFile('# Hello from disk', 'create-file-no-metadata.md')
|
||||
const metadataSchema = fieldsToTypeBoxSchema([
|
||||
{ id: 'prompt', config: { name: 'Prompt', type: 'text' } },
|
||||
])
|
||||
|
||||
const tool = createCreateFileTool('user-1', metadataSchema)
|
||||
await tool.execute('call-1', {
|
||||
parent: 'folder-1',
|
||||
path: filePath,
|
||||
data: null,
|
||||
metadata: null,
|
||||
})
|
||||
|
||||
const callArgs = vi.mocked(assetService.createFile).mock.calls[0][0]
|
||||
expect(callArgs.metadata).toBeUndefined()
|
||||
})
|
||||
|
||||
it('should throw when the local file does not exist', async () => {
|
||||
const tool = createCreateFileTool('user-1')
|
||||
await expect(
|
||||
tool.execute('call-1', { parent: 'folder-1', path: '/nonexistent/file.md' }),
|
||||
tool.execute('call-1', { parent: 'folder-1', path: '/nonexistent/file.md', data: null }),
|
||||
).rejects.toThrow('Local file not found at path: /nonexistent/file.md')
|
||||
expect(s3Service.uploadFileToKey).not.toHaveBeenCalled()
|
||||
expect(executeAgentToolWorkflow).not.toHaveBeenCalled()
|
||||
expect(assetService.createFile).not.toHaveBeenCalled()
|
||||
})
|
||||
|
||||
it('should create a file directly from name and content', async () => {
|
||||
const tool = createCreateFileTool('user-1')
|
||||
const result = await tool.execute('call-1', {
|
||||
parent: 'folder-1',
|
||||
path: null,
|
||||
data: { name: 'notes.md', content: '# Notes\n\nHello' },
|
||||
})
|
||||
|
||||
@@ -125,26 +205,30 @@ describe('createCreateFileTool', () => {
|
||||
expect(size).toBe(Buffer.byteLength('# Notes\n\nHello', 'utf-8'))
|
||||
expect(contentType).toBe('text/markdown')
|
||||
|
||||
expect(executeAgentToolWorkflow).toHaveBeenCalledWith({
|
||||
toolName: 'create_file',
|
||||
args: {
|
||||
parent: 'folder-1',
|
||||
s3Key,
|
||||
name: 'notes.md',
|
||||
size: Buffer.byteLength('# Notes\n\nHello', 'utf-8'),
|
||||
contentType: 'text/markdown',
|
||||
},
|
||||
userId: 'user-1',
|
||||
assetId: 'folder-1',
|
||||
expect(assetService.createFile).toHaveBeenCalledWith({
|
||||
parentId: 'folder-1',
|
||||
name: 'notes.md',
|
||||
key: s3Key,
|
||||
sizeByte: Buffer.byteLength('# Notes\n\nHello', 'utf-8'),
|
||||
contentType: 'text/markdown',
|
||||
creatorId: 'user-1',
|
||||
metadata: undefined,
|
||||
})
|
||||
|
||||
expect(result.details).toEqual({ id: 'file-1', name: 'test', type: 'file' })
|
||||
expect(result.details).toEqual({})
|
||||
expect(JSON.parse((result.content[0] as { text: string }).text)).toEqual({
|
||||
id: 'file-1',
|
||||
name: 'test',
|
||||
type: 'file',
|
||||
size: 100,
|
||||
})
|
||||
})
|
||||
|
||||
it('should default unknown extensions to text/plain when creating from content', async () => {
|
||||
const tool = createCreateFileTool('user-1')
|
||||
await tool.execute('call-1', {
|
||||
parent: 'folder-1',
|
||||
path: null,
|
||||
data: { name: 'script.ts', content: 'const x = 1' },
|
||||
})
|
||||
|
||||
@@ -162,6 +246,7 @@ describe('createCreateFileTool', () => {
|
||||
const tool = createCreateFileTool('user-1')
|
||||
await tool.execute('call-1', {
|
||||
parent: 'folder-1',
|
||||
path: null,
|
||||
data: { name: 'my/notes.md', content: 'hello' },
|
||||
})
|
||||
|
||||
@@ -174,18 +259,16 @@ describe('createCreateFileTool', () => {
|
||||
]
|
||||
expect(s3Key).toContain('my_notes.md')
|
||||
|
||||
expect(executeAgentToolWorkflow).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
args: expect.objectContaining({ name: 'my_notes.md' }),
|
||||
}),
|
||||
expect(assetService.createFile).toHaveBeenCalledWith(
|
||||
expect.objectContaining({ name: 'my_notes.md' }),
|
||||
)
|
||||
})
|
||||
|
||||
it('should throw when neither "path" nor "data" is provided', async () => {
|
||||
const tool = createCreateFileTool('user-1')
|
||||
await expect(tool.execute('call-1', { parent: 'folder-1' })).rejects.toThrow(
|
||||
'Provide exactly one of "path" (a local file) or "data" (name and content).',
|
||||
)
|
||||
await expect(
|
||||
tool.execute('call-1', { parent: 'folder-1', path: null, data: null }),
|
||||
).rejects.toThrow('Provide exactly one of "path" (a local file) or "data" (name and content).')
|
||||
})
|
||||
|
||||
it('should throw when both "path" and "data" are provided', async () => {
|
||||
@@ -199,6 +282,60 @@ describe('createCreateFileTool', () => {
|
||||
).rejects.toThrow('Provide exactly one of "path" (a local file) or "data" (name and content).')
|
||||
expect(s3Service.uploadFileToKey).not.toHaveBeenCalled()
|
||||
expect(s3Service.putObject).not.toHaveBeenCalled()
|
||||
expect(executeAgentToolWorkflow).not.toHaveBeenCalled()
|
||||
expect(assetService.createFile).not.toHaveBeenCalled()
|
||||
})
|
||||
|
||||
it('should expose a strict, all-required (nullable) metadata schema when fields are provided', () => {
|
||||
const metadataSchema = fieldsToTypeBoxSchema([
|
||||
{ id: 'prompt', config: { name: 'Prompt', type: 'text' } },
|
||||
{
|
||||
id: 'source',
|
||||
config: {
|
||||
name: 'Source',
|
||||
type: 'select',
|
||||
select: { options: [{ id: 'gemini', displayName: 'Gemini', color: '#ffffff' }] },
|
||||
},
|
||||
},
|
||||
{ id: 'rating', config: { name: 'Rating', type: 'rating' } },
|
||||
])
|
||||
|
||||
const tool = createCreateFileTool('user-1', metadataSchema)
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any -- inspecting the runtime schema shape of the dynamically-built tool
|
||||
const meta = (tool.parameters as any).properties.metadata
|
||||
// `metadata` is a nullable union: [strict object, null]
|
||||
const metaObject = meta.anyOf[0]
|
||||
|
||||
expect(meta).toBeDefined()
|
||||
expect(metaObject.required).toEqual(['prompt', 'source', 'rating'])
|
||||
expect(metaObject.additionalProperties).toBe(false)
|
||||
expect(metaObject.properties.prompt.anyOf[0].type).toBe('string')
|
||||
expect(metaObject.properties.prompt.anyOf[1].type).toBe('null')
|
||||
expect(metaObject.properties.source.anyOf[0].anyOf[0].enum).toEqual(['gemini'])
|
||||
expect(metaObject.properties.rating.anyOf[0].type).toBe('number')
|
||||
|
||||
// Every field must be present (use null when unknown); unknown keys and bad enums are rejected
|
||||
expect(Value.Check(meta, { prompt: 'hello', source: 'gemini', rating: 5 })).toBe(true)
|
||||
expect(
|
||||
Value.Check(meta, {
|
||||
prompt: 'hello',
|
||||
source: { newOption: { value: 'kling' } },
|
||||
rating: 5,
|
||||
}),
|
||||
).toBe(true)
|
||||
expect(Value.Check(meta, { prompt: null, source: null, rating: null })).toBe(true)
|
||||
expect(Value.Check(meta, { prompt: 'hello', source: null, rating: null })).toBe(true)
|
||||
expect(Value.Check(meta, { prompt: 'hello' })).toBe(false)
|
||||
expect(
|
||||
Value.Check(meta, { prompt: 'hello', source: 'gemini', rating: 5, unknownKey: 'x' }),
|
||||
).toBe(false)
|
||||
expect(Value.Check(meta, { prompt: 'hello', source: 'not-an-option', rating: null })).toBe(
|
||||
false,
|
||||
)
|
||||
})
|
||||
|
||||
it('should omit the metadata parameter when no schema is provided', () => {
|
||||
const tool = createCreateFileTool('user-1')
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any -- inspecting the runtime schema shape of the dynamically-built tool
|
||||
expect((tool.parameters as any).properties.metadata).toBeUndefined()
|
||||
})
|
||||
})
|
||||
|
||||
@@ -1,69 +1,81 @@
|
||||
import { type AgentTool } from '@earendil-works/pi-agent-core'
|
||||
import { assetService } from '@shumai/core/src/asset/asset'
|
||||
import { authzService, Permission, ResourceType } from '@shumai/core/src/authz/authz'
|
||||
import { s3Service } from '@shumai/core/src/s3/s3'
|
||||
import { getFileMimeType, readFileMimeType } from '@shumai/core/src/utils/file-mime'
|
||||
import { sanitizeFilename } from '@shumai/core/src/utils/filename'
|
||||
import { Type } from '@sinclair/typebox'
|
||||
import { type User } from '@shumai/db'
|
||||
import { Type, type TSchema } from 'typebox'
|
||||
import * as fs from 'fs'
|
||||
import * as path from 'path'
|
||||
import { ulid } from 'ulid'
|
||||
import { executeAgentToolWorkflow } from './utils'
|
||||
|
||||
const createFileSchema = Type.Object({
|
||||
parent: Type.String({
|
||||
description: 'The parent folder ID under which to create the file. This parameter is required.',
|
||||
}),
|
||||
path: Type.Optional(
|
||||
Type.String({
|
||||
description:
|
||||
'The absolute or relative local path to an existing file on disk. Provide either this or "data", but not both.',
|
||||
}),
|
||||
),
|
||||
data: Type.Optional(
|
||||
Type.Object({
|
||||
name: Type.String({
|
||||
minLength: 1,
|
||||
description:
|
||||
'The desired name for the new file, including its extension (e.g. "notes.md").',
|
||||
}),
|
||||
content: Type.String({
|
||||
description: 'The full content of the file as a plain string.',
|
||||
}),
|
||||
}),
|
||||
),
|
||||
context: Type.Optional(
|
||||
Type.String({
|
||||
description:
|
||||
'Optional short context about this file and how it was generated (max 50 words, e.g. "Generated using gemini"). ' +
|
||||
'Passed to the AI metadata autofill workflow to fill fields that cannot be determined from file content alone. ' +
|
||||
'Check autofillable fields with list_autofill_fields first.',
|
||||
}),
|
||||
),
|
||||
})
|
||||
interface CreateFileToolParams {
|
||||
parent: string
|
||||
path: string | null
|
||||
data: { name: string; content: string } | null
|
||||
metadata?: Record<string, unknown> | null
|
||||
}
|
||||
|
||||
function assertExactlyOneSource(params: {
|
||||
path?: string
|
||||
data?: { name: string; content: string }
|
||||
}) {
|
||||
const hasPath = params.path !== undefined
|
||||
const hasData = params.data !== undefined
|
||||
function assertExactlyOneSource(params: CreateFileToolParams) {
|
||||
const hasPath = params.path !== null
|
||||
const hasData = params.data !== null
|
||||
if (hasPath === hasData) {
|
||||
throw new Error('Provide exactly one of "path" (a local file) or "data" (name and content).')
|
||||
}
|
||||
return hasPath ? params.path! : params.data!
|
||||
}
|
||||
|
||||
export function createCreateFileTool(userId: string): AgentTool<typeof createFileSchema> {
|
||||
return {
|
||||
export function createCreateFileTool(userId: string, metadataSchema?: TSchema): AgentTool {
|
||||
const createFileSchema = Type.Object(
|
||||
{
|
||||
parent: Type.String({
|
||||
description:
|
||||
'The parent folder ID under which to create the file. This parameter is required.',
|
||||
}),
|
||||
path: Type.Union([
|
||||
Type.String({
|
||||
description:
|
||||
'The absolute or relative local path to an existing file on disk. Provide a value here OR in "data", but not both. Use null if you are providing "data".',
|
||||
}),
|
||||
Type.Null(),
|
||||
]),
|
||||
data: Type.Union([
|
||||
Type.Object(
|
||||
{
|
||||
name: Type.String({
|
||||
minLength: 1,
|
||||
description:
|
||||
'The desired name for the new file, including its extension (e.g. "notes.md").',
|
||||
}),
|
||||
content: Type.String({
|
||||
description: 'The full content of the file as a plain string.',
|
||||
}),
|
||||
},
|
||||
{ additionalProperties: false },
|
||||
),
|
||||
Type.Null(),
|
||||
]),
|
||||
...(metadataSchema ? { metadata: Type.Union([metadataSchema, Type.Null()]) } : {}),
|
||||
},
|
||||
{ additionalProperties: false },
|
||||
)
|
||||
|
||||
const tool: AgentTool = {
|
||||
name: 'create_file',
|
||||
label: 'Create File',
|
||||
description:
|
||||
'Create a new file under a folder. You MUST choose exactly ONE creation method: ' +
|
||||
'(1) provide "path" to upload an existing local file, OR ' +
|
||||
'(2) provide "data" with name and content to create a new text file. ' +
|
||||
'Never provide both "path" and "data" together. Never omit both.',
|
||||
'Set the unused parameter to null. ' +
|
||||
'The optional "metadata" parameter accepts only the CREATION_CONTEXT fields declared in its schema; never invent field keys, and use null for fields you do not know.',
|
||||
parameters: createFileSchema,
|
||||
execute: async (_toolCallId, params) => {
|
||||
const source = assertExactlyOneSource(params)
|
||||
// The harness validates tool args against `createFileSchema` before calling
|
||||
// execute, so `params` is guaranteed to match this shape.
|
||||
const p = params as CreateFileToolParams
|
||||
const source = assertExactlyOneSource(p)
|
||||
|
||||
let name: string
|
||||
let size: number
|
||||
@@ -95,23 +107,35 @@ export function createCreateFileTool(userId: string): AgentTool<typeof createFil
|
||||
await s3Service.putObject(process.env.S3_BUCKET || 'shumai', s3Key, content, size, mimeType)
|
||||
}
|
||||
|
||||
const result = await executeAgentToolWorkflow({
|
||||
toolName: 'create_file',
|
||||
args: {
|
||||
parent: params.parent,
|
||||
s3Key,
|
||||
name,
|
||||
size,
|
||||
contentType: mimeType,
|
||||
...(params.context ? { context: params.context } : {}),
|
||||
},
|
||||
userId,
|
||||
assetId: params.parent,
|
||||
await authzService.hasPermission({
|
||||
user: { id: userId } as User,
|
||||
permission: Permission.Edit,
|
||||
type: ResourceType.Asset,
|
||||
id: p.parent,
|
||||
})
|
||||
|
||||
const asset = await assetService.createFile({
|
||||
parentId: p.parent,
|
||||
name,
|
||||
key: s3Key,
|
||||
sizeByte: size,
|
||||
contentType: mimeType,
|
||||
creatorId: userId,
|
||||
metadata: p.metadata ?? undefined,
|
||||
})
|
||||
|
||||
const result = {
|
||||
id: asset.id,
|
||||
name: asset.name,
|
||||
type: asset.type,
|
||||
size: Number(asset.sizeByte),
|
||||
}
|
||||
|
||||
return {
|
||||
content: [{ type: 'text', text: JSON.stringify(result, null, 2) }],
|
||||
details: result,
|
||||
details: {},
|
||||
}
|
||||
},
|
||||
}
|
||||
return tool
|
||||
}
|
||||
|
||||
@@ -0,0 +1,56 @@
|
||||
import { describe, it, expect, vi, beforeEach } from 'vitest'
|
||||
import { createCreateFolderTool } from './create-folder'
|
||||
import { assetService } from '@shumai/core/src/asset/asset'
|
||||
import { authzService } from '@shumai/core/src/authz/authz'
|
||||
|
||||
vi.mock('@shumai/core/src/authz/authz', () => ({
|
||||
authzService: {
|
||||
hasPermission: vi.fn().mockResolvedValue(undefined),
|
||||
},
|
||||
Permission: { Edit: 'edit', Read: 'read' },
|
||||
ResourceType: { Asset: 'asset' },
|
||||
}))
|
||||
|
||||
vi.mock('@shumai/core/src/asset/asset', () => ({
|
||||
assetService: {
|
||||
createAsset: vi.fn().mockResolvedValue({
|
||||
id: 'folder-1',
|
||||
name: 'New Folder',
|
||||
type: 'folder',
|
||||
sizeByte: 0,
|
||||
}),
|
||||
},
|
||||
}))
|
||||
|
||||
describe('createCreateFolderTool', () => {
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks()
|
||||
})
|
||||
|
||||
it('checks edit permission and calls assetService.createAsset with folder type', async () => {
|
||||
const tool = createCreateFolderTool('user-1')
|
||||
const result = await tool.execute('call-1', { parent: 'root-folder', name: 'New Folder' })
|
||||
|
||||
expect(authzService.hasPermission).toHaveBeenCalledWith({
|
||||
user: { id: 'user-1' },
|
||||
permission: 'edit',
|
||||
type: 'asset',
|
||||
id: 'root-folder',
|
||||
})
|
||||
|
||||
expect(assetService.createAsset).toHaveBeenCalledWith({
|
||||
name: 'New Folder',
|
||||
parentId: 'root-folder',
|
||||
type: 'folder',
|
||||
creatorId: 'user-1',
|
||||
})
|
||||
|
||||
expect(result.details).toEqual({})
|
||||
expect(JSON.parse((result.content[0] as { text: string }).text)).toEqual({
|
||||
id: 'folder-1',
|
||||
name: 'New Folder',
|
||||
type: 'folder',
|
||||
size: 0,
|
||||
})
|
||||
})
|
||||
})
|
||||
@@ -1,6 +1,8 @@
|
||||
import { Type } from '@sinclair/typebox'
|
||||
import { Type } from 'typebox'
|
||||
import { type AgentTool } from '@earendil-works/pi-agent-core'
|
||||
import { executeAgentToolWorkflow } from './utils'
|
||||
import { assetService } from '@shumai/core/src/asset/asset'
|
||||
import { authzService, Permission, ResourceType } from '@shumai/core/src/authz/authz'
|
||||
import { type User } from '@shumai/db'
|
||||
|
||||
const createFolderSchema = Type.Object({
|
||||
parent: Type.String({
|
||||
@@ -19,15 +21,30 @@ export function createCreateFolderTool(userId: string): AgentTool<typeof createF
|
||||
description: 'Create a new folder in a specified parent folder.',
|
||||
parameters: createFolderSchema,
|
||||
execute: async (_toolCallId, params) => {
|
||||
const result = await executeAgentToolWorkflow({
|
||||
toolName: 'create_folder',
|
||||
args: params,
|
||||
userId,
|
||||
assetId: params.parent,
|
||||
await authzService.hasPermission({
|
||||
user: { id: userId } as User,
|
||||
permission: Permission.Edit,
|
||||
type: ResourceType.Asset,
|
||||
id: params.parent,
|
||||
})
|
||||
|
||||
const newFolder = await assetService.createAsset({
|
||||
name: params.name,
|
||||
parentId: params.parent,
|
||||
type: 'folder',
|
||||
creatorId: userId,
|
||||
})
|
||||
|
||||
const result = {
|
||||
id: newFolder.id,
|
||||
name: newFolder.name,
|
||||
type: newFolder.type,
|
||||
size: Number(newFolder.sizeByte),
|
||||
}
|
||||
|
||||
return {
|
||||
content: [{ type: 'text', text: JSON.stringify(result, null, 2) }],
|
||||
details: result,
|
||||
details: {},
|
||||
}
|
||||
},
|
||||
}
|
||||
|
||||
@@ -1,7 +1,10 @@
|
||||
import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest'
|
||||
import { createCreateVersionTool } from './create-version'
|
||||
import { fieldsToTypeBoxSchema } from '../index'
|
||||
import { s3Service } from '@shumai/core/src/s3/s3'
|
||||
import { executeAgentToolWorkflow } from './utils'
|
||||
import { assetService } from '@shumai/core/src/asset/asset'
|
||||
import { authzService } from '@shumai/core/src/authz/authz'
|
||||
import { Value } from 'typebox/value'
|
||||
import * as fs from 'fs'
|
||||
import * as os from 'os'
|
||||
import * as path from 'path'
|
||||
@@ -12,8 +15,20 @@ vi.mock('@shumai/core/src/s3/s3', () => ({
|
||||
},
|
||||
}))
|
||||
|
||||
vi.mock('./utils', () => ({
|
||||
executeAgentToolWorkflow: vi.fn().mockResolvedValue({ id: 'file-1', name: 'v2', type: 'file' }),
|
||||
vi.mock('@shumai/core/src/authz/authz', () => ({
|
||||
authzService: {
|
||||
hasPermission: vi.fn().mockResolvedValue(undefined),
|
||||
},
|
||||
Permission: { Edit: 'edit', Read: 'read' },
|
||||
ResourceType: { Asset: 'asset' },
|
||||
}))
|
||||
|
||||
vi.mock('@shumai/core/src/asset/asset', () => ({
|
||||
assetService: {
|
||||
createVersion: vi
|
||||
.fn()
|
||||
.mockResolvedValue({ id: 'file-1', name: 'v2', type: 'file', sizeByte: 100 }),
|
||||
},
|
||||
}))
|
||||
|
||||
describe('createCreateVersionTool', () => {
|
||||
@@ -39,7 +54,7 @@ describe('createCreateVersionTool', () => {
|
||||
return filePath
|
||||
}
|
||||
|
||||
it('should upload a local file and create a version via the agent tool workflow', async () => {
|
||||
it('should upload a local file and create a version via assetService.createVersion', async () => {
|
||||
const filePath = createTempFile('# Hello from disk', 'create-version-test.md')
|
||||
|
||||
const tool = createCreateVersionTool('user-1')
|
||||
@@ -51,47 +66,104 @@ describe('createCreateVersionTool', () => {
|
||||
expect(s3Key).toMatch(/^files\/.+\.md$/)
|
||||
expect(uploadArgs[2]).toBe('text/markdown')
|
||||
|
||||
expect(executeAgentToolWorkflow).toHaveBeenCalledWith({
|
||||
toolName: 'create_version',
|
||||
args: {
|
||||
parent: 'file-1',
|
||||
s3Key,
|
||||
name: 'create-version-test.md',
|
||||
size: Buffer.byteLength('# Hello from disk', 'utf-8'),
|
||||
contentType: 'text/markdown',
|
||||
},
|
||||
userId: 'user-1',
|
||||
assetId: 'file-1',
|
||||
expect(authzService.hasPermission).toHaveBeenCalledWith({
|
||||
user: { id: 'user-1' },
|
||||
permission: 'edit',
|
||||
type: 'asset',
|
||||
id: 'file-1',
|
||||
})
|
||||
|
||||
expect(result.details).toEqual({ id: 'file-1', name: 'v2', type: 'file' })
|
||||
expect(assetService.createVersion).toHaveBeenCalledWith({
|
||||
parentId: 'file-1',
|
||||
name: 'create-version-test.md',
|
||||
key: s3Key,
|
||||
sizeByte: Buffer.byteLength('# Hello from disk', 'utf-8'),
|
||||
contentType: 'text/markdown',
|
||||
creatorId: 'user-1',
|
||||
metadata: undefined,
|
||||
})
|
||||
|
||||
expect(result.details).toEqual({})
|
||||
expect(JSON.parse((result.content[0] as { text: string }).text)).toEqual({
|
||||
id: 'file-1',
|
||||
name: 'v2',
|
||||
type: 'file',
|
||||
size: 100,
|
||||
})
|
||||
})
|
||||
|
||||
it('should forward the optional context to the agent tool workflow when provided', async () => {
|
||||
const filePath = createTempFile('# Hello from disk', 'create-version-context.md')
|
||||
it('should forward the metadata to assetService.createVersion when provided', async () => {
|
||||
const filePath = createTempFile('# Hello from disk', 'create-version-metadata.md')
|
||||
const metadataSchema = fieldsToTypeBoxSchema([
|
||||
{ id: 'prompt', config: { name: 'Prompt', type: 'text' } },
|
||||
])
|
||||
|
||||
const tool = createCreateVersionTool('user-1')
|
||||
const tool = createCreateVersionTool('user-1', metadataSchema)
|
||||
await tool.execute('call-1', {
|
||||
parent: 'file-1',
|
||||
path: filePath,
|
||||
context: 'Generated using gemini',
|
||||
metadata: { prompt: 'Generated using gemini' },
|
||||
})
|
||||
|
||||
expect(executeAgentToolWorkflow).toHaveBeenCalledWith(
|
||||
expect(assetService.createVersion).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
args: expect.objectContaining({ context: 'Generated using gemini' }),
|
||||
metadata: { prompt: 'Generated using gemini' },
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
||||
it('should not include context in args when not provided', async () => {
|
||||
const filePath = createTempFile('# Hello from disk', 'create-version-no-context.md')
|
||||
it('should forward select and selectMulti newOption metadata', async () => {
|
||||
const filePath = createTempFile('# Hello from disk', 'create-version-new-option.md')
|
||||
const metadataSchema = fieldsToTypeBoxSchema([
|
||||
{
|
||||
id: 'provider',
|
||||
config: {
|
||||
name: 'Provider',
|
||||
type: 'select',
|
||||
select: { options: [{ id: 'openai', displayName: 'OpenAI', color: '#f43f5e' }] },
|
||||
},
|
||||
},
|
||||
{
|
||||
id: 'tags',
|
||||
config: {
|
||||
name: 'Tags',
|
||||
type: 'selectMulti',
|
||||
selectMulti: { options: [{ id: 'tag1', displayName: 'Tag 1', color: '#3b82f6' }] },
|
||||
},
|
||||
},
|
||||
])
|
||||
|
||||
const tool = createCreateVersionTool('user-1')
|
||||
await tool.execute('call-1', { parent: 'file-1', path: filePath })
|
||||
const tool = createCreateVersionTool('user-1', metadataSchema)
|
||||
await tool.execute('call-1', {
|
||||
parent: 'file-1',
|
||||
path: filePath,
|
||||
metadata: {
|
||||
provider: { newOption: { value: 'Kling' } },
|
||||
tags: ['tag1', { newOption: { value: 'Tag 2' } }],
|
||||
},
|
||||
})
|
||||
|
||||
const callArgs = vi.mocked(executeAgentToolWorkflow).mock.calls[0][0].args
|
||||
expect(callArgs).not.toHaveProperty('context')
|
||||
expect(assetService.createVersion).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
metadata: {
|
||||
provider: { newOption: { value: 'Kling' } },
|
||||
tags: ['tag1', { newOption: { value: 'Tag 2' } }],
|
||||
},
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
||||
it('should not include metadata when metadata is null', async () => {
|
||||
const filePath = createTempFile('# Hello from disk', 'create-version-no-metadata.md')
|
||||
const metadataSchema = fieldsToTypeBoxSchema([
|
||||
{ id: 'prompt', config: { name: 'Prompt', type: 'text' } },
|
||||
])
|
||||
|
||||
const tool = createCreateVersionTool('user-1', metadataSchema)
|
||||
await tool.execute('call-1', { parent: 'file-1', path: filePath, metadata: null })
|
||||
|
||||
const callArgs = vi.mocked(assetService.createVersion).mock.calls[0][0]
|
||||
expect(callArgs.metadata).toBeUndefined()
|
||||
})
|
||||
|
||||
it('should throw when the local file does not exist', async () => {
|
||||
@@ -100,6 +172,36 @@ describe('createCreateVersionTool', () => {
|
||||
tool.execute('call-1', { parent: 'file-1', path: '/nonexistent/file.md' }),
|
||||
).rejects.toThrow('Local file not found at path: /nonexistent/file.md')
|
||||
expect(s3Service.uploadFileToKey).not.toHaveBeenCalled()
|
||||
expect(executeAgentToolWorkflow).not.toHaveBeenCalled()
|
||||
expect(assetService.createVersion).not.toHaveBeenCalled()
|
||||
})
|
||||
|
||||
it('should expose a strict, all-required (nullable) metadata schema when fields are provided', () => {
|
||||
const metadataSchema = fieldsToTypeBoxSchema([
|
||||
{ id: 'prompt', config: { name: 'Prompt', type: 'text' } },
|
||||
{ id: 'toggle', config: { name: 'Active', type: 'toggle' } },
|
||||
])
|
||||
|
||||
const tool = createCreateVersionTool('user-1', metadataSchema)
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any -- inspecting the runtime schema shape of the dynamically-built tool
|
||||
const meta = (tool.parameters as any).properties.metadata
|
||||
// `metadata` is a nullable union: [strict object, null]
|
||||
const metaObject = meta.anyOf[0]
|
||||
|
||||
expect(meta).toBeDefined()
|
||||
expect(metaObject.required).toEqual(['prompt', 'toggle'])
|
||||
expect(metaObject.additionalProperties).toBe(false)
|
||||
expect(metaObject.properties.prompt.anyOf[0].type).toBe('string')
|
||||
expect(metaObject.properties.prompt.anyOf[1].type).toBe('null')
|
||||
expect(metaObject.properties.toggle.anyOf[0].type).toBe('boolean')
|
||||
|
||||
expect(Value.Check(meta, { prompt: 'p', toggle: true })).toBe(true)
|
||||
expect(Value.Check(meta, { prompt: null, toggle: null })).toBe(true)
|
||||
expect(Value.Check(meta, { prompt: 'p', toggle: null, unknownKey: 'x' })).toBe(false)
|
||||
})
|
||||
|
||||
it('should omit the metadata parameter when no schema is provided', () => {
|
||||
const tool = createCreateVersionTool('user-1')
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any -- inspecting the runtime schema shape of the dynamically-built tool
|
||||
expect((tool.parameters as any).properties.metadata).toBeUndefined()
|
||||
})
|
||||
})
|
||||
|
||||
@@ -1,68 +1,90 @@
|
||||
import { Type } from '@sinclair/typebox'
|
||||
import { type AgentTool } from '@earendil-works/pi-agent-core'
|
||||
import { executeAgentToolWorkflow } from './utils'
|
||||
import * as fs from 'fs'
|
||||
import * as path from 'path'
|
||||
import { assetService } from '@shumai/core/src/asset/asset'
|
||||
import { authzService, Permission, ResourceType } from '@shumai/core/src/authz/authz'
|
||||
import { s3Service } from '@shumai/core/src/s3/s3'
|
||||
import { readFileMimeType } from '@shumai/core/src/utils/file-mime'
|
||||
import { ulid } from 'ulid'
|
||||
import { sanitizeFilename } from '@shumai/core/src/utils/filename'
|
||||
import { type User } from '@shumai/db'
|
||||
import { Type, type TSchema } from 'typebox'
|
||||
import * as fs from 'fs'
|
||||
import * as path from 'path'
|
||||
import { ulid } from 'ulid'
|
||||
|
||||
const createVersionSchema = Type.Object({
|
||||
parent: Type.String({
|
||||
description:
|
||||
'The parent file ID for which to create a new version. This parameter is required.',
|
||||
}),
|
||||
path: Type.String({
|
||||
description:
|
||||
'The absolute or relative local path to the file on disk. This parameter is required.',
|
||||
}),
|
||||
context: Type.Optional(
|
||||
Type.String({
|
||||
description:
|
||||
'Optional short context about this version and how it was generated (max 50 words, e.g. "Generated using gemini"). ' +
|
||||
'Passed to the AI metadata autofill workflow to fill fields that cannot be determined from file content alone. ' +
|
||||
'Check autofillable fields with list_autofill_fields first.',
|
||||
}),
|
||||
),
|
||||
})
|
||||
interface CreateVersionToolParams {
|
||||
parent: string
|
||||
path: string
|
||||
metadata?: Record<string, unknown> | null
|
||||
}
|
||||
|
||||
export function createCreateVersionTool(userId: string): AgentTool<typeof createVersionSchema> {
|
||||
return {
|
||||
export function createCreateVersionTool(userId: string, metadataSchema?: TSchema): AgentTool {
|
||||
const createVersionSchema = Type.Object(
|
||||
{
|
||||
parent: Type.String({
|
||||
description:
|
||||
'The parent file ID for which to create a new version. This parameter is required.',
|
||||
}),
|
||||
path: Type.String({
|
||||
description:
|
||||
'The absolute or relative local path to the file on disk. This parameter is required.',
|
||||
}),
|
||||
...(metadataSchema ? { metadata: Type.Union([metadataSchema, Type.Null()]) } : {}),
|
||||
},
|
||||
{ additionalProperties: false },
|
||||
)
|
||||
|
||||
const tool: AgentTool = {
|
||||
name: 'create_version',
|
||||
label: 'Create Version',
|
||||
description: 'Create a new version of an existing file from a local file path.',
|
||||
description:
|
||||
'Create a new version of an existing file from a local file path. ' +
|
||||
'The optional "metadata" parameter accepts only the CREATION_CONTEXT fields declared in its schema; never invent field keys, and use null for fields you do not know.',
|
||||
parameters: createVersionSchema,
|
||||
execute: async (_toolCallId, params) => {
|
||||
const absolutePath = path.resolve(process.cwd(), params.path)
|
||||
// The harness validates tool args against `createVersionSchema` before calling
|
||||
// execute, so `params` is guaranteed to match this shape.
