Integrate latest baoyu-imagine updates without regressing Replicate runs

Merged origin/main into the PR branch to pick up the Z.AI provider work and
resolved the shared baoyu-imagine docs/code touches. While reconciling the
branch, fixed the outstanding review findings by preserving explicit
--imageSize validation for Replicate while ignoring inherited config defaults,
and by classifying Replicate multi-output extraction failures as
non-retryable so paid requests are not repeated.

Constraint: Merge had to preserve incoming Z.AI provider support from origin/main
Constraint: Replicate should still reject explicit --imageSize usage while tolerating inherited default_image_size config
Rejected: Silently ignore every Replicate imageSize value | would hide explicit CLI/task misuse
Rejected: Leave multi-output extraction under generic retry logic | repeats deterministic paid failures
Confidence: high
Scope-risk: moderate
Reversibility: clean
Directive: Keep imageSize source tracking aligned with CLI/config/batch task paths before tightening provider validation
Tested: node --import tsx --test skills/baoyu-imagine/scripts/main.test.ts skills/baoyu-imagine/scripts/providers/replicate.test.ts skills/baoyu-imagine/scripts/providers/zai.test.ts
Tested: npm test
Not-tested: Live GitHub thread resolution/reply actions

.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Skills shared by Baoyu for improving daily work efficiency",
-    "version": "1.99.1"
+    "version": "1.100.0"
   },
   "plugins": [
     {

CHANGELOG.md

@@ -2,6 +2,11 @@
 
 English | [中文](./CHANGELOG.zh.md)
 
+## 1.100.0 - 2026-04-12
+
+### Features
+- `baoyu-imagine`: add Z.AI GLM-Image provider — supports `glm-image` and `cogview-4-250304` models via the Z.AI sync image API; configure with `ZAI_API_KEY` (or `BIGMODEL_API_KEY` for backward compatibility)
+
 ## 1.99.1 - 2026-04-11
 
 ### Fixes

CHANGELOG.zh.md

@@ -2,6 +2,11 @@
 
 [English](./CHANGELOG.md) | 中文
 
+## 1.100.0 - 2026-04-12
+
+### 新功能
+- `baoyu-imagine`：新增 Z.AI GLM-Image 服务商支持，支持 `glm-image` 和 `cogview-4-250304` 模型，通过 Z.AI 同步图像 API 调用；配置 `ZAI_API_KEY`（或 `BIGMODEL_API_KEY` 向后兼容）
+
 ## 1.99.1 - 2026-04-11
 
 ### 修复

README.md

@@ -745,6 +745,9 @@ AI SDK-based image generation using OpenAI, Azure OpenAI, Google, OpenRouter, Da
 # DashScope with custom size
 /baoyu-imagine --prompt "为咖啡品牌设计一张 21:9 横幅海报，包含清晰中文标题" --image banner.png --provider dashscope --model qwen-image-2.0-pro --size 2048x872
 
+# Z.AI GLM-Image
+/baoyu-imagine --prompt "一张带清晰中文标题的科技海报" --image out.png --provider zai
+
 # MiniMax
 /baoyu-imagine --prompt "A fashion editorial portrait by a bright studio window" --image out.jpg --provider minimax
 
