sophhub 0.4.19 → 0.4.21

package/skills/sophnet-image-generate/skill.json

@@ -1,20 +1,20 @@
-{
-  "name": "sophnet-image-generate",
-  "version": "1.0.0",
-  "types": [
-    "builtin"
-  ],
-  "displayName": "",
-  "description": "",
-  "changelog": [
-    {
-      "version": "1.0.0",
-      "date": "2026-04-09",
-      "changes": [
-        "初次提交"
-      ]
-    }
-  ],
-  "createdAt": "2026-04-09",
-  "updatedAt": "2026-04-09"
-}
+{
+  "name": "sophnet-image-generate",
+  "version": "1.0.0",
+  "types": [
+    "builtin"
+  ],
+  "displayName": "",
+  "description": "",
+  "changelog": [
+    {
+      "version": "1.0.0",
+      "date": "2026-04-09",
+      "changes": [
+        "初次提交"
+      ]
+    }
+  ],
+  "createdAt": "2026-04-09",
+  "updatedAt": "2026-04-09"
+}

package/skills/sophnet-image-generate/src/SKILL.md

@@ -1,62 +1,62 @@
----
-name: sophnet-image-generate
-description: Use when a user requests Sophnet text-to-image generation, needs model selection across Z-Image-Turbo/Qwen-Image/Qwen-Image-Plus, or reports polling/output issues such as missing IMAGE_URL.
-metadata:
-  short-description: Generate Sophnet images with stable polling outputs
----
-
-# Sophnet Image Generate
-
-## Overview
-
-Generate Sophnet images with Python scripts that handle task polling and structured output.
-
-Script: `generate_image.py` — API 调用与轮询，输出 `TASK_ID`、`STATUS`、`IMAGE_URL`。
-
-## When to Use
-
-- User asks to generate an image with Sophnet models.
-- Prompt includes model choice (`Z-Image-Turbo`, `Qwen-Image`, `Qwen-Image-Plus`).
-- Do not use when the task is only to display an existing image URL/path; use `sophnet-smart-image-loader`.
-
-## Quick Reference
-
-| Goal     | Command                                                                                |
-| -------- | -------------------------------------------------------------------------------------- |
-| Generate | `uv run --project {baseDir} python {baseDir}/scripts/generate_image.py --prompt "..."` |
-| Options  | `uv run --project {baseDir} python {baseDir}/scripts/generate_image.py --help`         |
-
-## Implementation
-
-1. Run the script with `--prompt` (and optional `--model`, `--size`, `--n` etc.).
-2. Parse the stdout output: extract every line matching `IMAGE_URL=<url>`.
-3. **Output format (mandatory):**
-   - **First:** Output the original prompt used for generation, e.g. `**Prompt:** <the exact prompt string passed to --prompt>`.
-   - **Then:** For each extracted URL, present it as a Markdown image: `![image](<url>)`. If multiple URLs, output one per line.
-
-Example (single image):
-
-```
-**Prompt:** 一只在星空下奔跑的柴犬
-
-![image](https://example.com/generated/abc123.png)
-⚠️**提示**: 本内容有AI生成，图片保存24小时，请及时下载保存！
-```
-
-Example (multiple images):
-
-```
-**Prompt:** 赛博朋克风格的城市夜景
-
-![image](https://example.com/generated/abc123.png)
-![image](https://example.com/generated/def456.png)
-⚠️**提示**: 本内容有AI生成，图片保存24小时，请及时下载保存！
-```
-
-Do **not** output raw `IMAGE_URL=...` lines, JSON, or other internal format to the user. User-facing output must be: prompt line + Markdown image(s) only.
-
-## Common Mistakes
-
-- Forgetting to output the original **Prompt:** line before the image(s).
-- Returning raw `IMAGE_URL=...` lines instead of Markdown image syntax.
-- Wrapping the URL in extra quotes or angle brackets — use `![image](URL)` exactly.
+---
+name: sophnet-image-generate
+description: Use when a user requests Sophnet text-to-image generation, needs model selection across Z-Image-Turbo/Qwen-Image/Qwen-Image-Plus, or reports polling/output issues such as missing IMAGE_URL.
+metadata:
+  short-description: Generate Sophnet images with stable polling outputs
+---
+
+# Sophnet Image Generate
+
+## Overview
+
+Generate Sophnet images with Python scripts that handle task polling and structured output.
+
+Script: `generate_image.py` — API 调用与轮询，输出 `TASK_ID`、`STATUS`、`IMAGE_URL`。
+
+## When to Use
+
+- User asks to generate an image with Sophnet models.
+- Prompt includes model choice (`Z-Image-Turbo`, `Qwen-Image`, `Qwen-Image-Plus`).
+- Do not use when the task is only to display an existing image URL/path; use `sophnet-smart-image-loader`.
+
+## Quick Reference
+
+| Goal     | Command                                                                                |
+| -------- | -------------------------------------------------------------------------------------- |
+| Generate | `uv run --project {baseDir} python {baseDir}/scripts/generate_image.py --prompt "..."` |
+| Options  | `uv run --project {baseDir} python {baseDir}/scripts/generate_image.py --help`         |
+
+## Implementation
+
+1. Run the script with `--prompt` (and optional `--model`, `--size`, `--n` etc.).
+2. Parse the stdout output: extract every line matching `IMAGE_URL=<url>`.
+3. **Output format (mandatory):**
+   - **First:** Output the original prompt used for generation, e.g. `**Prompt:** <the exact prompt string passed to --prompt>`.
+   - **Then:** For each extracted URL, present it as a Markdown image: `![image](<url>)`. If multiple URLs, output one per line.
+
+Example (single image):
+
+```
+**Prompt:** 一只在星空下奔跑的柴犬
+
+![image](https://example.com/generated/abc123.png)
+⚠️**提示**: 本内容有AI生成，图片保存24小时，请及时下载保存！
+```
+
+Example (multiple images):
+
+```
+**Prompt:** 赛博朋克风格的城市夜景
+
+![image](https://example.com/generated/abc123.png)
+![image](https://example.com/generated/def456.png)
+⚠️**提示**: 本内容有AI生成，图片保存24小时，请及时下载保存！
+```
+
+Do **not** output raw `IMAGE_URL=...` lines, JSON, or other internal format to the user. User-facing output must be: prompt line + Markdown image(s) only.
+
+## Common Mistakes
+
+- Forgetting to output the original **Prompt:** line before the image(s).
+- Returning raw `IMAGE_URL=...` lines instead of Markdown image syntax.
+- Wrapping the URL in extra quotes or angle brackets — use `![image](URL)` exactly.

