@anionex/dsh-vision-toolkit 0.1.12 → 0.1.13
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.i18n.yaml +3 -3
- package/README.md +192 -343
- package/README.zh.md +192 -357
- package/docs/requirements-traceability/README.i18n.yaml +2 -2
- package/docs/requirements-traceability/README.md +1 -1
- package/docs/requirements-traceability/README.zh.md +1 -1
- package/lib/client.js +172 -6
- package/lib/client.js.map +1 -1
- package/lib/plugin-update.js +1011 -0
- package/lib/plugin-update.js.map +1 -0
- package/lib/runtime-install.js +61 -1
- package/lib/runtime-install.js.map +1 -1
- package/lib/runtime.js +20 -3
- package/lib/runtime.js.map +1 -1
- package/lib/skill.js +7 -3
- package/lib/skill.js.map +1 -1
- package/lib/tools.js +3 -2
- package/lib/tools.js.map +1 -1
- package/lib/types/client/index.d.ts +55 -1
- package/lib/types/client/index.d.ts.map +1 -1
- package/lib/types/plugin-update.d.ts +111 -0
- package/lib/types/plugin-update.d.ts.map +1 -0
- package/lib/types/runtime-install.d.ts +11 -0
- package/lib/types/runtime-install.d.ts.map +1 -1
- package/lib/types/runtime.d.ts +3 -0
- package/lib/types/runtime.d.ts.map +1 -1
- package/lib/types/skill.d.ts +1 -1
- package/lib/types/skill.d.ts.map +1 -1
- package/lib/types/tools.d.ts.map +1 -1
- package/lib/types/upstream.d.ts +1 -0
- package/lib/types/upstream.d.ts.map +1 -1
- package/lib/types/web.d.ts +13 -1
- package/lib/types/web.d.ts.map +1 -1
- package/lib/upstream.js +20 -8
- package/lib/upstream.js.map +1 -1
- package/lib/web.js +46 -7
- package/lib/web.js.map +1 -1
- package/package.json +1 -1
- package/src/client/index.tsx +228 -5
- package/src/plugin-update.ts +1142 -0
- package/src/runtime-install.ts +77 -1
- package/src/runtime.ts +23 -3
- package/src/skill.ts +7 -3
- package/src/tools.ts +4 -2
- package/src/upstream.ts +21 -8
- package/src/web.ts +69 -3
- package/vendor/agent-vision-toolkit/UPSTREAM_MANIFEST.json +3 -3
- package/vendor/agent-vision-toolkit/skills/vision-tools/scripts/html_shot.py +323 -11
- /package/assets/{hero.png → hero-v2.png} +0 -0
package/README.md
CHANGED
|
@@ -1,470 +1,319 @@
|
|
|
1
1
|
<p align="center">
|
|
2
|
-
<img src="assets/hero.png" alt="DSH Vision Toolkit
|
|
2
|
+
<img src="assets/hero-v2.png" alt="DSH Vision Toolkit helps text-only DeepSeek Harness agents understand images and complete visual tasks" />
|
|
3
3
|
</p>
|
|
4
4
|
|
|
5
|
-
<
|
|
5
|
+
<div align="center">
|
|
6
6
|
|
|
7
|
-
|
|
8
|
-
English | <a href="https://github.com/Anionex/dsh-vision-toolkit/blob/main/README.zh.md">中文</a>
|
|
9
|
-
</p>
|
|
7
|
+
# DSH Vision Toolkit
|
|
10
8
|
|
|
11
|
-
|
|
12
|
-
|
|
13
|
-
|
|
14
|
-
|
|
15
|
-
<a href="https://github.com/Anionex/dsh-vision-toolkit/releases/tag/v0.1.12"><img src="https://img.shields.io/badge/release-v0.1.12-5B4CF0?style=flat-square" alt="Release v0.1.12" /></a>
|
|
16
|
-
<a href="tests"><img src="https://img.shields.io/badge/verified-233%20tests-2EA44F?style=flat-square" alt="Verified: 233 tests" /></a>
|
|
17
|
-
</p>
|
|
9
|
+
[](https://dshfind.com/en/plugins/Anionex/dsh-vision-toolkit)
|
|
10
|
+
[](https://www.npmjs.com/package/@anionex/dsh-vision-toolkit)
|
|
11
|
+
[](LICENSE)
|
|
12
|
+
[](cordis.patch.yml)
|
|
18
13
|
|
|
19
|
-
|
|
20
|
-
|
|
21
|
-
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
</p>
|
|
14
|
+
**Give text-only DSH agents eyes: paste an image, ask a question, locate exact elements, extract assets, and verify UI restoration with measurable results.**
|
|
15
|
+
|
|
16
|
+
🌐 **English** | [中文](README.zh.md)
|
|
17
|
+
|
|
18
|
+
</div>
|
|
25
19
|
|
|
26
|
-
|
|
20
|
+
When you run DeepSeek or another text-only model in DeepSeek Harness (DSH), familiar problems appear quickly: the model cannot see a screenshot, generic image descriptions miss the point, buttons have no usable coordinates, and a rebuilt page may look “close enough” without any way to measure the remaining difference.
|
|
27
21
|
|
|
28
|
-
|
|
22
|
+
DSH Vision Toolkit packages [`agent-vision-toolkit`](https://github.com/Anionex/agent-vision-toolkit) as a native DSH plugin. It helps an agent do more than describe an image: the agent can read, locate, crop, trace, rebuild, and verify visual work around the task at hand.
|
|
29
23
|
|
|
30
|
-
|
|
24
|
+
> **Install and use it immediately.** The default setup includes a free Gemma 4 vision service and requires no API key. Cropping, pixel diffing, color analysis, foreground extraction, SVG tracing, and HTML screenshots run locally without spending vision API requests.