@@ -781,8 +784,8 @@ AI SDK-based image generation using OpenAI, Azure OpenAI, Google, OpenRouter, Da
 | `--image` | Output image path (required) |
 | `--batchfile` | JSON batch file for multi-image generation |
 | `--jobs` | Worker count for batch mode |
-| `--provider` | `google`, `openai`, `azure`, `openrouter`, `dashscope`, `minimax`, `jimeng`, `seedream`, or `replicate` |
+| `--provider` | `google`, `openai`, `azure`, `openrouter`, `dashscope`, `zai`, `minimax`, `jimeng`, `seedream`, or `replicate` |
-| `--model`, `-m` | Model ID or deployment name. Azure uses deployment name; OpenRouter uses full model IDs; MiniMax uses `image-01` / `image-01-live` |
+| `--model`, `-m` | Model ID or deployment name. Azure uses deployment name; OpenRouter uses full model IDs; Z.AI uses `glm-image`; MiniMax uses `image-01` / `image-01-live` |
 | `--ar` | Aspect ratio (e.g., `16:9`, `1:1`, `4:3`) |
 | `--size` | Size (e.g., `1024x1024`) |
 | `--quality` | `normal` or `2k` (default: `2k`) |
@@ -800,6 +803,8 @@ AI SDK-based image generation using OpenAI, Azure OpenAI, Google, OpenRouter, Da
 | `GOOGLE_API_KEY` | Google API key | - |
 | `GEMINI_API_KEY` | Alias for `GOOGLE_API_KEY` | - |
 | `DASHSCOPE_API_KEY` | DashScope API key (Aliyun) | - |
+| `ZAI_API_KEY` | Z.AI API key | - |
+| `BIGMODEL_API_KEY` | Backward-compatible alias for Z.AI API key | - |
 | `MINIMAX_API_KEY` | MiniMax API key | - |
 | `REPLICATE_API_TOKEN` | Replicate API token | - |
 | `JIMENG_ACCESS_KEY_ID` | Jimeng Volcengine access key | - |
@@ -811,6 +816,8 @@ AI SDK-based image generation using OpenAI, Azure OpenAI, Google, OpenRouter, Da
 | `OPENROUTER_IMAGE_MODEL` | OpenRouter model | `google/gemini-3.1-flash-image-preview` |
 | `GOOGLE_IMAGE_MODEL` | Google model | `gemini-3-pro-image-preview` |
 | `DASHSCOPE_IMAGE_MODEL` | DashScope model | `qwen-image-2.0-pro` |
+| `ZAI_IMAGE_MODEL` | Z.AI model | `glm-image` |
+| `BIGMODEL_IMAGE_MODEL` | Backward-compatible alias for Z.AI model | `glm-image` |
 | `MINIMAX_IMAGE_MODEL` | MiniMax model | `image-01` |
 | `REPLICATE_IMAGE_MODEL` | Replicate model | `google/nano-banana-2` |
 | `JIMENG_IMAGE_MODEL` | Jimeng model | `jimeng_t2i_v40` |
@@ -824,6 +831,8 @@ AI SDK-based image generation using OpenAI, Azure OpenAI, Google, OpenRouter, Da
 | `OPENROUTER_TITLE` | Optional app name for OpenRouter attribution | - |
 | `GOOGLE_BASE_URL` | Custom Google endpoint | - |
 | `DASHSCOPE_BASE_URL` | Custom DashScope endpoint | - |
+| `ZAI_BASE_URL` | Custom Z.AI endpoint | `https://api.z.ai/api/paas/v4` |
+| `BIGMODEL_BASE_URL` | Backward-compatible alias for Z.AI endpoint | - |
 | `MINIMAX_BASE_URL` | Custom MiniMax endpoint | `https://api.minimax.io` |
 | `REPLICATE_BASE_URL` | Custom Replicate endpoint | - |
 | `JIMENG_BASE_URL` | Custom Jimeng endpoint | `https://visual.volcengineapi.com` |
@@ -836,6 +845,7 @@ AI SDK-based image generation using OpenAI, Azure OpenAI, Google, OpenRouter, Da
 **Provider Notes**:
 - Azure OpenAI: `--model` means Azure deployment name, not the underlying model family.
 - DashScope: `qwen-image-2.0-pro` is the recommended default for custom `--size`, `21:9`, and strong Chinese/English text rendering.
+- Z.AI: `glm-image` is recommended for posters, diagrams, and text-heavy Chinese/English images. Reference images are not supported.
 - MiniMax: `image-01` supports documented custom `width` / `height`; `image-01-live` is lower latency and works best with `--ar`.
 - MiniMax reference images are sent as `subject_reference`; the current API is specialized toward character / portrait consistency.
 - Jimeng does not support reference images.
@@ -848,7 +858,7 @@ AI SDK-based image generation using OpenAI, Azure OpenAI, Google, OpenRouter, Da
 1. If `--provider` is specified → use it
 2. If `--ref` is provided and no provider is specified → try Google, then OpenAI, Azure, OpenRouter, Replicate, Seedream, and finally MiniMax
 3. If only one API key is available → use that provider
-4. If multiple providers are available → default to Google
+4. If multiple providers are available → default to Google, then OpenAI, Azure, OpenRouter, DashScope, Z.AI, MiniMax, Replicate, Jimeng, Seedream
 