|
||||
const p = params as CreateVersionToolParams
|
||||
const absolutePath = path.resolve(process.cwd(), p.path)
|
||||
if (!fs.existsSync(absolutePath)) {
|
||||
throw new Error(`Local file not found at path: ${params.path}`)
|
||||
throw new Error(`Local file not found at path: ${p.path}`)
|
||||
}
|
||||
|
||||
const fileSize = fs.statSync(absolutePath).size
|
||||
const mimeType = readFileMimeType(absolutePath)
|
||||
const name = path.basename(absolutePath)
|
||||
|
||||
// Generate compliant S3 key matching normal file upload format
|
||||
const s3Key = `files/${ulid()}/${sanitizeFilename(path.basename(absolutePath))}`
|
||||
const s3Key = `files/${ulid()}/${sanitizeFilename(name)}`
|
||||
await s3Service.uploadFileToKey(absolutePath, s3Key, mimeType)
|
||||
|
||||
const result = await executeAgentToolWorkflow({
|
||||
toolName: 'create_version',
|
||||
args: {
|
||||
parent: params.parent,
|
||||
s3Key,
|
||||
name: path.basename(absolutePath),
|
||||
size: fileSize,
|
||||
contentType: mimeType,
|
||||
...(params.context ? { context: params.context } : {}),
|
||||
},
|
||||
userId,
|
||||
assetId: params.parent,
|
||||
await authzService.hasPermission({
|
||||
user: { id: userId } as User,
|
||||
permission: Permission.Edit,
|
||||
type: ResourceType.Asset,
|
||||
id: p.parent,
|
||||
})
|
||||
|
||||
const asset = await assetService.createVersion({
|
||||
parentId: p.parent,
|
||||
name,
|
||||
key: s3Key,
|
||||
sizeByte: fileSize,
|
||||
contentType: mimeType,
|
||||
creatorId: userId,
|
||||
metadata: p.metadata ?? undefined,
|
||||
})
|
||||
|
||||
const result = {
|
||||
id: asset.id,
|
||||
name: asset.name,
|
||||
type: asset.type,
|
||||
size: Number(asset.sizeByte),
|
||||
}
|
||||
|
||||
return {
|
||||
content: [{ type: 'text', text: JSON.stringify(result, null, 2) }],
|
||||
details: result,
|
||||
details: {},
|
||||
}
|
||||
},
|
||||
}
|
||||
return tool
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest'
|
||||
import { createDownloadAssetTool } from './download-asset'
|
||||
import { prisma, type Asset } from '@shumai/db'
|
||||
import { createDownloadAssetTool, resolveAssetIdFromKey } from './download-asset'
|
||||
import { prisma, type Asset, type StorageKey } from '@shumai/db'
|
||||
import { s3Service } from '@shumai/core/src/s3/s3'
|
||||
import { authzService } from '@shumai/core/src/authz/authz'
|
||||
import * as fs from 'fs'
|
||||
@@ -13,6 +13,11 @@ vi.mock('@shumai/db', async (importOriginal) => {
|
||||
prisma: {
|
||||
asset: {
|
||||
findUnique: vi.fn(),
|
||||
findFirst: vi.fn(),
|
||||
},
|
||||
storageKey: {
|
||||
findFirst: vi.fn(),
|
||||
findUnique: vi.fn(),
|
||||
},
|
||||
},
|
||||
}
|
||||
@@ -51,119 +56,288 @@ describe('downloadAssetTool', () => {
|
||||
|
||||
it('should throw authorization error if user ID is empty', async () => {
|
||||
const tool = createDownloadAssetTool('')
|
||||
await expect(tool.execute('call-1', { assetId: 'asset-1' })).rejects.toThrow(
|
||||
await expect(tool.execute('call-1', { assetId: 'asset-1', key: null })).rejects.toThrow(
|
||||
'User ID is required for authorization.',
|
||||
)
|
||||
})
|
||||
|
||||
it('should throw error if asset not found', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue(null)
|
||||
|
||||
it('should throw error if both assetId and key are null', async () => {
|
||||
const tool = createDownloadAssetTool('user-1')
|
||||
await expect(tool.execute('call-1', { assetId: 'asset-1' })).rejects.toThrow(
|
||||
'Asset with ID asset-1 not found.',
|
||||
await expect(tool.execute('call-1', { assetId: null, key: null })).rejects.toThrow(
|
||||
'Provide exactly one of "assetId" (to download a workspace asset) or "key" (to download a specific S3 storage key). Set the unused parameter to null.',
|
||||
)
|
||||
})
|
||||
|
||||
it('should download proxy image to .pi directory when imageTranscodes is present', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'asset-img-1',
|
||||
name: 'sample_photo.jpg',
|
||||
storageKey: { key: 'raw/sample_photo.jpg' },
|
||||
media: {
|
||||
proxyType: 'image',
|
||||
imageTranscodes: [{ key: 'proxy/sample_photo.webp' }],
|
||||
},
|
||||
} as unknown as Asset)
|
||||
|
||||
vi.mocked(s3Service.getObject).mockResolvedValue({
|
||||
buffer: Buffer.from('fake-proxy-image-bytes'),
|
||||
contentType: 'image/webp',
|
||||
} as unknown as { buffer: Buffer; contentType: string })
|
||||
|
||||
it('should throw error if both assetId and key are provided', async () => {
|
||||
const tool = createDownloadAssetTool('user-1')
|
||||
const result = await tool.execute('call-1', { assetId: 'asset-img-1' })
|
||||
await expect(
|
||||
tool.execute('call-1', { assetId: 'asset-1', key: 'files/path/file.png' }),
|
||||
).rejects.toThrow(
|
||||
'Provide exactly one of "assetId" (to download a workspace asset) or "key" (to download a specific S3 storage key). Set the unused parameter to null.',
|
||||
)
|
||||
})
|
||||
|
||||
expect(authzService.hasPermission).toHaveBeenCalledWith({
|
||||
user: { id: 'user-1' },
|
||||
permission: 'Read',
|
||||
type: 'asset',
|
||||
id: 'asset-img-1',
|
||||
describe('Download by assetId', () => {
|
||||
it('should throw error if asset not found', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue(null)
|
||||
|
||||
const tool = createDownloadAssetTool('user-1')
|
||||
await expect(tool.execute('call-1', { assetId: 'asset-1', key: null })).rejects.toThrow(
|
||||
'Asset with ID asset-1 not found.',
|
||||
)
|
||||
})
|
||||
|
||||
expect(s3Service.getObject).toHaveBeenCalledWith('shumai', 'proxy/sample_photo.webp')
|
||||
it('should download proxy image to .pi directory when downloading by assetId', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'asset-img-1',
|
||||
name: 'sample_photo.jpg',
|
||||
storageKey: { key: 'raw/sample_photo.jpg' },
|
||||
media: {
|
||||
proxyType: 'image',
|
||||
imageTranscodes: [{ key: 'proxy/sample_photo.webp' }],
|
||||
},
|
||||
} as unknown as Asset)
|
||||
|
||||
const expectedPath = path.join(piDir, 'asset-img-1_sample_photo.jpg')
|
||||
createdFiles.push(expectedPath)
|
||||
vi.mocked(s3Service.getObject).mockResolvedValue({
|
||||
buffer: Buffer.from('fake-proxy-image-bytes'),
|
||||
contentType: 'image/webp',
|
||||
} as unknown as { buffer: Buffer; contentType: string })
|
||||
|
||||
expect(fs.existsSync(expectedPath)).toBe(true)
|
||||
expect(fs.readFileSync(expectedPath, 'utf-8')).toBe('fake-proxy-image-bytes')
|
||||
const tool = createDownloadAssetTool('user-1')
|
||||
const result = await tool.execute('call-1', { assetId: 'asset-img-1', key: null })
|
||||
|
||||
expect(result.details.filePath).toBe(path.join('.pi', 'asset-img-1_sample_photo.jpg'))
|
||||
expect(result.details.contentType).toBe('image/webp')
|
||||
expect((result.content[0] as { type: 'text'; text: string }).text).toContain(
|
||||
'Remember to delete this temporary file when finished.',
|
||||
)
|
||||
expect(authzService.hasPermission).toHaveBeenCalledWith({
|
||||
user: { id: 'user-1' },
|
||||
permission: 'Read',
|
||||
type: 'asset',
|
||||
id: 'asset-img-1',
|
||||
})
|
||||
|
||||
expect(s3Service.getObject).toHaveBeenCalledWith('shumai', 'proxy/sample_photo.webp')
|
||||
|
||||
const expectedPath = path.join(piDir, 'asset-img-1_sample_photo.jpg')
|
||||
createdFiles.push(expectedPath)
|
||||
|
||||
expect(fs.existsSync(expectedPath)).toBe(true)
|
||||
expect(fs.readFileSync(expectedPath, 'utf-8')).toBe('fake-proxy-image-bytes')
|
||||
|
||||
expect(result.details.filePath).toBe(path.join('.pi', 'asset-img-1_sample_photo.jpg'))
|
||||
expect(result.details.contentType).toBe('image/webp')
|
||||
expect((result.content[0] as { type: 'text'; text: string }).text).toContain(
|
||||
'Remember to delete this temporary file when finished.',
|
||||
)
|
||||
})
|
||||
|
||||
it('should resolve version_stack asset to its latest version file', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'stack-1',
|
||||
name: '',
|
||||
type: 'version_stack',
|
||||
storageKey: null,
|
||||
media: null,
|
||||
} as unknown as Asset)
|
||||
|
||||
vi.mocked(prisma.asset.findFirst).mockResolvedValue({
|
||||
id: 'file-ver-2',
|
||||
name: 'banana_pig.png',
|
||||
type: 'file',
|
||||
storageKey: { key: 'raw/banana_pig.png' },
|
||||
media: {
|
||||
proxyType: 'image',
|
||||
imageTranscodes: [{ key: 'proxy/banana_pig.webp' }],
|
||||
},
|
||||
} as unknown as Asset)
|
||||
|
||||
vi.mocked(s3Service.getObject).mockResolvedValue({
|
||||
buffer: Buffer.from('fake-version-bytes'),
|
||||
contentType: 'image/webp',
|
||||
} as unknown as { buffer: Buffer; contentType: string })
|
||||
|
||||
const tool = createDownloadAssetTool('user-1')
|
||||
const result = await tool.execute('call-1', { assetId: 'stack-1', key: null })
|
||||
|
||||
expect(prisma.asset.findFirst).toHaveBeenCalledWith({
|
||||
where: { parentId: 'stack-1', isDeleted: false },
|
||||
orderBy: { sortIndex: 'asc' },
|
||||
include: { storageKey: true },
|
||||
})
|
||||
|
||||
expect(s3Service.getObject).toHaveBeenCalledWith('shumai', 'proxy/banana_pig.webp')
|
||||
|
||||
const expectedPath = path.join(piDir, 'file-ver-2_banana_pig.png')
|
||||
createdFiles.push(expectedPath)
|
||||
|
||||
expect(fs.existsSync(expectedPath)).toBe(true)
|
||||
expect(result.details.name).toBe('banana_pig.png')
|
||||
})
|
||||
})
|
||||
|
||||
it('should download proxy video to .pi directory when videoTranscodes is present', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'asset-vid-1',
|
||||
name: 'video_test.mov',
|
||||
storageKey: { key: 'raw/video_test.mov' },
|
||||
media: {
|
||||
proxyType: 'video',
|
||||
videoTranscodes: [{ key: 'proxy/video_test.mp4' }],
|
||||
},
|
||||
} as unknown as Asset)
|
||||
describe('Download by S3 key and Authorization', () => {
|
||||
it('should reject keys that do not start with files/', async () => {
|
||||
const tool = createDownloadAssetTool('user-1')
|
||||
await expect(
|
||||
tool.execute('call-1', { assetId: null, key: 'avatars/user-1.png' }),
|
||||
).rejects.toThrow('Invalid storage key format: key must start with "files/"')
|
||||
})
|
||||
|
||||
vi.mocked(s3Service.getObject).mockResolvedValue({
|
||||
buffer: Buffer.from('fake-video-bytes'),
|
||||
contentType: 'video/mp4',
|
||||
} as unknown as { buffer: Buffer; contentType: string })
|
||||
it('should reject keys with path traversal (..)', async () => {
|
||||
const tool = createDownloadAssetTool('user-1')
|
||||
await expect(
|
||||
tool.execute('call-1', { assetId: null, key: 'files/../../etc/passwd' }),
|
||||
).rejects.toThrow('cannot contain ".."')
|
||||
})
|
||||
|
||||
const tool = createDownloadAssetTool('user-1')
|
||||
const result = await tool.execute('call-1', { assetId: 'asset-vid-1' })
|
||||
it('should reject keys with insufficient path segments', async () => {
|
||||
const tool = createDownloadAssetTool('user-1')
|
||||
await expect(tool.execute('call-1', { assetId: null, key: 'files/invalid' })).rejects.toThrow(
|
||||
'Invalid storage key format',
|
||||
)
|
||||
})
|
||||
|
||||
expect(s3Service.getObject).toHaveBeenCalledWith('shumai', 'proxy/video_test.mp4')
|
||||
it('should reject keys that do not belong to any valid asset in database', async () => {
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue(null)
|
||||
vi.mocked(prisma.storageKey.findFirst).mockResolvedValue(null)
|
||||
vi.mocked(prisma.storageKey.findUnique).mockResolvedValue(null)
|
||||
|
||||
const expectedPath = path.join(piDir, 'asset-vid-1_video_test.mov')
|
||||
createdFiles.push(expectedPath)
|
||||
const tool = createDownloadAssetTool('user-1')
|
||||
await expect(
|
||||
tool.execute('call-1', { assetId: null, key: 'files/nonexistent-id/shot.webp' }),
|
||||
).rejects.toThrow('does not belong to any valid asset or the asset has been deleted')
|
||||
})
|
||||
|
||||
expect(fs.existsSync(expectedPath)).toBe(true)
|
||||
expect(result.details.size).toBe(Buffer.from('fake-video-bytes').length)
|
||||
it('should reject download when user lacks read permission on the owning asset (cross-project protection)', async () => {
|
||||
// Key belongs to asset-in-other-project
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'asset-in-other-project',
|
||||
} as unknown as Asset)
|
||||
|
||||
// Authz rejects because user is in a different project/team
|
||||
vi.mocked(authzService.hasPermission).mockRejectedValue(
|
||||
new Error('User does not have Read permission on asset asset-in-other-project'),
|
||||
)
|
||||
|
||||
const tool = createDownloadAssetTool('user-1')
|
||||
await expect(
|
||||
tool.execute('call-1', {
|
||||
assetId: null,
|
||||
key: 'files/asset-in-other-project/screenshots/secret_frame.webp',
|
||||
}),
|
||||
).rejects.toThrow('User does not have Read permission on asset asset-in-other-project')
|
||||
|
||||
expect(authzService.hasPermission).toHaveBeenCalledWith({
|
||||
user: { id: 'user-1' },
|
||||
permission: 'Read',
|
||||
type: 'asset',
|
||||
id: 'asset-in-other-project',
|
||||
})
|
||||
expect(s3Service.getObject).not.toHaveBeenCalled()
|
||||
})
|
||||
|
||||
it('should authorize and download derived artifact key (files/<assetId>/...)', async () => {
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'ast-123',
|
||||
} as unknown as Asset)
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
|
||||
vi.mocked(s3Service.getObject).mockResolvedValue({
|
||||
buffer: Buffer.from('fake-screenshot-bytes'),
|
||||
contentType: 'image/webp',
|
||||
} as unknown as { buffer: Buffer; contentType: string })
|
||||
|
||||
const tool = createDownloadAssetTool('user-1')
|
||||
const result = await tool.execute('call-1', {
|
||||
assetId: null,
|
||||
key: 'files/ast-123/screenshots/shot_5.0s.webp',
|
||||
})
|
||||
|
||||
expect(authzService.hasPermission).toHaveBeenCalledWith({
|
||||
user: { id: 'user-1' },
|
||||
permission: 'Read',
|
||||
type: 'asset',
|
||||
id: 'ast-123',
|
||||
})
|
||||
|
||||
expect(s3Service.getObject).toHaveBeenCalledWith(
|
||||
'shumai',
|
||||
'files/ast-123/screenshots/shot_5.0s.webp',
|
||||
)
|
||||
|
||||
const expectedPath = path.join(piDir, 'shot_5.0s.webp')
|
||||
createdFiles.push(expectedPath)
|
||||
|
||||
expect(fs.existsSync(expectedPath)).toBe(true)
|
||||
expect(fs.readFileSync(expectedPath, 'utf-8')).toBe('fake-screenshot-bytes')
|
||||
|
||||
expect(result.details.filePath).toBe(path.join('.pi', 'shot_5.0s.webp'))
|
||||
expect(result.details.key).toBe('files/ast-123/screenshots/shot_5.0s.webp')
|
||||
expect(result.details.assetId).toBe('ast-123')
|
||||
expect(result.details.size).toBe(Buffer.from('fake-screenshot-bytes').length)
|
||||
})
|
||||
|
||||
it('should authorize and download original upload key (files/<uploadUlid>/...) via StorageKey', async () => {
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue(null)
|
||||
vi.mocked(prisma.storageKey.findFirst).mockResolvedValue({
|
||||
id: 'sk-1',
|
||||
key: 'files/upload-ulid-456/photo.png',
|
||||
assets: [{ id: 'asset-photo-1' }],
|
||||
} as unknown as StorageKey & { assets: Asset[] })
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
|
||||
vi.mocked(s3Service.getObject).mockResolvedValue({
|
||||
buffer: Buffer.from('fake-original-photo-bytes'),
|
||||
contentType: 'image/png',
|
||||
} as unknown as { buffer: Buffer; contentType: string })
|
||||
|
||||
const tool = createDownloadAssetTool('user-1')
|
||||
const result = await tool.execute('call-1', {
|
||||
assetId: null,
|
||||
key: 'files/upload-ulid-456/photo.png',
|
||||
})
|
||||
|
||||
expect(authzService.hasPermission).toHaveBeenCalledWith({
|
||||
user: { id: 'user-1' },
|
||||
permission: 'Read',
|
||||
type: 'asset',
|
||||
id: 'asset-photo-1',
|
||||
})
|
||||
|
||||
expect(s3Service.getObject).toHaveBeenCalledWith('shumai', 'files/upload-ulid-456/photo.png')
|
||||
|
||||
const expectedPath = path.join(piDir, 'photo.png')
|
||||
createdFiles.push(expectedPath)
|
||||
|
||||
expect(fs.existsSync(expectedPath)).toBe(true)
|
||||
expect(result.details.assetId).toBe('asset-photo-1')
|
||||
})
|
||||
})
|
||||
|
||||
it('should download original file to .pi directory even when pdfTranscode is present', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'asset-md-1',
|
||||
name: 'doc.md',
|
||||
storageKey: { key: 'raw/doc.md' },
|
||||
media: {
|
||||
proxyType: 'pdf',
|
||||
pdfTranscode: { key: 'proxy/doc.pdf' },
|
||||
original: { key: 'raw/doc.md' },
|
||||
},
|
||||
} as unknown as Asset)
|
||||
describe('resolveAssetIdFromKey helper unit tests', () => {
|
||||
it('resolves directly by asset ID', async () => {
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({ id: 'ast-999' } as unknown as Asset)
|
||||
const assetId = await resolveAssetIdFromKey('files/ast-999/pdf_pages/page_1.webp')
|
||||
expect(assetId).toBe('ast-999')
|
||||
})
|
||||
|
||||
vi.mocked(s3Service.getObject).mockResolvedValue({
|
||||
buffer: Buffer.from('# fake markdown bytes'),
|
||||
contentType: 'text/markdown',
|
||||
} as unknown as { buffer: Buffer; contentType: string })
|
||||
it('resolves via StorageKey prefix', async () => {
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue(null)
|
||||
vi.mocked(prisma.storageKey.findFirst).mockResolvedValue({
|
||||
assets: [{ id: 'ast-888' }],
|
||||
} as unknown as StorageKey & { assets: Asset[] })
|
||||
const assetId = await resolveAssetIdFromKey('files/ulid-777/document.pdf')
|
||||
expect(assetId).toBe('ast-888')
|
||||
})
|
||||
|
||||
const tool = createDownloadAssetTool('user-1')
|
||||
const result = await tool.execute('call-1', { assetId: 'asset-md-1' })
|
||||
|
||||
expect(s3Service.getObject).toHaveBeenCalledWith('shumai', 'raw/doc.md')
|
||||
|
||||
const expectedPath = path.join(piDir, 'asset-md-1_doc.md')
|
||||
createdFiles.push(expectedPath)
|
||||
|
||||
expect(fs.existsSync(expectedPath)).toBe(true)
|
||||
expect(result.details.contentType).toBe('text/markdown')
|
||||
it('resolves via exact StorageKey match', async () => {
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue(null)
|
||||
vi.mocked(prisma.storageKey.findFirst).mockResolvedValue(null)
|
||||
vi.mocked(prisma.storageKey.findUnique).mockResolvedValue({
|
||||
assets: [{ id: 'ast-777' }],
|
||||
} as unknown as StorageKey & { assets: Asset[] })
|
||||
const assetId = await resolveAssetIdFromKey('files/ulid-special/document.pdf')
|
||||
expect(assetId).toBe('ast-777')
|
||||
})
|
||||
})
|
||||
})
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import { Type } from '@sinclair/typebox'
|
||||
import { Type } from 'typebox'
|
||||
import { type AgentTool } from '@earendil-works/pi-agent-core'
|
||||
import { prisma, type User } from '@shumai/db'
|
||||
import { s3Service } from '@shumai/core/src/s3/s3'
|
||||
@@ -7,71 +7,107 @@ import { sanitizeFilename } from '@shumai/core/src/utils/filename'
|
||||
import * as fs from 'fs'
|
||||
import * as path from 'path'
|
||||
|
||||
const downloadAssetSchema = Type.Object({
|
||||
assetId: Type.String({
|
||||
description:
|
||||
'The asset ID of the workspace asset to download to local disk. This parameter is required.',
|
||||
}),
|
||||
})
|
||||
export const downloadAssetSchema = Type.Object(
|
||||
{
|
||||
assetId: Type.Union([
|
||||
Type.String({
|
||||
description:
|
||||
'The asset ID of the workspace asset to download to local disk, or null if providing "key".',
|
||||
}),
|
||||
Type.Null(),
|
||||
]),
|
||||
key: Type.Union([
|
||||
Type.String({
|
||||
description:
|
||||
'The storage S3 key of a specific media artifact (e.g. a screenshot or transcode key from read_asset) to download to local disk, or null if providing "assetId".',
|
||||
}),
|
||||
Type.Null(),
|
||||
]),
|
||||
},
|
||||
{ additionalProperties: false },
|
||||
)
|
||||
|
||||
export async function resolveAssetIdFromKey(key: string): Promise<string> {
|
||||
if (!key.startsWith('files/') || key.includes('..')) {
|
||||
throw new Error(
|
||||
'Invalid storage key format: key must start with "files/" and cannot contain "..".',
|
||||
)
|
||||
}
|
||||
|
||||
const segments = key.split('/')
|
||||
if (segments.length < 3) {
|
||||
throw new Error(
|
||||
'Invalid storage key format: key must follow "files/<identifier>/<path>" structure.',
|
||||
)
|
||||
}
|
||||
|
||||
const identifier = segments[1]
|
||||
|
||||
// 1. Check if identifier is directly an Asset ID (Derived Artifacts: screenshots, pdf_pages, annotations, proxies)
|
||||
const assetById = await prisma.asset.findUnique({
|
||||
where: { id: identifier, isDeleted: false },
|
||||
select: { id: true },
|
||||
})
|
||||
if (assetById) {
|
||||
return assetById.id
|
||||
}
|
||||
|
||||
// 2. Check if identifier is a StorageKey directory prefix (Original uploads / agent-created files)
|
||||
const storageKeyByPrefix = await prisma.storageKey.findFirst({
|
||||
where: { key: { startsWith: `files/${identifier}/` } },
|
||||
include: {
|
||||
assets: {
|
||||
where: { isDeleted: false },
|
||||
select: { id: true },
|
||||
},
|
||||
},
|
||||
})
|
||||
if (storageKeyByPrefix?.assets && storageKeyByPrefix.assets.length > 0) {
|
||||
return storageKeyByPrefix.assets[0].id
|
||||
}
|
||||
|
||||
// 3. Exact StorageKey fallback
|
||||
const exactStorageKey = await prisma.storageKey.findUnique({
|
||||
where: { key },
|
||||
include: {
|
||||
assets: {
|
||||
where: { isDeleted: false },
|
||||
select: { id: true },
|
||||
},
|
||||
},
|
||||
})
|
||||
if (exactStorageKey?.assets && exactStorageKey.assets.length > 0) {
|
||||
return exactStorageKey.assets[0].id
|
||||
}
|
||||
|
||||
throw new Error(
|
||||
`Storage key "${key}" does not belong to any valid asset or the asset has been deleted.`,
|
||||
)
|
||||
}
|
||||
|
||||
export function createDownloadAssetTool(userId: string): AgentTool<typeof downloadAssetSchema> {
|
||||
return {
|
||||
name: 'download_asset',
|
||||
label: 'Download Asset',
|
||||
description:
|
||||
'Downloads a workspace asset (proxy version if available) to the local .pi directory for processing with local scripts or bash commands. Remember to delete the temporary downloaded file when finished.',
|
||||
'Downloads a workspace asset or specific storage S3 key to the local .pi directory for processing with local scripts or bash commands. ' +
|
||||
'Provide exactly one of "assetId" (for full assets) or "key" (for intermediate artifacts like screenshots from read_asset). ' +
|
||||
'Remember to delete the temporary downloaded file when finished.',
|
||||
parameters: downloadAssetSchema,
|
||||
execute: async (_toolCallId, params) => {
|
||||
const assetId = params.assetId
|
||||
const { assetId, key } = params
|
||||
|
||||
if (!userId) {
|
||||
throw new Error('User ID is required for authorization.')
|
||||
}
|
||||
|
||||
await authzService.hasPermission({
|
||||
user: { id: userId } as User,
|
||||
permission: Permission.Read,
|
||||
type: ResourceType.Asset,
|
||||
id: assetId,
|
||||
})
|
||||
const hasAssetId = assetId !== null
|
||||
const hasKey = key !== null
|
||||
|
||||
const asset = await prisma.asset.findUnique({
|
||||
where: { id: assetId },
|
||||
include: { storageKey: true },
|
||||
})
|
||||
|
||||
if (!asset) {
|
||||
throw new Error(`Asset with ID ${assetId} not found.`)
|
||||
}
|
||||
|
||||
let mediaKey = asset.storageKey?.key
|
||||
|
||||
if (asset.media) {
|
||||
const mediaInfo = asset.media as unknown as PrismaJson.MediaInfo
|
||||
if (
|
||||
mediaInfo.proxyType === 'image' ||
|
||||
(mediaInfo.imageTranscodes && mediaInfo.imageTranscodes.length > 0)
|
||||
) {
|
||||
if (mediaInfo.imageTranscodes && mediaInfo.imageTranscodes.length > 0) {
|
||||
mediaKey = mediaInfo.imageTranscodes[0].key || mediaKey
|
||||
}
|
||||
} else if (
|
||||
mediaInfo.proxyType === 'video' ||
|
||||
(mediaInfo.videoTranscodes && mediaInfo.videoTranscodes.length > 0) ||
|
||||
mediaInfo.videoPreview?.key
|
||||
) {
|
||||
if (mediaInfo.videoTranscodes && mediaInfo.videoTranscodes.length > 0) {
|
||||
mediaKey = mediaInfo.videoTranscodes[0].key || mediaKey
|
||||
} else if (mediaInfo.videoPreview?.key) {
|
||||
mediaKey = mediaInfo.videoPreview.key
|
||||
}
|
||||
} else if (mediaInfo.original?.key) {
|
||||
mediaKey = mediaInfo.original.key || mediaKey
|
||||
}
|
||||
}
|
||||
|
||||
if (!mediaKey) {
|
||||
throw new Error(`No media content found for asset ${assetId}.`)
|
||||
if (hasAssetId === hasKey) {
|
||||
throw new Error(
|
||||
'Provide exactly one of "assetId" (to download a workspace asset) or "key" (to download a specific S3 storage key). Set the unused parameter to null.',
|
||||
)
|
||||
}
|
||||
|
||||
const piDir = path.join(process.cwd(), '.pi')
|
||||
@@ -79,32 +115,132 @@ export function createDownloadAssetTool(userId: string): AgentTool<typeof downlo
|
||||
fs.mkdirSync(piDir, { recursive: true })
|
||||
}
|
||||
|
||||
const safeName = sanitizeFilename(asset.name || 'file')
|
||||
const filename = `${asset.id}_${safeName}`
|
||||
const targetFilePath = path.join(piDir, filename)
|
||||
const relativePath = path.join('.pi', filename)
|
||||
|
||||
const bucket = process.env.S3_BUCKET || 'shumai'
|
||||
const { buffer, contentType } = await s3Service.getObject(bucket, mediaKey)
|
||||
|
||||
fs.writeFileSync(targetFilePath, buffer)
|
||||
// Branch A: Download by assetId
|
||||
if (assetId) {
|
||||
await authzService.hasPermission({
|
||||
user: { id: userId } as User,
|
||||
permission: Permission.Read,
|
||||
type: ResourceType.Asset,
|
||||
id: assetId,
|
||||
})
|
||||
|
||||
return {
|
||||
content: [
|
||||
{
|
||||
type: 'text',
|
||||
text: `Downloaded asset "${asset.name}" (ID: ${assetId}) to "${relativePath}". Remember to delete this temporary file when finished.`,
|
||||
let asset = await prisma.asset.findUnique({
|
||||
where: { id: assetId },
|
||||
include: { storageKey: true },
|
||||
})
|
||||
|
||||
if (!asset) {
|
||||
throw new Error(`Asset with ID ${assetId} not found.`)
|
||||
}
|
||||
|
||||
if (asset.type === 'version_stack') {
|
||||
const latestVersion = await prisma.asset.findFirst({
|
||||
where: { parentId: asset.id, isDeleted: false },
|
||||
orderBy: { sortIndex: 'asc' },
|
||||
include: { storageKey: true },
|
||||
})
|
||||
if (latestVersion) {
|
||||
asset = latestVersion
|
||||
}
|
||||
}
|
||||
|
||||
let mediaKey = asset.storageKey?.key
|
||||
|
||||
if (asset.media) {
|
||||
const mediaInfo = asset.media as unknown as PrismaJson.MediaInfo
|
||||
if (
|
||||
mediaInfo.proxyType === 'image' ||
|
||||
(mediaInfo.imageTranscodes && mediaInfo.imageTranscodes.length > 0)
|
||||
) {
|
||||
if (mediaInfo.imageTranscodes && mediaInfo.imageTranscodes.length > 0) {
|
||||
mediaKey = mediaInfo.imageTranscodes[0].key || mediaKey
|
||||
}
|
||||
} else if (
|
||||
mediaInfo.proxyType === 'video' ||
|
||||
(mediaInfo.videoTranscodes && mediaInfo.videoTranscodes.length > 0) ||
|
||||
mediaInfo.videoPreview?.key
|
||||
) {
|
||||
if (mediaInfo.videoTranscodes && mediaInfo.videoTranscodes.length > 0) {
|
||||
mediaKey = mediaInfo.videoTranscodes[0].key || mediaKey
|
||||
} else if (mediaInfo.videoPreview?.key) {
|
||||
mediaKey = mediaInfo.videoPreview.key
|
||||
}
|
||||
} else if (mediaInfo.original?.key) {
|
||||
mediaKey = mediaInfo.original.key || mediaKey
|
||||
}
|
||||
}
|
||||
|
||||
if (!mediaKey) {
|
||||
throw new Error(`No media content found for asset ${assetId}.`)
|
||||
}
|
||||
|
||||
const safeName = sanitizeFilename(asset.name || 'file')
|
||||
const filename = `${asset.id}_${safeName}`
|
||||
const targetFilePath = path.join(piDir, filename)
|
||||
const relativePath = path.join('.pi', filename)
|
||||
|
||||
const { buffer, contentType } = await s3Service.getObject(bucket, mediaKey)
|
||||
fs.writeFileSync(targetFilePath, buffer)
|
||||
|
||||
return {
|
||||
content: [
|
||||
{
|
||||
type: 'text',
|
||||
text: `Downloaded asset "${asset.name}" (ID: ${assetId}) to "${relativePath}". Remember to delete this temporary file when finished.`,
|
||||
},
|
||||
],
|
||||
details: {
|
||||
assetId,
|
||||
name: asset.name,
|
||||
filePath: relativePath,
|
||||
absolutePath: targetFilePath,
|
||||
contentType: contentType || 'application/octet-stream',
|
||||
size: buffer.length,
|
||||
},
|
||||
],
|
||||
details: {
|
||||
assetId,
|
||||
name: asset.name,
|
||||
filePath: relativePath,
|
||||
absolutePath: targetFilePath,
|
||||
contentType: contentType || 'application/octet-stream',
|
||||
size: buffer.length,
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
// Branch B: Download by S3 storage key
|
||||
if (key) {
|
||||
const owningAssetId = await resolveAssetIdFromKey(key)
|
||||
|
||||
await authzService.hasPermission({
|
||||
user: { id: userId } as User,
|
||||
permission: Permission.Read,
|
||||
type: ResourceType.Asset,
|
||||
id: owningAssetId,
|
||||
})
|
||||
|
||||
const rawBasename = path.basename(key)
|
||||
const safeBasename = sanitizeFilename(rawBasename) || 'downloaded_file'
|
||||
const filename = safeBasename
|
||||
const targetFilePath = path.join(piDir, filename)
|
||||
const relativePath = path.join('.pi', filename)
|
||||
|
||||
const { buffer, contentType } = await s3Service.getObject(bucket, key)
|
||||
fs.writeFileSync(targetFilePath, buffer)
|
||||
|
||||
return {
|
||||
content: [
|
||||
{
|
||||
type: 'text',
|
||||
text: `Downloaded storage key "${key}" to "${relativePath}". Remember to delete this temporary file when finished.`,
|
||||
},
|
||||
],
|
||||
details: {
|
||||
key,
|
||||
assetId: owningAssetId,
|
||||
filePath: relativePath,
|
||||
absolutePath: targetFilePath,
|
||||
contentType: contentType || 'application/octet-stream',
|
||||
size: buffer.length,
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
throw new Error('Invalid download_asset parameters.')