package/skills/sophnet-image-generate/src/pyproject.toml

@@ -1,9 +1,9 @@
-[project]
-name = "sophnet-image-generate"
-version = "1.0.0"
-description = "Sophnet text-to-image generation with task polling"
-requires-python = ">=3.8"
-dependencies = [
-    "requests>=2.28.0",
-    "sophnet-tools>=0.0.1",
-]
+[project]
+name = "sophnet-image-generate"
+version = "1.0.0"
+description = "Sophnet text-to-image generation with task polling"
+requires-python = ">=3.8"
+dependencies = [
+    "requests>=2.28.0",
+    "sophnet-tools>=0.0.1",
+]

package/skills/sophnet-image-generate/src/scripts/generate_image.py

@@ -1,156 +1,156 @@
-#!/usr/bin/env python3
-"""
-Sophnet text-to-image generation with async task polling.
-Outputs machine-friendly TASK_ID, STATUS, and IMAGE_URL lines.
-"""
-
-import argparse
-import json
-import sys
-import time
-
-import requests
-import sophnet_tools
-
-API_URL = "https://www.sophnet.com/api/open-apis/projects/easyllms/imagegenerator/task"
-VALID_MODELS = ["Z-Image-Turbo", "Qwen-Image", "Qwen-Image-Plus"]
-
-
-def parse_bool(value):
-    if value.lower() in ("true", "1", "yes", "y"):
-        return True
-    if value.lower() in ("false", "0", "no", "n"):
-        return False
-    raise argparse.ArgumentTypeError(f"invalid boolean value: {value!r}")
-
-
-def create_task(api_key, prompt, model, negative_prompt=None,
-                size="1024*1024", n=1, watermark=False, prompt_extend=True):
-    payload = {
-        "model": model,
-        "input": {"prompt": prompt},
-        "parameters": {
-            "size": size,
-            "n": n,
-            "watermark": watermark,
-            "prompt_extend": prompt_extend,
-        },
-    }
-    if negative_prompt:
-        payload["input"]["negative_prompt"] = negative_prompt
-
-    headers = {
-        "Authorization": f"Bearer {api_key}",
-        "Content-Type": "application/json",
-    }
-    resp = requests.post(API_URL, json=payload, headers=headers, timeout=60)
-    resp.raise_for_status()
-    data = resp.json()
-
-    for key in ("task_id", "taskId", "taskID", "id"):
-        if key in data:
-            return data[key]
-
-    if isinstance(data.get("output"), dict):
-        for key in ("task_id", "taskId", "taskID", "id"):
-            if key in data["output"]:
-                return data["output"][key]
-
-    print(f"Error: task_id not found in response.", file=sys.stderr)
-    print(json.dumps(data, ensure_ascii=False), file=sys.stderr)
-    sys.exit(1)
-
-
-def poll_task(api_key, task_id, poll_interval=2, max_wait=300):
-    headers = {"Authorization": f"Bearer {api_key}"}
-    start = time.time()
-
-    while True:
-        elapsed = time.time() - start
-        if elapsed > max_wait:
-            print(f"Error: timed out after {max_wait}s.", file=sys.stderr)
-            sys.exit(1)
-
-        resp = requests.get(f"{API_URL}/{task_id}", headers=headers, timeout=60)
-        resp.raise_for_status()
-        data = resp.json()
-
-        status = None
-        for key in ("status", "taskStatus", "task_status"):
-            if key in data:
-                status = data[key]
-                break
-            if isinstance(data.get("output"), dict) and key in data["output"]:
-                status = data["output"][key]
-                break
-
-        if status and status.lower() in ("succeeded", "success"):
-            return data
-        if status and status.lower() in ("failed", "error"):
-            print("STATUS=failed", file=sys.stderr)
-            print(json.dumps(data, ensure_ascii=False), file=sys.stderr)
-            sys.exit(1)
-