 #### baoyu-danger-gemini-web
 
@@ -1148,6 +1158,11 @@ DASHSCOPE_API_KEY=sk-xxx
 DASHSCOPE_IMAGE_MODEL=qwen-image-2.0-pro
 # DASHSCOPE_BASE_URL=https://dashscope.aliyuncs.com/api/v1
 
+# Z.AI
+ZAI_API_KEY=xxx
+ZAI_IMAGE_MODEL=glm-image
+# ZAI_BASE_URL=https://api.z.ai/api/paas/v4
+
 # MiniMax
 MINIMAX_API_KEY=xxx
 MINIMAX_IMAGE_MODEL=image-01

README.zh.md

@@ -745,6 +745,9 @@ AI 驱动的生成后端。
 # DashScope 自定义尺寸
 /baoyu-imagine --prompt "为咖啡品牌设计一张 21:9 横幅海报，包含清晰中文标题" --image banner.png --provider dashscope --model qwen-image-2.0-pro --size 2048x872
 
+# Z.AI GLM-Image
+/baoyu-imagine --prompt "一张带清晰中文标题的科技海报" --image out.png --provider zai
+
 # MiniMax
 /baoyu-imagine --prompt "A fashion editorial portrait by a bright studio window" --image out.jpg --provider minimax
 