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,79 @@
|
||||
import { describe, it, expect, vi, beforeEach } from 'vitest'
|
||||
import { createListAssetsTool } from './list-assets'
|
||||
import { assetService } from '@shumai/core/src/asset/asset'
|
||||
import { authzService } from '@shumai/core/src/authz/authz'
|
||||
|
||||
vi.mock('@shumai/core/src/authz/authz', () => ({
|
||||
authzService: {
|
||||
hasPermission: vi.fn().mockResolvedValue(undefined),
|
||||
},
|
||||
Permission: { Edit: 'edit', Read: 'read' },
|
||||
ResourceType: { Asset: 'asset' },
|
||||
}))
|
||||
|
||||
vi.mock('@shumai/core/src/asset/asset', () => ({
|
||||
assetService: {
|
||||
listChildren: vi.fn().mockResolvedValue({
|
||||
data: [
|
||||
{ id: '01M2FILE2', name: 'file2.txt', type: 'file', sizeByte: 200 },
|
||||
{ id: '01M1FILE1', name: 'file1.txt', type: 'file', sizeByte: 100 },
|
||||
],
|
||||
pageInfo: { hasNextPage: false, hasPreviousPage: false, cursor: 'abc' },
|
||||
}),
|
||||
},
|
||||
}))
|
||||
|
||||
describe('createListAssetsTool', () => {
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks()
|
||||
})
|
||||
|
||||
it('checks read permissions and invokes assetService.listChildren with default all and id desc ordering', async () => {
|
||||
const tool = createListAssetsTool('user-1')
|
||||
const result = await tool.execute('call-1', { parent: 'folder-1' })
|
||||
|
||||
expect(authzService.hasPermission).toHaveBeenCalledWith({
|
||||
user: { id: 'user-1' },
|
||||
permission: 'read',
|
||||
type: 'asset',
|
||||
id: 'folder-1',
|
||||
})
|
||||
|
||||
expect(assetService.listChildren).toHaveBeenCalledWith({
|
||||
assetId: 'folder-1',
|
||||
assetType: 'all',
|
||||
sort: 'createdAt',
|
||||
order: 'desc',
|
||||
first: 20,
|
||||
after: undefined,
|
||||
})
|
||||
|
||||
expect(result.details).toEqual({})
|
||||
expect(JSON.parse((result.content[0] as { text: string }).text)).toEqual({
|
||||
assets: [
|
||||
{ id: '01M2FILE2', name: 'file2.txt', type: 'file', size: 200 },
|
||||
{ id: '01M1FILE1', name: 'file1.txt', type: 'file', size: 100 },
|
||||
],
|
||||
pageInfo: { hasNextPage: false, hasPreviousPage: false, cursor: 'abc' },
|
||||
})
|
||||
})
|
||||
|
||||
it('passes explicit pagination and type filter options to assetService.listChildren', async () => {
|
||||
const tool = createListAssetsTool('user-1')
|
||||
await tool.execute('call-1', {
|
||||
parent: 'folder-1',
|
||||
page: 2,
|
||||
pageSize: 10,
|
||||
type: 'folder',
|
||||
})
|
||||
|
||||
expect(assetService.listChildren).toHaveBeenCalledWith({
|
||||
assetId: 'folder-1',
|
||||
assetType: 'folder',
|
||||
sort: 'createdAt',
|
||||
order: 'desc',
|
||||
first: 10,
|
||||
after: expect.any(String),
|
||||
})
|
||||
})
|
||||
})
|
||||
@@ -1,6 +1,9 @@
|
||||
import { Type } from '@sinclair/typebox'
|
||||
import { Type } from 'typebox'
|
||||
import { type AgentTool } from '@earendil-works/pi-agent-core'
|
||||
import { executeAgentToolWorkflow } from './utils'
|
||||
import { assetService } from '@shumai/core/src/asset/asset'
|
||||
import { authzService, Permission, ResourceType } from '@shumai/core/src/authz/authz'
|
||||
import { encodeCursor } from '@shumai/core/src/pagination'
|
||||
import { type User } from '@shumai/db'
|
||||
|
||||
const listAssetsSchema = Type.Object({
|
||||
parent: Type.String({
|
||||
@@ -19,9 +22,8 @@ const listAssetsSchema = Type.Object({
|
||||
}),
|
||||
),
|
||||
type: Type.Optional(
|
||||
Type.String({
|
||||
Type.Union([Type.Literal('file'), Type.Literal('folder'), Type.Literal('all')], {
|
||||
description: "Filter assets by type: 'file', 'folder', or 'all'. Default is 'all'.",
|
||||
enum: ['file', 'folder', 'all'],
|
||||
default: 'all',
|
||||
}),
|
||||
),
|
||||
@@ -34,15 +36,41 @@ export function createListAssetsTool(userId: string): AgentTool<typeof listAsset
|
||||
description: 'List the assets (files and folders) inside a parent folder with pagination.',
|
||||
parameters: listAssetsSchema,
|
||||
execute: async (_toolCallId, params) => {
|
||||
const result = await executeAgentToolWorkflow({
|
||||
toolName: 'list_assets',
|
||||
args: params,
|
||||
userId,
|
||||
assetId: params.parent,
|
||||
await authzService.hasPermission({
|
||||
user: { id: userId } as User,
|
||||
permission: Permission.Read,
|
||||
type: ResourceType.Asset,
|
||||
id: params.parent,
|
||||
})
|
||||
|
||||
const page = params.page || 1
|
||||
const pageSize = params.pageSize || 20
|
||||
const type = params.type || 'all'
|
||||
|
||||
const result = await assetService.listChildren({
|
||||
assetId: params.parent,
|
||||
assetType: type,
|
||||
sort: 'createdAt',
|
||||
order: 'desc',
|
||||
first: pageSize,
|
||||
after: page > 1 ? encodeCursor((page - 1) * pageSize) : undefined,
|
||||
})
|
||||
|
||||
const assets = result.data.map((a) => ({
|
||||
id: a.id,
|
||||
name: a.name,
|
||||
type: a.type,
|
||||
size: Number(a.sizeByte),
|
||||
}))
|
||||
|
||||
const output = {
|
||||
assets,
|
||||
pageInfo: result.pageInfo,
|
||||
}
|
||||
|
||||
return {
|
||||
content: [{ type: 'text', text: JSON.stringify(result, null, 2) }],
|
||||
details: result,
|
||||
content: [{ type: 'text', text: JSON.stringify(output, null, 2) }],
|
||||
details: {},
|
||||
}
|
||||
},
|
||||
}
|
||||
|
||||
@@ -1,31 +0,0 @@
|
||||
import { describe, it, expect, vi, beforeEach } from 'vitest'
|
||||
import { createListAutofillFieldsTool } from './list-autofill-fields'
|
||||
import { executeAgentToolWorkflow } from './utils'
|
||||
|
||||
vi.mock('./utils', () => ({
|
||||
executeAgentToolWorkflow: vi.fn().mockResolvedValue({
|
||||
fields: [{ name: 'Source', type: 'select', options: [{ displayName: 'Gemini' }] }],
|
||||
}),
|
||||
}))
|
||||
|
||||
describe('createListAutofillFieldsTool', () => {
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks()
|
||||
})
|
||||
|
||||
it('should list autofill fields for the parent folder via the agent tool workflow', async () => {
|
||||
const tool = createListAutofillFieldsTool('user-1')
|
||||
const result = await tool.execute('call-1', { parent: 'folder-1' })
|
||||
|
||||
expect(executeAgentToolWorkflow).toHaveBeenCalledWith({
|
||||
toolName: 'list_autofill_fields',
|
||||
args: { parent: 'folder-1' },
|
||||
userId: 'user-1',
|
||||
assetId: 'folder-1',
|
||||
})
|
||||
|
||||
expect(result.details).toEqual({
|
||||
fields: [{ name: 'Source', type: 'select', options: [{ displayName: 'Gemini' }] }],
|
||||
})
|
||||
})
|
||||
})
|
||||
@@ -1,35 +0,0 @@
|
||||
import { Type } from '@sinclair/typebox'
|
||||
import { type AgentTool } from '@earendil-works/pi-agent-core'
|
||||
import { executeAgentToolWorkflow } from './utils'
|
||||
|
||||
const listAutofillFieldsSchema = Type.Object({
|
||||
parent: Type.String({
|
||||
description:
|
||||
'The parent folder ID whose project autofillable metadata fields to list. This parameter is required.',
|
||||
}),
|
||||
})
|
||||
|
||||
export function createListAutofillFieldsTool(
|
||||
userId: string,
|
||||
): AgentTool<typeof listAutofillFieldsSchema> {
|
||||
return {
|
||||
name: 'list_autofill_fields',
|
||||
label: 'List Autofill Fields',
|
||||
description:
|
||||
'List the AI-autofillable metadata fields defined for the project of a parent folder, including their types and available options. ' +
|
||||
'Use this before creating a file or version so you can pass relevant context (e.g. generation source) to create_file/create_version.',
|
||||
parameters: listAutofillFieldsSchema,
|
||||
execute: async (_toolCallId, params) => {
|
||||
const result = await executeAgentToolWorkflow({
|
||||
toolName: 'list_autofill_fields',
|
||||
args: params,
|
||||
userId,
|
||||
assetId: params.parent,
|
||||
})
|
||||
return {
|
||||
content: [{ type: 'text', text: JSON.stringify(result, null, 2) }],
|
||||
details: result,
|
||||
}
|
||||
},
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,544 @@
|
||||
import { describe, it, expect, vi, beforeEach } from 'vitest'
|
||||
import { createReadAssetTool } from './read-asset'
|
||||
import {
|
||||
prisma,
|
||||
WorkflowTaskType,
|
||||
WorkflowTaskStatus,
|
||||
type Asset,
|
||||
type WorkflowTask,
|
||||
} from '@shumai/db'
|
||||
import { s3Service } from '@shumai/core/src/s3/s3'
|
||||
import { workflowService } from '@shumai/workflow-core'
|
||||
import { authzService } from '@shumai/core/src/authz/authz'
|
||||
import * as annotationResolver from './annotation-resolver'
|
||||
|
||||
vi.mock('@shumai/db', async (importOriginal) => {
|
||||
const actual = await importOriginal<typeof import('@shumai/db')>()
|
||||
return {
|
||||
...actual,
|
||||
prisma: {
|
||||
asset: {
|
||||
findUnique: vi.fn(),
|
||||
findFirst: vi.fn(),
|
||||
},
|
||||
workflowTask: {
|
||||
create: vi.fn(),
|
||||
},
|
||||
},
|
||||
}
|
||||
})
|
||||
|
||||
vi.mock('@shumai/core/src/s3/s3', () => ({
|
||||
s3Service: {
|
||||
getObject: vi.fn(),
|
||||
presign: vi.fn().mockResolvedValue('https://mock-presigned-url.com'),
|
||||
},
|
||||
}))
|
||||
|
||||
vi.mock('@shumai/workflow-core', () => ({
|
||||
workflowService: {
|
||||
executeWait: vi.fn(),
|
||||
},
|
||||
}))
|
||||
|
||||
vi.mock('@shumai/core/src/authz/authz', () => ({
|
||||
authzService: {
|
||||
hasPermission: vi.fn(),
|
||||
},
|
||||
Permission: { Read: 'Read' },
|
||||
ResourceType: { Asset: 'asset' },
|
||||
}))
|
||||
|
||||
describe('readAssetTool', () => {
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks()
|
||||
vi.spyOn(annotationResolver, 'resolveAnnotationsById').mockResolvedValue({
|
||||
annotations: null,
|
||||
timestamp: null,
|
||||
})
|
||||
})
|
||||
|
||||
it('should throw authorization error if user ID is empty', async () => {
|
||||
const tool = createReadAssetTool('')
|
||||
await expect(
|
||||
tool.execute('call-1', {
|
||||
assetId: 'asset-1',
|
||||
annotationId: null,
|
||||
imageConfig: null,
|
||||
videoConfig: null,
|
||||
docConfig: null,
|
||||
}),
|
||||
).rejects.toThrow('User ID is required for authorization.')
|
||||
})
|
||||
|
||||
it('should throw error if asset not found', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue(null)
|
||||
|
||||
const tool = createReadAssetTool('user-1')
|
||||
await expect(
|
||||
tool.execute('call-1', {
|
||||
assetId: 'asset-1',
|
||||
annotationId: null,
|
||||
imageConfig: null,
|
||||
videoConfig: null,
|
||||
docConfig: null,
|
||||
}),
|
||||
).rejects.toThrow('Asset with ID asset-1 not found.')
|
||||
})
|
||||
|
||||
describe('Image Assets', () => {
|
||||
it('should read image and return ImageContent and S3 key', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'img-1',
|
||||
name: 'photo.png',
|
||||
mediaType: 'image/png',
|
||||
storageKey: { key: 'raw/photo.png' },
|
||||
media: {
|
||||
proxyType: 'image',
|
||||
imageTranscodes: [{ key: 'proxy/photo.webp' }],
|
||||
},
|
||||
} as unknown as Asset)
|
||||
|
||||
vi.mocked(s3Service.getObject).mockResolvedValue({
|
||||
buffer: Buffer.from('fake-image-bytes'),
|
||||
contentType: 'image/webp',
|
||||
} as unknown as { buffer: Buffer; contentType: string })
|
||||
|
||||
const tool = createReadAssetTool('user-1')
|
||||
const result = await tool.execute('call-1', {
|
||||
assetId: 'img-1',
|
||||
annotationId: null,
|
||||
imageConfig: null,
|
||||
videoConfig: null,
|
||||
docConfig: null,
|
||||
})
|
||||
|
||||
expect(authzService.hasPermission).toHaveBeenCalledWith({
|
||||
user: { id: 'user-1' },
|
||||
permission: 'Read',
|
||||
type: 'asset',
|
||||
id: 'img-1',
|
||||
})
|
||||
expect(s3Service.getObject).toHaveBeenCalledWith('shumai', 'proxy/photo.webp')
|
||||
|
||||
const textItem = result.content[0] as { type: 'text'; text: string }
|
||||
const imageItem = result.content[1] as { type: 'image'; data: string; mimeType: string }
|
||||
|
||||
expect(textItem.text).toContain('proxy/photo.webp')
|
||||
expect(imageItem.type).toBe('image')
|
||||
expect(imageItem.data).toBe(Buffer.from('fake-image-bytes').toString('base64'))
|
||||
expect(result.details.key).toBe('proxy/photo.webp')
|
||||
})
|
||||
|
||||
it('should trigger image annotation transcode workflow when annotationId is provided', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'img-1',
|
||||
name: 'photo.png',
|
||||
mediaType: 'image/png',
|
||||
projectId: 'project-1',
|
||||
storageKey: { key: 'raw/photo.png' },
|
||||
media: {
|
||||
proxyType: 'image',
|
||||
imageTranscodes: [{ key: 'proxy/photo.webp' }],
|
||||
},
|
||||
} as unknown as Asset)
|
||||
|
||||
vi.spyOn(annotationResolver, 'resolveAnnotationsById').mockResolvedValue({
|
||||
annotations: [
|
||||
{
|
||||
type: 'arrow',
|
||||
color: '#ff0000',
|
||||
points: [
|
||||
[0, 0],
|
||||
[10, 10],
|
||||
],
|
||||
},
|
||||
],
|
||||
timestamp: null,
|
||||
})
|
||||
|
||||
vi.mocked(prisma.workflowTask.create).mockResolvedValue({
|
||||
id: 'task-anno',
|
||||
} as unknown as WorkflowTask)
|
||||
vi.mocked(workflowService.executeWait).mockResolvedValue({
|
||||
id: 'task-anno',
|
||||
output: { key: 'annotated/photo.webp' },
|
||||
} as unknown as WorkflowTask)
|
||||
|
||||
vi.mocked(s3Service.getObject).mockResolvedValue({
|
||||
buffer: Buffer.from('annotated-bytes'),
|
||||
contentType: 'image/webp',
|
||||
} as unknown as { buffer: Buffer; contentType: string })
|
||||
|
||||
const tool = createReadAssetTool('user-1')
|
||||
const result = await tool.execute('call-1', {
|
||||
assetId: 'img-1',
|
||||
annotationId: 'comment-1',
|
||||
imageConfig: null,
|
||||
videoConfig: null,
|
||||
docConfig: null,
|
||||
})
|
||||
|
||||
expect(prisma.workflowTask.create).toHaveBeenCalledWith({
|
||||
data: {
|
||||
assetId: 'img-1',
|
||||
projectId: 'project-1',
|
||||
type: WorkflowTaskType.transcode_image_annotation,
|
||||
status: WorkflowTaskStatus.pending,
|
||||
payload: {
|
||||
projectId: 'project-1',
|
||||
imageAnnotation: {
|
||||
annotations: [
|
||||
{
|
||||
type: 'arrow',
|
||||
color: '#ff0000',
|
||||
points: [
|
||||
[0, 0],
|
||||
[10, 10],
|
||||
],
|
||||
},
|
||||
],
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
expect(s3Service.getObject).toHaveBeenCalledWith('shumai', 'annotated/photo.webp')
|
||||
expect(result.details.key).toBe('annotated/photo.webp')
|
||||
})
|
||||
})
|
||||
|
||||
describe('Video Assets', () => {
|
||||
it('should throw error if videoConfig is missing for video assets', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'vid-1',
|
||||
name: 'video.mp4',
|
||||
mediaType: 'video/mp4',
|
||||
media: { proxyType: 'video' },
|
||||
} as unknown as Asset)
|
||||
|
||||
const tool = createReadAssetTool('user-1')
|
||||
await expect(
|
||||
tool.execute('call-1', {
|
||||
assetId: 'vid-1',
|
||||
annotationId: null,
|
||||
imageConfig: null,
|
||||
videoConfig: null,
|
||||
docConfig: null,
|
||||
}),
|
||||
).rejects.toThrow('videoConfig with start, end, and count is required')
|
||||
})
|
||||
|
||||
it('should throw error on invalid video time range', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'vid-1',
|
||||
name: 'video.mp4',
|
||||
mediaType: 'video/mp4',
|
||||
media: { proxyType: 'video' },
|
||||
} as unknown as Asset)
|
||||
|
||||
const tool = createReadAssetTool('user-1')
|
||||
await expect(
|
||||
tool.execute('call-1', {
|
||||
assetId: 'vid-1',
|
||||
annotationId: null,
|
||||
imageConfig: null,
|
||||
videoConfig: { start: 10, end: 5, count: 1 },
|
||||
docConfig: null,
|
||||
}),
|
||||
).rejects.toThrow(
|
||||
'Invalid video time range: start (10) must be less than or equal to end (5).',
|
||||
)
|
||||
})
|
||||
|
||||
it('should extract frames and return ImageContent array and keys', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'vid-1',
|
||||
name: 'video.mp4',
|
||||
mediaType: 'video/mp4',
|
||||
projectId: 'project-1',
|
||||
media: { proxyType: 'video' },
|
||||
} as unknown as Asset)
|
||||
|
||||
vi.mocked(prisma.workflowTask.create).mockResolvedValue({
|
||||
id: 'task-shot',
|
||||
} as unknown as WorkflowTask)
|
||||
vi.mocked(workflowService.executeWait).mockResolvedValue({
|
||||
id: 'task-shot',
|
||||
output: {
|
||||
screenshots: [
|
||||
{ key: 'screenshots/shot1.webp', timestamp: 2.0 },
|
||||
{ key: 'screenshots/shot2.webp', timestamp: 4.0 },
|
||||
],
|
||||
},
|
||||
} as unknown as WorkflowTask)
|
||||
|
||||
vi.mocked(s3Service.getObject).mockImplementation(async (_bucket, key) => ({
|
||||
buffer: Buffer.from(`bytes-for-${key}`),
|
||||
contentType: 'image/webp',
|
||||
}))
|
||||
|
||||
const tool = createReadAssetTool('user-1')
|
||||
const result = await tool.execute('call-1', {
|
||||
assetId: 'vid-1',
|
||||
annotationId: null,
|
||||
imageConfig: null,
|
||||
videoConfig: { start: 2.0, end: 4.0, count: 2 },
|
||||
docConfig: null,
|
||||
})
|
||||
|
||||
expect(prisma.workflowTask.create).toHaveBeenCalledWith({
|
||||
data: {
|
||||
assetId: 'vid-1',
|
||||
projectId: 'project-1',
|
||||
type: WorkflowTaskType.transcode_screenshot,
|
||||
status: WorkflowTaskStatus.pending,
|
||||
payload: {
|
||||
projectId: 'project-1',
|
||||
screenshot: {
|
||||
start: 2.0,
|
||||
end: 4.0,
|
||||
count: 2,
|
||||
commentTimestamp: null,
|
||||
annotations: null,
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
expect(result.content.length).toBe(3) // 1 text + 2 images
|
||||
expect(result.details.keys).toEqual(['screenshots/shot1.webp', 'screenshots/shot2.webp'])
|
||||
})
|
||||
})
|
||||
|
||||
describe('Document Assets', () => {
|
||||
it('should throw error if docConfig is missing for document assets', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'doc-1',
|
||||
name: 'doc.pdf',
|
||||
mediaType: 'application/pdf',
|
||||
media: { proxyType: 'pdf' },
|
||||
} as unknown as Asset)
|
||||
|
||||
const tool = createReadAssetTool('user-1')
|
||||
await expect(
|
||||
tool.execute('call-1', {
|
||||
assetId: 'doc-1',
|
||||
annotationId: null,
|
||||
imageConfig: null,
|
||||
videoConfig: null,
|
||||
docConfig: null,
|
||||
}),
|
||||
).rejects.toThrow('docConfig with mode ("pages" or "text") is required')
|
||||
})
|
||||
|
||||
it('should render PDF pages in mode: "pages"', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'doc-1',
|
||||
name: 'doc.pdf',
|
||||
mediaType: 'application/pdf',
|
||||
projectId: 'project-1',
|
||||
media: { proxyType: 'pdf' },
|
||||
} as unknown as Asset)
|
||||
|
||||
vi.mocked(prisma.workflowTask.create).mockResolvedValue({
|
||||
id: 'task-pdf',
|
||||
} as unknown as WorkflowTask)
|
||||
vi.mocked(workflowService.executeWait).mockResolvedValue({
|
||||
id: 'task-pdf',
|
||||
output: {
|
||||
pages: [
|
||||
{ key: 'pdf_pages/page1.webp', page: 1 },
|
||||
{ key: 'pdf_pages/page2.webp', page: 2 },
|
||||
],
|
||||
},
|
||||
} as unknown as WorkflowTask)
|
||||
|
||||
vi.mocked(s3Service.getObject).mockImplementation(async (_bucket, key) => ({
|
||||
buffer: Buffer.from(`bytes-for-${key}`),
|
||||
contentType: 'image/webp',
|
||||
}))
|
||||
|
||||
const tool = createReadAssetTool('user-1')
|
||||
const result = await tool.execute('call-1', {
|
||||
assetId: 'doc-1',
|
||||
annotationId: null,
|
||||
imageConfig: null,
|
||||
videoConfig: null,
|
||||
docConfig: { mode: 'pages', startPage: 1, endPage: 2 },
|
||||
})
|
||||
|
||||
expect(result.content.length).toBe(3) // 1 text + 2 images
|
||||
expect(result.details.keys).toEqual(['pdf_pages/page1.webp', 'pdf_pages/page2.webp'])
|
||||
})
|
||||
|
||||
it('should throw error in mode: "pages" when page range exceeds 20 pages', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'doc-1',
|
||||
name: 'doc.pdf',
|
||||
mediaType: 'application/pdf',
|
||||
media: { proxyType: 'pdf' },
|
||||
} as unknown as Asset)
|
||||
|
||||
const tool = createReadAssetTool('user-1')
|
||||
await expect(
|
||||
tool.execute('call-1', {
|
||||
assetId: 'doc-1',
|
||||
annotationId: null,
|
||||
imageConfig: null,
|
||||
videoConfig: null,
|
||||
docConfig: { mode: 'pages', startPage: 1, endPage: 25 },
|
||||
}),
|
||||
).rejects.toThrow('exceeds the maximum limit of 20 pages')
|
||||
})
|
||||
|
||||
it('should throw error in mode: "text" when called on binary PDF', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'doc-1',
|
||||
name: 'manual.pdf',
|
||||
mediaType: 'application/pdf',
|
||||
media: { proxyType: 'pdf' },
|
||||
} as unknown as Asset)
|
||||
|
||||
const tool = createReadAssetTool('user-1')
|
||||
await expect(
|
||||
tool.execute('call-1', {
|
||||
assetId: 'doc-1',
|
||||
annotationId: null,
|
||||
imageConfig: null,
|
||||
videoConfig: null,
|
||||
docConfig: { mode: 'text', startPage: null, endPage: null },
|
||||
}),
|
||||
).rejects.toThrow('is a binary PDF/document and cannot be read as raw text')
|
||||
})
|
||||
|
||||
it('should throw error in mode: "text" when annotationId is provided', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'doc-1',
|
||||
name: 'notes.md',
|
||||
mediaType: 'text/markdown',
|
||||
media: { proxyType: 'pdf' },
|
||||
} as unknown as Asset)
|
||||
|
||||
const tool = createReadAssetTool('user-1')
|
||||
await expect(
|
||||
tool.execute('call-1', {
|
||||
assetId: 'doc-1',
|
||||
annotationId: 'comment-123',
|
||||
imageConfig: null,
|
||||
videoConfig: null,
|
||||
docConfig: { mode: 'text', startPage: null, endPage: null },
|
||||
}),
|
||||
).rejects.toThrow('annotationId cannot be used with docConfig mode "text"')
|
||||
})
|
||||
|
||||
it('should throw error in mode: "text" when startPage or endPage is non-null', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'doc-1',
|
||||
name: 'notes.md',
|
||||
mediaType: 'text/markdown',
|
||||
media: { proxyType: 'pdf' },
|
||||
} as unknown as Asset)
|
||||
|
||||
const tool = createReadAssetTool('user-1')
|
||||
await expect(
|
||||
tool.execute('call-1', {
|
||||
assetId: 'doc-1',
|
||||
annotationId: null,
|
||||
imageConfig: null,
|
||||
videoConfig: null,
|
||||
docConfig: { mode: 'text', startPage: 1, endPage: 2 },
|
||||
}),
|
||||
).rejects.toThrow('startPage and endPage must be null when docConfig mode is "text"')
|
||||
})
|
||||
|
||||
it('should read raw text from S3 in mode: "text" for markdown files', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'doc-md',
|
||||
name: 'README.md',
|
||||
mediaType: 'text/markdown',
|
||||
storageKey: { key: 'raw/README.md' },
|
||||
media: { proxyType: 'pdf' },
|
||||
} as unknown as Asset)
|
||||
|
||||
vi.mocked(s3Service.getObject).mockResolvedValue({
|
||||
buffer: Buffer.from('# Hello Shumai\nThis is markdown text.'),
|
||||
contentType: 'text/markdown',
|
||||
} as unknown as { buffer: Buffer; contentType: string })
|
||||
|
||||
const tool = createReadAssetTool('user-1')
|
||||
const result = await tool.execute('call-1', {
|
||||
assetId: 'doc-md',
|
||||
annotationId: null,
|
||||
imageConfig: null,
|
||||
videoConfig: null,
|
||||
docConfig: { mode: 'text', startPage: null, endPage: null },
|
||||
})
|
||||
|
||||
expect(s3Service.getObject).toHaveBeenCalledWith('shumai', 'raw/README.md')
|
||||
expect(result.content[0].type).toBe('text')
|
||||
expect((result.content[0] as { type: 'text'; text: string }).text).toContain(
|
||||
'# Hello Shumai\nThis is markdown text.',
|
||||
)
|
||||
expect(result.details.key).toBe('raw/README.md')
|
||||
})
|
||||
})
|
||||
|
||||
describe('Version Stack Resolution', () => {
|
||||
it('should resolve version_stack to latest version asset', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'stack-1',
|
||||
name: '',
|
||||
type: 'version_stack',
|
||||
} as unknown as Asset)
|
||||
|
||||
vi.mocked(prisma.asset.findFirst).mockResolvedValue({
|
||||
id: 'file-v2',
|
||||
name: 'diagram_v2.png',
|
||||
type: 'file',
|
||||
mediaType: 'image/png',
|
||||
storageKey: { key: 'raw/diagram_v2.png' },
|
||||
media: {
|
||||
proxyType: 'image',
|
||||
imageTranscodes: [{ key: 'proxy/diagram_v2.webp' }],
|
||||
},
|
||||
} as unknown as Asset)
|
||||
|
||||
vi.mocked(s3Service.getObject).mockResolvedValue({
|
||||
buffer: Buffer.from('v2-image-bytes'),
|
||||
contentType: 'image/webp',
|
||||
} as unknown as { buffer: Buffer; contentType: string })
|
||||
|
||||
const tool = createReadAssetTool('user-1')
|
||||
const result = await tool.execute('call-1', {
|
||||
assetId: 'stack-1',
|
||||
annotationId: null,
|
||||
imageConfig: null,
|
||||
videoConfig: null,
|
||||
docConfig: null,
|
||||
})
|
||||
|
||||
expect(prisma.asset.findFirst).toHaveBeenCalledWith({
|
||||
where: { parentId: 'stack-1', isDeleted: false },
|
||||
orderBy: { sortIndex: 'asc' },
|
||||
include: { storageKey: true },
|
||||
})
|
||||
expect(result.details.name).toBe('diagram_v2.png')
|
||||
expect(result.details.key).toBe('proxy/diagram_v2.webp')
|
||||
})
|
||||
})
|
||||
})
|
||||
@@ -0,0 +1,576 @@
|
||||
import { Type } from 'typebox'
|
||||
import { type AgentTool } from '@earendil-works/pi-agent-core'
|
||||
import { type ImageContent, type TextContent } from '@earendil-works/pi-ai'
|
||||
import { prisma, WorkflowTaskType, WorkflowTaskStatus, type User } from '@shumai/db'
|
||||
import { s3Service } from '@shumai/core/src/s3/s3'
|
||||
import { workflowService } from '@shumai/workflow-core'
|
||||
import { authzService, Permission, ResourceType } from '@shumai/core/src/authz/authz'
|
||||
import { resolveAnnotationsById } from './annotation-resolver'
|
||||
|
||||
export const readAssetSchema = Type.Object(
|
||||
{
|
||||
assetId: Type.String({
|
||||
description: 'The asset ID of the workspace asset to inspect. Required.',
|
||||
}),
|
||||
annotationId: Type.Union([
|
||||
Type.String({
|
||||
description:
|
||||
'The ID of the comment or message entry from <annotation id="..." /> whose visual markup should be overlaid, or null.',
|
||||
}),
|
||||
Type.Null(),
|
||||
]),
|
||||
imageConfig: Type.Union([
|
||||
Type.Object(
|
||||
{},
|
||||
{
|
||||
additionalProperties: false,
|
||||
description: 'Optional configuration for image assets, or null.',
|
||||
},
|
||||
),
|
||||
Type.Null(),
|
||||
]),
|
||||
videoConfig: Type.Union([
|
||||
Type.Object(
|
||||
{
|
||||
start: Type.Number({ description: 'Start time in seconds.' }),
|
||||
end: Type.Number({ description: 'End time in seconds.' }),
|
||||
count: Type.Number({ description: 'Number of frames to extract (e.g. 1 to 10).' }),
|
||||
},
|
||||
{
|
||||
additionalProperties: false,
|
||||
description:
|
||||
'Configuration for video assets. Required when inspecting videos, or null for other asset types.',
|
||||
},
|
||||
),
|
||||
Type.Null(),
|
||||
]),
|
||||
docConfig: Type.Union([
|
||||
Type.Object(
|
||||
{
|
||||
mode: Type.Union([
|
||||
Type.Literal('pages', {
|
||||
description:
|
||||
'Render specific page range as images for visual layout, charts, or visual annotations (required for binary PDFs).',
|
||||
}),
|
||||
Type.Literal('text', {
|
||||
description:
|
||||
'Read raw text content directly (ideal for .md, .txt, .csv, code files).',
|
||||
}),
|
||||
]),
|
||||
startPage: Type.Union([
|
||||
Type.Number({
|
||||
description:
|
||||
'Start page number (1-based index, required when mode="pages"), or null when mode="text".',
|
||||
}),
|
||||
Type.Null(),
|
||||
]),
|
||||
endPage: Type.Union([
|
||||
Type.Number({
|
||||
description:
|
||||
'End page number (1-based index, max 20 pages per call, required when mode="pages"), or null when mode="text".',
|
||||
}),
|
||||
Type.Null(),
|
||||
]),
|
||||
},
|
||||
{
|
||||
additionalProperties: false,
|
||||
description:
|
||||
'Configuration for document/PDF/text assets, or null if inspecting another asset type.',
|
||||
},
|
||||
),
|
||||
Type.Null(),
|
||||
]),
|
||||
},
|
||||
{ additionalProperties: false },
|
||||
)
|
||||
|
||||
export function isPlainTextAsset(mediaType: string, filename: string): boolean {
|
||||
if (
|
||||
mediaType.startsWith('text/') ||
|
||||
mediaType === 'application/json' ||
|
||||
mediaType === 'application/javascript' ||
|
||||
mediaType === 'application/typescript' ||
|
||||
mediaType === 'application/xml' ||
|
||||
mediaType === 'application/x-yaml'
|
||||
) {
|
||||
return true
|
||||
}
|
||||
const textExtensions = [
|
||||
'.txt',
|
||||
'.md',
|
||||
'.markdown',
|
||||
'.json',
|
||||
'.csv',
|
||||
'.tsv',
|
||||
'.js',
|
||||
'.ts',
|
||||
'.tsx',
|
||||
'.jsx',
|
||||
'.html',
|
||||
'.htm',
|
||||
'.css',
|
||||
'.scss',
|
||||
'.yaml',
|
||||
'.yml',
|
||||
'.xml',
|
||||
'.py',
|
||||
'.rb',
|
||||
'.go',
|
||||
'.rs',
|
||||
'.c',
|
||||
'.cpp',
|
||||
'.h',
|
||||
'.hpp',
|
||||
'.java',
|
||||
'.sh',
|
||||
'.bash',
|
||||
'.zsh',
|
||||
'.sql',
|
||||
]
|
||||
return textExtensions.some((ext) => filename.endsWith(ext))
|
||||
}
|
||||
|
||||
const MAX_TEXT_BYTES = 50 * 1024
|
||||
const MAX_TEXT_LINES = 1000
|
||||
|
||||
export function createReadAssetTool(userId: string): AgentTool<typeof readAssetSchema> {
|
||||
return {
|
||||
name: 'read_asset',
|
||||
label: 'Read Asset',
|
||||
description:
|
||||
'Inspects and reads the content of an asset in the workspace. ' +
|
||||
'Supports visual analysis for images, video frame extraction, PDF page rendering, and direct text reading for text/markdown files. ' +
|
||||
'Pass assetId, and provide the specific config (imageConfig, videoConfig, or docConfig) while setting unused configs to null. ' +
|
||||
'Optionally provide annotationId to view visual markups drawn on the asset.',
|
||||
parameters: readAssetSchema,
|
||||
execute: async (_toolCallId, params) => {
|
||||
const { assetId, annotationId, videoConfig, docConfig } = params
|
||||
|
||||
if (!userId) {
|
||||
throw new Error('User ID is required for authorization.')