|
|
31
25
|
|
|
32
26
|
```sh
|
|
33
27
|
dsh plugin --profile web add @anionex/dsh-vision-toolkit
|
|
34
28
|
```
|
|
35
29
|
|
|
36
|
-
The npm package includes the visual toolkit snapshot and uses a managed runtime by default. **Normal installation does not require a source checkout or an `agentVisionToolkitPath`.**
|
|
37
|
-
|
|
38
30
|
**Upstream toolkit:** [Anionex/agent-vision-toolkit](https://github.com/Anionex/agent-vision-toolkit) · **Project website:** [agent-vision.anionex.me](https://agent-vision.anionex.me)
|
|
39
31
|
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
|
|
46
|
-
|
|
47
|
-
|
|
48
|
-
|
|
49
|
-
|
|
32
|
+
<details>
|
|
33
|
+
<summary><strong>Table of contents</strong></summary>
|
|
34
|
+
|
|
35
|
+
- [Recent updates](#recent-updates)
|
|
36
|
+
- [Problems it solves](#problems-it-solves)
|
|
37
|
+
- [See it in action](#see-it-in-action)
|
|
38
|
+
- [Highlights](#highlights)
|
|
39
|
+
- [Quick start: three steps](#quick-start-three-steps)
|
|
40
|
+
- [Common workflows](#common-workflows)
|
|
41
|
+
- [Toolbox](#toolbox)
|
|
42
|
+
- [Configuration and limits](#configuration-and-limits)
|
|
43
|
+
- [Troubleshooting](#troubleshooting)
|
|
44
|
+
- [Development and community](#development-and-community)
|
|
50
45
|
|
|
51
|
-
|
|
46
|
+
</details>
|
|
52
47
|
|
|
53
|
-
##
|
|
48
|
+
## Recent updates
|
|
54
49
|
|
|
55
|
-
|
|
50
|
+
- **2026-08-16 · Windows Python:** Added Microsoft Store Python support, fixing first-time isolated-runtime setup failures for affected Windows users.
|
|
51
|
+
- **2026-08-16 · Better free vision:** Switched the default model to Gemma 4, improving the no-key image-understanding path.
|
|
52
|
+
- **2026-08-16 · Image paste:** Text-only routes now switch to a `(Vision Toolkit)` variant and keep a workspace path, fixing blocked pastes and images that could not be reused later.
|
|
53
|
+
- **2026-08-16 · Higher free quotas:** Raised per-client, global, and burst limits to `100/day`, `400/day`, and `20/minute`, reducing avoidable rate-limit failures while the shared capacity is lightly used.
|
|
54
|
+
- **2026-08-16 · Real model test:** Added a full image-request test in Settings, fixing the false confidence caused by a successful `/models` request to a model that still cannot process images.
|
|
56
55
|
|
|
57
|
-
|
|
56
|
+
## Problems it solves
|
|
58
57
|
|
|
59
|
-
|
|
60
|
-
|
|
61
|
-
|
|
58
|
+
| The problem | What Vision Toolkit delivers |
|
|
59
|
+
|---|---|
|
|
60
|
+
| **A text-only model cannot see a screenshot** | Paste an image in DSH Web; the plugin obtains visual evidence and returns the task-relevant parts to the text model |
|
|
61
|
+
| **The description is long but misses the point** | Ask “Where is the error?” or “What color is the submit button?” and receive an answer focused on that question |
|
|
62
|
+
| **The model knows an element exists but cannot act on it** | Get original-image pixel coordinates and an optional labeled or numbered preview |
|
|
63
|
+
| **Long-screenshot OCR skips or duplicates lines** | Split and audit the image while preserving Markdown, chunks, manifests, and resumable run state |
|
|
64
|
+
| **UI restoration is judged by feel** | Compare the reference and implementation screenshots to get a difference percentage, ranked regions, a heatmap, and JSON |
|
|
65
|
+
| **Screenshot assets cannot be reused** | Produce a crop, transparent PNG, color palette, or editable SVG instead of stopping at prose |
|
|
62
66
|
|
|
63
|
-
|
|
67
|
+
## See it in action
|
|
64
68
|
|
|
65
|
-
###
|
|
69
|
+
### Paste an image directly into DSH
|
|
66
70
|
|
|
67
71
|
<p align="center">
|
|
68
|
-
<img src="assets/
|
|
69
|
-
<img src="assets/upstream/infographic-result.webp" width="49%" alt="Upstream editable HTML and CSS reconstruction of the model-training infographic." />
|
|
72
|
+
<img src="assets/dsh-view-example.png" width="82%" alt="A text-only DeepSeek model answering a question about a pasted image through Vision Toolkit in DSH Web" />
|
|
70
73
|
</p>
|
|
71
74
|
|
|
72
|
-
*
|
|
75
|
+
*Paste an image into the conversation. A text-only model can switch to its `Vision Toolkit` variant and inspect the image in the context of the user's question.*
|
|
73
76
|
|
|
74
|
-
###
|
|
77
|
+
### Screenshot to editable page
|
|
75
78
|
|
|
76
79
|
<p align="center">
|
|
77
|
-
<img src="assets/upstream/
|
|
78
|
-
<img src="assets/upstream/
|
|
80
|
+
<img src="assets/upstream/infographic-reference.webp" width="49%" alt="Reference infographic screenshot used for restoration" />
|
|
81
|
+
<img src="assets/upstream/infographic-result.webp" width="49%" alt="Editable HTML and CSS reconstruction created from the reference screenshot" />
|
|
79
82
|
</p>
|
|
80
83
|
|
|
81
|
-
*Left:
|
|
84
|
+
*Left: the reference screenshot. Right: an editable HTML/CSS result. The result can continue into screenshot rendering and pixel comparison instead of ending as an image description.*
|
|
82
85
|
|
|
83
|
-
###
|
|
86
|
+
### Sketch to working interface
|
|
84
87
|
|
|
85
88
|
<p align="center">
|
|
86
|
-
<img src="assets/
|
|
87
|
-
<img src="assets/
|
|
89
|
+
<img src="assets/upstream/ui-sketch.webp" width="49%" alt="Hand-drawn JupyterLab interface used as the restoration reference" />
|
|
90
|
+
<img src="assets/upstream/ui-result.webp" width="49%" alt="Working JupyterLab-style interface reconstructed from the sketch" />
|
|
88
91
|
</p>
|
|
89
92
|
|
|
90
|
-
*Left:
|
|
93
|
+
*Left: a hand-drawn reference. Right: the working interface reconstructed from it.*
|
|
91
94
|
|
|
92
|
-
|
|
95
|
+
### Turn “looks close” into a verifiable result
|
|
93
96
|
|
|
94
|
-
|
|
95
|
-
|
|
96
|
-
The included UI-restoration workflow starts with an intentionally inaccurate HTML implementation. Vision Toolkit measures a `6.04%` difference, points to the worst regions, and helps drive the next iteration. The final render reaches an exact `0%` difference at `1200 × 720`.
|
|
97
|
+
The repository includes a reproducible UI-restoration example. The first implementation differs from the reference by **6.04%**. After the highlighted regions are corrected, the final `1200 × 720` render reaches **0% pixel difference**.