@@ -781,8 +784,8 @@ AI 驱动的生成后端。
 | `--image` | 输出图片路径（必需） |
 | `--batchfile` | 多图批量生成的 JSON 文件 |
 | `--jobs` | 批量模式的并发 worker 数 |
-| `--provider` | `google`、`openai`、`azure`、`openrouter`、`dashscope`、`minimax`、`jimeng`、`seedream` 或 `replicate` |
+| `--provider` | `google`、`openai`、`azure`、`openrouter`、`dashscope`、`zai`、`minimax`、`jimeng`、`seedream` 或 `replicate` |
-| `--model`, `-m` | 模型 ID 或部署名。Azure 使用部署名；OpenRouter 使用完整模型 ID；MiniMax 使用 `image-01` / `image-01-live` |
+| `--model`, `-m` | 模型 ID 或部署名。Azure 使用部署名；OpenRouter 使用完整模型 ID；Z.AI 使用 `glm-image`；MiniMax 使用 `image-01` / `image-01-live` |
 | `--ar` | 宽高比（如 `16:9`、`1:1`、`4:3`） |
 | `--size` | 尺寸（如 `1024x1024`） |
 | `--quality` | `normal` 或 `2k`（默认：`2k`） |
@@ -800,6 +803,8 @@ AI 驱动的生成后端。
 | `GOOGLE_API_KEY` | Google API 密钥 | - |
 | `GEMINI_API_KEY` | `GOOGLE_API_KEY` 的别名 | - |
 | `DASHSCOPE_API_KEY` | DashScope API 密钥（阿里云） | - |
+| `ZAI_API_KEY` | Z.AI API 密钥 | - |
+| `BIGMODEL_API_KEY` | Z.AI API 密钥向后兼容别名 | - |
 | `MINIMAX_API_KEY` | MiniMax API 密钥 | - |
 | `REPLICATE_API_TOKEN` | Replicate API Token | - |
 | `JIMENG_ACCESS_KEY_ID` | 即梦火山引擎 Access Key | - |
@@ -811,6 +816,8 @@ AI 驱动的生成后端。
 | `OPENROUTER_IMAGE_MODEL` | OpenRouter 模型 | `google/gemini-3.1-flash-image-preview` |
 | `GOOGLE_IMAGE_MODEL` | Google 模型 | `gemini-3-pro-image-preview` |
 | `DASHSCOPE_IMAGE_MODEL` | DashScope 模型 | `qwen-image-2.0-pro` |
+| `ZAI_IMAGE_MODEL` | Z.AI 模型 | `glm-image` |
+| `BIGMODEL_IMAGE_MODEL` | Z.AI 模型向后兼容别名 | `glm-image` |
 | `MINIMAX_IMAGE_MODEL` | MiniMax 模型 | `image-01` |
 | `REPLICATE_IMAGE_MODEL` | Replicate 模型 | `google/nano-banana-2` |
 | `JIMENG_IMAGE_MODEL` | 即梦模型 | `jimeng_t2i_v40` |
@@ -824,6 +831,8 @@ AI 驱动的生成后端。
 | `OPENROUTER_TITLE` | OpenRouter 归因用应用名 | - |
 | `GOOGLE_BASE_URL` | 自定义 Google 端点 | - |
 | `DASHSCOPE_BASE_URL` | 自定义 DashScope 端点 | - |
+| `ZAI_BASE_URL` | 自定义 Z.AI 端点 | `https://api.z.ai/api/paas/v4` |
+| `BIGMODEL_BASE_URL` | Z.AI 端点向后兼容别名 | - |
 | `MINIMAX_BASE_URL` | 自定义 MiniMax 端点 | `https://api.minimax.io` |
 | `REPLICATE_BASE_URL` | 自定义 Replicate 端点 | - |
 | `JIMENG_BASE_URL` | 自定义即梦端点 | `https://visual.volcengineapi.com` |
@@ -836,6 +845,7 @@ AI 驱动的生成后端。
 **Provider 说明**：
 - Azure OpenAI：`--model` 表示 Azure deployment name，不是底层模型家族名。
 - DashScope：`qwen-image-2.0-pro` 是自定义 `--size`、`21:9` 和中英文排版的推荐默认模型。
+- Z.AI：`glm-image` 适合海报、图表和中英文排版密集的图片生成，暂不支持参考图。
 - MiniMax：`image-01` 支持官方文档里的自定义 `width` / `height`；`image-01-live` 更偏低延迟，适合配合 `--ar` 使用。
 - MiniMax 参考图会走 `subject_reference`，当前能力更偏角色 / 人像一致性。
 - 即梦不支持参考图。
@@ -848,7 +858,7 @@ AI 驱动的生成后端。
 1. 如果指定了 `--provider` → 使用指定的
 2. 如果传了 `--ref` 且未指定 provider → 依次尝试 Google、OpenAI、Azure、OpenRouter、Replicate、Seedream，最后是 MiniMax
 3. 如果只有一个 API 密钥 → 使用对应服务商
-4. 如果多个可用 → 默认使用 Google
+4. 如果多个可用 → 默认使用 Google，然后依次为 OpenAI、Azure、OpenRouter、DashScope、Z.AI、MiniMax、Replicate、即梦、豆包
 
 #### baoyu-danger-gemini-web
 
@@ -1148,6 +1158,11 @@ DASHSCOPE_API_KEY=sk-xxx
 DASHSCOPE_IMAGE_MODEL=qwen-image-2.0-pro
 # DASHSCOPE_BASE_URL=https://dashscope.aliyuncs.com/api/v1
 
+# Z.AI
+ZAI_API_KEY=xxx
+ZAI_IMAGE_MODEL=glm-image
+# ZAI_BASE_URL=https://api.z.ai/api/paas/v4
+
 # MiniMax
 MINIMAX_API_KEY=xxx
 MINIMAX_IMAGE_MODEL=image-01

skills/baoyu-imagine/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: baoyu-imagine
-description: AI image generation with OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, MiniMax, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
+description: AI image generation with OpenAI, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
-version: 1.56.5
+version: 1.57.0
 metadata:
   openclaw:
     homepage: https://github.com/JimLiu/baoyu-skills#baoyu-imagine
@@ -13,7 +13,7 @@ metadata:
 
 # Image Generation (AI SDK)
 
-Official API-based image generation. Supports OpenAI, Azure OpenAI, Google, OpenRouter, DashScope (阿里通义万象), MiniMax, Jimeng (即梦), Seedream (豆包) and Replicate providers.
+Official API-based image generation. Supports OpenAI, Azure OpenAI, Google, OpenRouter, DashScope (阿里通义万象), Z.AI GLM-Image, MiniMax, Jimeng (即梦), Seedream (豆包) and Replicate providers.
 