|
||||
}
|
||||
|
||||
await authzService.hasPermission({
|
||||
user: { id: userId } as User,
|
||||
permission: Permission.Read,
|
||||
type: ResourceType.Asset,
|
||||
id: assetId,
|
||||
})
|
||||
|
||||
let asset = await prisma.asset.findUnique({
|
||||
where: { id: assetId },
|
||||
include: { storageKey: true },
|
||||
})
|
||||
|
||||
if (!asset) {
|
||||
throw new Error(`Asset with ID ${assetId} not found.`)
|
||||
}
|
||||
|
||||
if (asset.type === 'version_stack') {
|
||||
const latestVersion = await prisma.asset.findFirst({
|
||||
where: { parentId: asset.id, isDeleted: false },
|
||||
orderBy: { sortIndex: 'asc' },
|
||||
include: { storageKey: true },
|
||||
})
|
||||
if (latestVersion) {
|
||||
asset = latestVersion
|
||||
}
|
||||
}
|
||||
|
||||
const mediaInfo = asset.media as unknown as PrismaJson.MediaInfo | null
|
||||
const proxyType = mediaInfo?.proxyType
|
||||
const mediaType = asset.mediaType?.toLowerCase() || ''
|
||||
const filename = asset.name?.toLowerCase() || ''
|
||||
const bucket = process.env.S3_BUCKET || 'shumai'
|
||||
|
||||
// ----------------------------------------------------------------------
|
||||
// Branch 1: Image Assets
|
||||
// ----------------------------------------------------------------------
|
||||
if (proxyType === 'image' || mediaType.startsWith('image/') || filename.endsWith('.psd')) {
|
||||
let mediaKey = asset.storageKey?.key
|
||||
if (mediaInfo?.imageTranscodes && mediaInfo.imageTranscodes.length > 0) {
|
||||
mediaKey = mediaInfo.imageTranscodes[0].key || mediaKey
|
||||
}
|
||||
|
||||
if (!mediaKey) {
|
||||
throw new Error('No media content found for this asset.')
|
||||
}
|
||||
|
||||
const { annotations } = await resolveAnnotationsById(asset.id, annotationId)
|
||||
let keyToUse = mediaKey
|
||||
|
||||
if (annotations) {
|
||||
const task = await prisma.workflowTask.create({
|
||||
data: {
|
||||
assetId: asset.id,
|
||||
projectId: asset.projectId || 'none',
|
||||
type: WorkflowTaskType.transcode_image_annotation,
|
||||
status: WorkflowTaskStatus.pending,
|
||||
payload: {
|
||||
projectId: asset.projectId || 'none',
|
||||
imageAnnotation: {
|
||||
annotations,
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
const completedTask = await workflowService.executeWait(task)
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any -- transcode image annotation task output
|
||||
const output = completedTask.output as any
|
||||
if (output?.key) {
|
||||
keyToUse = output.key
|
||||
} else {
|
||||
throw new Error('Image annotation transcode workflow failed to output S3 key.')
|
||||
}
|
||||
}
|
||||
|
||||
const { buffer, contentType } = await s3Service.getObject(bucket, keyToUse)
|
||||
const mimeType =
|
||||
contentType && contentType !== 'application/octet-stream' ? contentType : 'image/webp'
|
||||
const downloadUrl = await s3Service.presign(
|
||||
bucket,
|
||||
keyToUse,
|
||||
'GET',
|
||||
true,
|
||||
asset.name || undefined,
|
||||
)
|
||||
|
||||
const content: Array<TextContent | ImageContent> = [
|
||||
{
|
||||
type: 'text',
|
||||
text: `Image asset "${asset.name}" (ID: ${asset.id}):\n- S3 Key: "${keyToUse}"`,
|
||||
},
|
||||
{
|
||||
type: 'image',
|
||||
data: buffer.toString('base64'),
|
||||
mimeType,
|
||||
},
|
||||
]
|
||||
|
||||
return {
|
||||
content,
|
||||
details: {
|
||||
assetId: asset.id,
|
||||
name: asset.name,
|
||||
mediaType: asset.mediaType,
|
||||
key: keyToUse,
|
||||
downloadUrl,
|
||||
sourceKeys: [keyToUse],
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
// ----------------------------------------------------------------------
|
||||
// Branch 2: Video Assets
|
||||
// ----------------------------------------------------------------------
|
||||
if (proxyType === 'video' || mediaType.startsWith('video/')) {
|
||||
if (!videoConfig) {
|
||||
throw new Error(
|
||||
'videoConfig with start, end, and count is required when inspecting video assets.',
|
||||
)
|
||||
}
|
||||
|
||||
const { start, end, count } = videoConfig
|
||||
|
||||
if (start < 0 || end < 0) {
|
||||
throw new Error('Invalid video time range: start and end must be non-negative numbers.')
|
||||
}
|
||||
|
||||
if (start > end) {
|
||||
throw new Error(
|
||||
`Invalid video time range: start (${start}) must be less than or equal to end (${end}).`,
|
||||
)
|
||||
}
|
||||
|
||||
if (count < 1) {
|
||||
throw new Error(`Invalid frame count: count (${count}) must be at least 1.`)
|
||||
}
|
||||
|
||||
const { annotations, timestamp: commentTimestamp } = await resolveAnnotationsById(
|
||||
asset.id,
|
||||
annotationId,
|
||||
)
|
||||
|
||||
const task = await prisma.workflowTask.create({
|
||||
data: {
|
||||
assetId: asset.id,
|
||||
projectId: asset.projectId || 'none',
|
||||
type: WorkflowTaskType.transcode_screenshot,
|
||||
status: WorkflowTaskStatus.pending,
|
||||
payload: {
|
||||
projectId: asset.projectId || 'none',
|
||||
screenshot: {
|
||||
start,
|
||||
end,
|
||||
count,
|
||||
commentTimestamp,
|
||||
annotations,
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
const completedTask = await workflowService.executeWait(task)
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any -- transcode screenshot output
|
||||
const output = completedTask.output as any
|
||||
const screenshots = output?.screenshots as
|
||||
| Array<{ key: string; timestamp: number }>
|
||||
| undefined
|
||||
|
||||
if (!screenshots || screenshots.length === 0) {
|
||||
throw new Error('No screenshots were generated.')
|
||||
}
|
||||
|
||||
const content: Array<TextContent | ImageContent> = []
|
||||
const sourceKeys: string[] = []
|
||||
const results: Array<{ key: string; timestamp: number; downloadUrl: string }> = []
|
||||
const textLines: string[] = [
|
||||
`Extracted ${screenshots.length} frame(s) from "${asset.name}" (${start}s - ${end}s):`,
|
||||
]
|
||||
|
||||
for (const shot of screenshots) {
|
||||
const { buffer, contentType } = await s3Service.getObject(bucket, shot.key)
|
||||
const mimeType =
|
||||
contentType && contentType !== 'application/octet-stream' ? contentType : 'image/webp'
|
||||
const downloadUrl = await s3Service.presign(
|
||||
bucket,
|
||||
shot.key,
|
||||
'GET',
|
||||
true,
|
||||
asset.name || undefined,
|
||||
)
|
||||
|
||||
textLines.push(`- Frame at ${shot.timestamp}s: S3 Key: "${shot.key}"`)
|
||||
content.push({
|
||||
type: 'image',
|
||||
data: buffer.toString('base64'),
|
||||
mimeType,
|
||||
})
|
||||
sourceKeys.push(shot.key)
|
||||
results.push({
|
||||
key: shot.key,
|
||||
timestamp: shot.timestamp,
|
||||
downloadUrl,
|
||||
})
|
||||
}
|
||||
|
||||
content.unshift({
|
||||
type: 'text',
|
||||
text: textLines.join('\n'),
|
||||
})
|
||||
|
||||
return {
|
||||
content,
|
||||
details: {
|
||||
assetId: asset.id,
|
||||
name: asset.name,
|
||||
mediaType: asset.mediaType,
|
||||
keys: sourceKeys,
|
||||
results,
|
||||
sourceKeys,
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
// ----------------------------------------------------------------------
|
||||
// Branch 3: Documents & PDF Assets
|
||||
// ----------------------------------------------------------------------
|
||||
if (
|
||||
proxyType === 'pdf' ||
|
||||
mediaType === 'application/pdf' ||
|
||||
isPlainTextAsset(mediaType, filename)
|
||||
) {
|
||||
if (!docConfig) {
|
||||
throw new Error(
|
||||
'docConfig with mode ("pages" or "text") is required when inspecting document/PDF assets.',
|
||||
)
|
||||
}
|
||||
|
||||
if (docConfig.mode === 'text') {
|
||||
if (annotationId !== null) {
|
||||
throw new Error(
|
||||
'annotationId cannot be used with docConfig mode "text" because visual markups can only be rendered on visual pages. Use docConfig: { mode: "pages", startPage: ..., endPage: ... } instead.',
|
||||
)
|
||||
}
|
||||
|
||||
if (docConfig.startPage !== null || docConfig.endPage !== null) {
|
||||
throw new Error(
|
||||
'startPage and endPage must be null when docConfig mode is "text". To inspect specific page numbers, use mode: "pages".',
|
||||
)
|
||||
}
|
||||
|
||||
if (!isPlainTextAsset(mediaType, filename)) {
|
||||
throw new Error(
|
||||
`Asset "${asset.name}" is a binary PDF/document and cannot be read as raw text. Please call read_asset with docConfig: { mode: "pages", startPage: 1, endPage: ... } to view its visual pages.`,
|
||||
)
|
||||
}
|
||||
|
||||
const mediaKey = asset.storageKey?.key
|
||||
if (!mediaKey) {
|
||||
throw new Error(`No media content found for asset ${asset.id}.`)
|
||||
}
|
||||
|
||||
const { buffer } = await s3Service.getObject(bucket, mediaKey)
|
||||
const rawText = buffer.toString('utf-8')
|
||||
let text = rawText
|
||||
let isTruncated = false
|
||||
|
||||
const lines = text.split('\n')
|
||||
if (lines.length > MAX_TEXT_LINES) {
|
||||
text = lines.slice(0, MAX_TEXT_LINES).join('\n')
|
||||
isTruncated = true
|
||||
}
|
||||
|
||||
if (Buffer.byteLength(text, 'utf-8') > MAX_TEXT_BYTES) {
|
||||
text = Buffer.from(text, 'utf-8').subarray(0, MAX_TEXT_BYTES).toString('utf-8')
|
||||
isTruncated = true
|
||||
}
|
||||
|
||||
if (isTruncated) {
|
||||
text += `\n\n[Content truncated to ${MAX_TEXT_LINES} lines / ${MAX_TEXT_BYTES / 1024}KB limit. Use download_asset to process the full file.]`
|
||||
}
|
||||
|
||||
const downloadUrl = await s3Service.presign(
|
||||
bucket,
|
||||
mediaKey,
|
||||
'GET',
|
||||
true,
|
||||
asset.name || undefined,
|
||||
)
|
||||
|
||||
return {
|
||||
content: [
|
||||
{
|
||||
type: 'text',
|
||||
text: `Document "${asset.name}" (ID: ${asset.id}, S3 Key: "${mediaKey}"):\n\n${text}`,
|
||||
},
|
||||
],
|
||||
details: {
|
||||
assetId: asset.id,
|
||||
name: asset.name,
|
||||
mediaType: asset.mediaType,
|
||||
key: mediaKey,
|
||||
downloadUrl,
|
||||
sourceKeys: [mediaKey],
|
||||
size: buffer.length,
|
||||
isTruncated,
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
// docConfig.mode === 'pages'
|
||||
if (docConfig.startPage === null || docConfig.endPage === null) {
|
||||
throw new Error('startPage and endPage are required when docConfig mode is "pages".')
|
||||
}
|
||||
|
||||
const start = docConfig.startPage
|
||||
const end = docConfig.endPage
|
||||
|
||||
if (start < 1) {
|
||||
throw new Error(`Invalid page range: start page (${start}) must be at least 1.`)
|
||||
}
|
||||
|
||||
if (start > end) {
|
||||
throw new Error(
|
||||
`Invalid page range: start page (${start}) must be less than or equal to end page (${end}).`,
|
||||
)
|
||||
}
|
||||
|
||||
const MAX_PAGE_RANGE = 20
|
||||
const requestedPages = end - start + 1
|
||||
if (requestedPages > MAX_PAGE_RANGE) {
|
||||
throw new Error(
|
||||
`Page range (${requestedPages} pages requested) exceeds the maximum limit of ${MAX_PAGE_RANGE} pages per request.`,
|
||||
)
|
||||
}
|
||||
|
||||
const { annotations, timestamp: commentTimestamp } = await resolveAnnotationsById(
|
||||
asset.id,
|
||||
annotationId,
|
||||
)
|
||||
|
||||
const task = await prisma.workflowTask.create({
|
||||
data: {
|
||||
assetId: asset.id,
|
||||
projectId: asset.projectId || 'none',
|
||||
type: WorkflowTaskType.transcode_pdf_pages,
|
||||
status: WorkflowTaskStatus.pending,
|
||||
payload: {
|
||||
projectId: asset.projectId || 'none',
|
||||
pdfPages: {
|
||||
start,
|
||||
end,
|
||||
commentTimestamp,
|
||||
annotations,
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
const completedTask = await workflowService.executeWait(task)
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any -- transcode pdf pages output
|
||||
const output = completedTask.output as any
|
||||
const pages = output?.pages as Array<{ key: string; page: number }> | undefined
|
||||
|
||||
if (!pages || pages.length === 0) {
|
||||
throw new Error('No PDF page images were generated.')
|
||||
}
|
||||
|
||||
const content: Array<TextContent | ImageContent> = []
|
||||
const sourceKeys: string[] = []
|
||||
const results: Array<{ key: string; page: number; downloadUrl: string }> = []
|
||||
const textLines: string[] = [
|
||||
`Rendered ${pages.length} page(s) of "${asset.name}" (Pages ${start} to ${end}):`,
|
||||
]
|
||||
|
||||
for (const pageItem of pages) {
|
||||
const { buffer, contentType } = await s3Service.getObject(bucket, pageItem.key)
|
||||
const mimeType =
|
||||
contentType && contentType !== 'application/octet-stream' ? contentType : 'image/webp'
|
||||
const downloadUrl = await s3Service.presign(
|
||||
bucket,
|
||||
pageItem.key,
|
||||
'GET',
|
||||
true,
|
||||
asset.name || undefined,
|
||||
)
|
||||
|
||||
textLines.push(`- Page ${pageItem.page}: S3 Key: "${pageItem.key}"`)
|
||||
content.push({
|
||||
type: 'image',
|
||||
data: buffer.toString('base64'),
|
||||
mimeType,
|
||||
})
|
||||
sourceKeys.push(pageItem.key)
|
||||
results.push({
|
||||
key: pageItem.key,
|
||||
page: pageItem.page,
|
||||
downloadUrl,
|
||||
})
|
||||
}
|
||||
|
||||
content.unshift({
|
||||
type: 'text',
|
||||
text: textLines.join('\n'),
|
||||
})
|
||||
|
||||
return {
|
||||
content,
|
||||
details: {
|
||||
assetId: asset.id,
|
||||
name: asset.name,
|
||||
mediaType: asset.mediaType,
|
||||
keys: sourceKeys,
|
||||
results,
|
||||
sourceKeys,
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
throw new Error(
|
||||
`Unsupported asset type for read_asset. Asset ${asset.id} has media type "${mediaType || 'unknown'}". Use download_asset to download this file to disk.`,
|
||||
)
|
||||
},
|
||||
}
|
||||
}
|
||||
@@ -1,209 +0,0 @@
|
||||
import { describe, it, expect, vi, beforeEach } from 'vitest'
|
||||
import { createReadPdfPagesTool } from './read-pdf-pages'
|
||||
import {
|
||||
prisma,
|
||||
WorkflowTaskStatus,
|
||||
type Asset,
|
||||
type AssetComment,
|
||||
type User,
|
||||
type WorkflowTask,
|
||||
} from '@shumai/db'
|
||||
import { s3Service } from '@shumai/core/src/s3/s3'
|
||||
import { workflowService } from '@shumai/workflow-core'
|
||||
import { authzService } from '@shumai/core/src/authz/authz'
|
||||
|
||||
vi.mock('@shumai/db', async (importOriginal) => {
|
||||
const actual = await importOriginal<typeof import('@shumai/db')>()
|
||||
return {
|
||||
...actual,
|
||||
prisma: {
|
||||
user: {
|
||||
findUnique: vi.fn(),
|
||||
},
|
||||
asset: {
|
||||
findUnique: vi.fn(),
|
||||
},
|
||||
assetComment: {
|
||||
findUnique: vi.fn(),
|
||||
},
|
||||
workflowTask: {
|
||||
create: vi.fn(),
|
||||
},
|
||||
},
|
||||
}
|
||||
})
|
||||
|
||||
vi.mock('@shumai/core/src/s3/s3', () => ({
|
||||
s3Service: {
|
||||
getObject: vi.fn(),
|
||||
},
|
||||
}))
|
||||
|
||||
vi.mock('@shumai/workflow-core', () => ({
|
||||
workflowService: {
|
||||
executeWait: vi.fn(),
|
||||
},
|
||||
}))
|
||||
|
||||
vi.mock('@shumai/core/src/authz/authz', () => ({
|
||||
authzService: {
|
||||
hasPermission: vi.fn(),
|
||||
},
|
||||
Permission: { Read: 'Read' },
|
||||
ResourceType: { Asset: 'asset' },
|
||||
}))
|
||||
|
||||
describe('readPdfPagesTool', () => {
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks()
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
})
|
||||
|
||||
it('should trigger pdfPages transcode workflow and return image outputs', async () => {
|
||||
vi.mocked(prisma.user.findUnique).mockResolvedValue({ id: 'user-1' } as User)
|
||||
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'asset-1',
|
||||
projectId: 'project-1',
|
||||
media: { proxyType: 'pdf' },
|
||||
} as unknown as Asset)
|
||||
|
||||
vi.mocked(prisma.assetComment.findUnique).mockResolvedValue({
|
||||
id: 'comment-1',
|
||||
assetId: 'asset-1',
|
||||
second: 2,
|
||||
annotation: [
|
||||
{
|
||||
type: 'box',
|
||||
color: '#ff0000',
|
||||
points: [
|
||||
[0, 0],
|
||||
[1, 1],
|
||||
],
|
||||
},
|
||||
],
|
||||
} as unknown as AssetComment)
|
||||
|
||||
vi.mocked(prisma.workflowTask.create).mockResolvedValue({
|
||||
id: 'task-1',
|
||||
} as unknown as WorkflowTask)
|
||||
|
||||
vi.mocked(workflowService.executeWait).mockResolvedValue({
|
||||
id: 'task-1',
|
||||
status: WorkflowTaskStatus.completed,
|
||||
output: {
|
||||
pages: [
|
||||
{ key: 'pdf_pages/page_1.webp', page: 1 },
|
||||
{ key: 'pdf_pages/page_2.webp', page: 2 },
|
||||
],
|
||||
},
|
||||
} as unknown as WorkflowTask)
|
||||
|
||||
vi.mocked(s3Service.getObject).mockImplementation(async (_bucket: string, key: string) => {
|
||||
return {
|
||||
buffer: Buffer.from(`fake-bytes-for-${key}`),
|
||||
contentType: 'image/webp',
|
||||
} as unknown as { buffer: Buffer; contentType: string }
|
||||
})
|
||||
|
||||
const tool = createReadPdfPagesTool('user-1', 'comment-1')
|
||||
const result = await tool.execute('call-1', { assetId: 'asset-1', start: 1, end: 2 })
|
||||
|
||||
expect(authzService.hasPermission).toHaveBeenCalledWith({
|
||||
user: { id: 'user-1' },
|
||||
permission: 'Read',
|
||||
type: 'asset',
|
||||
id: 'asset-1',
|
||||
})
|
||||
|
||||
expect(prisma.workflowTask.create).toHaveBeenCalledWith({
|
||||
data: {
|
||||
assetId: 'asset-1',
|
||||
projectId: 'project-1',
|
||||
type: 'transcode_pdf_pages',
|
||||
status: 'pending',
|
||||
payload: {
|
||||
projectId: 'project-1',
|
||||
pdfPages: {
|
||||
start: 1,
|
||||
end: 2,
|
||||
commentTimestamp: 2,
|
||||
annotations: [
|
||||
{
|
||||
type: 'box',
|
||||
color: '#ff0000',
|
||||
points: [
|
||||
[0, 0],
|
||||
[1, 1],
|
||||
],
|
||||
},
|
||||
],
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
expect(result.content.length).toBe(2)
|
||||
expect(result.content[0].type).toBe('image')
|
||||
expect((result.content[0] as unknown as { data: string }).data).toBe(
|
||||
Buffer.from('fake-bytes-for-pdf_pages/page_1.webp').toString('base64'),
|
||||
)
|
||||
expect(result.details.sourceKeys).toEqual(['pdf_pages/page_1.webp', 'pdf_pages/page_2.webp'])
|
||||
})
|
||||
|
||||
it('should throw error if start page is less than 1', async () => {
|
||||
const tool = createReadPdfPagesTool('user-1')
|
||||
await expect(tool.execute('call-1', { assetId: 'asset-1', start: 0, end: 5 })).rejects.toThrow(
|
||||
'Invalid page range: start page (0) must be at least 1.',
|
||||
)
|
||||
})
|
||||
|
||||
it('should throw error if start page is greater than end page', async () => {
|
||||
const tool = createReadPdfPagesTool('user-1')
|
||||
await expect(tool.execute('call-1', { assetId: 'asset-1', start: 5, end: 2 })).rejects.toThrow(
|
||||
'Invalid page range: start page (5) must be less than or equal to end page (2).',
|
||||
)
|
||||
})
|
||||
|
||||
it('should throw error if page range exceeds maximum limit of 20', async () => {
|
||||
const tool = createReadPdfPagesTool('user-1')
|
||||
await expect(tool.execute('call-1', { assetId: 'asset-1', start: 1, end: 25 })).rejects.toThrow(
|
||||
'Page range (25 pages requested) exceeds the maximum limit of 20 pages per request.',
|
||||
)
|
||||
})
|
||||
|
||||
it('should throw error if asset not found', async () => {
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue(null)
|
||||
|
||||
const tool = createReadPdfPagesTool('user-1')
|
||||
await expect(tool.execute('call-1', { assetId: 'asset-1', start: 1, end: 3 })).rejects.toThrow(
|
||||
'Asset with ID asset-1 not found.',
|
||||
)
|
||||
})
|
||||
|
||||
it('should throw error if proxyType is not pdf', async () => {
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'asset-1',
|
||||
projectId: 'project-1',
|
||||
media: { proxyType: 'image' },
|
||||
} as unknown as Asset)
|
||||
|
||||
const tool = createReadPdfPagesTool('user-1')
|
||||
await expect(tool.execute('call-1', { assetId: 'asset-1', start: 1, end: 3 })).rejects.toThrow(
|
||||
'Asset asset-1 is not a PDF or document.',
|
||||
)
|
||||
})
|
||||
|
||||
it('should throw error if proxyType is null/undefined (unprocessed)', async () => {
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'asset-1',
|
||||
projectId: 'project-1',
|
||||
media: null,
|
||||
} as unknown as Asset)
|
||||
|
||||
const tool = createReadPdfPagesTool('user-1')
|
||||
await expect(tool.execute('call-1', { assetId: 'asset-1', start: 1, end: 3 })).rejects.toThrow(
|
||||
'Asset asset-1 is not a PDF or document.',
|
||||
)
|
||||
})
|
||||
})
|
||||
@@ -1,142 +0,0 @@
|
||||
import { Type } from '@sinclair/typebox'
|
||||
import { type AgentTool } from '@earendil-works/pi-agent-core'
|
||||
import { type ImageContent } from '@earendil-works/pi-ai'
|
||||
import { prisma, WorkflowTaskType, WorkflowTaskStatus, type User } from '@shumai/db'
|
||||
import { s3Service } from '@shumai/core/src/s3/s3'
|
||||
import { workflowService } from '@shumai/workflow-core'
|
||||
import { authzService, Permission, ResourceType } from '@shumai/core/src/authz/authz'
|
||||
|
||||
const readPdfPagesSchema = Type.Object({
|
||||
assetId: Type.String({
|
||||
description: 'Asset ID of the PDF document. This parameter is required.',
|
||||
}),
|
||||
start: Type.Number({ description: 'Start page number (1-based index)' }),
|
||||
end: Type.Number({ description: 'End page number (1-based index)' }),
|
||||
})
|
||||
|
||||
export function createReadPdfPagesTool(
|
||||
userId: string,
|
||||
userCommentId?: string | null,
|
||||
): AgentTool<typeof readPdfPagesSchema> {
|
||||
return {
|
||||
name: 'read_pdf_pages',
|
||||
label: 'Read PDF Pages',
|
||||
description:
|
||||
'Converts specific page range of a PDF document into 1080p WebP images for visual analysis. Maximum 20 pages allowed per call.',
|
||||
parameters: readPdfPagesSchema,
|
||||
execute: async (_toolCallId, params) => {
|
||||
if (params.start < 1) {
|
||||
throw new Error(`Invalid page range: start page (${params.start}) must be at least 1.`)
|
||||
}
|
||||
|
||||
if (params.start > params.end) {
|
||||
throw new Error(
|
||||
`Invalid page range: start page (${params.start}) must be less than or equal to end page (${params.end}).`,
|
||||
)
|
||||
}
|
||||
|
||||
const MAX_PAGE_RANGE = 20
|
||||
const requestedPages = params.end - params.start + 1
|
||||
if (requestedPages > MAX_PAGE_RANGE) {
|
||||
throw new Error(
|
||||
`Page range (${requestedPages} pages requested) exceeds the maximum limit of ${MAX_PAGE_RANGE} pages per request.`,
|
||||
)
|
||||
}
|
||||
|
||||
const targetAssetId = params.assetId
|
||||
|
||||
if (!userId) {
|
||||
throw new Error('User ID is required for authorization.')
|
||||
}
|
||||
|
||||
await authzService.hasPermission({
|
||||
user: { id: userId } as User,
|
||||
permission: Permission.Read,
|
||||
type: ResourceType.Asset,
|
||||
id: targetAssetId,
|
||||
})
|
||||
|
||||
const asset = await prisma.asset.findUnique({
|
||||
where: { id: targetAssetId },
|
||||
})
|
||||
|
||||
if (!asset) {
|
||||
throw new Error(`Asset with ID ${targetAssetId} not found.`)
|
||||
}
|
||||
|
||||
const proxyType = (asset.media as PrismaJson.MediaInfo | null)?.proxyType
|
||||
if (proxyType !== 'pdf') {
|
||||
throw new Error(`Asset ${targetAssetId} is not a PDF or document.`)
|
||||
}
|
||||
|
||||
// Fetch trigger comment details for comment page and annotations
|
||||
let commentTimestamp: number | null = null
|
||||
let annotations: unknown = null
|
||||
if (userCommentId) {
|
||||
const comment = await prisma.assetComment.findUnique({
|
||||
where: { id: userCommentId },
|
||||
})
|
||||
if (comment && comment.assetId === targetAssetId) {
|
||||
commentTimestamp = comment.second !== null ? comment.second : null
|
||||
if (comment.annotation) {
|
||||
const list = comment.annotation
|
||||
if (Array.isArray(list) && list.length > 0) {
|
||||
annotations = list
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Trigger transcode workflow to render PDF pages
|
||||
const task = await prisma.workflowTask.create({
|
||||
data: {
|
||||
assetId: targetAssetId,
|
||||
projectId: asset.projectId || 'none',
|
||||
type: WorkflowTaskType.transcode_pdf_pages,
|
||||
status: WorkflowTaskStatus.pending,
|
||||
payload: {
|
||||
projectId: asset.projectId || 'none',
|
||||
pdfPages: {
|
||||
start: params.start,
|
||||
end: params.end,
|
||||
commentTimestamp,
|
||||
annotations: annotations as PrismaJson.AnnotationList,
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
const completedTask = await workflowService.executeWait(task)
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const output = completedTask.output as any
|
||||
const pages = output?.pages as Array<{ key: string; page: number }> | undefined
|
||||
|
||||
if (!pages || pages.length === 0) {
|
||||
throw new Error('No PDF page images were generated.')