|
|
97
98
|
|
|
98
99
|
<p>
|
|
99
|
-
<img src="examples/ui-restoration/assets/initial.png" width="49%" alt="Initial UI
|
|
100
|
-
<img src="examples/ui-restoration/assets/implementation.png" width="49%" alt="Final UI
|
|
100
|
+
<img src="examples/ui-restoration/assets/initial.png" width="49%" alt="Initial UI implementation with measurable layout and styling differences" />
|
|
101
|
+
<img src="examples/ui-restoration/assets/implementation.png" width="49%" alt="Final UI implementation after visual diagnosis, reaching zero pixel difference" />
|
|
101
102
|
</p>
|
|
102
103
|
|
|
103
|
-
|
|
104
|
-
|---|---|
|
|
105
|
-
| Reference image | A working HTML implementation you can open and edit |
|
|
106
|
-
| First comparison | `6.04%` difference across the visible problem regions |
|
|
107
|
-
| Final comparison | `0%` difference at `1200 × 720` |
|
|
108
|
-
|
|
109
|
-
## Why it feels different
|
|
104
|
+
## Highlights
|
|
110
105
|
|
|
111
|
-
- **
|
|
112
|
-
- **
|
|
113
|
-
- **
|
|
114
|
-
- **
|
|
115
|
-
- **
|
|
106
|
+
- **Free by default.** New installations use the built-in Gemma 4 service without requiring another account or API key.
|
|
107
|
+
- **Focused on the current task.** The agent sends the reason it needs to inspect the image, so the result emphasizes useful evidence instead of producing a generic caption.
|
|
108
|
+
- **Outputs you can keep working with.** Coordinates, OCR, transparent PNGs, SVGs, screenshots, heatmaps, and JSON can feed directly into the next step.
|
|
109
|
+
- **Built for UI and screenshot work.** Reference analysis, element location, asset extraction, HTML rendering, and pixel comparison form one continuous workflow.
|
|
110
|
+
- **Local where possible.** Crop, trace, pixel diff, color, foreground, and HTML screenshot operations do not need a remote vision model.
|
|
111
|
+
- **The same capabilities in Web and Headless.** Web users can preview and download artifacts; Headless runs still receive replayable structured results and workspace paths.
|
|
116
112
|
|
|
117
|
-
##
|
|
113
|
+
## Quick start: three steps
|
|
118
114
|
|
|
119
|
-
|
|
115
|
+
### 1. Install
|
|
120
116
|
|
|
121
117
|
```sh
|
|
122
118
|
dsh plugin --profile web add @anionex/dsh-vision-toolkit
|
|
123
|
-
dsh plugin --profile headless add @anionex/dsh-vision-toolkit
|
|
124
119
|
```
|
|
125
120
|
|
|
126
|
-
|
|
127
|
-
2. New installations use the built-in free Gemma 4 provider, so you can run **Test API connection** and **Test vision model** without an API key. To use another provider, edit the endpoint/model/protocol and provide its DSH Credential.
|
|
128
|
-
3. In a conversation, paste an image or put it in the workspace, invoke `/vision-tools`, and ask for a concrete visual task.
|
|
129
|
-
|
|
130
|
-
If you use an older DSH launcher, the profile may need `nodeLinker: hoisted` and `autoInstallPeers: false` before installation. Current launchers repair these settings for you.
|
|
131
|
-
|
|
132
|
-
Local crop, trace, pixel, color, foreground, and HTML operations do not require a visual API credential.
|
|
121
|
+
You can install it into a Headless Profile too:
|
|
133
122
|
|
|
134
|
-
|
|
135
|
-
|
|
136
|
-
Join the `agent-vision-toolkit` community group to exchange usage tips, share feedback, and suggest improvements.
|
|
137
|
-
|
|
138
|
-
<p align="center">
|
|
139
|
-
<img src="assets/community-group-qr.png" alt="QR code for the agent-vision-toolkit community group" width="260">
|
|
140
|
-
</p>
|
|
141
|
-
|
|
142
|
-
> **No local path is required.** Keep the default `runtime.mode: managed` for the normal npm installation. The optional `runtime.agentVisionToolkitPath` setting is only for developers or controlled deployments that deliberately use an external pinned checkout.
|
|
143
|
-
|
|
144
|
-
<details>
|
|
145
|
-
<summary><strong>Technical architecture</strong></summary>
|
|
146
|
-
|
|
147
|
-
## How it works
|
|
148
|
-
|
|
149
|
-
```mermaid
|
|
150
|
-
flowchart LR
|
|
151
|
-
User["Workspace image or local HTML"] --> Skill["vision-tools Skill"]
|
|
152
|
-
Skill --> Activate["Agent-scoped activation"]
|
|
153
|
-
Activate --> Tools["10 independent vision_* tools"]
|
|
154
|
-
Tools --> Runtime["Shared VisionToolkitRuntime"]
|
|
155
|
-
Credentials["DSH Credentials"] --> Runtime
|
|
156
|
-
Settings["Web Settings and health"] --> Runtime
|
|
157
|
-
Runtime --> Upstream["Pinned agent-vision-toolkit"]
|
|
158
|
-
Runtime --> Remote["Configured vision API"]
|
|
159
|
-
Upstream --> Result["Text, coordinates, JSON"]
|
|
160
|
-
Remote --> Result
|
|
161
|
-
Runtime --> Artifacts["Workspace Artifacts"]
|
|
162
|
-
Result --> Session["Reconstructable Session log"]
|
|
163
|
-
Artifacts --> Web["Preview, download, or open file"]
|
|
123
|
+
```sh
|
|
124
|
+
dsh plugin --profile headless add @anionex/dsh-vision-toolkit
|
|
164
125
|
```
|
|
165
126
|
|
|
166
|
-
|
|
167
|
-
|
|
168
|
-
</details>
|
|
169
|
-
|
|
170
|
-
## Tools
|
|
171
|
-
|
|
172
|
-
| Tool | Execution | Structured result | Artifact delivery |
|
|
173
|
-
|---|---|---|---|
|
|
174
|
-
| `vision_glance` | Remote vision API | Description, targeted answer, OCR, or multi-image comparison | None |
|
|
175
|
-
| `vision_ground` | Remote vision API; optional local preview | Target, original-image dimensions, and pixel boxes | Optional labeled PNG |
|
|
176
|
-
| `vision_detect` | Remote vision API; optional local preview | Numbered element inventory and original-image pixel boxes | Optional numbered PNG |
|
|
177
|
-
| `vision_trace` | Local pinned vtracer pipeline | SVG geometry status, path count, scale, and size | SVG |
|
|
178
|
-
| `vision_crop` | Local Pillow pipeline | Applied pixel box, dimensions, format, and clamp status | PNG or JPEG |
|
|
179
|
-
| `vision_pixel_diff` | Local NumPy/Pillow pipeline | Difference percentage and ranked grid regions | PNG heatmap and JSON report |
|
|
180
|
-
| `vision_long_screenshot_ocr` | Local split/audit; remote OCR unless `splitOnly=true` | Chunk boundaries, reuse state, completion state, and run directory | Markdown, manifest, boundary audit, chunk PNGs, and OCR sidecars |
|
|
181
|
-
| `vision_extract_foreground` | Local pinned extraction pipeline | Selected box, component counts, foreground coverage, and dimensions | Transparent PNG |
|
|
182
|
-
| `vision_dominant_colors` | Local pinned color analysis | Extracted palette or pixel-backed candidate ranking | None |
|
|
183
|
-
| `vision_html_screenshot` | Local Chrome/Chromium/Edge adapter | Authorized source facts, viewport, and rendered dimensions | PNG |
|
|
184
|
-
|
|
185
|
-
The plugin does not reimplement visual algorithms. Its DSH-owned layer validates paths and limits, resolves credentials, calls the pinned upstream scripts with argv vectors, parses their exact output contracts, classifies failures, describes files, and projects results to the model and Web client.