 ## Script Directory
 
@@ -103,6 +103,12 @@ ${BUN_X} {baseDir}/scripts/main.ts --prompt "为咖啡品牌设计一张 21:9
 # DashScope legacy Qwen fixed-size model
 ${BUN_X} {baseDir}/scripts/main.ts --prompt "一张电影感海报" --image out.png --provider dashscope --model qwen-image-max --size 1664x928
 
+# Z.AI GLM-image
+${BUN_X} {baseDir}/scripts/main.ts --prompt "一张带清晰中文标题的科技海报" --image out.png --provider zai
+
+# Z.AI GLM-image with explicit custom size
+${BUN_X} {baseDir}/scripts/main.ts --prompt "A science illustration with labels" --image out.png --provider zai --model glm-image --size 1472x1088
+
 # MiniMax
 ${BUN_X} {baseDir}/scripts/main.ts --prompt "A fashion editorial portrait by a bright studio window" --image out.jpg --provider minimax
 
@@ -164,8 +170,8 @@ Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch fi
 | `--image <path>` | Output image path (required in single-image mode) |
 | `--batchfile <path>` | JSON batch file for multi-image generation |
 | `--jobs <count>` | Worker count for batch mode (default: auto, max from config, built-in default 10) |
-| `--provider google\|openai\|azure\|openrouter\|dashscope\|minimax\|jimeng\|seedream\|replicate` | Force provider (default: auto-detect) |
+| `--provider google\|openai\|azure\|openrouter\|dashscope\|zai\|minimax\|jimeng\|seedream\|replicate` | Force provider (default: auto-detect) |
-| `--model <id>`, `-m` | Model ID (Google: `gemini-3-pro-image-preview`; OpenAI: `gpt-image-1.5`; Azure: deployment name such as `gpt-image-1.5` or `image-prod`; OpenRouter: `google/gemini-3.1-flash-image-preview`; DashScope: `qwen-image-2.0-pro`; MiniMax: `image-01`) |
+| `--model <id>`, `-m` | Model ID (Google: `gemini-3-pro-image-preview`; OpenAI: `gpt-image-1.5`; Azure: deployment name such as `gpt-image-1.5` or `image-prod`; OpenRouter: `google/gemini-3.1-flash-image-preview`; DashScope: `qwen-image-2.0-pro`; Z.AI: `glm-image`; MiniMax: `image-01`) |
 | `--ar <ratio>` | Aspect ratio (e.g., `16:9`, `1:1`, `4:3`) |
 | `--size <WxH>` | Size (e.g., `1024x1024`) |
 | `--quality normal\|2k` | Quality preset (default: `2k`) |
@@ -183,6 +189,8 @@ Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch fi
 | `OPENROUTER_API_KEY` | OpenRouter API key |
 | `GOOGLE_API_KEY` | Google API key |
 | `DASHSCOPE_API_KEY` | DashScope API key (阿里云) |
+| `ZAI_API_KEY` | Z.AI API key |
+| `BIGMODEL_API_KEY` | Backward-compatible alias for Z.AI API key |
 | `MINIMAX_API_KEY` | MiniMax API key |
 | `REPLICATE_API_TOKEN` | Replicate API token |
 | `JIMENG_ACCESS_KEY_ID` | Jimeng (即梦) Volcengine access key |
@@ -194,6 +202,8 @@ Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch fi
 | `OPENROUTER_IMAGE_MODEL` | OpenRouter model override (default: `google/gemini-3.1-flash-image-preview`) |
 | `GOOGLE_IMAGE_MODEL` | Google model override |
 | `DASHSCOPE_IMAGE_MODEL` | DashScope model override (default: `qwen-image-2.0-pro`) |
+| `ZAI_IMAGE_MODEL` | Z.AI model override (default: `glm-image`) |
+| `BIGMODEL_IMAGE_MODEL` | Backward-compatible alias for Z.AI model override |
 | `MINIMAX_IMAGE_MODEL` | MiniMax model override (default: `image-01`) |
 | `REPLICATE_IMAGE_MODEL` | Replicate model override (default: google/nano-banana-2) |
 | `JIMENG_IMAGE_MODEL` | Jimeng model override (default: jimeng_t2i_v40) |
@@ -206,6 +216,8 @@ Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch fi
 | `OPENROUTER_TITLE` | Optional app name for OpenRouter attribution |
 | `GOOGLE_BASE_URL` | Custom Google endpoint |
 | `DASHSCOPE_BASE_URL` | Custom DashScope endpoint |
+| `ZAI_BASE_URL` | Custom Z.AI endpoint (default: `https://api.z.ai/api/paas/v4`) |
+| `BIGMODEL_BASE_URL` | Backward-compatible alias for Z.AI endpoint |
 | `MINIMAX_BASE_URL` | Custom MiniMax endpoint (default: `https://api.minimax.io`) |
 | `REPLICATE_BASE_URL` | Custom Replicate endpoint |
 | `JIMENG_BASE_URL` | Custom Jimeng endpoint (default: `https://visual.volcengineapi.com`) |
@@ -280,6 +292,32 @@ Official references:
 - [Text-to-image guide](https://help.aliyun.com/zh/model-studio/text-to-image)
 - [Qwen-Image Edit API](https://help.aliyun.com/zh/model-studio/qwen-image-edit-api)
 