|
||||
}
|
||||
|
||||
const content: ImageContent[] = []
|
||||
const sourceKeys: string[] = []
|
||||
const bucket = process.env.S3_BUCKET || 'shumai'
|
||||
|
||||
for (const pageItem of pages) {
|
||||
const { buffer, contentType } = await s3Service.getObject(bucket, pageItem.key)
|
||||
const mimeType =
|
||||
contentType && contentType !== 'application/octet-stream' ? contentType : 'image/webp'
|
||||
content.push({
|
||||
type: 'image',
|
||||
data: buffer.toString('base64'),
|
||||
mimeType,
|
||||
})
|
||||
sourceKeys.push(pageItem.key)
|
||||
}
|
||||
|
||||
return {
|
||||
content,
|
||||
details: {
|
||||
sourceKeys,
|
||||
},
|
||||
}
|
||||
},
|
||||
}
|
||||
}
|
||||
@@ -307,6 +307,77 @@ describe('readSkillTool', () => {
|
||||
reviewerTool.execute('1', { skillId: ownerSkill.id }, undefined, undefined),
|
||||
).rejects.toThrow('Permission denied')
|
||||
})
|
||||
|
||||
it('uses the effective project role for skill permission checks', async () => {
|
||||
const team = await prisma.team.create({ data: { name: 'Project Skill Team' } })
|
||||
const project = await prisma.project.create({ data: { name: 'Skill Proj', teamId: team.id } })
|
||||
const editorSkill = await prisma.skill.create({
|
||||
data: {
|
||||
name: 'Editor Project Skill',
|
||||
assetId: 'asset1',
|
||||
hash: 'proj-editor-hash',
|
||||
teamId: team.id,
|
||||
permission: 'editor',
|
||||
},
|
||||
})
|
||||
|
||||
// Team editor demoted to project reviewer: denied inside the project
|
||||
const demoted = await prisma.user.create({
|
||||
data: { name: 'Demoted Skill', email: 'dem-skill@test.com' },
|
||||
})
|
||||
const demotedTm = await prisma.teamMember.create({
|
||||
data: { teamId: team.id, userId: demoted.id, role: 'editor', scope: 'team' },
|
||||
})
|
||||
await prisma.projectMember.create({
|
||||
data: { projectId: project.id, teamMemberId: demotedTm.id, role: 'reviewer' },
|
||||
})
|
||||
|
||||
const demotedTool = createReadSkillTool(
|
||||
demoted.id,
|
||||
() => {},
|
||||
undefined,
|
||||
undefined,
|
||||
project.id,
|
||||
)
|
||||
await expect(
|
||||
demotedTool.execute('1', { skillId: editorSkill.id }, undefined, undefined),
|
||||
).rejects.toThrow('Permission denied')
|
||||
|
||||
// Project-scoped member invited as editor: allowed
|
||||
const projEditor = await prisma.user.create({
|
||||
data: { name: 'PE Skill', email: 'pe-skill@test.com' },
|
||||
})
|
||||
const projEditorTm = await prisma.teamMember.create({
|
||||
data: { teamId: team.id, userId: projEditor.id, role: 'reviewer', scope: 'project' },
|
||||
})
|
||||
await prisma.projectMember.create({
|
||||
data: { projectId: project.id, teamMemberId: projEditorTm.id, role: 'editor' },
|
||||
})
|
||||
|
||||
vi.spyOn(fs, 'existsSync').mockReturnValue(true)
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any -- mocking node fs calls
|
||||
vi.spyOn(fs, 'readFileSync').mockImplementation((path: any) => {
|
||||
if (path.toString().endsWith('.hash')) return 'proj-editor-hash'
|
||||
if (path.toString().endsWith('SKILL.md')) return '# Editor Project Skill Content'
|
||||
return ''
|
||||
})
|
||||
|
||||
const projEditorTool = createReadSkillTool(
|
||||
projEditor.id,
|
||||
() => {},
|
||||
undefined,
|
||||
undefined,
|
||||
project.id,
|
||||
)
|
||||
const result = await projEditorTool.execute(
|
||||
'1',
|
||||
{ skillId: editorSkill.id },
|
||||
undefined,
|
||||
undefined,
|
||||
)
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
expect((result.content[0] as any).text).toBe('# Editor Project Skill Content')
|
||||
})
|
||||
})
|
||||
|
||||
describe('onSkillLoaded callback', () => {
|
||||
@@ -363,4 +434,75 @@ describe('readSkillTool', () => {
|
||||
expect(onSkillLoaded).not.toHaveBeenCalled()
|
||||
})
|
||||
})
|
||||
|
||||
describe('enabled skills enforcement', () => {
|
||||
it('should reject loading a skill that is not enabled for the agent', async () => {
|
||||
const team = await prisma.team.create({ data: { name: 'Enabled Filter Team' } })
|
||||
const skill = await prisma.skill.create({
|
||||
data: {
|
||||
name: 'Disabled For Agent Skill',
|
||||
assetId: 'asset1',
|
||||
hash: 'disabled-agent-hash',
|
||||
teamId: team.id,
|
||||
},
|
||||
})
|
||||
|
||||
const readSkillTool = createReadSkillTool(undefined, () => {}, undefined, [
|
||||
'some-other-enabled-skill',
|
||||
])
|
||||
await expect(
|
||||
readSkillTool.execute('1', { skillId: skill.id }, undefined, undefined),
|
||||
).rejects.toThrow('not enabled for this agent')
|
||||
})
|
||||
|
||||
it('should allow loading a skill that is enabled for the agent', async () => {
|
||||
const team = await prisma.team.create({ data: { name: 'Enabled Allow Team' } })
|
||||
const skill = await prisma.skill.create({
|
||||
data: {
|
||||
name: 'Enabled For Agent Skill',
|
||||
assetId: 'asset1',
|
||||
hash: 'enabled-agent-hash',
|
||||
teamId: team.id,
|
||||
},
|
||||
})
|
||||
|
||||
vi.spyOn(fs, 'existsSync').mockReturnValue(true)
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any -- mocking node fs readFileSync which has complex overloaded signatures
|
||||
vi.spyOn(fs, 'readFileSync').mockImplementation((path: any) => {
|
||||
if (path.toString().endsWith('.hash')) return 'enabled-agent-hash'
|
||||
if (path.toString().endsWith('SKILL.md')) return '# Enabled For Agent Skill'
|
||||
return ''
|
||||
})
|
||||
|
||||
const readSkillTool = createReadSkillTool(undefined, () => {}, undefined, [skill.id])
|
||||
const result = await readSkillTool.execute('1', { skillId: skill.id }, undefined, undefined)
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
expect((result.content[0] as any).text).toBe('# Enabled For Agent Skill')
|
||||
})
|
||||
|
||||
it('should allow loading any skill when enabledSkillIds is not provided (backward compatibility)', async () => {
|
||||
const team = await prisma.team.create({ data: { name: 'No Filter Team' } })
|
||||
const skill = await prisma.skill.create({
|
||||
data: {
|
||||
name: 'No Filter Skill',
|
||||
assetId: 'asset1',
|
||||
hash: 'no-filter-hash',
|
||||
teamId: team.id,
|
||||
},
|
||||
})
|
||||
|
||||
vi.spyOn(fs, 'existsSync').mockReturnValue(true)
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any -- mocking node fs readFileSync which has complex overloaded signatures
|
||||
vi.spyOn(fs, 'readFileSync').mockImplementation((path: any) => {
|
||||
if (path.toString().endsWith('.hash')) return 'no-filter-hash'
|
||||
if (path.toString().endsWith('SKILL.md')) return '# No Filter Skill'
|
||||
return ''
|
||||
})
|
||||
|
||||
const readSkillTool = createReadSkillTool(undefined, () => {})
|
||||
const result = await readSkillTool.execute('1', { skillId: skill.id }, undefined, undefined)
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
expect((result.content[0] as any).text).toBe('# No Filter Skill')
|
||||
})
|
||||
})
|
||||
})
|
||||
|
||||
@@ -1,7 +1,8 @@
|
||||
import { prisma } from '@shumai/db'
|
||||
import { Type } from '@sinclair/typebox'
|
||||
import { Type } from 'typebox'
|
||||
import { type AgentTool } from '@earendil-works/pi-agent-core'
|
||||
import { agentService } from '@shumai/core/src/agent/agent'
|
||||
import { resolveEffectiveRole } from '@shumai/core/src/authz/authz'
|
||||
|
||||
const readSkillSchema = Type.Object({
|
||||
skillId: Type.String({ description: 'The ID of the skill to read' }),
|
||||
@@ -17,6 +18,8 @@ export const createReadSkillTool = (
|
||||
userId: string | undefined,
|
||||
onEnvsAdded: (envs: Record<string, string>) => void,
|
||||
onSkillLoaded?: () => Promise<void> | void,
|
||||
enabledSkillIds?: string[],
|
||||
projectId?: string,
|
||||
): AgentTool<typeof readSkillSchema, { skillId: string }> => ({
|
||||
name: 'read_skill',
|
||||
label: 'Read Agent Skill',
|
||||
@@ -31,18 +34,21 @@ export const createReadSkillTool = (
|
||||
throw new Error(`Skill with ID ${params.skillId} not found.`)
|
||||
}
|
||||
|
||||
// Skills disabled for this agent must not be loadable, even if the model
|
||||
// somehow knows their ID (e.g. from earlier conversation history).
|
||||
if (enabledSkillIds && !enabledSkillIds.includes(params.skillId)) {
|
||||
throw new Error(`Skill with ID ${params.skillId} is not enabled for this agent.`)
|
||||
}
|
||||
|
||||
const requiredLevel = ROLE_HIERARCHY[skill.permission] || 1
|
||||
const effectiveRole = userId
|
||||
? await resolveEffectiveRole(skill.teamId, projectId, userId)
|
||||
: null
|
||||
|
||||
if (userId) {
|
||||
const member = await prisma.teamMember.findUnique({
|
||||
where: {
|
||||
teamIdUserId: {
|
||||
teamId: skill.teamId,
|
||||
userId,
|
||||
},
|
||||
},
|
||||
})
|
||||
const userLevel = member ? ROLE_HIERARCHY[member.role] || 0 : 0
|
||||
// Resolve the user's effective role for the project context (project
|
||||
// override wins; project-scoped members without project access are denied).
|
||||
const userLevel = effectiveRole ? ROLE_HIERARCHY[effectiveRole] || 0 : 0
|
||||
if (userLevel < requiredLevel) {
|
||||
throw new Error(
|
||||
`Permission denied: Insufficient role to load skill "${skill.name}". Minimum required role is "${skill.permission}".`,
|
||||
|
||||
@@ -51,6 +51,8 @@ describe('createReadThreadTool', () => {
|
||||
id: 'root-1',
|
||||
message: 'Initial top-level question',
|
||||
creator: { name: 'Alice' },
|
||||
second: 12.5,
|
||||
annotation: [{ type: 'box' }],
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
} as any)
|
||||
vi.mocked(prisma.assetComment.findMany).mockResolvedValue([])
|
||||
@@ -59,7 +61,9 @@ describe('createReadThreadTool', () => {
|
||||
const result = await tool.execute('call-2', { threadId: 'root-1' })
|
||||
const textContent = (result.content[0] as { text: string }).text
|
||||
|
||||
expect(textContent).toContain('Thread Root [Alice] (root-1): Initial top-level question')
|
||||
expect(textContent).toContain(
|
||||
'Thread Root [Alice] (id: root-1, time: 12.5s, has_markup: true): Initial top-level question',
|
||||
)
|
||||
expect(textContent).toContain('(No replies in this thread yet)')
|
||||
})
|
||||
|
||||
@@ -75,6 +79,8 @@ describe('createReadThreadTool', () => {
|
||||
id: 'reply-1',
|
||||
message: 'First reply to thread',
|
||||
creator: { name: 'Bob' },
|
||||
second: 15.0,
|
||||
annotation: [{ type: 'line' }],
|
||||
},
|
||||
{
|
||||
id: 'reply-2',
|
||||
@@ -88,8 +94,45 @@ describe('createReadThreadTool', () => {
|
||||
const result = await tool.execute('call-3', { threadId: 'root-1' })
|
||||
const textContent = (result.content[0] as { text: string }).text
|
||||
|
||||
expect(textContent).toContain('Thread Root [Alice] (root-1): Initial top-level question')
|
||||
expect(textContent).toContain('- [Bob]: First reply to thread')
|
||||
expect(textContent).toContain('- [Charlie]: Second reply to thread')
|
||||
expect(textContent).toContain(
|
||||
'Thread Root [Alice] (id: root-1, has_markup: false): Initial top-level question',
|
||||
)
|
||||
expect(textContent).toContain(
|
||||
'- [Bob] (id: reply-1, time: 15s, has_markup: true): First reply to thread',
|
||||
)
|
||||
expect(textContent).toContain(
|
||||
'- [Charlie] (id: reply-2, has_markup: false): Second reply to thread',
|
||||
)
|
||||
})
|
||||
|
||||
it('should label agent replies as [Ai Agent] when creator is null but sessionId exists', async () => {
|
||||
vi.mocked(prisma.assetComment.findUnique).mockResolvedValue({
|
||||
id: 'root-1',
|
||||
message: 'Question to agent',
|
||||
creator: { name: 'Alice' },
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
} as any)
|
||||
vi.mocked(prisma.assetComment.findMany).mockResolvedValue([
|
||||
{
|
||||
id: 'reply-1',
|
||||
message: 'Agent answer',
|
||||
creator: null,
|
||||
sessionId: 'session-123',
|
||||
},
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
] as any)
|
||||
|
||||
const tool = createReadThreadTool()
|
||||
const result = await tool.execute('call-agent', { threadId: 'root-1' })
|
||||
const textContent = (result.content[0] as { text: string }).text
|
||||
|
||||
expect(textContent).toContain('- [Ai Agent] (id: reply-1, has_markup: false): Agent answer')
|
||||
})
|
||||
|
||||
it('should describe threadId parameter as referencing <thread id="..." /> in <context>', () => {
|
||||
const tool = createReadThreadTool()
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const description = (tool.parameters as any).properties.threadId.description
|
||||
expect(description).toContain('<thread id="..." />')
|
||||
})
|
||||
})
|
||||
|
||||
@@ -1,14 +1,28 @@
|
||||
import { prisma } from '@shumai/db'
|
||||
import { Type } from '@sinclair/typebox'
|
||||
import { Type } from 'typebox'
|
||||
import { type AgentTool } from '@earendil-works/pi-agent-core'
|
||||
|
||||
const readThreadSchema = Type.Object({
|
||||
threadId: Type.String({
|
||||
description:
|
||||
'The root comment ID of a thread (e.g. from [Thread ID: ...]). Do NOT pass an asset ID or project ID.',
|
||||
'The root comment ID of a thread (from <thread id="..." /> in the <context> block). Do NOT pass an asset ID or project ID.',
|
||||
}),
|
||||
})
|
||||
|
||||
function formatCommentMeta(c: {
|
||||
id: string
|
||||
second?: number | null
|
||||
annotation?: unknown
|
||||
}): string {
|
||||
const parts = [`id: ${c.id}`]
|
||||
if (c.second !== null && c.second !== undefined) {
|
||||
parts.push(`time: ${c.second}s`)
|
||||
}
|
||||
const hasMarkup = Boolean(c.annotation && Array.isArray(c.annotation) && c.annotation.length > 0)
|
||||
parts.push(`has_markup: ${hasMarkup}`)
|
||||
return `(${parts.join(', ')})`
|
||||
}
|
||||
|
||||
export const createReadThreadTool = (): AgentTool<
|
||||
typeof readThreadSchema,
|
||||
{ threadId: string }
|
||||
@@ -47,15 +61,19 @@ export const createReadThreadTool = (): AgentTool<
|
||||
include: { creator: true },
|
||||
})
|
||||
|
||||
const rootAuthor = rootComment.creator?.name || 'User'
|
||||
let output = `Thread Root [${rootAuthor}] (${rootComment.id}): ${rootComment.message || ''}\n\nReplies (${replies.length}):`
|
||||
const isRootAgent = rootComment.creator?.type === 'agent' || rootComment.sessionId !== null
|
||||
const rootAuthor = rootComment.creator?.name || (isRootAgent ? 'Ai Agent' : 'User')
|
||||
const rootMeta = formatCommentMeta(rootComment)
|
||||
let output = `Thread Root [${rootAuthor}] ${rootMeta}: ${rootComment.message || ''}\n\nReplies (${replies.length}):`
|
||||
|
||||
if (replies.length === 0) {
|
||||
output += '\n(No replies in this thread yet)'
|
||||
} else {
|
||||
for (const reply of replies) {
|
||||
const author = reply.creator?.name || 'User'
|
||||
output += `\n- [${author}]: ${reply.message || ''}`
|
||||
const isAgent = reply.creator?.type === 'agent' || reply.sessionId !== null
|
||||
const author = reply.creator?.name || (isAgent ? 'Ai Agent' : 'User')
|
||||
const replyMeta = formatCommentMeta(reply)
|
||||
output += `\n- [${author}] ${replyMeta}: ${reply.message || ''}`
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
import { logger } from '@shumai/core/src/logger'
|
||||
import { SandboxManager } from '@anthropic-ai/sandbox-runtime'
|
||||
import { type AgentTool, type AgentToolResult } from '@earendil-works/pi-agent-core'
|
||||
import { Type } from '@sinclair/typebox'
|
||||
import { Type } from 'typebox'
|
||||
import { spawn } from 'node:child_process'
|
||||
import { OutputAccumulator } from '../utils/output-accumulator'
|
||||
import {
|
||||
@@ -10,6 +10,8 @@ import {
|
||||
formatSize,
|
||||
type TruncationResult,
|
||||
} from '../utils/truncate'
|
||||
import { quotaService } from '@shumai/core/src/quota/quota-service'
|
||||
import type { TeamMemberRole } from '@shumai/db'
|
||||
|
||||
const BashSource = Type.String({
|
||||
enum: ['user', 'skill'],
|
||||
@@ -33,6 +35,9 @@ export interface BashDetails {
|
||||
}
|
||||
|
||||
export interface SandboxedBashOptions {
|
||||
teamId?: string
|
||||
userId?: string
|
||||
role?: TeamMemberRole | null
|
||||
getBlockedHost?: () => string
|
||||
clearBlockedHost?: () => void
|
||||
/**
|
||||
@@ -66,6 +71,18 @@ export const createSandboxedBashTool = (
|
||||
'Only commands required by a loaded skill (source="skill") can be executed.',
|
||||
)
|
||||
}
|
||||
if (options?.teamId) {
|
||||
await quotaService.checkQuota(
|
||||
{
|
||||
teamId: options.teamId,
|
||||
userId: options.userId,
|
||||
role: options.role,
|
||||
resource: 'agent_bash_call_count',
|
||||
resourceData: { command },
|
||||
},
|
||||
1,
|
||||
)
|
||||
}
|
||||
options?.clearBlockedHost?.()
|
||||
const wrappedCommand = await SandboxManager.wrapWithSandbox(command)
|
||||
|
||||
@@ -219,6 +236,23 @@ export const createSandboxedBashTool = (
|
||||
const snapshot = await finishOutput()
|
||||
const { text: outputText, details: truncationDetails } = formatOutput(snapshot)
|
||||
|
||||
if (options?.teamId) {
|
||||
try {
|
||||
await quotaService.consumeQuota(
|
||||
{
|
||||
teamId: options.teamId,
|
||||
userId: options.userId,
|
||||
role: options.role,
|
||||
resource: 'agent_bash_call_count',
|
||||
resourceData: { command },
|
||||
},
|
||||
1,
|
||||
)
|
||||
} catch (err) {
|
||||
logger.error({ err }, 'Failed to record quota usage for bash command')
|
||||
}
|
||||
}
|
||||
|
||||
if (signal?.aborted) {
|
||||
logger.error({ command, outputText }, 'Sandboxed bash command aborted')
|
||||
reject(new Error(appendStatus(outputText, 'Command aborted')))
|
||||
|
||||
@@ -1,156 +0,0 @@
|
||||
import { describe, it, expect, vi, beforeEach } from 'vitest'
|
||||
import { createScreenshotTool } from './screenshot'
|
||||
import {
|
||||
prisma,
|
||||
WorkflowTaskStatus,
|
||||
type Asset,
|
||||
type AssetComment,
|
||||
type User,
|
||||
type WorkflowTask,
|
||||
} from '@shumai/db'
|
||||
import { s3Service } from '@shumai/core/src/s3/s3'
|
||||
import { workflowService } from '@shumai/workflow-core'
|
||||
import { authzService } from '@shumai/core/src/authz/authz'
|
||||
|
||||
vi.mock('@shumai/db', async (importOriginal) => {
|
||||
const actual = await importOriginal<typeof import('@shumai/db')>()
|
||||
return {
|
||||
...actual,
|
||||
prisma: {
|
||||
user: {
|
||||
findUnique: vi.fn(),
|
||||
},
|
||||
asset: {
|
||||
findUnique: vi.fn(),
|
||||
},
|
||||
assetComment: {
|
||||
findUnique: vi.fn(),
|
||||
},
|
||||
workflowTask: {
|
||||
create: vi.fn(),
|
||||
},
|
||||
},
|
||||
}
|
||||
})
|
||||
|
||||
vi.mock('@shumai/core/src/s3/s3', () => ({
|
||||
s3Service: {
|
||||
getObject: vi.fn(),
|
||||
},
|
||||
}))
|
||||
|
||||
vi.mock('@shumai/workflow-core', () => ({
|
||||
workflowService: {
|
||||
executeWait: vi.fn(),
|
||||
},
|
||||
}))
|
||||
|
||||
vi.mock('@shumai/core/src/authz/authz', () => ({
|
||||
authzService: {
|
||||
hasPermission: vi.fn(),
|
||||
},
|
||||
Permission: { Read: 'Read' },
|
||||
ResourceType: { Asset: 'asset' },
|
||||
}))
|
||||
|
||||
describe('screenshotTool', () => {
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks()
|
||||
})
|
||||
|
||||
it('should trigger screenshot transcode workflow and return image outputs', async () => {
|
||||
vi.mocked(prisma.user.findUnique).mockResolvedValue({ id: 'user-1' } as User)
|
||||
vi.mocked(authzService.hasPermission).mockResolvedValue()
|
||||
|
||||
vi.mocked(prisma.asset.findUnique).mockResolvedValue({
|
||||
id: 'asset-1',
|
||||
projectId: 'project-1',
|
||||
} as unknown as Asset)
|
||||
|
||||
vi.mocked(prisma.assetComment.findUnique).mockResolvedValue({
|
||||
id: 'comment-1',
|
||||
assetId: 'asset-1',
|
||||
second: 5.0,
|
||||
annotation: [
|
||||
{
|
||||
type: 'line',
|
||||
color: '#00ff00',
|
||||
points: [
|
||||
[0, 0],
|
||||
[1, 1],
|
||||
],
|
||||
},
|
||||
],
|
||||
} as unknown as AssetComment)
|
||||
|
||||
vi.mocked(prisma.workflowTask.create).mockResolvedValue({
|
||||
id: 'task-1',
|
||||
} as unknown as WorkflowTask)
|
||||
|
||||
vi.mocked(workflowService.executeWait).mockResolvedValue({
|
||||
id: 'task-1',
|
||||
status: WorkflowTaskStatus.completed,
|
||||
output: {
|
||||
screenshots: [
|
||||
{ key: 'screenshots/shot1.webp', timestamp: 0.0 },
|
||||
{ key: 'screenshots/shot2.webp', timestamp: 5.0 },
|
||||
],
|
||||
},
|
||||
} as unknown as WorkflowTask)
|
||||
|
||||
vi.mocked(s3Service.getObject).mockImplementation(async (_bucket: string, key: string) => {
|
||||
return {
|
||||
buffer: Buffer.from(`fake-bytes-for-${key}`),
|
||||
contentType: 'image/webp',
|
||||
} as unknown as { buffer: Buffer; contentType: string }
|
||||
})
|
||||
|
||||
const tool = createScreenshotTool('user-1', 'comment-1')
|
||||
const result = await tool.execute('call-1', { assetId: 'asset-1', start: 0, end: 10, count: 2 })
|
||||
|
||||
expect(authzService.hasPermission).toHaveBeenCalledWith({
|
||||
user: { id: 'user-1' },
|
||||
permission: 'Read',
|
||||
type: 'asset',
|
||||
id: 'asset-1',
|
||||
})
|
||||
|
||||
expect(prisma.workflowTask.create).toHaveBeenCalledWith({
|
||||
data: {
|
||||
assetId: 'asset-1',
|
||||
projectId: 'project-1',
|
||||
type: 'transcode_screenshot',
|
||||
status: 'pending',
|
||||
payload: {
|
||||
projectId: 'project-1',
|
||||
screenshot: {
|
||||
start: 0,
|
||||
end: 10,
|
||||
count: 2,
|
||||
commentTimestamp: 5.0,
|
||||
annotations: [
|
||||
{
|
||||
type: 'line',
|
||||
color: '#00ff00',
|
||||
points: [
|
||||
[0, 0],
|
||||
[1, 1],
|
||||
],
|
||||
},
|
||||
],
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
expect(result.content.length).toBe(2)
|
||||
expect(result.content[0].type).toBe('image')
|
||||
expect((result.content[0] as unknown as { data: string }).data).toBe(
|
||||
Buffer.from('fake-bytes-for-screenshots/shot1.webp').toString('base64'),
|
||||
)
|
||||
expect((result.content[1] as unknown as { data: string }).data).toBe(
|
||||
Buffer.from('fake-bytes-for-screenshots/shot2.webp').toString('base64'),
|
||||
)
|
||||
expect(result.details.sourceKeys).toEqual(['screenshots/shot1.webp', 'screenshots/shot2.webp'])
|
||||
})
|
||||
})
|
||||
@@ -1,123 +0,0 @@
|
||||
import { Type } from '@sinclair/typebox'
|
||||
import { type AgentTool } from '@earendil-works/pi-agent-core'
|
||||
import { type ImageContent } from '@earendil-works/pi-ai'
|
||||
import { prisma, WorkflowTaskType, WorkflowTaskStatus, type User } from '@shumai/db'
|
||||
import { s3Service } from '@shumai/core/src/s3/s3'
|
||||
import { workflowService } from '@shumai/workflow-core'
|
||||
import { authzService, Permission, ResourceType } from '@shumai/core/src/authz/authz'
|
||||
|
||||
const screenshotSchema = Type.Object({
|
||||
assetId: Type.String({
|
||||
description: 'The asset ID of the video asset. This parameter is required.',
|
||||
}),
|
||||
start: Type.Number({ description: 'Start time in seconds' }),
|
||||
end: Type.Number({ description: 'End time in seconds' }),
|
||||
count: Type.Number({ description: 'Number of screenshots to take' }),
|
||||
})
|
||||
|
||||
export function createScreenshotTool(
|
||||
userId: string,
|
||||
userCommentId?: string | null,
|
||||
): AgentTool<typeof screenshotSchema> {
|
||||
return {
|
||||
name: 'screenshot',
|
||||
label: 'Take Video Screenshots',
|
||||
description:
|
||||
'Takes screenshots for a video at specified interval. It returns the images to the agent context.',
|
||||
parameters: screenshotSchema,
|
||||
execute: async (_toolCallId, params) => {
|
||||
const assetId = params.assetId
|
||||
|
||||
if (!userId) {
|
||||
throw new Error('User ID is required for authorization.')
|
||||
}
|
||||
|
||||
await authzService.hasPermission({
|
||||
user: { id: userId } as User,
|
||||
permission: Permission.Read,
|
||||
type: ResourceType.Asset,
|
||||
id: assetId,
|
||||
})
|
||||
|
||||
const asset = await prisma.asset.findUnique({
|
||||
where: { id: assetId },
|
||||
})
|
||||
|
||||
if (!asset) {
|
||||
throw new Error(`Asset with ID ${assetId} not found.`)
|
||||
}
|
||||
|
||||
// Fetch trigger comment details for timestamp and annotations
|
||||
let commentTimestamp: number | null = null
|
||||
let annotations: unknown = null
|
||||
if (userCommentId) {
|
||||
const comment = await prisma.assetComment.findUnique({
|
||||
where: { id: userCommentId },
|
||||
})
|
||||
if (comment && comment.assetId === assetId) {
|
||||
commentTimestamp = comment.second !== null ? comment.second : null
|
||||
if (comment.annotation) {
|
||||
const list = comment.annotation
|
||||
if (Array.isArray(list) && list.length > 0) {
|
||||
annotations = list
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Trigger transcode workflow to take screenshots
|
||||
const task = await prisma.workflowTask.create({
|
||||
data: {
|
||||
assetId,
|
||||
projectId: asset.projectId || 'none',
|
||||
type: WorkflowTaskType.transcode_screenshot,
|
||||
status: WorkflowTaskStatus.pending,
|
||||
payload: {
|
||||
projectId: asset.projectId || 'none',
|
||||
screenshot: {
|
||||
start: params.start,
|
||||
end: params.end,
|
||||
count: params.count,
|
||||
commentTimestamp,
|
||||
annotations: annotations as PrismaJson.AnnotationList,
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
const completedTask = await workflowService.executeWait(task)
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const output = completedTask.output as any
|
||||
const screenshots = output?.screenshots as
|
||||
| Array<{ key: string; timestamp: number }>
|
||||
| undefined
|
||||
|
||||
if (!screenshots || screenshots.length === 0) {
|
||||
throw new Error('No screenshots were generated.')
