dsh-vision-worker

1. 安装并启动 DeepSeek Harness：npx @deepseek-ai/dsh web
2. 在终端执行上面的安装命令（CLI 会解析插件并核验来源）
3. 用 dsh plugins list 确认已安装，必要时重启 Harness 生效

插件以当前 dsh 进程的权限运行，安装时可能执行代码。请先通读仓库源码与许可证，确认无破坏性命令与越权访问；本站只做索引，不对第三方插件安全性作担保。

事实信息来自公开插件目录快照（2026-10-01），介绍文案由本站再加工。

以下为插件仓库 README 全文（原始内容，由公开目录抓取整理）。

# @try-works/dsh-vision-worker

A DeepSeek Harness plugin that gives text-only models real vision.

When a caller cannot see images, `dsh-vision-worker` routes the image to
Cloudflare Workers AI `@cf/moonshotai/kimi-k2.6` (vision-capable) and returns a
deterministic, versioned envelope — so the text-only caller can act on
structured facts instead of guessing from prose.

## The problem

- Text-only models reject image content, so they cannot read a website
  screenshot, a photo, a chart, or a scanned table.
- Handing them raw vision prose forces re-parsing and loses structure.

## The fix

One call returns a `righthand.vision.v1` envelope:

```json
{
  "schema": "righthand.vision.v1",
  "model": "@cf/moonshotai/kimi-k2.6",
  "status": "ok",
  "summary": "...",
  "answer": "...",
  "content": {
    "text": [{"value": "...", "confidence": 0.97, "bbox": [x,y,w,h]}],
    "measurements": [{"name": "...", "value": 12, "unit": "%"}],
    "tables": [{"name": "...", "columns": [...], "rows": [[...]]}],
    "code": [{"language": "...", "text": "..."}],
    "entities": [{"type": "...", "value": "..."}]
  },
  "actions": ["verify the Q3 total against the source table"],
  "confidence": 0.9,
  "warnings": [],
  "images": []
}
```

## Install

```bash
dsh plugin --profile  add @try-works/dsh-vision-worker
```

Or apply the overlay directly:

```bash
dsh --profile  --patch ./cordis.patch.yml
```

## Configure

Set **one** of these transports (the plugin tries `workerUrl` first, then
`accountId` + `apiTokenRef`):

```yaml
# cordis.patch.yml
- insert:
    - id: dsh-vision-worker
      name: '@try-works/dsh-vision-worker'
      config:
        # Deployed worker (see cloud/):
        workerUrl: 'https://vision-worker..workers.dev'
        # …or Workers AI REST directly:
        # accountId: ''
        # apiTokenRef: 'CLOUDFLARE_API_TOKEN'
        # model: '@cf/moonshotai/kimi-k2.6'
        # locale: 'en'
```

Store the token with the harness credential provider (never inline):

```
rh_credential_set ref=CLOUDFLARE_API_TOKEN value=
```

## Tools

| Tool | Purpose |
| --- | --- |
| `vw_analyze` | Analyze image(s) with a prompt → envelope + `callerText` |
| `vw_ask` | Follow-up question about the same image(s) |
| `vw_status` | Report active transport/model without exposing the token |
| `vw_locale` | Get/set UI language (`en` or `zh-CN`) |

Tool **names** are stable identifiers; descriptions and rendered status text
localize live via the `locale` setting.

## Deploy the worker

```bash
cd cloud
npx wrangler deploy
```

`cloud/index.js` is a zero-build Worker exposing `POST /analyze` (plus
`GET /health`). It takes `{ prompt, images, system? }` and returns the same
`righthand.vision.v1` envelope.

## Test

```bash
pnpm install
pnpm test          # 20 tests: core, schema, transport, tools, fixtures
pnpm typecheck
node --experimental-strip-types test.ts   # inside cloud/ — worker handler test
```

## Routing architecture

The observable Workers AI routing protocol (name→effective-model
aliasing, task-family dispatch, result-envelope shapes, gating) is
documented in [`docs/workers-ai-routing-protocol.md`](docs/workers-ai-routing-protocol.md),
derived from live probes of every cataloged model.

## Layout

- `src/core/vision.ts` — capability routing, multimodal input, normalization,
  multi-step (transport injected; zero deps).
- `src/core/schema.ts` — the envelope format, prompt template, tolerant parser,
  and `callerText` renderer.
- `src/transport.ts` — Workers AI REST client + deployed-worker client.
- `src/vision-tools.ts` — the DSH-native tool surface (`ctx.tools`/
  `ctx.settings`/`ctx.credentials`).
- `src/i18n.ts` — EN + zh-CN string tables.
- `src/fixture.ts` — deterministic PNG fixtures (real bytes, no deps).
- `cloud/` — deployable Worker.