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

Files

xyx 42617e292d fix(dashscope-image-gen): 切换到 /images/generations 端点 v1.3.0 (#26 )

## 概要 / Summary

修复 dashscope-image-gen 技能的核心端点问题，从 `/chat/completions`（对 wan 图片模型返回 HTTP
400）切换到 `/images/generations`，同时新增多项防护措施防止模型偏离执行路径。

Fix the core endpoint issue: switch from `/chat/completions` (returns
HTTP 400 for wan image models) to `/images/generations`, with enhanced
guardrails to prevent model deviation.

## 变更内容 / Changes

**核心修复**
- 端点：`/chat/completions` → `/images/generations`
- 请求体：`messages` 数组 → `prompt` 字符串 + `size` + `n`
- 响应处理：`choices[].message.content` 图片 URL → `b64_json` base64 解码

**新增防护**
- `curl -o` 保存响应到临时文件，避免 ~2MB base64 灌入终端浪费 token
- 新增"供应商与默认算力"章节，明确 DesireCore Cloud 始终可用，无需探索
- 强化 7 条强制规则（原 5 条），禁止探索未列出的模型/端点/配置文件
- 端口发现优先从系统提示词获取，兜底 `${DESIRECORE_HOME:-$HOME/.desirecore}`
- 错误处理改为表格格式 + "禁止自行重试其他方案"

## 测试 / Test Plan

- [x] dev 模式端到端测试：用户输入"生成一张小猪" → 4 次工具调用，0 失败，图片成功生成并展示
- [x] 对比历史：第一次测试 472 条/7+ 失败 → 第二次 141 条/5 失败 → **本次 108 条/0 失败**

2026-06-10 17:23:52 +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 "本机 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

This skill uses Alibaba Cloud DashScope's Wan (通义万相) models. You do NOT need to specify a provider — just pass "serviceType": "image_gen" and the system will automatically route to the correct provider:

DesireCore Cloud (default, always available): The built-in compute provider already supports image_gen with Wan models. Users can generate images immediately without any configuration.
DashScope (user-configured): If the user has configured their own DashScope API key, the system may route to it.

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
wan2.7-image-pro	Flagship, 4K resolution, thinking_mode	User asks for top quality, 4K, or rich detail
wan2.7-image	Standard high quality, thinking_mode	Default, for unspecified requests

Default rule: if the user does not specify a model, use wan2.7-image.

Full Execution Flow (strictly follow these steps)

How to get the API address

The system prompt already contains the agent-service API address under "本机 API" (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": "wan2.7-image",
      "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": "wan2.7-image",
  "prompt": "your image description",
  "size": "1024x1024",
  "n": 1
}

User intent	size value
Square / avatar / default	"1024x1024"
Landscape / scenery / wallpaper	"1792x1024"
Portrait / mobile / poster	"1024x1792"

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`	Bad parameters	Check model name and size are from the tables above
`statusCode: 403 AccessDenied.Unpurchased`	Model not activated	Tell user to enable the model in Alibaba Cloud console

On any error: Do NOT try alternative models, alternative endpoints, or read config files. Report the error to the user clearly.

Notes

Image generation calls are synchronous and typically return in 10-60 seconds (wan2.7-image-pro can take longer)
Image URLs expire; download promptly
English prompts usually produce the best results; Chinese is also supported
When the user does not specify a model or size, default to wan2.7-image + 1024x1024

9.4 KiB Raw Blame History Unescape Escape