|
||||
}
|
||||
|
||||
const content: ImageContent[] = []
|
||||
const sourceKeys: string[] = []
|
||||
const bucket = process.env.S3_BUCKET || 'shumai'
|
||||
|
||||
for (const shot of screenshots) {
|
||||
const { buffer, contentType } = await s3Service.getObject(bucket, shot.key)
|
||||
const mimeType =
|
||||
contentType && contentType !== 'application/octet-stream' ? contentType : 'image/webp'
|
||||
content.push({
|
||||
type: 'image',
|
||||
data: buffer.toString('base64'),
|
||||
mimeType,
|
||||
})
|
||||
sourceKeys.push(shot.key)
|
||||
}
|
||||
|
||||
return {
|
||||
content,
|
||||
details: {
|
||||
sourceKeys,
|
||||
},
|
||||
}
|
||||
},
|
||||
}
|
||||
}
|
||||
@@ -1,35 +0,0 @@
|
||||
import { prisma } from '@shumai/db'
|
||||
import { workflowService } from '@shumai/workflow-core'
|
||||
import { WorkflowTaskType, WorkflowTaskStatus } from '@shumai/db'
|
||||
|
||||
export async function executeAgentToolWorkflow(params: {
|
||||
toolName: string
|
||||
args: Record<string, unknown>
|
||||
userId: string
|
||||
assetId: string
|
||||
}): Promise<unknown> {
|
||||
const task = await prisma.workflowTask.create({
|
||||
data: {
|
||||
type: WorkflowTaskType.agent_tool_call,
|
||||
status: WorkflowTaskStatus.pending,
|
||||
assetId: params.assetId,
|
||||
payload: {
|
||||
projectId: 'none',
|
||||
agentToolCall: {
|
||||
toolName: params.toolName,
|
||||
args: params.args,
|
||||
userId: params.userId,
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
const completedTask = await workflowService.executeWait(task)
|
||||
if (completedTask.status === WorkflowTaskStatus.failed) {
|
||||
const output = completedTask.output as Record<string, unknown> | null
|
||||
const errorMsg = (output?.error as string) || 'Workflow task failed'
|
||||
throw new Error(errorMsg)
|
||||
}
|
||||
|
||||
return completedTask.output
|
||||
}
|
||||
@@ -64,6 +64,7 @@ describe('Agent Autofill Workflow', () => {
|
||||
mockActivities.createCommentActivity.mockResolvedValue({ id: 'comment-placeholder-id' })
|
||||
mockActivities.getAssetActivity.mockResolvedValue({
|
||||
id: 'a1',
|
||||
projectId: 'p1',
|
||||
storageKey: { key: 'asset-key' },
|
||||
project: { id: 'p1', teamId: 't1' },
|
||||
mediaType: 'image/png',
|
||||
@@ -78,7 +79,6 @@ describe('Agent Autofill Workflow', () => {
|
||||
{ key: 'title', config: { name: 'Title', type: 'text' }, description: 'The title' },
|
||||
])
|
||||
mockActivities.getAgentAutofillContextActivity.mockResolvedValue({ agent: { id: 'b1' } })
|
||||
mockActivities.getAssetAutofillContextActivity.mockResolvedValue('Generated using gemini')
|
||||
mockActivities.autofillAiActivity.mockResolvedValue({
|
||||
text: '{"title":"Extracted Title"}',
|
||||
sessionId: 'session-123',
|
||||
@@ -118,6 +118,9 @@ describe('Agent Autofill Workflow', () => {
|
||||
status: 'processing',
|
||||
})
|
||||
|
||||
// Verify asset fetched
|
||||
expect(mockActivities.getAssetActivity).toHaveBeenCalledWith('a1')
|
||||
|
||||
// Verify placeholder comment created
|
||||
expect(mockActivities.createCommentActivity).toHaveBeenCalledWith({
|
||||
assetId: 'a1',
|
||||
@@ -140,11 +143,12 @@ describe('Agent Autofill Workflow', () => {
|
||||
expect(mockActivities.getAgentAutofillContextActivity).toHaveBeenCalledWith({
|
||||
teamId: 't1',
|
||||
})
|
||||
expect(mockActivities.getAssetAutofillContextActivity).toHaveBeenCalledWith('a1')
|
||||
|
||||
// Verify AI autofill called with mapped fields
|
||||
expect(mockActivities.autofillAiActivity).toHaveBeenCalledWith({
|
||||
teamId: 't1',
|
||||
assetId: 'a1',
|
||||
projectId: 'p1',
|
||||
images: ['/tmp/test-dir/1.webp'],
|
||||
fields: [
|
||||
{
|
||||
@@ -154,7 +158,6 @@ describe('Agent Autofill Workflow', () => {
|
||||
},
|
||||
],
|
||||
context: { agent: { id: 'b1' } },
|
||||
agentContext: 'Generated using gemini',
|
||||
})
|
||||
|
||||
// Verify task usage update
|
||||
@@ -195,42 +198,6 @@ describe('Agent Autofill Workflow', () => {
|
||||
})
|
||||
})
|
||||
|
||||
it('should run autofill without agentContext when the asset has no context', async () => {
|
||||
mockActivities.getAssetAutofillContextActivity.mockResolvedValue(null)
|
||||
|
||||
const task = await prisma.workflowTask.create({
|
||||
data: {
|
||||
type: 'ai_metadata_autofill',
|
||||
status: 'pending',
|
||||
assetId: 'a1',
|
||||
payload: {
|
||||
projectId: 'p1',
|
||||
agent: { sessionId: 's1', agentId: 'agent-1' },
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
await agentAutofillMedia(task)
|
||||
|
||||
expect(mockActivities.getAssetAutofillContextActivity).toHaveBeenCalledWith('a1')
|
||||
expect(mockActivities.autofillAiActivity).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
teamId: 't1',
|
||||
images: ['/tmp/test-dir/1.webp'],
|
||||
fields: [
|
||||
{
|
||||
id: 'title',
|
||||
config: { name: 'Title', type: 'text' },
|
||||
description: 'The title',
|
||||
},
|
||||
],
|
||||
context: { agent: { id: 'b1' } },
|
||||
}),
|
||||
)
|
||||
const aiCallArgs = mockActivities.autofillAiActivity.mock.calls[0][0]
|
||||
expect(aiCallArgs).not.toHaveProperty('agentContext')
|
||||
})
|
||||
|
||||
it('should complete early if no image files could be extracted', async () => {
|
||||
mockActivities.extractAiMetadataActivity.mockResolvedValue([])
|
||||
|
||||
|
||||
@@ -15,7 +15,6 @@ export async function agentAutofillMedia(task: WorkflowTask): Promise<void> {
|
||||
extractAiMetadataActivity,
|
||||
getProjectAutofillFieldsActivity,
|
||||
getAgentAutofillContextActivity,
|
||||
getAssetAutofillContextActivity,
|
||||
autofillAiActivity,
|
||||
updateTaskUsageActivity,
|
||||
updateAssetMetadataActivity,
|
||||
@@ -132,17 +131,12 @@ export async function agentAutofillMedia(task: WorkflowTask): Promise<void> {
|
||||
teamId,
|
||||
})
|
||||
|
||||
// 3c. Fetch Agent-Provided Autofill Context (from create_file/create_version)
|
||||
const agentContext = await executeActivity(
|
||||
agentWorkerQueue,
|
||||
getAssetAutofillContextActivity,
|
||||
asset.id,
|
||||
)
|
||||
|
||||
// 4. Call AI Service
|
||||
const aiResult = await executeActivity(agentWorkerQueue, autofillAiActivity, {
|
||||
teamId,
|
||||
images: generatedFiles,
|
||||
assetId: asset.id,
|
||||
projectId: asset.projectId ?? undefined,
|
||||
fields: fields.map(
|
||||
(f: { key: string; config: Record<string, unknown>; description?: string | null }) => ({
|
||||
id: f.key,
|
||||
@@ -151,7 +145,6 @@ export async function agentAutofillMedia(task: WorkflowTask): Promise<void> {
|
||||
}),
|
||||
),
|
||||
context,
|
||||
...(agentContext ? { agentContext } : {}),
|
||||
})
|
||||
|
||||
if (aiResult.usage) {
|
||||
@@ -166,10 +159,12 @@ export async function agentAutofillMedia(task: WorkflowTask): Promise<void> {
|
||||
|
||||
// 6. Update Asset Metadata
|
||||
const result = JSON.parse(aiResult.text)
|
||||
const metadataUpdates = Object.entries(result).map(([key, value]) => ({
|
||||
key,
|
||||
value,
|
||||
}))
|
||||
const metadataUpdates = Object.entries(result)
|
||||
.filter(([, value]) => value !== null)
|
||||
.map(([key, value]) => ({
|
||||
key,
|
||||
value,
|
||||
}))
|
||||
|
||||
if (metadataUpdates.length > 0) {
|
||||
await executeActivity(agentWorkerQueue, updateAssetMetadataActivity, {
|
||||
|
||||
@@ -1,171 +0,0 @@
|
||||
import { describe, it, expect } from 'vitest'
|
||||
import { AgentChatPromptBuilder } from './agent-chat-prompt-builder'
|
||||
|
||||
describe('AgentChatPromptBuilder', () => {
|
||||
it('should build prompt with baseline configurations', () => {
|
||||
const builder = new AgentChatPromptBuilder('a1')
|
||||
const result = builder.build()
|
||||
|
||||
expect(result).toContain('The user is discussing an asset with ID: a1.')
|
||||
})
|
||||
|
||||
it('should build prompt with path context', () => {
|
||||
const builder = new AgentChatPromptBuilder('a1').withPathContext('folder/sub/file.png')
|
||||
const result = builder.build()
|
||||
|
||||
expect(result).toContain('Asset Path Context:\nfolder/sub/file.png')
|
||||
})
|
||||
|
||||
it('should build prompt with image asset details', () => {
|
||||
const builder = new AgentChatPromptBuilder('a1').withAssetDetails(
|
||||
'test.png',
|
||||
'image/png',
|
||||
undefined,
|
||||
undefined,
|
||||
'image',
|
||||
)
|
||||
const result = builder.build()
|
||||
|
||||
expect(result).toContain('File Name: test.png')
|
||||
expect(result).toContain('File Type: image')
|
||||
expect(result).toContain("call the 'analyze_image' tool")
|
||||
expect(result).not.toContain("call the 'screenshot' tool")
|
||||
})
|
||||
|
||||
it('should build prompt with video asset details and duration', () => {
|
||||
const builder = new AgentChatPromptBuilder('a1').withAssetDetails(
|
||||
'movie.mp4',
|
||||
'video/mp4',
|
||||
12.34,
|
||||
undefined,
|
||||
'video',
|
||||
)
|
||||
const result = builder.build()
|
||||
|
||||
expect(result).toContain('File Name: movie.mp4')
|
||||
expect(result).toContain('File Type: video')
|
||||
expect(result).toContain('Video Length: 12.34 seconds')
|
||||
expect(result).toContain("call the 'screenshot' tool")
|
||||
expect(result).not.toContain("call the 'analyze_image' tool")
|
||||
})
|
||||
|
||||
it('should build prompt with PDF asset details and total pages', () => {
|
||||
const builder = new AgentChatPromptBuilder('a1').withAssetDetails(
|
||||
'doc.pdf',
|
||||
'application/pdf',
|
||||
undefined,
|
||||
15,
|
||||
'pdf',
|
||||
)
|
||||
const result = builder.build()
|
||||
|
||||
expect(result).toContain('File Name: doc.pdf')
|
||||
expect(result).toContain('File Type: pdf')
|
||||
expect(result).toContain('Total Pages: 15')
|
||||
expect(result).toContain("call the 'read_pdf_pages' tool")
|
||||
expect(result).toContain('Maximum 20 pages allowed per call.')
|
||||
expect(result).not.toContain("call the 'screenshot' tool")
|
||||
expect(result).not.toContain("call the 'analyze_image' tool")
|
||||
})
|
||||
|
||||
it('should build prompt with comment page for PDF asset', () => {
|
||||
const builder = new AgentChatPromptBuilder('a1')
|
||||
.withAssetDetails('doc.pdf', 'application/pdf', undefined, 10, 'pdf')
|
||||
.withCommentTimestamp(3)
|
||||
const result = builder.build()
|
||||
|
||||
expect(result).toContain('Comment Page: 3')
|
||||
})
|
||||
|
||||
it('should build prompt for PDF continuation mode with comment page', () => {
|
||||
const builder = new AgentChatPromptBuilder('a1')
|
||||
.withContinuation(true)
|
||||
.withAssetDetails('doc.pdf', 'application/pdf', undefined, 10, 'pdf')
|
||||
.withCommentTimestamp(4)
|
||||
const result = builder.build()
|
||||
|
||||
expect(result).toContain('Comment Page: 4')
|
||||
expect(result).not.toContain('Comment Timestamp:')
|
||||
})
|
||||
|
||||
it('should build prompt with comment timestamp', () => {
|
||||
const builder = new AgentChatPromptBuilder('a1').withCommentTimestamp(5.5)
|
||||
const result = builder.build()
|
||||
|
||||
expect(result).toContain('Comment Timestamp: 5.50 seconds')
|
||||
})
|
||||
|
||||
it('should build prompt with all fields combined', () => {
|
||||
const builder = new AgentChatPromptBuilder('a1')
|
||||
.withPathContext('src/main.ts')
|
||||
.withAssetDetails('movie.mp4', 'video/mp4', 12.34, undefined, 'video')
|
||||
.withCommentTimestamp(8.2)
|
||||
const result = builder.build()
|
||||
|
||||
expect(result).toContain('The user is discussing an asset with ID: a1.')
|
||||
expect(result).toContain('File Name: movie.mp4')
|
||||
expect(result).toContain('File Type: video')
|
||||
expect(result).toContain('Video Length: 12.34 seconds')
|
||||
expect(result).toContain('Comment Timestamp: 8.20 seconds')
|
||||
expect(result).toContain('Asset Path Context:\nsrc/main.ts')
|
||||
expect(result).toContain("call the 'screenshot' tool")
|
||||
})
|
||||
|
||||
it('should build prompt with attached files and referenced assets', () => {
|
||||
const builder = new AgentChatPromptBuilder('a1')
|
||||
.withAttachedFiles(['- file1.txt', '- file2.png'])
|
||||
.withReferencedAssets(['- folder1', '- file3.mp4'])
|
||||
const result = builder.build()
|
||||
|
||||
expect(result).toContain('[Context: Attached Files & Referenced Assets]')
|
||||
expect(result).toContain('Attached Files:\n- file1.txt\n- file2.png')
|
||||
expect(result).toContain('Referenced Workspace Assets:\n- folder1\n- file3.mp4')
|
||||
})
|
||||
|
||||
it('should build prompt for continuation mode returning only turn-specific modifications', () => {
|
||||
const builder = new AgentChatPromptBuilder('a1')
|
||||
.withContinuation(true)
|
||||
.withAssetDetails('movie.mp4', 'video/mp4', 12.34)
|
||||
.withPathContext('src/main.ts')
|
||||
.withCommentTimestamp(8.2)
|
||||
.withAttachedFiles(['- file1.txt'])
|
||||
.withReferencedAssets(['- folder1'])
|
||||
const result = builder.build()
|
||||
|
||||
expect(result).not.toContain('The user is discussing an asset with ID:')
|
||||
expect(result).not.toContain('File Name: movie.mp4')
|
||||
expect(result).not.toContain('Asset Path Context:')
|
||||
expect(result).toContain('Comment Timestamp: 8.20 seconds')
|
||||
expect(result).toContain('[Context: New Attached Files & Referenced Assets]')
|
||||
expect(result).toContain('Attached Files:\n- file1.txt')
|
||||
expect(result).toContain('Referenced Workspace Assets:\n- folder1')
|
||||
})
|
||||
|
||||
it('should include location change context block in continuation mode when asset has changed', () => {
|
||||
const builder = new AgentChatPromptBuilder('a2')
|
||||
.withContinuation(true)
|
||||
.withAssetChanged(true)
|
||||
.withAssetDetails('new-folder', 'folder', undefined, undefined, 'folder')
|
||||
.withPathContext('projects/my-proj/new-folder')
|
||||
const result = builder.build()
|
||||
|
||||
expect(result).toContain('[Context: User Navigated to a New Location]')
|
||||
expect(result).toContain('New Location Asset ID: a2')
|
||||
expect(result).toContain('File Name: new-folder')
|
||||
expect(result).toContain('Asset Path Context:\nprojects/my-proj/new-folder')
|
||||
})
|
||||
|
||||
it('should build prompt with user info when provided and not continuation', () => {
|
||||
const builder = new AgentChatPromptBuilder('a1').withUserInfo('Alice', 'owner')
|
||||
const result = builder.build()
|
||||
|
||||
expect(result).toContain('User Info:\nName: Alice\nRole: owner')
|
||||
})
|
||||
|
||||
it('should build prompt with download_asset tool instruction', () => {
|
||||
const builder = new AgentChatPromptBuilder('a1')
|
||||
const result = builder.build()
|
||||
|
||||
expect(result).toContain("call the 'download_asset' tool with assetId.")
|
||||
})
|
||||
})
|
||||
@@ -1,185 +0,0 @@
|
||||
export function getSimpleMediaType(proxyType?: string | null): 'image' | 'video' | 'pdf' | 'other' {
|
||||
if (proxyType === 'image') return 'image'
|
||||
if (proxyType === 'video') return 'video'
|
||||
if (proxyType === 'pdf') return 'pdf'
|
||||
return 'other'
|
||||
}
|
||||
|
||||
export class AgentChatPromptBuilder {
|
||||
private assetId: string
|
||||
private assetName?: string
|
||||
private mediaType?: string
|
||||
private proxyType?: string
|
||||
private videoDuration?: number
|
||||
private totalPages?: number
|
||||
private commentTimestamp?: number
|
||||
private pathContext?: string
|
||||
private attachedFiles: string[] = []
|
||||
private referencedAssets: string[] = []
|
||||
private userInfo?: { name: string; role: string }
|
||||
|
||||
private isContinuation = false
|
||||
private hasAssetChanged = false
|
||||
|
||||
constructor(assetId: string) {
|
||||
this.assetId = assetId
|
||||
}
|
||||
|
||||
withUserInfo(name?: string, role?: string): this {
|
||||
if (name) {
|
||||
this.userInfo = { name, role: role || 'user' }
|
||||
}
|
||||
return this
|
||||
}
|
||||
|
||||
withContinuation(isContinuation: boolean): this {
|
||||
this.isContinuation = isContinuation
|
||||
return this
|
||||
}
|
||||
|
||||
withAssetChanged(hasAssetChanged?: boolean): this {
|
||||
this.hasAssetChanged = !!hasAssetChanged
|
||||
return this
|
||||
}
|
||||
|
||||
withAttachedFiles(files?: string[]): this {
|
||||
if (files) {
|
||||
this.attachedFiles = files
|
||||
}
|
||||
return this
|
||||
}
|
||||
|
||||
withReferencedAssets(assets?: string[]): this {
|
||||
if (assets) {
|
||||
this.referencedAssets = assets
|
||||
}
|
||||
return this
|
||||
}
|
||||
|
||||
withPathContext(pathContext?: string): this {
|
||||
this.pathContext = pathContext
|
||||
return this
|
||||
}
|
||||
|
||||
withAssetDetails(
|
||||
name: string,
|
||||
mediaType: string | null,
|
||||
duration?: number,
|
||||
totalPages?: number,
|
||||
proxyType?: string | null,
|
||||
): this {
|
||||
this.assetName = name
|
||||
this.mediaType = mediaType || undefined
|
||||
this.proxyType = proxyType || undefined
|
||||
this.videoDuration = duration
|
||||
this.totalPages = totalPages
|
||||
return this
|
||||
}
|
||||
|
||||
withCommentTimestamp(second?: number | null): this {
|
||||
if (second !== undefined && second !== null) {
|
||||
this.commentTimestamp = second
|
||||
}
|
||||
return this
|
||||
}
|
||||
|
||||
build(): string {
|
||||
const effectiveType = this.proxyType
|
||||
|
||||
if (this.isContinuation) {
|
||||
let instruction = ''
|
||||
if (this.hasAssetChanged) {
|
||||
instruction += `[Context: User Navigated to a New Location]\nNew Location Asset ID: ${this.assetId}`
|
||||
if (this.assetName) {
|
||||
instruction += `\nFile Name: ${this.assetName}`
|
||||
}
|
||||
if (effectiveType) {
|
||||
const type = getSimpleMediaType(effectiveType)
|
||||
instruction += `\nFile Type: ${type}`
|
||||
if (type === 'video' && this.videoDuration !== undefined) {
|
||||
instruction += `\nVideo Length: ${this.videoDuration.toFixed(2)} seconds`
|
||||
} else if (type === 'pdf' && this.totalPages !== undefined) {
|
||||
instruction += `\nTotal Pages: ${this.totalPages}`
|
||||
}
|
||||
}
|
||||
if (this.pathContext) {
|
||||
instruction += `\n\nAsset Path Context:\n${this.pathContext}`
|
||||
}
|
||||
}
|
||||
if (this.commentTimestamp !== undefined) {
|
||||
const type = getSimpleMediaType(effectiveType)
|
||||
if (instruction) instruction += '\n\n'
|
||||
if (type === 'pdf') {
|
||||
instruction += `Comment Page: ${Math.round(this.commentTimestamp)}`
|
||||
} else {
|
||||
instruction += `Comment Timestamp: ${this.commentTimestamp.toFixed(2)} seconds`
|
||||
}
|
||||
}
|
||||
if (this.attachedFiles.length > 0 || this.referencedAssets.length > 0) {
|
||||
if (instruction) instruction += '\n\n'
|
||||
instruction += `[Context: New Attached Files & Referenced Assets]`
|
||||
if (this.attachedFiles.length > 0) {
|
||||
instruction += `\nAttached Files:\n${this.attachedFiles.join('\n')}`
|
||||
}
|
||||
if (this.referencedAssets.length > 0) {
|
||||
instruction += `\nReferenced Workspace Assets:\n${this.referencedAssets.join('\n')}`
|
||||
}
|
||||
}
|
||||
return instruction.trim()
|
||||
}
|
||||
|
||||
let instruction = `The user is discussing an asset with ID: ${this.assetId}.`
|
||||
if (this.assetName) {
|
||||
instruction += `\nFile Name: ${this.assetName}`
|
||||
}
|
||||
if (effectiveType) {
|
||||
const type = getSimpleMediaType(effectiveType)
|
||||
instruction += `\nFile Type: ${type}`
|
||||
if (type === 'video' && this.videoDuration !== undefined) {
|
||||
instruction += `\nVideo Length: ${this.videoDuration.toFixed(2)} seconds`
|
||||
} else if (type === 'pdf' && this.totalPages !== undefined) {
|
||||
instruction += `\nTotal Pages: ${this.totalPages}`
|
||||
}
|
||||
}
|
||||
if (this.commentTimestamp !== undefined) {
|
||||
const type = getSimpleMediaType(effectiveType)
|
||||
if (type === 'pdf') {
|
||||
instruction += `\nComment Page: ${Math.round(this.commentTimestamp)}`
|
||||
} else {
|
||||
instruction += `\nComment Timestamp: ${this.commentTimestamp.toFixed(2)} seconds`
|
||||
}
|
||||
}
|
||||
if (this.pathContext) {
|
||||
instruction += `\n\nAsset Path Context:\n${this.pathContext}`
|
||||
}
|
||||
|
||||
if (this.attachedFiles.length > 0 || this.referencedAssets.length > 0) {
|
||||
instruction += `\n\n[Context: Attached Files & Referenced Assets]`
|
||||
if (this.attachedFiles.length > 0) {
|
||||
instruction += `\nAttached Files:\n${this.attachedFiles.join('\n')}`
|
||||
}
|
||||
if (this.referencedAssets.length > 0) {
|
||||
instruction += `\nReferenced Workspace Assets:\n${this.referencedAssets.join('\n')}`
|
||||
}
|
||||
}
|
||||
|
||||
if (effectiveType) {
|
||||
const type = getSimpleMediaType(effectiveType)
|
||||
if (type === 'image') {
|
||||
instruction += `\n\nIf you need to view the image data, call the 'analyze_image' tool with assetId "${this.assetId}".`
|
||||
} else if (type === 'video') {
|
||||
instruction += `\n\nIf you need to view visual frames or take screenshots of the video, call the 'screenshot' tool. You must specify the 'start' (seconds), 'end' (seconds), and 'count' (number of screenshots) parameters.`
|
||||
} else if (type === 'pdf') {
|
||||
instruction += `\n\nIf you need to view pages of the PDF document, call the 'read_pdf_pages' tool. You must specify the 'start' (page number) and 'end' (page number) parameters. Maximum 20 pages allowed per call.`
|
||||
}
|
||||
}
|
||||
|
||||
instruction += `\n\nIf you need a local file on disk to run bash commands or scripts (e.g. processing or combining assets), call the 'download_asset' tool with assetId.`
|
||||
|
||||
if (this.userInfo) {
|
||||
instruction += `\n\nUser Info:\nName: ${this.userInfo.name}\nRole: ${this.userInfo.role}`
|
||||
}
|
||||
|
||||
return instruction
|
||||
}
|
||||
}
|
||||
@@ -3,7 +3,6 @@ import { agentChat } from './agent-chat'
|
||||
import { prisma } from '@shumai/db'
|
||||
import { setupTestDbHooks } from '@shumai/db/test'
|
||||
import * as workflowUtils from '@shumai/workflow-core'
|
||||
import { AgentChatPromptBuilder } from './agent-chat-prompt-builder'
|
||||
|
||||
vi.mock('@shumai/workflow-core', async () => {
|
||||
const actual = await vi.importActual('@shumai/workflow-core')
|
||||
@@ -43,6 +42,9 @@ describe('Agent Chat Workflow', () => {
|
||||
updateCommentActivity: Object.assign(vi.fn(), { _activityName: 'updateCommentActivity' }),
|
||||
updateTaskUsageActivity: Object.assign(vi.fn(), { _activityName: 'updateTaskUsageActivity' }),
|
||||
deleteCommentActivity: Object.assign(vi.fn(), { _activityName: 'deleteCommentActivity' }),
|
||||
getAssetPathHierarchyActivity: Object.assign(vi.fn(), {
|
||||
_activityName: 'getAssetPathHierarchyActivity',
|
||||
}),
|
||||
getAssetPathContextActivity: Object.assign(vi.fn(), {
|
||||
_activityName: 'getAssetPathContextActivity',
|
||||
}),
|
||||
@@ -70,13 +72,21 @@ describe('Agent Chat Workflow', () => {
|
||||
})
|
||||
mockActivities.getCommentActivity.mockResolvedValue({
|
||||
id: 'c1',
|
||||
creatorId: 'user-c1',
|
||||
message: 'hello agent',
|
||||
replyToId: null,
|
||||
attachments: [],
|
||||
})
|
||||
mockActivities.initializeAgentSessionActivity.mockResolvedValue('session-123')
|
||||
mockActivities.getAgentChatContextActivity.mockResolvedValue({ agent: { id: 'b1' } })
|
||||
mockActivities.getAssetPathContextActivity.mockResolvedValue('Path: folder/subfolder/file.png')
|
||||
mockActivities.getAssetPathHierarchyActivity.mockResolvedValue({
|
||||
path: 'folder/subfolder/test-file.png',
|
||||
ancestors: [
|
||||
{ id: 'f1', name: 'folder' },
|
||||
{ id: 'f2', name: 'subfolder' },
|
||||
],
|
||||
})
|
||||
mockActivities.getAssetPathContextActivity.mockResolvedValue('folder/subfolder/test-file.png')
|
||||
mockActivities.agentChatActivity.mockResolvedValue({
|
||||
text: 'Hello user, how can I help you?',
|
||||
sessionId: 'session-123',
|
||||
@@ -118,6 +128,14 @@ describe('Agent Chat Workflow', () => {
|
||||
// Verify comment context fetched
|
||||
expect(mockActivities.getCommentActivity).toHaveBeenCalledWith('c1')
|
||||
|
||||
// Verify agent context fetched with the project context forwarded
|
||||
expect(mockActivities.getAgentChatContextActivity).toHaveBeenCalledWith({
|
||||
teamId: 't1',
|
||||
agentId: 'b1',
|
||||
userId: undefined,
|
||||
projectId: 'p1',
|
||||
})
|
||||
|
||||
// Verify placeholder comment created
|
||||
expect(mockActivities.createCommentActivity).toHaveBeenCalledWith({
|
||||
assetId: 'a1',
|
||||
@@ -135,21 +153,31 @@ describe('Agent Chat Workflow', () => {
|
||||
userId: undefined,
|
||||
})
|
||||
|
||||
// Verify agent instruction composition
|
||||
const expectedInstruction1 = new AgentChatPromptBuilder('a1')
|
||||
.withPathContext('Path: folder/subfolder/file.png')
|
||||
.withAssetDetails('test-file.png', 'image/png', undefined, undefined, 'image')
|
||||
.withCommentTimestamp(null)
|
||||
.build()
|
||||
|
||||
// Verify agent chat called with structured messageContext
|
||||
expect(mockActivities.agentChatActivity).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
teamId: 't1',
|
||||
agentId: 'b1',
|
||||
message: 'hello agent',
|
||||
agentsInstruction: expectedInstruction1,
|
||||
sessionId: 'session-123',
|
||||
folderId: 'parent-folder-id',
|
||||
assetId: 'a1',
|
||||
messageContext: expect.objectContaining({
|
||||
user: { id: 'user-c1', name: 'Test User', role: 'owner' },
|
||||
currentAsset: expect.objectContaining({
|
||||
id: 'a1',
|
||||
name: 'test-file.png',
|
||||
type: 'file',
|
||||
mediaType: 'image',
|
||||
mimeType: 'image/png',
|
||||
parentId: 'parent-folder-id',
|
||||
path: 'folder/subfolder/test-file.png',
|
||||
ancestors: [
|
||||
{ id: 'f1', name: 'folder' },
|
||||
{ id: 'f2', name: 'subfolder' },
|
||||
],
|
||||
}),
|
||||
}),
|
||||
}),
|
||||
)
|
||||
|
||||
@@ -201,17 +229,13 @@ describe('Agent Chat Workflow', () => {
|
||||
await agentChat(task)
|
||||
|
||||
expect(mockActivities.initializeAgentSessionActivity).not.toHaveBeenCalled()
|
||||
const expectedInstruction2 = new AgentChatPromptBuilder('a1')
|
||||
.withContinuation(true)
|
||||
.withPathContext('Path: folder/subfolder/file.png')
|
||||
.withAssetDetails('test-file.png', 'image/png', undefined)
|
||||
.withCommentTimestamp(null)
|
||||
.build()
|
||||
|
||||
expect(mockActivities.agentChatActivity).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
sessionId: 'existing-session-456',
|
||||
agentsInstruction: expectedInstruction2,
|
||||
messageContext: expect.objectContaining({
|
||||
currentAsset: expect.objectContaining({ id: 'a1', name: 'test-file.png' }),
|
||||
}),
|
||||
}),
|
||||
)
|
||||
|
||||
@@ -263,16 +287,9 @@ describe('Agent Chat Workflow', () => {
|
||||
|
||||
await agentChat(task)
|
||||
|
||||
const expectedInstruction4 = new AgentChatPromptBuilder('a1')
|
||||
.withPathContext('Path: folder/subfolder/file.png')
|
||||
.withAssetDetails('test-file.png', 'image/png', undefined, undefined, 'image')
|
||||
.withCommentTimestamp(null)
|
||||
.build()
|
||||
|
||||
expect(mockActivities.agentChatActivity).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
imageUrls: ['attachments/image1.png', 'attachments/image2.jpg'],
|
||||
agentsInstruction: expectedInstruction4,
|
||||
}),
|
||||
)
|
||||
})
|
||||
@@ -305,15 +322,13 @@ describe('Agent Chat Workflow', () => {
|
||||
|
||||
await agentChat(task)
|
||||
|
||||
const expectedInstruction5 = new AgentChatPromptBuilder('a1')
|
||||
.withPathContext('Path: folder/subfolder/file.png')
|
||||
.withAssetDetails('test-asset', 'video/mp4', 10)
|
||||
.withCommentTimestamp(null)
|
||||
.build()
|
||||
|
||||
expect(mockActivities.agentChatActivity).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
agentsInstruction: expectedInstruction5,
|
||||
messageContext: expect.objectContaining({
|
||||
currentAsset: expect.objectContaining({
|
||||
durationSeconds: 10,
|
||||
}),
|
||||
}),
|
||||
}),
|
||||
)
|
||||
})
|
||||
@@ -381,6 +396,7 @@ describe('Agent Chat Workflow', () => {
|
||||
name: 'attachment.png',
|
||||
type: 'file',
|
||||
mediaType: 'image/png',
|
||||
media: { proxyType: 'image' },
|
||||
projectId: 'p1',
|
||||
}
|
||||
}
|
||||
@@ -390,6 +406,7 @@ describe('Agent Chat Workflow', () => {
|
||||
name: 'ref-folder',
|
||||
type: 'folder',
|
||||
mediaType: null,
|
||||
media: null,
|
||||
projectId: 'p1',
|
||||
}
|
||||
}
|
||||
@@ -398,6 +415,7 @@ describe('Agent Chat Workflow', () => {
|
||||
name: 'test-file.png',
|
||||
type: 'file',
|
||||
mediaType: 'image/png',
|
||||
media: { proxyType: 'image' },
|
||||
projectId: 'p1',
|
||||
project: { teamId: 't1' },
|
||||
}
|
||||
@@ -433,20 +451,7 @@ describe('Agent Chat Workflow', () => {
|
||||
expect(mockActivities.createCommentActivity).not.toHaveBeenCalled()
|
||||
expect(mockActivities.updateCommentActivity).not.toHaveBeenCalled()
|
||||
|
||||
// Verify prompt builder is populated and workflow runs agentChatActivity with context instruction
|
||||
const expectedInstruction = new AgentChatPromptBuilder('a1')
|
||||
.withContinuation(true)
|
||||
.withPathContext('folder/subfolder/file.png')
|
||||
.withAssetDetails('test-file.png', 'image/png', undefined)
|
||||
.withCommentTimestamp(undefined)
|
||||
.withAttachedFiles([
|
||||
'- Name: attachment.png (ID: file-attachment-1, Type: file, Media Type: image/png, Project ID: p1, Path: attachment.png)',
|
||||
])
|
||||
.withReferencedAssets([
|
||||
'- Name: ref-folder (ID: referenced-asset-1, Type: folder, Media Type: unknown, Project ID: p1, Path: ref-folder)',
|
||||
])
|
||||
.build()
|
||||
|
||||
// Verify messageContext is populated with attachedFiles and referencedAssets
|
||||
expect(mockActivities.agentChatActivity).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
teamId: 't1',
|
||||
@@ -455,15 +460,32 @@ describe('Agent Chat Workflow', () => {
|
||||
imageUrls: [],
|
||||
projectId: 'p1',
|
||||
folderId: '',
|
||||
agentsInstruction: expectedInstruction,
|
||||
sessionId: 'session-direct-123',
|
||||
userId: undefined,
|
||||
userCommentId: undefined,
|
||||
context: { agent: { id: 'b1' } },
|
||||
attachedAssets: [
|
||||
{ id: 'file-attachment-1', name: 'attachment.png', type: 'file' },
|
||||
{ id: 'referenced-asset-1', name: 'ref-folder', type: 'folder' },
|
||||
],
|
||||
messageContext: expect.objectContaining({
|
||||
attachedFiles: [
|
||||
{
|
||||
id: 'file-attachment-1',
|
||||
name: 'attachment.png',
|
||||
type: 'file',
|
||||
mediaType: 'image',
|
||||
mimeType: 'image/png',
|
||||