|
|
186
|
-
|
|
187
|
-
<details>
|
|
188
|
-
<summary><strong>Advanced model behavior</strong></summary>
|
|
189
|
-
|
|
190
|
-
## Progressive model exposure
|
|
127
|
+
### 2. Restart and check it
|
|
191
128
|
|
|
192
|
-
|
|
129
|
+
Restart a running Web Profile, then open **Settings → Vision Toolkit**. The free provider is already configured; run **Test vision model** to confirm it is reachable.
|
|
193
130
|
|
|
194
|
-
|
|
131
|
+
The first start prepares an isolated runtime, so it needs access to the Python package cache or the network. A normal installation does not require an `agent-vision-toolkit` source checkout or a local path setting.
|
|
195
132
|
|
|
196
|
-
|
|
133
|
+
### 3. Paste an image and describe the outcome you want
|
|
197
134
|
|
|
198
|
-
|
|
135
|
+
Paste a screenshot into the conversation or place an image in the session workspace, then invoke `/vision-tools`. For example:
|
|
199
136
|
|
|
200
|
-
|
|
201
|
-
|
|
202
|
-
|
|
203
|
-
|
|
204
|
-
|
|
205
|
-
|
|
206
|
-
## Requirements
|
|
207
|
-
|
|
208
|
-
- DeepSeek Harness with a Web or Headless profile and `pnpm` available to `dsh plugin`.
|
|
209
|
-
- Python 3.11 or newer. Managed mode creates an isolated environment, so users do not install the upstream CLI or Python packages manually.
|
|
210
|
-
- Network access on the first managed-runtime activation unless the exact packages in `runtime/requirements.lock` are already available in the configured package cache.
|
|
211
|
-
- The built-in free Gemma 4 provider is ready for `vision_glance`, `vision_ground`, `vision_detect`, and non-split-only long-screenshot OCR. A DSH Credential is required only when a custom OpenAI-compatible or Anthropic endpoint is configured. Local tools remain usable without either provider.
|
|
212
|
-
- Chrome, Chromium, or Edge only for `vision_html_screenshot`; all other tools remain available when no supported browser is installed.
|
|
213
|
-
- PNG, JPEG, GIF, or WebP inputs inside the session workspace or an explicitly configured `allowedDirs` root.
|
|
214
|
-
|
|
215
|
-
## Install and lifecycle
|
|
216
|
-
|
|
217
|
-
### Install
|
|
218
|
-
|
|
219
|
-
Install the bundle into each profile that should expose it:
|
|
220
|
-
|
|
221
|
-
```sh
|
|
222
|
-
dsh plugin --profile web add @anionex/dsh-vision-toolkit
|
|
223
|
-
dsh plugin --profile headless add @anionex/dsh-vision-toolkit
|
|
224
|
-
dsh --profile web --dump-config | grep vision-toolkit
|
|
225
|
-
dsh --profile headless --dump-config | grep vision-toolkit
|
|
137
|
+
```text
|
|
138
|
+
Inspect this screenshot. Explain the error and tell me what to fix first.
|
|
139
|
+
Find the login button in the top-right corner, return original pixel coordinates, and make a boxed preview.
|
|
140
|
+
Crop this icon and convert it to SVG.
|
|
141
|
+
Rebuild the page from reference.png. After each pass, render it and run a pixel diff until the major differences are gone.
|
|
226
142
|
```
|
|
227
143
|
|
|
228
|
-
|
|
229
|
-
|
|
230
|
-
The first managed start verifies the packaged upstream manifest and atomically prepares an isolated environment under `DSH_HOME/cache/dsh-vision-toolkit`. Only after preparation succeeds does the plugin publish the same-version `vision-tools` Skill and activation bootstrap; each Agent receives the execution tools only after loading that Skill. An initial preparation failure leaves the Web Settings repair surface available but exposes neither model capability nor a misleading Skill.
