mirror of https://git.openapi.site/https://github.com/desirecore/market.git synced 2026-07-23 07:03:51 +08:00

Files

合并市场索引、分类、i18n 校验、skill-creator 工具和已修改 skill 版本号更新。

2026-07-07 21:14:31 +08:00

9.4 KiB

Raw Blame History

name, description, license, version, type, risk_level, status, disable-model-invocation, provider, tags, requires, metadata, market

name

description

license

version

type

risk_level

status

disable-model-invocation

provider

dashscope-image-gen Skill

Mandatory Rules (violations cause failure)

STRICTLY follow the execution steps below — do NOT improvise, explore alternative endpoints, or try models not listed in this document
Must access agent-service over HTTPS — the API address is already provided in the system prompt under the local API section (e.g. https://127.0.0.1:PORT); use it directly with -k to skip certificate verification
Must upload to media-store via /api/media/upload — /tmp is only a transient download/decode location, never use a local path as the final output
Must use the dc-media:// protocol to display images — the only form the frontend can render correctly
Use Bash curl throughout — do not use the HttpRequest tool or Python
Use /images/generations endpoint — synchronous call; the response contains b64_json image data
Only use models listed below — do NOT try dall-e-3, qwen-vl, or any model not in the Model Selection table

Provider & Default Compute

You do NOT need to specify a provider — just pass "serviceType": "image_gen" and the system will automatically route to the correct provider.

Never try to query provider lists, read compute.json, or explore available models through API calls. The models listed below are guaranteed to work.

Model Selection

Model	Characteristics	When to use
gpt-image-2	High quality, fast, versatile styles	Default — use when user does not specify a model
wan2.7-image	Standard high quality (requires DashScope provider)	Only when user explicitly asks for Wan / DashScope
wan2.7-image-pro	Flagship, 4K resolution (requires DashScope provider)	Only when user explicitly asks for top quality Wan model

Default rule: if the user does not specify a model, use gpt-image-2.

Note: wan2.7-image and wan2.7-image-pro only work when the user has configured their own Alibaba Cloud DashScope provider. If you get an error with these models, fall back to gpt-image-2.

Full Execution Flow (strictly follow these steps)

How to get the API address

The system prompt already contains the agent-service API address under the local API section (e.g. Agent Service: https://127.0.0.1:61000). Extract the URL from there and use it directly.

If for any reason you cannot find it in the system prompt, use this fallback:

PORT=$(cat "${DESIRECORE_HOME:-$HOME/.desirecore}/agent-service.port")
# Then use https://127.0.0.1:${PORT}

Step 1: Generate the image (single curl command)

Call /images/generations through media-proxy. You MUST use this exact request structure — do not add messages, response_format, or any other parameters not shown here:

# Save response to a temp file to avoid base64 flooding the terminal
curl -sk -X POST "https://127.0.0.1:${PORT}/api/media-proxy" \
  -H "Content-Type: application/json" \
  -d '{
    "serviceType": "image_gen",
    "endpoint": "/images/generations",
    "body": {
      "model": "gpt-image-2",
      "prompt": "Replace this with the image description (English usually gives better results)",
      "size": "1024x1024",
      "n": 1
    },
    "responseType": "json"
  }' -o /tmp/dashscope-response.json

# Check success and extract b64_json directly to image file (NEVER cat the response to stdout)
python3 -c "
import json, base64, sys
with open('/tmp/dashscope-response.json') as f:
    resp = json.load(f)
if not resp.get('success'):
    print('ERROR:', json.dumps(resp, ensure_ascii=False)[:500])
    sys.exit(1)
b64 = resp['data']['data'][0]['b64_json']
with open('/tmp/dashscope-gen.png', 'wb') as f:
    f.write(base64.b64decode(b64))
print('OK: saved to /tmp/dashscope-gen.png')
"

CRITICAL: The response contains a large base64 image (~2MB). NEVER print the raw response or b64_json to the terminal. Always save to file with -o and extract with the python3 script above.

Response format (saved in /tmp/dashscope-response.json):

{
  "success": true,
  "data": {
    "created": 1781060911,
    "data": [{"b64_json": "<very large base64 string>"}],
    "size": "1024x1024"
  }
}

Step 2: Upload to media-store

curl -sk -X POST "https://127.0.0.1:${PORT}/api/media/upload" \
  -F "file=@/tmp/dashscope-gen.png;type=image/png"

Pick the mediaId field from the JSON response (format xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx.png).

Step 3: Render the image via the dc-media protocol

In your reply text, write Markdown image syntax directly:

![Image description](dc-media://replace-with-mediaId)

For example: ![White fox in a forest](dc-media://a1b2c3d4-e5f6-47a8-b9c0-d1e2f3a4b5c6.png)

The frontend will translate dc-media:// into a reachable image URL and render it.

Parameter Mapping

Size selection

Pass size in the body object:

{
  "model": "gpt-image-2",
  "prompt": "your image description",
  "size": "1024x1024",
  "n": 1
}

User intent	size value
Square / avatar / default	"1024x1024"
Landscape / scenery / wallpaper	"1536x1024"
Portrait / mobile / poster	"1024x1536"

Optional parameters (top-level body fields)

Parameter	Description
`n`	Number of images, 1-4, default 1
`size`	Image size, e.g. "1024x1024"

Multiple Image Generation

When n > 1, download and upload each image, then render them one by one:

![Image 1 description](dc-media://mediaId1)
![Image 2 description](dc-media://mediaId2)

Error Handling

Error	Meaning	Action
`"No matching provider"`	No enabled provider supports `image_gen`	Tell user to enable a provider with image_gen support in settings
`"API Key not configured"`	API Key missing	Tell user to configure API key
`statusCode: 401`	API Key invalid or expired	Tell user to check API key
`statusCode: 429`	Rate limited	Wait and retry once
`statusCode: 400` + `model_price_error`	Model not available on current provider	Switch to `gpt-image-2` and retry
`statusCode: 400`	Other bad parameters	Check model name and size are from the tables above

On model error: If wan2.7-image or wan2.7-image-pro fails with model_price_error, automatically retry with gpt-image-2. Do NOT ask the user before retrying.

On other errors: Report the error to the user clearly. Do NOT try alternative endpoints or read config files.

Notes

Image generation calls are synchronous and typically return in 10-60 seconds
English prompts usually produce the best results; Chinese is also supported
When the user does not specify a model or size, default to gpt-image-2 + 1024x1024

9.4 KiB Raw Blame History Unescape Escape