path: 'attachment.png',
|
||||
},
|
||||
],
|
||||
referencedAssets: [
|
||||
{
|
||||
id: 'referenced-asset-1',
|
||||
name: 'ref-folder',
|
||||
type: 'folder',
|
||||
mediaType: undefined,
|
||||
mimeType: undefined,
|
||||
path: 'ref-folder',
|
||||
},
|
||||
],
|
||||
}),
|
||||
}),
|
||||
)
|
||||
})
|
||||
@@ -502,19 +524,18 @@ describe('Agent Chat Workflow', () => {
|
||||
|
||||
await agentChat(task)
|
||||
|
||||
const expectedInstruction = new AgentChatPromptBuilder('v2-latest')
|
||||
.withContinuation(true)
|
||||
.withPathContext('Path: folder/subfolder/file.png')
|
||||
.withAssetDetails('latest-video.mp4', 'video/mp4', 42, undefined, 'video')
|
||||
.build()
|
||||
|
||||
expect(mockActivities.agentChatActivity).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
teamId: 't1',
|
||||
agentId: 'b1',
|
||||
message: 'Explain this version stack video',
|
||||
agentsInstruction: expectedInstruction,
|
||||
sessionId: 'session-vs-123',
|
||||
messageContext: expect.objectContaining({
|
||||
currentAsset: expect.objectContaining({
|
||||
id: 'v2-latest',
|
||||
durationSeconds: 42,
|
||||
}),
|
||||
}),
|
||||
}),
|
||||
)
|
||||
})
|
||||
@@ -547,7 +568,241 @@ describe('Agent Chat Workflow', () => {
|
||||
|
||||
expect(mockActivities.agentChatActivity).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
agentsInstruction: expect.stringContaining('User Info:\nName: Test User\nRole: owner'),
|
||||
messageContext: expect.objectContaining({
|
||||
user: { id: 'user-alice', name: 'Test User', role: 'owner' },
|
||||
}),
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
||||
it('should populate comment attachments into structured messageContext.attachedFiles', async () => {
|
||||
mockActivities.getCommentActivity.mockResolvedValue({
|
||||
id: 'c1',
|
||||
creatorId: 'user-c1',
|
||||
message: 'check these attachments',
|
||||
replyToId: null,
|
||||
attachments: [
|
||||
{
|
||||
asset: {
|
||||
id: 'att-doc-1',
|
||||
name: 'brief.pdf',
|
||||
type: 'file',
|
||||
mediaType: 'application/pdf',
|
||||
media: { proxyType: 'pdf' },
|
||||
storageKey: { key: 'brief.pdf' },
|
||||
},
|
||||
},
|
||||
{
|
||||
asset: {
|
||||
id: 'att-img-1',
|
||||
name: 'mockup.png',
|
||||
type: 'file',
|
||||
mediaType: 'image/png',
|
||||
media: { proxyType: 'image' },
|
||||
storageKey: { key: 'mockup.png' },
|
||||
},
|
||||
},
|
||||
],
|
||||
})
|
||||
|
||||
mockActivities.getAssetPathContextActivity.mockImplementation(async (id: string) => {
|
||||
if (id === 'att-doc-1') return 'Docs/brief.pdf'
|
||||
if (id === 'att-img-1') return 'Designs/mockup.png'
|
||||
return 'folder/subfolder/file.png'
|
||||
})
|
||||
|
||||
const task = await prisma.workflowTask.create({
|
||||
data: {
|
||||
type: 'chat',
|
||||
status: 'pending',
|
||||
assetId: 'a1',
|
||||
payload: {
|
||||
projectId: 'p1',
|
||||
agent: { userCommentId: 'c1', agentId: 'b1' },
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
await agentChat(task)
|
||||
|
||||
expect(mockActivities.agentChatActivity).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
imageUrls: ['mockup.png'],
|
||||
messageContext: expect.objectContaining({
|
||||
attachedFiles: [
|
||||
{
|
||||
id: 'att-doc-1',
|
||||
name: 'brief.pdf',
|
||||
type: 'file',
|
||||
mediaType: 'pdf',
|
||||
mimeType: 'application/pdf',
|
||||
path: 'Docs/brief.pdf',
|
||||
},
|
||||
{
|
||||
id: 'att-img-1',
|
||||
name: 'mockup.png',
|
||||
type: 'file',
|
||||
mediaType: 'image',
|
||||
mimeType: 'image/png',
|
||||
path: 'Designs/mockup.png',
|
||||
},
|
||||
],
|
||||
}),
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
||||
it('should set totalFrames for video assets and totalPages for pdf assets in currentAsset context', async () => {
|
||||
mockActivities.getAssetActivity.mockImplementation(async (id: string) => {
|
||||
if (id === 'video-asset-1') {
|
||||
return {
|
||||
id: 'video-asset-1',
|
||||
project: { teamId: 't1' },
|
||||
type: 'file',
|
||||
name: 'clip.mp4',
|
||||
mediaType: 'video/mp4',
|
||||
media: { proxyType: 'video', duration: 9, frames: 268 },
|
||||
parentId: 'f1',
|
||||
}
|
||||
}
|
||||
if (id === 'pdf-asset-1') {
|
||||
return {
|
||||
id: 'pdf-asset-1',
|
||||
project: { teamId: 't1' },
|
||||
type: 'file',
|
||||
name: 'doc.pdf',
|
||||
mediaType: 'application/pdf',
|
||||
media: { proxyType: 'pdf', frames: 15, duration: 0 },
|
||||
parentId: 'f1',
|
||||
}
|
||||
}
|
||||
return null
|
||||
})
|
||||
|
||||
// Test Video asset
|
||||
const videoTask = await prisma.workflowTask.create({
|
||||
data: {
|
||||
type: 'chat',
|
||||
status: 'pending',
|
||||
assetId: 'video-asset-1',
|
||||
payload: {
|
||||
projectId: 'p1',
|
||||
agent: { prompt: 'Analyze video', agentId: 'b1', sessionId: 'session-video-1' },
|
||||
},
|
||||
},
|
||||
})
|
||||
await agentChat(videoTask)
|
||||
|
||||
expect(mockActivities.agentChatActivity).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
messageContext: expect.objectContaining({
|
||||
currentAsset: expect.objectContaining({
|
||||
id: 'video-asset-1',
|
||||
mediaType: 'video',
|
||||
durationSeconds: 9,
|
||||
totalFrames: 268,
|
||||
totalPages: undefined,
|
||||
}),
|
||||
}),
|
||||
}),
|
||||
)
|
||||
|
||||
// Test PDF asset
|
||||
const pdfTask = await prisma.workflowTask.create({
|
||||
data: {
|
||||
type: 'chat',
|
||||
status: 'pending',
|
||||
assetId: 'pdf-asset-1',
|
||||
payload: {
|
||||
projectId: 'p1',
|
||||
agent: { prompt: 'Analyze pdf', agentId: 'b1', sessionId: 'session-pdf-1' },
|
||||
},
|
||||
},
|
||||
})
|
||||
await agentChat(pdfTask)
|
||||
|
||||
expect(mockActivities.agentChatActivity).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
messageContext: expect.objectContaining({
|
||||
currentAsset: expect.objectContaining({
|
||||
id: 'pdf-asset-1',
|
||||
mediaType: 'pdf',
|
||||
totalPages: 15,
|
||||
totalFrames: undefined,
|
||||
durationSeconds: undefined,
|
||||
}),
|
||||
}),
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
||||
it('should include annotations and second in direct chat messageContext', async () => {
|
||||
const task = await prisma.workflowTask.create({
|
||||
data: {
|
||||
type: 'chat',
|
||||
status: 'pending',
|
||||
assetId: 'a1',
|
||||
payload: {
|
||||
projectId: 'p1',
|
||||
agent: {
|
||||
prompt: 'Look at the highlighted zone',
|
||||
agentId: 'b1',
|
||||
sessionId: 'session-markup-1',
|
||||
second: 14.2,
|
||||
annotations: [{ type: 'rectangle', x: 20, y: 30, width: 40, height: 50 }],
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
await agentChat(task)
|
||||
|
||||
expect(mockActivities.agentChatActivity).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
messageContext: expect.objectContaining({
|
||||
position: { type: 'time', seconds: 14.2 },
|
||||
annotations: [{ type: 'rectangle', x: 20, y: 30, width: 40, height: 50 }],
|
||||
}),
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
||||
it('should include userCommentId as id in comment messageContext', async () => {
|
||||
mockActivities.getCommentActivity.mockResolvedValue({
|
||||
id: 'comment-with-id-123',
|
||||
creatorId: 'user-c1',
|
||||
message: 'Check this out',
|
||||
replyToId: null,
|
||||
second: 5.0,
|
||||
annotation: [{ type: 'arrow' }],
|
||||
attachments: [],
|
||||
})
|
||||
|
||||
const task = await prisma.workflowTask.create({
|
||||
data: {
|
||||
type: 'chat',
|
||||
status: 'pending',
|
||||
assetId: 'a1',
|
||||
payload: {
|
||||
projectId: 'p1',
|
||||
agent: {
|
||||
agentId: 'b1',
|
||||
userCommentId: 'comment-with-id-123',
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
await agentChat(task)
|
||||
|
||||
expect(mockActivities.agentChatActivity).toHaveBeenCalledWith(
|
||||
expect.objectContaining({
|
||||
messageContext: expect.objectContaining({
|
||||
id: 'comment-with-id-123',
|
||||
position: { type: 'time', seconds: 5.0 },
|
||||
annotation: true,
|
||||
annotations: [{ type: 'arrow' }],
|
||||
}),
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
||||
@@ -1,7 +1,13 @@
|
||||
import { ApplicationFailure } from '@temporalio/workflow'
|
||||
import type { WorkflowTask } from '@shumai/db'
|
||||
import { executeActivity, getActivities, TaskQueueAgent } from '@shumai/workflow-core'
|
||||
import { AgentChatPromptBuilder } from './agent-chat-prompt-builder'
|
||||
import type {
|
||||
ShumaiMessageContext,
|
||||
ShumaiAssetContext,
|
||||
ShumaiAttachedFileContext,
|
||||
ShumaiMediaPosition,
|
||||
} from '@shumai/dtos'
|
||||
import { getProxyType } from '@shumai/core/src/utils/mime'
|
||||
|
||||
export async function agentChat(task: WorkflowTask): Promise<void> {
|
||||
const {
|
||||
@@ -15,6 +21,7 @@ export async function agentChat(task: WorkflowTask): Promise<void> {
|
||||
updateTaskUsageActivity,
|
||||
getAgentWorkerQueueActivity,
|
||||
initializeAgentSessionActivity,
|
||||
getAssetPathHierarchyActivity,
|
||||
getAssetPathContextActivity,
|
||||
generateSessionNameActivity,
|
||||
getUserTeamInfoActivity,
|
||||
@@ -47,19 +54,33 @@ export async function agentChat(task: WorkflowTask): Promise<void> {
|
||||
|
||||
// 1. Get User Comment
|
||||
const userCommentId = payload.agent?.userCommentId
|
||||
let userComment: Awaited<ReturnType<typeof getCommentActivity>> | null = null
|
||||
let prompt = ''
|
||||
let attachmentImageUrls: string[] = []
|
||||
let commentTimestamp: number | undefined
|
||||
let commentAnnotation = false
|
||||
let commentCreatorId: string | undefined
|
||||
|
||||
let commentAnnotations: unknown[] | undefined
|
||||
|
||||
if (userCommentId) {
|
||||
const userComment = await executeActivity(agentWorkerQueue, getCommentActivity, userCommentId)
|
||||
userComment = await executeActivity(agentWorkerQueue, getCommentActivity, userCommentId)
|
||||
if (!userComment) {
|
||||
throw ApplicationFailure.create({ message: 'User comment not found', nonRetryable: true })
|
||||
}
|
||||
prompt = userComment.message || ''
|
||||
commentCreatorId = userComment.creatorId || undefined
|
||||
if (userComment.second !== null && userComment.second !== undefined) {
|
||||
commentTimestamp = userComment.second
|
||||
}
|
||||
if (
|
||||
userComment.annotation &&
|
||||
Array.isArray(userComment.annotation) &&
|
||||
userComment.annotation.length > 0
|
||||
) {
|
||||
commentAnnotation = true
|
||||
commentAnnotations = userComment.annotation
|
||||
}
|
||||
|
||||
// 2. Create Placeholder Comment
|
||||
const placeholder = await executeActivity(agentWorkerQueue, createCommentActivity, {
|
||||
@@ -71,7 +92,7 @@ export async function agentChat(task: WorkflowTask): Promise<void> {
|
||||
})
|
||||
placeholderCommentId = placeholder.id
|
||||
|
||||
// 5. Prepare Images (Attachments only)
|
||||
// Prepare Images (Attachments only)
|
||||
if (userComment.attachments) {
|
||||
for (const att of userComment.attachments) {
|
||||
const attProxyType = (att.asset?.media as PrismaJson.MediaInfo | null)?.proxyType
|
||||
@@ -83,6 +104,17 @@ export async function agentChat(task: WorkflowTask): Promise<void> {
|
||||
} else {
|
||||
prompt = payload.agent?.prompt || ''
|
||||
attachmentImageUrls = payload.agent?.imageUrls || []
|
||||
if (payload.agent?.second !== null && payload.agent?.second !== undefined) {
|
||||
commentTimestamp = payload.agent.second
|
||||
}
|
||||
if (
|
||||
payload.agent?.annotations &&
|
||||
Array.isArray(payload.agent.annotations) &&
|
||||
payload.agent.annotations.length > 0
|
||||
) {
|
||||
commentAnnotation = true
|
||||
commentAnnotations = payload.agent.annotations
|
||||
}
|
||||
}
|
||||
|
||||
// 3. Get Asset
|
||||
@@ -114,45 +146,111 @@ export async function agentChat(task: WorkflowTask): Promise<void> {
|
||||
const context = await executeActivity(agentWorkerQueue, getAgentChatContextActivity, {
|
||||
teamId,
|
||||
agentId: agentId,
|
||||
userId: payload.agent?.userId,
|
||||
projectId: payload.projectId,
|
||||
})
|
||||
|
||||
const pathContext = await executeActivity(
|
||||
const pathHierarchy = await executeActivity(
|
||||
agentWorkerQueue,
|
||||
getAssetPathContextActivity,
|
||||
getAssetPathHierarchyActivity,
|
||||
task.assetId,
|
||||
)
|
||||
const assetPath = pathHierarchy?.path || ''
|
||||
const ancestors = pathHierarchy?.ancestors || []
|
||||
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const mediaInfo = asset.media as any
|
||||
const duration = mediaInfo?.duration
|
||||
const totalPages = mediaInfo?.frames || mediaInfo?.metadata?.totalFrames
|
||||
const proxyType =
|
||||
(asset.media as PrismaJson.MediaInfo | null)?.proxyType ||
|
||||
getProxyType(asset.mediaType, asset.name) ||
|
||||
undefined
|
||||
const duration =
|
||||
(proxyType === 'video' || proxyType === 'audio') && typeof mediaInfo?.duration === 'number'
|
||||
? mediaInfo.duration
|
||||
: undefined
|
||||
const totalPages =
|
||||
proxyType === 'pdf' ? mediaInfo?.frames || mediaInfo?.metadata?.totalFrames : undefined
|
||||
const totalFrames =
|
||||
proxyType === 'video' ? mediaInfo?.frames || mediaInfo?.metadata?.totalFrames : undefined
|
||||
|
||||
// Resolve Attached Files Details
|
||||
const attachedFileDetailsList: string[] = []
|
||||
const attachedFiles: ShumaiAttachedFileContext[] = []
|
||||
const attachedAssets: Array<{ id: string; name: string; type: string }> = []
|
||||
if (payload.agent?.attachedFiles) {
|
||||
if (userCommentId && userComment?.attachments) {
|
||||
for (const att of userComment.attachments) {
|
||||
if (att.asset) {
|
||||
const filePath = await executeActivity(
|
||||
agentWorkerQueue,
|
||||
getAssetPathContextActivity,
|
||||
att.asset.id,
|
||||
)
|
||||
const attProxyType =
|
||||
(att.asset.media as PrismaJson.MediaInfo | null)?.proxyType ||
|
||||
getProxyType(att.asset.mediaType, att.asset.name) ||
|
||||
undefined
|
||||
attachedFiles.push({
|
||||
id: att.asset.id,
|
||||
name: att.asset.name,
|
||||
type: att.asset.type,
|
||||
mediaType: attProxyType as ShumaiAttachedFileContext['mediaType'],
|
||||
mimeType: att.asset.mediaType || undefined,
|
||||
path: filePath || undefined,
|
||||
url: (att.asset as { url?: string }).url || undefined,
|
||||
})
|
||||
attachedAssets.push({ id: att.asset.id, name: att.asset.name, type: att.asset.type })
|
||||
}
|
||||
}
|
||||
} else if (payload.agent?.attachedFiles) {
|
||||
for (const fileId of payload.agent.attachedFiles) {
|
||||
const file = await executeActivity(agentWorkerQueue, getAssetActivity, fileId)
|
||||
if (file) {
|
||||
const path = await executeActivity(agentWorkerQueue, getAssetPathContextActivity, fileId)
|
||||
attachedFileDetailsList.push(
|
||||
`- Name: ${file.name} (ID: ${file.id}, Type: ${file.type}, Media Type: ${file.mediaType || 'unknown'}, Project ID: ${file.projectId || 'unknown'}, Path: ${path})`,
|
||||
const filePath = await executeActivity(
|
||||
agentWorkerQueue,
|
||||
getAssetPathContextActivity,
|
||||
fileId,
|
||||
)
|
||||
const fileProxyType =
|
||||
(file.media as PrismaJson.MediaInfo | null)?.proxyType ||
|
||||
getProxyType(file.mediaType, file.name) ||
|
||||
undefined
|
||||
attachedFiles.push({
|
||||
id: file.id,
|
||||
name: file.name,
|
||||
type: file.type,
|
||||
mediaType: fileProxyType as ShumaiAttachedFileContext['mediaType'],
|
||||
mimeType: file.mediaType || undefined,
|
||||
path: filePath || undefined,
|
||||
url: (file as { url?: string }).url || undefined,
|
||||
})
|
||||
attachedAssets.push({ id: file.id, name: file.name, type: file.type })
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Resolve Referenced Workspace Assets Details
|
||||
const referencedAssetDetailsList: string[] = []
|
||||
const referencedAssets: ShumaiAttachedFileContext[] = []
|
||||
if (payload.agent?.assetIds) {
|
||||
for (const assetId of payload.agent.assetIds) {
|
||||
const referencedAsset = await executeActivity(agentWorkerQueue, getAssetActivity, assetId)
|
||||
if (referencedAsset) {
|
||||
const path = await executeActivity(agentWorkerQueue, getAssetPathContextActivity, assetId)
|
||||
referencedAssetDetailsList.push(
|
||||
`- Name: ${referencedAsset.name} (ID: ${referencedAsset.id}, Type: ${referencedAsset.type}, Media Type: ${referencedAsset.mediaType || 'unknown'}, Project ID: ${referencedAsset.projectId || 'unknown'}, Path: ${path})`,
|
||||
const filePath = await executeActivity(
|
||||
agentWorkerQueue,
|
||||
getAssetPathContextActivity,
|
||||
assetId,
|
||||
)
|
||||
const refProxyType =
|
||||
(referencedAsset.media as PrismaJson.MediaInfo | null)?.proxyType ||
|
||||
getProxyType(referencedAsset.mediaType, referencedAsset.name) ||
|
||||
undefined
|
||||
referencedAssets.push({
|
||||
id: referencedAsset.id,
|
||||
name: referencedAsset.name,
|
||||
type: referencedAsset.type,
|
||||
mediaType: refProxyType as ShumaiAttachedFileContext['mediaType'],
|
||||
mimeType: referencedAsset.mediaType || undefined,
|
||||
path: filePath || undefined,
|
||||
url: (referencedAsset as { url?: string }).url || undefined,
|
||||
})
|
||||
attachedAssets.push({
|
||||
id: referencedAsset.id,
|
||||
name: referencedAsset.name,
|
||||
@@ -162,29 +260,59 @@ export async function agentChat(task: WorkflowTask): Promise<void> {
|
||||
}
|
||||
}
|
||||
|
||||
// Resolve User Info
|
||||
const targetUserId = userCommentId ? commentCreatorId : payload.agent?.userId
|
||||
let userInfo: { name: string; role: string } | null = null
|
||||
if (!userCommentId && isNewChat && payload.agent?.userId) {
|
||||
if (targetUserId) {
|
||||
userInfo = await executeActivity(agentWorkerQueue, getUserTeamInfoActivity, {
|
||||
userId: payload.agent.userId,
|
||||
userId: targetUserId,
|
||||
teamId,
|
||||
})
|
||||
}
|
||||
|
||||
const proxyType = (asset.media as PrismaJson.MediaInfo | null)?.proxyType
|
||||
const promptBuilder = new AgentChatPromptBuilder(asset.id)
|
||||
.withContinuation(!isNewChat)
|
||||
.withAssetChanged(payload.agent?.hasAssetChanged)
|
||||
.withPathContext(pathContext)
|
||||
.withAssetDetails(asset.name, asset.mediaType, duration, totalPages, proxyType)
|
||||
.withCommentTimestamp(commentTimestamp)
|
||||
.withAttachedFiles(attachedFileDetailsList)
|
||||
.withReferencedAssets(referencedAssetDetailsList)
|
||||
|
||||
if (userInfo) {
|
||||
promptBuilder.withUserInfo(userInfo.name, userInfo.role)
|
||||
// Build position
|
||||
let mediaPosition: ShumaiMediaPosition | undefined
|
||||
if (commentTimestamp !== undefined && commentTimestamp !== null) {
|
||||
if (proxyType === 'pdf') {
|
||||
mediaPosition = { type: 'page', page: Math.round(commentTimestamp) }
|
||||
} else {
|
||||
mediaPosition = { type: 'time', seconds: commentTimestamp }
|
||||
}
|
||||
}
|
||||
|
||||
const instruction = promptBuilder.build()
|
||||
// Build Current Asset Context
|
||||
const currentAssetContext: ShumaiAssetContext = {
|
||||
id: asset.id,
|
||||
name: asset.name,
|
||||
type: asset.type,
|
||||
mediaType: proxyType as ShumaiAssetContext['mediaType'],
|
||||
mimeType: asset.mediaType || undefined,
|
||||
parentId: asset.parentId || undefined,
|
||||
path: assetPath || undefined,
|
||||
durationSeconds: duration !== undefined ? duration : undefined,
|
||||
totalFrames: totalFrames !== undefined ? totalFrames : undefined,
|
||||
totalPages: totalPages !== undefined ? totalPages : undefined,
|
||||
navigated: payload.agent?.hasAssetChanged === true ? true : undefined,
|
||||
ancestors: ancestors.length > 0 ? ancestors : undefined,
|
||||
}
|
||||
|
||||
// Build structured ShumaiMessageContext
|
||||
const messageContext: ShumaiMessageContext = {
|
||||
...(userCommentId ? { id: userCommentId } : {}),
|
||||
...(userInfo
|
||||
? { user: { id: targetUserId!, name: userInfo.name, role: userInfo.role } }
|
||||
: {}),
|
||||
currentAsset: currentAssetContext,
|
||||
...(mediaPosition ? { position: mediaPosition } : {}),
|
||||
...(commentAnnotation
|
||||
? {
|
||||
annotation: true,
|
||||
annotations: commentAnnotations as ShumaiMessageContext['annotations'],
|
||||
}
|
||||
: {}),
|
||||
...(attachedFiles.length > 0 ? { attachedFiles } : {}),
|
||||
...(referencedAssets.length > 0 ? { referencedAssets } : {}),
|
||||
}
|
||||
|
||||
// 6. Call AI Chat
|
||||
let folderId = ''
|
||||
@@ -202,11 +330,12 @@ export async function agentChat(task: WorkflowTask): Promise<void> {
|
||||
imageUrls: attachmentImageUrls,
|
||||
projectId: payload.projectId,
|
||||
folderId,
|
||||
agentsInstruction: instruction,
|
||||
assetId: asset.id,
|
||||
sessionId,
|
||||
userId: payload.agent?.userId,
|
||||
userCommentId: userCommentId || undefined,
|
||||
context,
|
||||
messageContext,
|
||||
attachedAssets,
|
||||
})
|
||||
|
||||
|
||||
@@ -186,7 +186,7 @@ describe('Agent Embedding Workflow', () => {
|
||||
mediaType: 'image/png',
|
||||
storageKey: { key: 'test.png' },
|
||||
media: {
|
||||
imageTranscodes: [{ key: 'test-transcoded.webp', isRaw: false, format: 'webp' }],
|
||||
imageTranscodes: [{ key: 'test-transcoded.webp', format: 'webp' }],
|
||||
},
|
||||
},
|
||||
chunkDuration: 60.0,
|
||||
@@ -220,7 +220,7 @@ describe('Agent Embedding Workflow', () => {
|
||||
storageKey: { key: 'test.mp4' },
|
||||
media: {
|
||||
duration: 150.0,
|
||||
videoTranscodes: [{ key: 'test-transcoded.mp4', isRaw: false }],
|
||||
videoTranscodes: [{ key: 'test-transcoded.mp4' }],
|
||||
},
|
||||
},
|
||||
chunkDuration: 60.0,
|
||||
|
||||
@@ -91,20 +91,14 @@ export async function agentEmbeddingMedia(task: WorkflowTask): Promise<void> {
|
||||
const media = asset.media as any
|
||||
if (isVideo) {
|
||||
if (media.videoTranscodes && media.videoTranscodes.length > 0) {
|
||||
// Find first non-raw transcode or fallback to first transcode
|
||||
const transcode =
|
||||
media.videoTranscodes.find((t: PrismaJson.VideoTranscode) => !t.isRaw) ||
|
||||
media.videoTranscodes[0]
|
||||
const transcode = media.videoTranscodes[0] as PrismaJson.VideoTranscode
|
||||
if (transcode?.key) {
|
||||
embeddingKey = transcode.key
|
||||
}
|
||||
}
|
||||
} else if (isImage) {
|
||||
if (media.imageTranscodes && media.imageTranscodes.length > 0) {
|
||||
// Find first non-raw transcode or fallback to first transcode
|
||||
const transcode =
|
||||
media.imageTranscodes.find((t: PrismaJson.ImageTranscode) => !t.isRaw) ||
|
||||
media.imageTranscodes[0]
|
||||
const transcode = media.imageTranscodes[0] as PrismaJson.ImageTranscode
|
||||
if (transcode?.key) {
|
||||
embeddingKey = transcode.key
|
||||
if (transcode.format) {
|
||||
|
||||
@@ -1,140 +0,0 @@
|
||||
import { describe, it, expect, vi, beforeEach } from 'vitest'
|
||||
import { agentToolCall } from './agent-tool-call'
|
||||
import { prisma } from '@shumai/db'
|
||||
import { setupTestDbHooks } from '@shumai/db/test'
|
||||
import * as workflowUtils from '@shumai/workflow-core'
|
||||
|
||||
vi.mock('@shumai/workflow-core', async () => {
|
||||
const actual = await vi.importActual('@shumai/workflow-core')
|
||||
return {
|
||||
...actual,
|
||||
getActivities: vi.fn(),
|
||||
executeActivity: vi.fn(),
|
||||
}
|
||||
})
|
||||
|
||||
describe('Agent Tool Call Workflow', () => {
|
||||
setupTestDbHooks()
|
||||
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any -- mockActivities holds mock functions cast to expected types
|
||||
let mockActivities: any
|
||||
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks()
|
||||
|
||||
mockActivities = {
|
||||
updateTaskStatusActivity: Object.assign(vi.fn(), {
|
||||
_activityName: 'updateTaskStatusActivity',
|
||||
}),
|
||||
executeAgentToolActivity: Object.assign(vi.fn(), {
|
||||
_activityName: 'executeAgentToolActivity',
|
||||
}),
|
||||
getAgentWorkerQueueActivity: Object.assign(vi.fn(), {
|
||||
_activityName: 'getAgentWorkerQueueActivity',
|
||||
}),
|
||||
}
|
||||
|
||||
mockActivities.getAgentWorkerQueueActivity.mockResolvedValue('agent_queue')
|
||||
mockActivities.updateTaskStatusActivity.mockResolvedValue({})
|
||||
mockActivities.executeAgentToolActivity.mockResolvedValue({ success: true, count: 42 })
|
||||
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any -- mockActivities contains vi.fn mock functions which are cast to expected activity proxy types
|
||||
vi.mocked(workflowUtils.getActivities).mockReturnValue(mockActivities as any)
|
||||
vi.mocked(workflowUtils.executeActivity).mockImplementation(async (_queue, act, ...args) => {
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any -- act is one of the mocked activities
|
||||
return (act as any)(...args)
|
||||
})
|
||||
})
|
||||
|
||||
it('should run agent tool call workflow successfully', async () => {
|
||||
const task = await prisma.workflowTask.create({
|
||||
data: {
|
||||
type: 'agent_tool_call',
|
||||
status: 'pending',
|
||||
assetId: 'a1',
|
||||
payload: {
|
||||
projectId: 'p1',
|
||||
agentToolCall: {
|
||||
toolName: 'list_assets',
|
||||
args: { parent: 'folder-123' },
|
||||
userId: 'user-456',
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
await agentToolCall(task)
|
||||
|
||||
// Verify queue discovery
|
||||
expect(mockActivities.getAgentWorkerQueueActivity).toHaveBeenCalled()
|
||||
|
||||
// Verify task processing status
|
||||
expect(mockActivities.updateTaskStatusActivity).toHaveBeenCalledWith({
|
||||
taskId: task.id,
|
||||
status: 'processing',
|
||||
})
|
||||
|
||||
// Verify tool execution
|
||||
expect(mockActivities.executeAgentToolActivity).toHaveBeenCalledWith({
|
||||
taskId: task.id,
|
||||
toolName: 'list_assets',
|
||||
args: { parent: 'folder-123' },
|
||||
userId: 'user-456',
|
||||
})
|
||||
|
||||
// Verify task completed status with output
|
||||
expect(mockActivities.updateTaskStatusActivity).toHaveBeenCalledWith({
|
||||
taskId: task.id,
|
||||
status: 'completed',
|
||||
output: { success: true, count: 42 },
|
||||
})
|
||||
})
|
||||
|
||||
it('should throw if payload or agentToolCall is missing', async () => {
|
||||
const task = await prisma.workflowTask.create({
|
||||
data: {
|
||||
type: 'agent_tool_call',
|
||||
status: 'pending',
|
||||
assetId: 'a1',
|
||||
},
|
||||
})
|
||||
|
||||
await expect(agentToolCall(task)).rejects.toThrow('Task payload or agentToolCall is missing')
|
||||
|
||||
// Verify status updated to failed
|
||||
expect(mockActivities.updateTaskStatusActivity).toHaveBeenCalledWith({
|
||||
taskId: task.id,
|
||||
status: 'failed',
|
||||
output: { error: 'Task payload or agentToolCall is missing' },
|
||||
})
|
||||
})
|
||||
|
||||
it('should handle tool execution failures by updating task to failed and throwing', async () => {
|
||||
mockActivities.executeAgentToolActivity.mockRejectedValue(new Error('Authz failure'))
|
||||
|
||||
const task = await prisma.workflowTask.create({
|
||||
data: {
|
||||
type: 'agent_tool_call',
|
||||
status: 'pending',
|
||||
assetId: 'a1',
|
||||
payload: {
|
||||
projectId: 'p1',
|
||||
agentToolCall: {
|
||||
toolName: 'create_folder',
|
||||
args: { parent: 'folder-123', name: 'new-folder' },
|
||||
userId: 'user-456',
|
||||
},
|
||||
},
|
||||
},
|
||||
})
|
||||
|
||||
await expect(agentToolCall(task)).rejects.toThrow('Authz failure')
|
||||
|
||||
// Verify task status failed
|
||||
expect(mockActivities.updateTaskStatusActivity).toHaveBeenCalledWith({
|
||||
taskId: task.id,
|
||||
status: 'failed',
|
||||
output: { error: 'Authz failure' },
|
||||
})
|
||||
})
|
||||
})
|
||||
@@ -1,60 +0,0 @@
|
||||
import { ApplicationFailure } from '@temporalio/workflow'
|
||||
import type { WorkflowTask } from '@shumai/db'
|
||||
import { getActivities, executeActivity, TaskQueueAgent } from '@shumai/workflow-core'
|
||||
|
||||
export async function agentToolCall(task: WorkflowTask): Promise<void> {
|
||||
const { updateTaskStatusActivity, executeAgentToolActivity, getAgentWorkerQueueActivity } =
|
||||
getActivities()
|
||||
|
||||
let agentWorkerQueue = ''
|
||||
|
||||
try {
|
||||
// 0. Discover queue
|
||||
agentWorkerQueue = await executeActivity(TaskQueueAgent, getAgentWorkerQueueActivity)
|
||||
|
||||
// Update status to processing
|
||||
await executeActivity(agentWorkerQueue, updateTaskStatusActivity, {
|
||||
taskId: task.id,
|
||||
status: 'processing',
|
||||
})
|
||||
|
||||
const payload = task.payload
|
||||
if (!payload || !payload.agentToolCall) {
|
||||
throw ApplicationFailure.create({
|
||||
message: 'Task payload or agentToolCall is missing',
|
||||
nonRetryable: true,
|
||||
})
|
||||
}
|
||||
|
||||
const { toolName, args, userId } = payload.agentToolCall
|
||||
|
||||
// Execute the agent activity on specific queue
|
||||
const result = await executeActivity(agentWorkerQueue, executeAgentToolActivity, {
|
||||
taskId: task.id,
|
||||
toolName,
|
||||
args,
|
||||
userId,
|
||||
})
|
||||
|
||||
// Update status to completed with output
|
||||
await executeActivity(agentWorkerQueue, updateTaskStatusActivity, {
|
||||
taskId: task.id,
|
||||
status: 'completed',
|
||||
output: result,
|
||||
})
|
||||
} catch (err) {
|
||||
console.error(`AgentToolCall failed for task ${task.id}:`, err)
|
||||
|
||||
// Update status to failed
|
||||
if (agentWorkerQueue) {
|
||||
await executeActivity(agentWorkerQueue, updateTaskStatusActivity, {
|
||||
taskId: task.id,
|
||||
status: 'failed',
|
||||
output: { error: err instanceof Error ? err.message : String(err) },
|
||||
})
|
||||
}
|
||||
throw err
|
||||
}
|
||||
}
|
||||
|
||||
export const agentToolCallWorkflow = agentToolCall
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@shumai/api",
|
||||
"version": "0.3.3",
|
||||
"version": "0.4.2",
|
||||
"private": true,
|
||||
"type": "module",
|
||||
"main": "./src/index.ts",
|
||||
|
||||
@@ -1,7 +1,9 @@
|
||||
import { describe, it, expect, vi, beforeEach } from 'vitest'
|
||||
import { HTTPException } from 'hono/http-exception'
|
||||
import { agentService } from '@shumai/core/src/agent/agent'
|
||||
import { authzService } from '@shumai/core/src/authz/authz'
|
||||
import { auditLogService } from '@shumai/core/src/auditLog/auditLog'
|
||||
import type { AgentInfo } from '@shumai/dtos'
|
||||
import app from './agent'
|
||||
|
||||
vi.mock('@shumai/core/src/agent/agent')
|
||||
@@ -12,6 +14,24 @@ vi.mock('@shumai/core/src/auditLog/auditLog', () => ({
|
||||
},
|
||||
}))
|
||||
|
||||
/**
|
||||
* Shape of the agent rows returned by the (mocked) service methods. Mirrors
|
||||
* the real AgentInfoSource consumed by AgentService.toAgentInfo.