-        time.sleep(poll_interval)
-
-
-def extract_urls(data):
-    urls = []
-
-    def _walk(obj):
-        if isinstance(obj, dict):
-            if "url" in obj and isinstance(obj["url"], str):
-                urls.append(obj["url"])
-            for v in obj.values():
-                _walk(v)
-        elif isinstance(obj, list):
-            for item in obj:
-                _walk(item)
-
-    _walk(data)
-    return urls
-
-
-def main():
-    parser = argparse.ArgumentParser(description="SophNet image generation")
-    parser.add_argument("--prompt", required=True, help="Image prompt")
-    parser.add_argument("--negative-prompt", default=None, help="Negative prompt")
-    parser.add_argument("--model", default="Z-Image-Turbo",
-                        choices=VALID_MODELS, help="Model name")
-    parser.add_argument("--size", default="1024*1024", help="Image size")
-    parser.add_argument("--n", type=int, default=1, help="Number of images")
-    parser.add_argument("--watermark", type=parse_bool, default=False)
-    parser.add_argument("--prompt-extend", type=parse_bool, default=True)
-    parser.add_argument("--poll-interval", type=int, default=2)
-    parser.add_argument("--max-wait", type=int, default=300)
-    args = parser.parse_args()
-
-    api_key = sophnet_tools.get_api_key()
-    if not api_key:
-        print("Error: No API key found.", file=sys.stderr)
-        sys.exit(1)
-
-    task_id = create_task(
-        api_key, args.prompt, args.model,
-        negative_prompt=args.negative_prompt,
-        size=args.size, n=args.n,
-        watermark=args.watermark,
-        prompt_extend=args.prompt_extend,
-    )
-    print(f"TASK_ID={task_id}")
-
-    result = poll_task(api_key, task_id, args.poll_interval, args.max_wait)
-    print("STATUS=succeeded")
-
-    urls = extract_urls(result)
-    if not urls:
-        print("Error: url not found in response.", file=sys.stderr)
-        print(json.dumps(result, ensure_ascii=False), file=sys.stderr)
-        sys.exit(1)
-
-    for u in urls:
-        print(f"IMAGE_URL={u}")
-
-
-if __name__ == "__main__":
-    main()
+#!/usr/bin/env python3
+"""
+Sophnet text-to-image generation with async task polling.
+Outputs machine-friendly TASK_ID, STATUS, and IMAGE_URL lines.
+"""
+
+import argparse
+import json
+import sys
+import time
+
+import requests
+import sophnet_tools
+
+API_URL = "https://www.sophnet.com/api/open-apis/projects/easyllms/imagegenerator/task"
+VALID_MODELS = ["Z-Image-Turbo", "Qwen-Image", "Qwen-Image-Plus"]
+
+
+def parse_bool(value):
+    if value.lower() in ("true", "1", "yes", "y"):
+        return True
+    if value.lower() in ("false", "0", "no", "n"):
+        return False
+    raise argparse.ArgumentTypeError(f"invalid boolean value: {value!r}")
+
+
+def create_task(api_key, prompt, model, negative_prompt=None,
+                size="1024*1024", n=1, watermark=False, prompt_extend=True):
+    payload = {
+        "model": model,
+        "input": {"prompt": prompt},
+        "parameters": {
+            "size": size,
+            "n": n,
+            "watermark": watermark,
+            "prompt_extend": prompt_extend,
+        },
+    }
+    if negative_prompt:
+        payload["input"]["negative_prompt"] = negative_prompt
+
+    headers = {
+        "Authorization": f"Bearer {api_key}",
+        "Content-Type": "application/json",
+    }
+    resp = requests.post(API_URL, json=payload, headers=headers, timeout=60)
+    resp.raise_for_status()
+    data = resp.json()
+
+    for key in ("task_id", "taskId", "taskID", "id"):
+        if key in data:
+            return data[key]
+
+    if isinstance(data.get("output"), dict):
+        for key in ("task_id", "taskId", "taskID", "id"):
+            if key in data["output"]:
+                return data["output"][key]
+
+    print(f"Error: task_id not found in response.", file=sys.stderr)
+    print(json.dumps(data, ensure_ascii=False), file=sys.stderr)
+    sys.exit(1)
+
+
+def poll_task(api_key, task_id, poll_interval=2, max_wait=300):
+    headers = {"Authorization": f"Bearer {api_key}"}
+    start = time.time()
+
+    while True:
+        elapsed = time.time() - start
+        if elapsed > max_wait:
+            print(f"Error: timed out after {max_wait}s.", file=sys.stderr)
+            sys.exit(1)
+
+        resp = requests.get(f"{API_URL}/{task_id}", headers=headers, timeout=60)
+        resp.raise_for_status()
+        data = resp.json()
+
+        status = None
+        for key in ("status", "taskStatus", "task_status"):
+            if key in data:
+                status = data[key]
+                break
+            if isinstance(data.get("output"), dict) and key in data["output"]:
+                status = data["output"][key]
+                break
+
+        if status and status.lower() in ("succeeded", "success"):
+            return data
+        if status and status.lower() in ("failed", "error"):
+            print("STATUS=failed", file=sys.stderr)
+            print(json.dumps(data, ensure_ascii=False), file=sys.stderr)
+            sys.exit(1)
+
+        time.sleep(poll_interval)
+
+
+def extract_urls(data):
+    urls = []
+
+    def _walk(obj):
+        if isinstance(obj, dict):
+            if "url" in obj and isinstance(obj["url"], str):
+                urls.append(obj["url"])
+            for v in obj.values():
+                _walk(v)
+        elif isinstance(obj, list):
+            for item in obj:
+                _walk(item)
+
+    _walk(data)
+    return urls
+
+
+def main():
+    parser = argparse.ArgumentParser(description="SophNet image generation")
+    parser.add_argument("--prompt", required=True, help="Image prompt")
+    parser.add_argument("--negative-prompt", default=None, help="Negative prompt")
+    parser.add_argument("--model", default="Z-Image-Turbo",
+                        choices=VALID_MODELS, help="Model name")
+    parser.add_argument("--size", default="1024*1024", help="Image size")
+    parser.add_argument("--n", type=int, default=1, help="Number of images")
+    parser.add_argument("--watermark", type=parse_bool, default=False)
+    parser.add_argument("--prompt-extend", type=parse_bool, default=True)
+    parser.add_argument("--poll-interval", type=int, default=2)
+    parser.add_argument("--max-wait", type=int, default=300)
+    args = parser.parse_args()
+
+    api_key = sophnet_tools.get_api_key()
+    if not api_key:
+        print("Error: No API key found.", file=sys.stderr)
+        sys.exit(1)
+
+    task_id = create_task(
+        api_key, args.prompt, args.model,
+        negative_prompt=args.negative_prompt,
+        size=args.size, n=args.n,
+        watermark=args.watermark,
+        prompt_extend=args.prompt_extend,
+    )
+    print(f"TASK_ID={task_id}")
+
+    result = poll_task(api_key, task_id, args.poll_interval, args.max_wait)
+    print("STATUS=succeeded")
+
+    urls = extract_urls(result)
+    if not urls:
+        print("Error: url not found in response.", file=sys.stderr)
+        print(json.dumps(result, ensure_ascii=False), file=sys.stderr)
+        sys.exit(1)
+
+    for u in urls:
+        print(f"IMAGE_URL={u}")
+
+
+if __name__ == "__main__":
+    main()