|
|
144
|
+
## Common workflows
|
|
231
145
|
|
|
232
|
-
|
|
146
|
+
| Task | Recommended workflow |
|
|
147
|
+
|---|---|
|
|
148
|
+
| Image Q&A or screenshot debugging | Inspect → answer around the current question → locate details when needed |
|
|
149
|
+
| Find a button, icon, or text region | Ground the target → return pixel box → create a labeled preview |
|
|
150
|
+
| Extract an icon from a screenshot | Ground → crop → trace to SVG |
|
|
151
|
+
| Read a long webpage screenshot | Split → OCR → merge Markdown → audit boundaries |
|
|
152
|
+
| Recreate a page or component | Reference → implementation → HTML screenshot → pixel diff → iterate |
|
|
153
|
+
| Extract brand visuals | Crop region → analyze dominant colors → extract foreground → export transparent PNG |
|
|
233
154
|
|
|
234
|
-
|
|
155
|
+
## Toolbox
|
|
235
156
|
|
|
236
|
-
|
|
237
|
-
- id: vision-toolkit
|
|
238
|
-
disabled: true
|
|
239
|
-
```
|
|
157
|
+
The plugin provides 10 tools that can be called independently or composed into a workflow:
|
|
240
158
|
|
|
241
|
-
|
|
159
|
+
| Tool | Best question to ask | Main result |
|
|
160
|
+
|---|---|---|
|
|
161
|
+
| `vision_glance` | “What is happening in this image?” | Focused answer, description, OCR, or multi-image comparison |
|
|
162
|
+
| `vision_ground` | “Where is the thing I need?” | Original pixel coordinates and optional boxed preview |
|
|
163
|
+
| `vision_detect` | “Which buttons, icons, or elements are present?” | Numbered element inventory, coordinates, and optional preview |
|
|
164
|
+
| `vision_crop` | “Extract this region as its own image” | PNG or JPEG crop |
|
|
165
|
+
| `vision_trace` | “Turn this shape into an editable vector” | SVG |
|
|
166
|
+
| `vision_pixel_diff` | “Where does the implementation differ from the reference?” | Difference percentage, ranked regions, heatmap, and JSON |
|
|
167
|
+
| `vision_long_screenshot_ocr` | “Read this entire long screenshot” | Markdown, chunks, manifest, and audit output |
|
|
168
|
+
| `vision_extract_foreground` | “Remove the background from this subject” | Transparent PNG |
|
|
169
|
+
| `vision_dominant_colors` | “Which colors dominate this area?” | Palette or ranked candidate colors |
|
|
170
|
+
| `vision_html_screenshot` | “Render this local page at an exact viewport or capture the full page” | PNG and optional CSS `pageHeight` |
|
|
242
171
|
|
|
243
|
-
|
|
172
|
+
Coordinates always use original-image pixels in `x1,y1,x2,y2` form, so grounding output can feed directly into cropping, tracing, or later automation.
|
|
244
173
|
|
|
245
|
-
|
|
174
|
+
For a long HTML document, pass `fullPage=true`. The requested width and height remain the layout viewport, while the resulting PNG covers the complete document and reports `pageHeight` in CSS pixels.
|
|
246
175
|
|
|
247
|
-
|
|
248
|
-
dsh plugin --profile web remove @dsh-external/dsh-vision-toolkit
|
|
249
|
-
dsh plugin --profile web add @anionex/dsh-vision-toolkit
|
|
250
|
-
```
|
|
176
|
+
## How it works
|
|
251
177
|
|
|
252
|
-
|
|
178
|
+
The plugin keeps image understanding and deterministic local image processing in one Agent workflow. Expand the flow below for the implementation boundary.
|
|
253
179
|
|
|
254
|
-
|
|
180
|
+
<details>
|
|
181
|
+
<summary><strong>Architecture and image-input behavior</strong></summary>
|
|
255
182
|
|
|
256
|
-
```
|
|
257
|
-
|
|
258
|
-
|
|
183
|
+
```mermaid
|
|
184
|
+
flowchart LR
|
|
185
|
+
Image["Screenshot or local HTML"] --> Skill["vision-tools Skill"]
|
|
186
|
+
Skill --> Agent["Text agent selects a task"]
|
|
187
|
+
Agent --> Vision["Use a vision model when image understanding is needed"]
|
|
188
|
+
Agent --> Local["Run crop, SVG, and pixel work locally"]
|
|
189
|
+
Vision --> Result["Answer, OCR, coordinates"]
|
|
190
|
+
Local --> Artifact["PNG, SVG, heatmap, JSON"]
|
|
191
|
+
Result --> Session["Continue reasoning and acting"]
|
|
192
|
+
Artifact --> Session
|
|
259
193
|
```
|
|
260
194
|
|
|
261
|
-
|
|
195
|
+
The visual capabilities come from a packaged, pinned `agent-vision-toolkit` snapshot. The DSH plugin handles installation, session-scoped tool exposure, Credentials, path checks, cancellation, timeouts, result files, and Web presentation. The runtime never fetches upstream `main` in the background.
|
|
262
196
|
|
|
263
|
-
|
|
197
|
+
For routes that DSH positively identifies as text-only, the plugin registers a sibling `<model> (Vision Toolkit)` variant. By default, pasting an image in DSH Web switches to that variant and gives the model both a reusable workspace path and a visual description focused on the current task.
|
|
264
198
|
|
|
265
|
-
|
|
266
|
-
dsh plugin --profile web remove @anionex/dsh-vision-toolkit
|
|
267
|
-
dsh plugin --profile headless remove @anionex/dsh-vision-toolkit
|
|
268
|
-
```
|
|
199
|
+
</details>
|
|
269
200
|
|
|
270
|
-
|
|
201
|
+
## Configuration and limits
|
|
271
202
|
|
|
272
|
-
|
|
203
|
+
### Built-in free service
|
|
273
204
|
|
|
274
|
-
The
|
|
205
|
+
The default setup uses:
|
|
275
206
|
|
|
276
|
-
```
|
|
277
|
-
|
|
278
|
-
|
|
279
|
-
|
|
280
|
-
baseUrl: https://vision.anionex.me/v1
|
|
281
|
-
credential: ANIONEX_FREE_VISION
|
|
282
|
-
model: gemma-4-26b-a4b-it
|
|
283
|
-
protocol: openai
|
|
284
|
-
anthropicThinking: omit
|
|
285
|
-
userAgent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36
|
|
286
|
-
language: zh
|
|
287
|
-
timeoutMs: 60000
|
|
288
|
-
maxImageBytes: 4194304
|
|
289
|
-
maxImagePixels: 20000000
|
|
290
|
-
concurrency: 4
|
|
291
|
-
runtime:
|
|
292
|
-
mode: managed
|
|
293
|
-
allowedDirs: []
|
|
294
|
-
imageInputVariants:
|
|
295
|
-
enabled: true
|
|
296
|
-
providers: []
|
|
297
|
-
autoSwitch: true
|
|
207
|
+
```text
|
|
208
|
+
Base URL: https://vision.anionex.me/v1
|
|
209
|
+
Model: gemma-4-26b-a4b-it
|
|
210
|
+
API Key: no user configuration required
|
|
298
211
|
```
|
|
299
212
|
|
|
300
|
-
|
|
301
|
-
|
|
302
|
-
| Field | Default | Contract |
|
|
303
|
-
|---|---|---|
|
|
304
|
-
| `provider.baseUrl` | `https://vision.anionex.me/v1` | Built-in free OpenAI-compatible endpoint; custom providers may use another base URL, normalized without trailing slashes |