|
||||
*/
|
||||
interface MockAgentRow {
|
||||
id: string
|
||||
user: { name: string; image?: string | null }
|
||||
type: string
|
||||
enabled?: boolean
|
||||
permission?: string
|
||||
providerId?: string | null
|
||||
modelId?: string | null
|
||||
soul?: string | null
|
||||
config?: { thinkingLevel?: string; systemPrompt?: string; deniedTools?: string[] }
|
||||
skills?: Array<{ id: string; skillId: string; skill?: { id: string; name: string } }>
|
||||
mcpServers?: Array<{ mcpServerId: string }>
|
||||
}
|
||||
|
||||
describe('Agent API', () => {
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks()
|
||||
@@ -20,6 +40,32 @@ describe('Agent API', () => {
|
||||
id: 'agent1',
|
||||
teamId: 'team1',
|
||||
} as unknown as Awaited<ReturnType<typeof agentService.getAgent>>)
|
||||
|
||||
// The route delegates AgentInfo mapping to the service; replicate the real
|
||||
// mapping so response assertions keep working.
|
||||
vi.mocked(agentService.toAgentInfo).mockImplementation(async (agent) => {
|
||||
const config = agent.config as MockAgentRow['config']
|
||||
return {
|
||||
id: agent.id,
|
||||
name: agent.user.name,
|
||||
type: agent.type,
|
||||
enabled: agent.enabled ?? true,
|
||||
permission: agent.permission ?? 'reviewer',
|
||||
avatar: agent.user.image || undefined,
|
||||
providerId: agent.providerId || undefined,
|
||||
modelId: agent.modelId || undefined,
|
||||
thinkingLevel: config?.thinkingLevel || 'off',
|
||||
systemPrompt: config?.systemPrompt,
|
||||
soul: agent.soul || undefined,
|
||||
skills: (agent.skills || []).map((s) => ({
|
||||
id: s.id,
|
||||
skillId: s.skillId,
|
||||
skill: s.skill,
|
||||
})),
|
||||
mcpServerIds: (agent.mcpServers || []).map((m) => m.mcpServerId),
|
||||
deniedTools: config?.deniedTools || [],
|
||||
} as unknown as AgentInfo
|
||||
})
|
||||
})
|
||||
|
||||
describe('GET /teams/:teamId/agents', () => {
|
||||
@@ -183,6 +229,63 @@ describe('Agent API', () => {
|
||||
})
|
||||
})
|
||||
|
||||
describe('PATCH /agents/:agentId/permission', () => {
|
||||
it('updates agent permission when user is admin', async () => {
|
||||
const mockAgent = {
|
||||
id: 'agent1',
|
||||
teamId: 'team1',
|
||||
user: { name: 'Bot 1', image: 'avatar1' },
|
||||
type: 'chat',
|
||||
enabled: true,
|
||||
permission: 'owner',
|
||||
config: {
|
||||
provider: 'prov1',
|
||||
model: 'model1',
|
||||
},
|
||||
skills: [],
|
||||
}
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
vi.mocked(agentService.updateAgentPermission).mockResolvedValue(mockAgent as any)
|
||||
|
||||
const res = await app.request('/agents/agent1/permission', {
|
||||
method: 'PATCH',
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
body: JSON.stringify({ permission: 'owner' }),
|
||||
})
|
||||
|
||||
expect(res.status).toBe(200)
|
||||
const data = await res.json()
|
||||
expect(data.permission).toBe('owner')
|
||||
expect(authzService.hasPermission).toHaveBeenCalledWith({
|
||||
user: undefined,
|
||||
permission: 'Admin',
|
||||
type: 'agent',
|
||||
id: 'agent1',
|
||||
})
|
||||
expect(agentService.updateAgentPermission).toHaveBeenCalledWith('agent1', 'owner')
|
||||
expect(auditLogService.logAction).toHaveBeenCalledWith({
|
||||
action: 'agent_update',
|
||||
teamId: 'team1',
|
||||
userId: undefined,
|
||||
itemId: 'agent1',
|
||||
})
|
||||
})
|
||||
|
||||
it('denies access when user is not admin', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockRejectedValue(
|
||||
new HTTPException(403, { message: 'Forbidden' }),
|
||||
)
|
||||
|
||||
const res = await app.request('/agents/agent1/permission', {
|
||||
method: 'PATCH',
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
body: JSON.stringify({ permission: 'owner' }),
|
||||
})
|
||||
|
||||
expect(res.status).toBe(403)
|
||||
})
|
||||
})
|
||||
|
||||
describe('GET /agent-sessions/:sessionId/entries', () => {
|
||||
it('returns entries of agent session if user is admin', async () => {
|
||||
const mockEntries = [
|
||||
@@ -258,4 +361,53 @@ describe('Agent API', () => {
|
||||
})
|
||||
})
|
||||
})
|
||||
|
||||
describe('GET /projects/:projectId/chat-agents', () => {
|
||||
it('returns project-scoped chat agents for the user', async () => {
|
||||
const mockAgents = [
|
||||
{
|
||||
id: 'agent1',
|
||||
name: 'Chat Bot',
|
||||
type: 'chat',
|
||||
enabled: true,
|
||||
permission: 'reviewer',
|
||||
skills: [],
|
||||
mcpServerIds: [],
|
||||
deniedTools: [],
|
||||
},
|
||||
]
|
||||
vi.mocked(agentService.listProjectChatAgents).mockResolvedValue(
|
||||
mockAgents as unknown as Awaited<ReturnType<typeof agentService.listProjectChatAgents>>,
|
||||
)
|
||||
|
||||
const res = await app.request('/projects/project1/chat-agents', {
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
})
|
||||
|
||||
expect(res.status).toBe(200)
|
||||
const data = await res.json()
|
||||
expect(data).toHaveLength(1)
|
||||
expect(data[0].name).toBe('Chat Bot')
|
||||
expect(authzService.hasPermission).toHaveBeenCalledWith({
|
||||
user: undefined,
|
||||
permission: 'Read',
|
||||
type: 'project',
|
||||
id: 'project1',
|
||||
})
|
||||
expect(agentService.listProjectChatAgents).toHaveBeenCalledWith('project1', undefined)
|
||||
})
|
||||
|
||||
it('denies access when the user has no project access', async () => {
|
||||
vi.mocked(authzService.hasPermission).mockRejectedValue(
|
||||
new HTTPException(403, { message: 'Forbidden' }),
|
||||
)
|
||||
|
||||
const res = await app.request('/projects/project1/chat-agents', {
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
})
|
||||
|
||||
expect(res.status).toBe(403)
|
||||
expect(agentService.listProjectChatAgents).not.toHaveBeenCalled()
|
||||
})
|
||||
})
|
||||
})
|
||||
|
||||
+48
-62
@@ -2,13 +2,12 @@ import { Hono } from 'hono'
|
||||
import { zValidator } from '@hono/zod-validator'
|
||||
import { agentService } from '@shumai/core/src/agent/agent'
|
||||
import { authzService, Permission, ResourceType } from '@shumai/core/src/authz/authz'
|
||||
import { getAvatarUrl } from '@shumai/core/src/user/avatar'
|
||||
import {
|
||||
createAgentRequestSchema,
|
||||
updateAgentRequestSchema,
|
||||
updateAgentPermissionRequestSchema,
|
||||
paginationParamsSchema,
|
||||
AgentInfo,
|
||||
AgentType,
|
||||
AuditAction,
|
||||
} from '@shumai/dtos'
|
||||
|
||||
@@ -29,34 +28,28 @@ const route = new Hono<{ Variables: { user: User } }>()
|
||||
id: teamId,
|
||||
})
|
||||
|
||||
const agents = await agentService.listAgents({ teamId })
|
||||
const agents = await agentService.listAgents({ teamId, userId: userReq?.id })
|
||||
|
||||
const res: AgentInfo[] = await Promise.all(
|
||||
agents.map(async (agent) => {
|
||||
const config = agent.config as unknown as PrismaJson.AgentConfig
|
||||
return {
|
||||
id: agent.id,
|
||||
name: agent.user.name,
|
||||
type: agent.type as AgentType,
|
||||
enabled: agent.enabled,
|
||||
avatar: (await getAvatarUrl(agent.user.image)) || undefined,
|
||||
providerId: agent.providerId || undefined,
|
||||
modelId: agent.modelId || undefined,
|
||||
thinkingLevel: config.thinkingLevel || 'off',
|
||||
systemPrompt: config.systemPrompt,
|
||||
soul: agent.soul || undefined,
|
||||
skills: agent.skills.map((s) => ({
|
||||
id: s.id,
|
||||
skillId: s.skillId,
|
||||
skill: s.skill,
|
||||
})),
|
||||
deniedTools: config.deniedTools || [],
|
||||
}
|
||||
}),
|
||||
agents.map((agent) => agentService.toAgentInfo(agent)),
|
||||
)
|
||||
|
||||
return c.json(res, 200)
|
||||
})
|
||||
.get('/projects/:projectId/chat-agents', async (c) => {
|
||||
const projectId = c.req.param('projectId')
|
||||
const userReq = c.get('user')
|
||||
|
||||
await authzService.hasPermission({
|
||||
user: userReq,
|
||||
permission: Permission.Read,
|
||||
type: ResourceType.Project,
|
||||
id: projectId,
|
||||
})
|
||||
|
||||
const agents = await agentService.listProjectChatAgents(projectId, userReq?.id)
|
||||
return c.json(agents, 200)
|
||||
})
|
||||
.post('/teams/:teamId/agents', zValidator('json', createAgentRequestSchema), async (c) => {
|
||||
const teamId = c.req.param('teamId')
|
||||
const userReq = c.get('user')
|
||||
@@ -76,25 +69,7 @@ const route = new Hono<{ Variables: { user: User } }>()
|
||||
|
||||
if (!agent) throw new Error('failed to create agent')
|
||||
|
||||
const config = agent.config as unknown as PrismaJson.AgentConfig
|
||||
const info: AgentInfo = {
|
||||
id: agent.id,
|
||||
name: agent.user.name,
|
||||
type: agent.type as AgentType,
|
||||
enabled: agent.enabled,
|
||||
avatar: (await getAvatarUrl(agent.user.image)) || undefined,
|
||||
providerId: agent.providerId || undefined,
|
||||
modelId: agent.modelId || undefined,
|
||||
thinkingLevel: config.thinkingLevel || 'off',
|
||||
systemPrompt: config.systemPrompt,
|
||||
soul: agent.soul || undefined,
|
||||
skills: agent.skills.map((s) => ({
|
||||
id: s.id,
|
||||
skillId: s.skillId,
|
||||
skill: s.skill,
|
||||
})),
|
||||
deniedTools: config.deniedTools || [],
|
||||
}
|
||||
const info = await agentService.toAgentInfo(agent)
|
||||
|
||||
await auditLogService.logAction({
|
||||
action: AuditAction.agent_create,
|
||||
@@ -129,28 +104,39 @@ const route = new Hono<{ Variables: { user: User } }>()
|
||||
itemId: agent.id,
|
||||
})
|
||||
|
||||
const config = agent.config as unknown as PrismaJson.AgentConfig
|
||||
const info: AgentInfo = {
|
||||
id: agent.id,
|
||||
name: agent.user.name,
|
||||
type: agent.type as AgentType,
|
||||
enabled: agent.enabled,
|
||||
avatar: (await getAvatarUrl(agent.user.image)) || undefined,
|
||||
providerId: agent.providerId || undefined,
|
||||
modelId: agent.modelId || undefined,
|
||||
thinkingLevel: config.thinkingLevel || 'off',
|
||||
systemPrompt: config.systemPrompt,
|
||||
soul: agent.soul || undefined,
|
||||
skills: agent.skills.map((s) => ({
|
||||
id: s.id,
|
||||
skillId: s.skillId,
|
||||
skill: s.skill,
|
||||
})),
|
||||
deniedTools: config.deniedTools || [],
|
||||
}
|
||||
const info = await agentService.toAgentInfo(agent)
|
||||
|
||||
return c.json(info, 200)
|
||||
})
|
||||
.patch(
|
||||
'/agents/:agentId/permission',
|
||||
zValidator('json', updateAgentPermissionRequestSchema),
|
||||
async (c) => {
|
||||
const agentId = c.req.param('agentId')
|
||||
const userReq = c.get('user')
|
||||
const req = c.req.valid('json')
|
||||
|
||||
await authzService.hasPermission({
|
||||
user: userReq,
|
||||
permission: Permission.Admin,
|
||||
type: ResourceType.Agent,
|
||||
id: agentId,
|
||||
})
|
||||
|
||||
const agent = await agentService.updateAgentPermission(agentId, req.permission)
|
||||
|
||||
await auditLogService.logAction({
|
||||
action: AuditAction.agent_update,
|
||||
teamId: agent.teamId,
|
||||
userId: userReq?.id,
|
||||
itemId: agent.id,
|
||||
})
|
||||
|
||||
const info = await agentService.toAgentInfo(agent)
|
||||
|
||||
return c.json(info, 200)
|
||||
},
|
||||
)
|
||||
.delete('/agents/:agentId', async (c) => {
|
||||
const agentId = c.req.param('agentId')
|
||||
const userReq = c.get('user')
|
||||
|
||||
@@ -148,6 +148,48 @@ describe('Chat API', () => {
|
||||
)
|
||||
})
|
||||
|
||||
it('accepts chat request with annotations, second, and attachmentIds', async () => {
|
||||
vi.mocked(chatService.startOrContinueChat).mockResolvedValue({
|
||||
sessionId: 'session1',
|
||||
taskId: 'task1',
|
||||
})
|
||||
|
||||
vi.mocked(chatService.getNewSessionMessages).mockResolvedValue({
|
||||
messages: [],
|
||||
lastEntryId: null,
|
||||
})
|
||||
|
||||
vi.mocked(chatService.getChatWorkflowStatus).mockResolvedValue({
|
||||
status: 'completed',
|
||||
output: {},
|
||||
})
|
||||
|
||||
const res = await app.request('/teams/team1/chat', {
|
||||
method: 'POST',
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
body: JSON.stringify({
|
||||
agentId: 'agent1',
|
||||
textPrompt: 'Review annotation',
|
||||
attachedFiles: ['att1'],
|
||||
annotations: [{ type: 'rectangle', x: 10, y: 20 }],
|
||||
second: 5.5,
|
||||
}),
|
||||
})
|
||||
|
||||
expect(res.status).toBe(200)
|
||||
expect(chatService.startOrContinueChat).toHaveBeenCalledWith(
|
||||
expect.objectContaining({ id: 'user1' }),
|
||||
'team1',
|
||||
expect.objectContaining({
|
||||
agentId: 'agent1',
|
||||
textPrompt: 'Review annotation',
|
||||
attachedFiles: ['att1'],
|
||||
annotations: [{ type: 'rectangle', x: 10, y: 20 }],
|
||||
second: 5.5,
|
||||
}),
|
||||
)
|
||||
})
|
||||
|
||||
it('sends ping keep-alive SSE events when there are no new messages', async () => {
|
||||
vi.mocked(chatService.startOrContinueChat).mockResolvedValue({
|
||||
sessionId: 'session1',
|
||||
|
||||
@@ -351,7 +351,8 @@ const route = new Hono<{ Variables: { user: User } }>()
|
||||
contentType,
|
||||
)
|
||||
|
||||
return c.json({ key })
|
||||
const url = await s3Service.presign(process.env.S3_BUCKET || 'shumai', key, 'GET')
|
||||
return c.json({ key, url })
|
||||
})
|
||||
.post('/files/download-links', zValidator('json', getDownloadLinksRequestSchema), async (c) => {
|
||||
const user = c.get('user')
|
||||
|
||||
@@ -188,6 +188,46 @@ describe('folder api', () => {
|
||||
type: ResourceType.Asset,
|
||||
id: 'test-id',
|
||||
})
|
||||
expect(assetService.listChildren).toHaveBeenCalledWith({
|
||||
assetId: 'test-id',
|
||||
assetType: 'folder',
|
||||
})
|
||||
})
|
||||
|
||||
it('GET /folders/:folderId/children forwards pagination parameters', async () => {
|
||||
vi.mocked(assetService.listChildren).mockResolvedValue({
|
||||
data: [
|
||||
{
|
||||
id: 'child-id-2',
|
||||
name: 'child-folder-2',
|
||||
sizeByte: 0,
|
||||
fileCount: 0,
|
||||
type: 'folder',
|
||||
status: 'active',
|
||||
createdAt: new Date().toISOString(),
|
||||
updatedAt: new Date().toISOString(),
|
||||
},
|
||||
],
|
||||
pageInfo: { total: 30, cursor: 'cursorNextToken' },
|
||||
})
|
||||
|
||||
const app = new Hono().use('*', authMiddleware).route('/', folderRoute)
|
||||
const res = await app.request(
|
||||
'/folders/test-id/children?assetType=folder&first=20&after=cursorToken123&prefix=sub',
|
||||
)
|
||||
|
||||
expect(res.status).toBe(200)
|
||||
const json = await res.json()
|
||||
expect(json.data).toHaveLength(1)
|
||||
expect(json.pageInfo.cursor).toBe('cursorNextToken')
|
||||
|
||||
expect(assetService.listChildren).toHaveBeenCalledWith({
|
||||
assetId: 'test-id',
|
||||
assetType: 'folder',
|
||||
first: 20,
|
||||
after: 'cursorToken123',
|
||||
prefix: 'sub',
|
||||
})
|
||||
})
|
||||
|
||||
it('DELETE /folders', async () => {
|
||||
@@ -310,4 +350,59 @@ describe('folder api', () => {
|
||||
beforeIndex: 'index-1',
|
||||
})
|
||||
})
|
||||
|
||||
it('GET /folders/:folderId/agentsmd', async () => {
|
||||
vi.spyOn(assetService, 'getAgentsMd').mockResolvedValue('# Folder Guidelines')
|
||||
|
||||
const app = new Hono().use('*', authMiddleware).route('/', folderRoute)
|
||||
const res = await app.request('/folders/test-id/agentsmd')
|
||||
|
||||
expect(res.status).toBe(200)
|
||||
const json = await res.json()
|
||||
expect(json.content).toBe('# Folder Guidelines')
|
||||
|
||||
expect(authzService.hasPermission).toHaveBeenCalledWith({
|
||||
user: { id: 'user1', name: 'Test User' },
|
||||
permission: Permission.Read,
|
||||
type: ResourceType.Asset,
|
||||
id: 'test-id',
|
||||
})
|
||||
expect(assetService.getAgentsMd).toHaveBeenCalledWith('test-id')
|
||||
})
|
||||
|
||||
it('PATCH /folders/:folderId/agentsmd', async () => {
|
||||
vi.spyOn(assetService, 'updateAgentsMd').mockResolvedValue({ content: '# Updated Guidelines' })
|
||||
|
||||
const app = new Hono().use('*', authMiddleware).route('/', folderRoute)
|
||||
const res = await app.request('/folders/test-id/agentsmd', {
|
||||
method: 'PATCH',
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
body: JSON.stringify({ content: '# Updated Guidelines' }),
|
||||
})
|
||||
|
||||
expect(res.status).toBe(200)
|
||||
const json = await res.json()
|
||||
expect(json.content).toBe('# Updated Guidelines')
|
||||
|
||||
expect(authzService.hasPermission).toHaveBeenCalledWith({
|
||||
user: { id: 'user1', name: 'Test User' },
|
||||
permission: Permission.Admin,
|
||||
type: ResourceType.Asset,
|
||||
id: 'test-id',
|
||||
})
|
||||
expect(assetService.updateAgentsMd).toHaveBeenCalledWith('test-id', '# Updated Guidelines')
|
||||
})
|
||||
|
||||
it('PATCH /folders/:folderId/agentsmd rejects oversized content', async () => {
|
||||
const mockUpdate = vi.spyOn(assetService, 'updateAgentsMd').mockResolvedValue({ content: '' })
|
||||
const app = new Hono().use('*', authMiddleware).route('/', folderRoute)
|
||||
const res = await app.request('/folders/test-id/agentsmd', {
|
||||
method: 'PATCH',
|
||||
headers: { 'Content-Type': 'application/json' },
|
||||
body: JSON.stringify({ content: 'x'.repeat(100_001) }),
|
||||
})
|
||||
|
||||
expect(res.status).toBe(400)
|
||||
expect(mockUpdate).not.toHaveBeenCalled()
|
||||
})
|
||||
})
|
||||
|
||||
@@ -8,6 +8,7 @@ import {
|
||||
updateFolderRequestSchema,
|
||||
deleteFoldersRequestSchema,
|
||||
restoreFoldersRequestSchema,
|
||||
updateAgentsMdRequestSchema,
|
||||
} from '@shumai/dtos'
|
||||
import { listChildrenRequestSchema, updateAssetOrderRequestSchema, AuditAction } from '@shumai/dtos'
|
||||
import { searchRequestSchema } from '@shumai/dtos'
|
||||
@@ -119,12 +120,8 @@ const route = new Hono<{ Variables: { user: User } }>()
|
||||
})
|
||||
|
||||
const resp = await assetService.listChildren({
|
||||
...req,
|
||||
assetId: folderId,
|
||||
assetType: req.assetType,
|
||||
projectId: req.projectId,
|
||||
showDeleted: req.showDeleted,
|
||||
sort: req.sort,
|
||||
order: req.order,
|
||||
})
|
||||
return c.json(resp)
|
||||
})
|
||||
@@ -189,5 +186,48 @@ const route = new Hono<{ Variables: { user: User } }>()
|
||||
const result = await searchService.search(folderId, req)
|
||||
return c.json(result)
|
||||
})
|
||||
.get('/folders/:folderId/agentsmd', async (c) => {
|
||||
const folderId = c.req.param('folderId')
|
||||
const user = c.get('user')
|
||||
|
||||
await authzService.hasPermission({
|
||||
user,
|
||||
permission: Permission.Read,
|
||||
type: ResourceType.Asset,
|
||||
id: folderId,
|
||||
})
|
||||
|
||||
const content = await assetService.getAgentsMd(folderId)
|
||||
return c.json({ content })
|
||||
})
|
||||
.patch(
|
||||
'/folders/:folderId/agentsmd',
|
||||
zValidator('json', updateAgentsMdRequestSchema),
|
||||
async (c) => {
|
||||
const folderId = c.req.param('folderId')
|
||||
const user = c.get('user')
|
||||
const req = c.req.valid('json')
|
||||
|
||||
await authzService.hasPermission({
|
||||
user,
|
||||
permission: Permission.Admin,
|
||||
type: ResourceType.Asset,
|
||||
id: folderId,
|
||||
})
|
||||
|
||||
const res = await assetService.updateAgentsMd(folderId, req.content)
|
||||
|
||||
const ctx = await assetService.getAssetContext(folderId)
|
||||
await auditLogService.logAction({
|
||||
action: AuditAction.folder_update,
|
||||
teamId: ctx.teamId,
|
||||
userId: user.id,
|
||||
projectId: ctx.projectId,
|
||||
itemId: folderId,
|
||||
})
|
||||
|
||||
return c.json(res)
|
||||
},
|
||||
)
|
||||
|
||||
export default route
|
||||
|
||||
@@ -9,6 +9,7 @@ import fileRoute from './file'
|
||||
import folderRoute from './folder'
|
||||
import inviteRoute from './invite'
|
||||
import metadataRoute from './metadata'
|
||||
import mcpRoute, { mcpOauthCallbackRoute } from './mcp'
|
||||
import { authMiddleware } from './middleware/auth'
|
||||
import { tokenAuthMiddleware } from './middleware/tokenAuth'
|
||||
import notificationRoute from './notification'
|
||||
@@ -19,9 +20,12 @@ import publicShareRoute from './public-share'
|
||||
import s3Route from './s3'
|
||||
import shareRoute from './share'
|
||||
import skillRoute from './skill'
|
||||
import watermarkTemplateRoute from './watermark-template'
|
||||
import quotaRoute from './quota'
|
||||
import teamRoute from './team'
|
||||
import uploadRoute, { localUploadRoute } from './upload'
|
||||
import versionStackRoute from './versionStack'
|
||||
import kanbanRoute from './kanban'
|
||||
|
||||
type User = Prisma.UserGetPayload<Record<string, never>>
|
||||
|
||||
@@ -33,6 +37,7 @@ const apiRoute = new Hono<{ Variables: { user: User } }>()
|
||||
.route('/', publicInviteRoute)
|
||||
.route('/', publicShareRoute)
|
||||
.route('/', localUploadRoute)
|
||||
.route('/', mcpOauthCallbackRoute)
|
||||
|
||||
// Selected routes supporting API token authentication
|
||||
.use('/projects', tokenAuthMiddleware)
|
||||
@@ -60,6 +65,10 @@ const apiRoute = new Hono<{ Variables: { user: User } }>()
|
||||
.route('/', uploadRoute)
|
||||
.route('/', shareRoute)
|
||||
.route('/', skillRoute)
|
||||
.route('/', mcpRoute)
|
||||
.route('/', watermarkTemplateRoute)
|
||||
.route('/', quotaRoute)
|
||||
.route('/', kanbanRoute)
|
||||
|
||||
app.route('/files', s3Route)
|
||||
|
||||
|
||||
@@ -0,0 +1,130 @@
|
||||
import { zValidator } from '@hono/zod-validator'
|
||||
import { Hono } from 'hono'
|
||||
import { kanbanService } from '@shumai/core/src/kanban/kanban'
|
||||
import { notificationService } from '@shumai/core/src/notification/notification'
|
||||
import { auditLogService } from '@shumai/core/src/auditLog/auditLog'
|
||||
import {
|
||||
authzService,
|
||||
Permission,
|
||||
ResourceType,
|
||||
resolveEffectiveRole,
|
||||
} from '@shumai/core/src/authz/authz'
|
||||
import { createKanbanCommentSchema, postAttachmentRequestSchema, AuditAction } from '@shumai/dtos'
|
||||
import type { Prisma } from '@shumai/db'
|
||||
|
||||
type User = Prisma.UserGetPayload<Record<string, never>>
|
||||
|
||||
const route = new Hono<{ Variables: { user: User } }>()
|
||||
.post(
|
||||
'/teams/:teamId/kanban/attachments',
|
||||
zValidator('json', postAttachmentRequestSchema),
|
||||
async (c) => {
|
||||
const { teamId } = c.req.param()
|
||||
const req = c.req.valid('json')
|
||||
const user = c.get('user')
|
||||
|
||||
await authzService.hasPermission({
|
||||
user,
|
||||
permission: Permission.Read,
|
||||
type: ResourceType.Team,
|
||||
id: teamId,
|
||||
})
|
||||
|
||||
const attachment = await kanbanService.createAttachment(teamId, req)
|
||||
return c.json(attachment)
|
||||
},
|
||||
)
|
||||
.post(
|
||||
'/teams/:teamId/kanban/tasks/:taskId/comments',
|
||||
zValidator('json', createKanbanCommentSchema),
|
||||
async (c) => {
|
||||
const { teamId, taskId } = c.req.param()
|
||||
const req = c.req.valid('json')
|
||||
const user = c.get('user')
|
||||
|
||||
await authzService.hasPermission({
|
||||
user,
|
||||
permission: Permission.Read,
|
||||
type: ResourceType.KanbanTask,
|
||||
id: taskId,
|
||||
})
|
||||
|
||||
const comment = await kanbanService.addComment(taskId, user.id, req.body, req.attachments)
|
||||
const task = await kanbanService.getTask(taskId)
|
||||
|
||||
await auditLogService.logAction({
|
||||
action: AuditAction.kanban_comment_create,
|
||||
teamId,
|
||||
userId: user.id,
|
||||
projectId: task.projectId ?? undefined,
|
||||
itemId: comment.id,
|
||||
})
|
||||
|
||||
notificationService.notifyKanbanTaskEvent({
|
||||
type: 'kanban_task_comment_created',
|
||||
teamId,
|
||||
projectId: task.projectId,
|
||||
creatorId: user.id,
|
||||
kanbanTaskId: taskId,
|
||||
stakeholderIds: [task.creator?.id, task.assignee?.id, task.reporter?.id],
|
||||
commentMessage: req.body,
|
||||
})
|
||||
|
||||
return c.json(comment)
|
||||
},
|
||||
)
|
||||
.get('/teams/:teamId/kanban/tasks/:taskId/comments', async (c) => {
|
||||
const { taskId } = c.req.param()
|
||||
const user = c.get('user')
|
||||
|
||||
await authzService.hasPermission({
|
||||
user,
|
||||
permission: Permission.Read,
|
||||
type: ResourceType.KanbanTask,
|
||||
id: taskId,
|
||||
})
|
||||
|
||||
const comments = await kanbanService.listComments(taskId)
|
||||
return c.json({ data: comments })
|
||||
})
|
||||
.delete('/teams/:teamId/kanban/tasks/:taskId/comments/:commentId', async (c) => {
|
||||
const { teamId, taskId, commentId } = c.req.param()
|
||||
const user = c.get('user')
|
||||
|
||||
await authzService.hasPermission({
|
||||
user,
|
||||
permission: Permission.Read,
|
||||
type: ResourceType.KanbanTask,
|
||||
id: taskId,
|
||||
})
|
||||
|
||||
const userRole = await resolveEffectiveRole(teamId, undefined, user.id)
|
||||
const task = await kanbanService.getTask(taskId)
|
||||
await kanbanService.deleteComment(taskId, commentId, user.id, userRole)
|
||||
|
||||
await auditLogService.logAction({
|
||||
action: AuditAction.kanban_comment_delete,
|
||||
teamId,
|
||||
userId: user.id,
|
||||
projectId: task.projectId ?? undefined,
|
||||
itemId: commentId,
|
||||
})
|
||||
|
||||
return c.json({ success: true })
|
||||
})
|
||||
.get('/teams/:teamId/kanban/tasks/:taskId/events', async (c) => {
|
||||
const { taskId } = c.req.param()
|
||||
const user = c.get('user')
|
||||
|
||||
await authzService.hasPermission({
|
||||
user,
|
||||
permission: Permission.Read,
|
||||
type: ResourceType.KanbanTask,
|
||||
id: taskId,
|
||||
})
|
||||
|
||||
const events = await kanbanService.listEvents(taskId)
|
||||
return c.json({ data: events })
|
||||
})
|
||||
|
||||
export default route
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user