|
|
305
|
-
| `provider.credential` | `ANIONEX_FREE_VISION` | Read-only built-in reference for the free service; custom providers use a DSH Credential reference, never a secret value |
|
|
306
|
-
| `provider.model` | `gemma-4-26b-a4b-it` | Multimodal model name sent to remote tools |
|
|
307
|
-
| `provider.protocol` | `openai` | `openai` sends Chat Completions requests; `anthropic` sends native Messages requests |
|
|
308
|
-
| `provider.anthropicThinking` | `omit` | Anthropic thinking field. `omit` sends no thinking field and has the broadest compatibility. Use `disabled` or `adaptive` only when the selected model documents that mode; restore `omit` first if the provider returns HTTP 400. |
|
|
309
|
-
| `provider.userAgent` | browser-compatible default | User-Agent sent by vision requests and explicit connection tests; override it for provider or proxy compatibility |
|
|
310
|
-
| `language` | `zh` | Vision output language: `zh` or `en` |
|
|
311
|
-
| `timeoutMs` | `60000` | Whole-operation deadline, 1000-600000 ms; each tool may request a narrower override |
|
|
312
|
-
| `maxImageBytes` | `4194304` | Encoded-byte limit per input image; the built-in free service accepts up to 4 MiB |
|
|
313
|
-
| `maxImagePixels` | `20000000` | Decoded-pixel limit per input image; the built-in free service accepts up to 20,000,000 pixels |
|
|
314
|
-
| `concurrency` | `4` | In-flight operations per session, 1-16 |
|
|
315
|
-
| `runtime.mode` | `managed` | `managed` uses the packaged snapshot; `external` accepts only the exact pin |
|
|
316
|
-
| `runtime.agentVisionToolkitPath` | unset | Required in `external` mode; exported exact snapshot or clean pinned Git checkout |
|
|
317
|
-
| `runtime.python` | unset | Optional Python 3.11+ bootstrap/interpreter override |
|
|
318
|
-
| `allowedDirs` | `[]` | Additional realpath-resolved input roots; the session workspace is always allowed |
|
|
319
|
-
| `imageInputVariants.enabled` | `true` | Register image-input variant entries for text-only model routes in the model selector |
|
|
320
|
-
| `imageInputVariants.providers` | `[]` | Restrict wrapped upstream routes by provider id; empty wraps every eligible route |
|
|
321
|
-
| `imageInputVariants.autoSwitch` | `true` | Automatically switch a text-only session to its image-input variant; the model receives both the workspace path and focused description. `false` keeps the path-only takeover |
|
|
322
|
-
|
|
323
|
-
### Credentials
|
|
324
|
-
|
|
325
|
-
The built-in free provider uses the fixed `ANIONEX_FREE_VISION` reference and does not accept or store a user API key. If you change the endpoint, model, or protocol to a custom provider, the write-only **API key** field unlocks; saving a non-empty value writes it under the advanced **Credential name** reference. Headless deployments can pre-provision that custom reference in `$DSH_HOME/.credentials.yaml`.
|
|
326
|
-
|
|
327
|
-
Settings store only the reference, never the value. The browser does not receive a stored value, and a successful save clears the field instead of echoing it. Remote operations resolve the reference once per call and inject the value only into that subprocess environment. The plugin excludes user `.env` files, checkout `.env` files, `PYTHONPATH`, `PYTHONHOME`, `VIRTUAL_ENV`, and user site-packages so ambient Python or upstream configuration cannot override the selected DSH provider. Logs, errors, tool results, Artifact metadata, and Settings responses never contain the secret.
|
|
328
|
-
|
|
329
|
-
### Built-in free service limits
|
|
330
|
-
|
|
331
|
-
The public service is shared and intended as a zero-configuration default, not an unlimited private endpoint. Limits are enforced by the proxy and returned as OpenAI-style errors with a reason code and readable message; rate-limit responses also include `Retry-After` and request-quota headers.
|
|
213
|
+
This is a shared zero-configuration entry point, not an unlimited private endpoint. Current limits are:
|
|
332
214
|
|
|
333
215
|
| Limit | Current value |
|
|
334
216
|
|---|---:|
|
|
335
217
|
| Per client | 100 requests per UTC day |
|
|
336
|
-
|
|
|
218
|
+
| Whole service | 400 requests per UTC day |
|
|
337
219
|
| Burst | 20 requests per 60 seconds |
|
|
338
|
-
| Image
|
|
220
|
+
| Image size | 4 MiB per image |
|
|
339
221
|
| Decoded pixels | 20,000,000 per image |
|
|
340
|
-
| Output | 512 tokens
|
|
222
|
+
| Output | 512 tokens per request |
|
|
341
223
|
|
|
342
|
-
|
|
224
|
+
The limits protect shared capacity and prevent unusually large images from monopolizing memory or request time. When a limit is reached, the service returns a readable reason and error code. Rate-limit responses also include `Retry-After` instead of collapsing into an unexplained model failure.
|
|
343
225
|
|
|
344
|
-
|
|
226
|
+
### Bring your own vision model
|
|
345
227
|
|
|
346
|
-
|
|
228
|
+
For higher quotas, private endpoints, or another model, change the provider in **Settings → Vision Toolkit** and store the API key as a DSH Credential. Settings stores the Credential reference and never reads the saved secret back into the browser.
|
|
347
229
|
|
|
348
|
-
|
|
230
|
+
You can also configure a Profile patch:
|
|
349
231
|
|
|
350
232
|
```yaml
|
|
351
233
|
- id: vision-toolkit
|
|
352
234
|
config:
|
|
353
|
-
|
|
354
|
-
|
|
355
|
-
|
|
356
|
-
|
|
235
|
+
provider:
|
|
236
|
+
baseUrl: https://api.example.com/v1
|
|
237
|
+
credential: MY_VISION_KEY
|
|
238
|
+
model: your-vision-model
|
|
239
|
+
protocol: openai
|
|
357
240
|
```
|
|
358
241
|
|
|
359
|
-
|
|
360
|
-
|
|
361
|
-
## Web Settings
|
|
362
|
-
|
|
363
|
-
The Web profile registers a Vision Toolkit Settings section for the provider URL, Credential reference, model, OpenAI/Anthropic protocol, Anthropic thinking mode, User-Agent, language, timeout, byte/pixel limits, concurrency, runtime mode, Python override, external source path, and allowed directories. It also shows plugin/upstream versions, the active runtime generation, non-secret Credential configured/source/writable facts, runtime paths, health results, and Artifact-route availability.
|
|
364
|
-
|
|
365
|
-
The **Plugin updates** card checks the profile's configured npm registry for a newer `@anionex/dsh-vision-toolkit` release. **Update and restart** installs that exact confirmed version into the current DSH profile, verifies the installed package, starts an independent restart helper, and gracefully restarts DSH Web; the open page waits for the replacement process and reloads after the new plugin version is serving. The action is same-origin, fixed to this package, serialized, and unavailable for `link:`, `file:`, workspace, git, URL, transitive, ambiguous, read-only, or missing-`pnpm` installations so local development sources are never overwritten. A restart can interrupt work that is currently running, so the UI requires an explicit confirmation.
|
|
242
|
+
OpenAI Chat Completions-compatible endpoints and Anthropic Messages are supported. The Web Settings panel exposes the full provider, runtime, timeout, image-limit, and image-input-variant configuration.
|
|
366
243
|
|
|
367
|
-
|
|
244
|
+
### Requirements
|
|
368
245
|
|
|
369
|
-
|
|
246
|
+
- A DeepSeek Harness Web or Headless Profile.
|
|
247
|
+
- Node.js `^22.19.0` or `>=24.0.0`.
|
|
248
|
+
- Python 3.11+; the plugin prepares an isolated environment by default.
|
|
249
|
+
- Only `vision_html_screenshot` requires Chrome, Chromium, or Edge.
|
|
250
|
+
- Inputs must be PNG, JPEG, GIF, or WebP files in the session workspace or an explicitly allowed directory.
|
|
370
251
|
|
|
371
|
-
|
|
372
|
-
|
|
373
|
-
## Artifacts and presentation
|
|
374
|
-
|
|
375
|
-
Artifact-producing tools write only under `<workspace>/.dsh-vision-toolkit/artifacts`, either as one validated file or an atomically committed run directory. Each model-visible descriptor contains the path, filename, MIME type, kind, description, source tool, preview intent, and byte size, so Headless agents can reuse the path in later calls without browser support. Before a traced SVG is committed, the runtime parses it as XML: standard declarations and comments are accepted, while doctypes, malformed or multi-root documents, a non-SVG namespace, and reported path/byte mismatches are rejected.
|
|
252
|
+
<details>
|
|
253
|
+
<summary><strong>Install, upgrade, disable, and uninstall</strong></summary>
|
|
376
254
|
|
|
377
|
-
|
|
255
|
+
```sh
|
|
256
|
+
dsh plugin --profile web update @anionex/dsh-vision-toolkit
|
|
257
|
+
dsh plugin --profile web remove @anionex/dsh-vision-toolkit
|
|
258
|
+
```
|
|
378
259
|
|
|
379
|
-
|
|
260
|
+
If you are migrating from the retired `@dsh-external/dsh-vision-toolkit`, remove the old package first and install `@anionex/dsh-vision-toolkit`.
|
|
380
261
|
|
|
381
|
-
|
|
262
|
+
To disable the bundle temporarily, set this in the Profile patch:
|
|
382
263
|
|
|
383
|
-
```
|
|
384
|
-
|
|
385
|
-
|
|
386
|
-
vision_detect image="screenshot.png" category="buttons" preview=true
|
|
387
|
-
vision_crop image="screenshot.png" region="1067,841,1108,881"
|
|
388
|
-
vision_trace image="icon.png" color=true output="icon.svg"
|
|
389
|
-
vision_pixel_diff original="reference.png" rebuilt="actual.png" runName="comparison"
|
|
390
|
-
vision_long_screenshot_ocr image="page.png" mode="general" jobs=2
|
|
391
|
-
vision_extract_foreground image="logo.png" mode="color"
|
|
392
|
-
vision_dominant_colors image="screen.png" region="0,0,600,300" top=8
|
|
393
|
-
vision_html_screenshot source="implementation.html" width=1200 height=720
|
|
264
|
+
```yaml
|
|
265
|
+
- id: vision-toolkit
|
|
266
|
+
disabled: true
|
|
394
267
|
```
|
|
395
268
|
|
|
396
|
-
|
|
269
|
+
Restart the Web Profile and refresh the page after enabling or upgrading the Web plugin.
|
|
397
270
|
|
|
398
|
-
|
|
271
|
+
</details>
|
|
399
272
|
|
|
400
|
-
|
|
273
|
+
### Plugin updates
|
|
401
274
|
|
|
402
|
-
|
|
403
|
-
npm run example:ui-restoration
|
|
404
|
-
npm run example:ui-restoration:write
|
|
405
|
-
```
|
|
275
|
+
In **Settings → Vision Toolkit**, **Check for updates** queries the Profile's npm registry. For a direct registry installation, **Update and restart** installs only the exact version you confirmed, verifies it, and restarts an explicitly opted-in POSIX Web process on a fixed `--port`. Local/workspace/file/git/URL installs, Windows, dynamic ports, read-only Profiles, and manager-owned processes remain check-only.
|
|
406
276
|
|
|
407
|
-
The
|
|
277
|
+
The updater revalidates the Profile before mutation, snapshots the original manifest and lockfile, and holds a token-owned cross-process lock. The current Web process exits only after the restart helper confirms that the backup is readable and the lock handoff succeeded. When the Profile was already operational, the replacement must report both the target plugin version and a ready runtime; failed replacements restore the original manifest/lockfile and rebuild dependencies with a frozen lockfile before retrying the previous exact version. If automatic recovery itself fails, the backup and lock are preserved and their paths are written to `$DSH_HOME/logs/vision-toolkit-restart.log`. Detached restart requires `DSH_VISION_TOOLKIT_ALLOW_DETACHED_RESTART=1`; unsaved Settings or API-key input blocks installation.
|
|
408
278
|
|
|
409
279
|
## Troubleshooting
|
|
410
280
|
|
|
411
|
-
|
|
|
281
|
+
| Problem | What to do |
|
|
412
282
|
|---|---|
|
|
413
|
-
|
|
|
414
|
-
|
|
|
415
|
-
|
|
|
416
|
-
|
|
|
417
|
-
|
|
|
418
|
-
|
|
|
419
|
-
|
|
|
420
|
-
|
|
421
|
-
|
|
422
|
-
|
|
423
|
-
|
|
424
|
-
|
|
425
|
-
|
|
426
|
-
## Development and verification
|
|
283
|
+
| Pasting an image still says the model does not support image input | Restart the Web Profile, refresh the page, and confirm the selected route has the `(Vision Toolkit)` suffix. You can also place the image in the session workspace and invoke `/vision-tools` |
|
|
284
|
+
| The free service returns 429 | Wait for the `Retry-After` interval, or switch to your own endpoint when you need stable higher volume |
|
|
285
|
+
| The image exceeds a size or pixel limit | Crop or resize it first; the error identifies whether bytes or decoded pixels caused the rejection |
|
|
286
|
+
| A custom Credential is missing | Enter the API key in **Settings → Vision Toolkit** and confirm the Credential name matches the provider configuration |
|
|
287
|
+
| First-time runtime setup fails | Check Python 3.11+, network or package-cache access, and disk permissions, then retry the model test in Settings |
|
|
288
|
+
| Chrome is not found | Install Chrome, Chromium, or Edge. Only HTML screenshot rendering is unavailable; the other tools still work |
|
|
289
|
+
| An artifact cannot be previewed | Use **Open file** or the workspace path in the result. Preview URLs exist only while the Web route is available |
|
|
290
|
+
|
|
291
|
+
## Project status and limitations
|
|
292
|
+
|
|
293
|
+
The current release focuses on screenshot understanding, visual grounding, OCR, asset extraction, UI restoration, and pixel-level verification. It is not a video, audio, or camera-input system and does not automatically click GUI controls. Interactive box editing, remote service clusters, model voting, and cross-session visual caches are also outside the current scope.
|
|
294
|
+
|
|
295
|
+
## Development and community
|
|
427
296
|
|
|
428
297
|
```sh
|
|
429
298
|
pnpm install --frozen-lockfile --trust-lockfile
|
|
430
299
|
pnpm run verify:portable
|
|
431
300
|
pnpm run build
|
|
432
301
|
pnpm test
|
|
433
|
-
pnpm
|
|
434
|
-
pnpm pack --dry-run
|
|
302
|
+
TSX_TSCONFIG_PATH=tsconfig.json pnpm dlx tsx scripts/ui-restoration-example.ts --check
|
|
435
303
|
```
|
|
436
304
|
|
|
437
|
-
|
|
438
|
-
|
|
439
|
-
|
|
440
|
-
|
|
441
|
-
|
|
442
|
-
|
|
443
|
-
## Project status and scope
|
|
444
|
-
|
|
445
|
-
Version `0.1.12` is the current public npm release. The product focuses on screenshot understanding, visual grounding, OCR, asset extraction, UI restoration, and pixel-level verification in DSH Web and Headless profiles. Web upload, drag-and-drop, camera/video/audio/document ingestion, interactive box editing, automatic GUI clicking, service clusters, model routing, model voting, and cross-session vision caches remain outside the current product.
|
|
446
|
-
|
|
447
|
-
<details>
|
|
448
|
-
<summary><strong>Maintainer scope note</strong></summary>
|
|
305
|
+
- Read [CONTRIBUTING.md](CONTRIBUTING.md) before contributing.
|
|
306
|
+
- Use [GitHub Issues](https://github.com/Anionex/dsh-vision-toolkit/issues) for bugs, focused feature requests, and usage questions; see [SUPPORT.md](SUPPORT.md) for channel guidance.
|
|
307
|
+
- Report vulnerabilities privately through [SECURITY.md](SECURITY.md).
|
|
308
|
+
- See [CHANGELOG.md](CHANGELOG.md) for releases and [FUNDING.md](FUNDING.md) for sponsorship details.
|
|
309
|
+
- Visit upstream [agent-vision-toolkit](https://github.com/Anionex/agent-vision-toolkit) for the general toolkit, cross-agent integrations, and visual-task playbooks.
|
|
449
310
|
|
|
450
|
-
|
|
451
|
-
|
|
452
|
-
</
|
|
453
|
-
|
|
454
|
-
## Community and About
|
|
455
|
-
|
|
456
|
-
- Read [CONTRIBUTING.md](CONTRIBUTING.md) before proposing code, protocol, or upstream-snapshot changes.
|
|
457
|
-
- Use [GitHub Issues](https://github.com/Anionex/dsh-vision-toolkit/issues) for reproducible bugs, focused feature requests, and usage questions; use [SUPPORT.md](SUPPORT.md) to choose the right channel.
|
|
458
|
-
- Report vulnerabilities privately through the process in [SECURITY.md](SECURITY.md), never in a public issue.
|
|
459
|
-
- Follow releases and compatibility notes in [CHANGELOG.md](CHANGELOG.md).
|
|
460
|
-
- Optional sponsorship is described transparently in [FUNDING.md](FUNDING.md); support does not purchase roadmap priority or private support.
|
|
461
|
-
- Use the upstream [project website](https://agent-vision.anionex.me) and [repository](https://github.com/Anionex/agent-vision-toolkit) for the general toolkit, cross-harness integrations, visual-task playbooks, and reference runs.
|
|
462
|
-
- Star, share, contribute to, or sponsor `agent-vision-toolkit` if its algorithms or methods save time; DSH-specific bugs and integration requests belong in this repository.
|
|
463
|
-
|
|
464
|
-
[`agent-vision-toolkit`](https://github.com/Anionex/agent-vision-toolkit) was created by [Anionex](https://anionex.me/). This repository maintains its native DeepSeek Harness integration: DSH owns lifecycle, security, structured schemas, Credentials, Artifacts, and Web presentation, while the upstream project remains the home of the visual algorithms and reusable playbooks.
|
|
311
|
+
<p align="center">
|
|
312
|
+
<img src="assets/community-group-qr.png" alt="QR code for the agent-vision-toolkit community group" width="240" />
|
|
313
|
+
</p>
|
|
465
314
|
|
|
466
|
-
|
|
315
|
+
[`agent-vision-toolkit`](https://github.com/Anionex/agent-vision-toolkit) was created by [Anionex](https://anionex.me/). This repository maintains its native DeepSeek Harness integration.
|
|
467
316
|
|
|
468
317
|
## License
|
|
469
318
|
|
|
470
|
-
The plugin is MIT
|
|
319
|
+
The plugin is available under the [MIT License](LICENSE). The packaged upstream snapshot retains its original MIT license in [`vendor/agent-vision-toolkit/LICENSE`](vendor/agent-vision-toolkit/LICENSE).
|