+### Z.AI Models
+
+Use `--model glm-image` or set `default_model.zai` / `ZAI_IMAGE_MODEL` when the user wants GLM-image output.
+
+Official Z.AI image model options currently documented in the sync image API:
+
+- `glm-image` (recommended default)
+  - Text-to-image only in `baoyu-imagine`
+  - Native `quality` options are `hd` and `standard`; this skill maps `2k -> hd` and `normal -> standard`
+  - Recommended sizes: `1280x1280`, `1568x1056`, `1056x1568`, `1472x1088`, `1088x1472`, `1728x960`, `960x1728`
+  - Custom `--size` requires width and height between `1024` and `2048`, divisible by `32`, with total pixels <= `2^22`
+- `cogview-4-250304`
+  - Legacy Z.AI image model family exposed by the same endpoint
+  - Custom `--size` requires width and height between `512` and `2048`, divisible by `16`, with total pixels <= `2^21`
+
+Notes:
+
+- The official sync API returns a temporary image URL; `baoyu-imagine` downloads that URL and writes the image locally
+- `--ref` is not supported for Z.AI in this skill yet
+- The sync API currently returns a single image, so `--n > 1` is rejected
+
+Official references:
+
+- [GLM-Image Guide](https://docs.z.ai/guides/image/glm-image)
+- [Generate Image API](https://docs.z.ai/api-reference/image/generate-image)
+
 ### MiniMax Models
 
 Use `--model image-01` or set `default_model.minimax` / `MINIMAX_IMAGE_MODEL` when the user wants MiniMax image generation.
@@ -368,7 +406,7 @@ ${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider r
 1. `--ref` provided + no `--provider` → auto-select Google first, then OpenAI, then Azure, then OpenRouter, then Replicate, then Seedream, then MiniMax (MiniMax subject reference is more specialized toward character/portrait consistency)
 2. `--provider` specified → use it (if `--ref`, must be `google`, `openai`, `azure`, `openrouter`, `replicate`, `seedream`, or `minimax`)
 3. Only one API key available → use that provider
-4. Multiple available → default to Google
+4. Multiple available → default to Google, then OpenAI, Azure, OpenRouter, DashScope, Z.AI, MiniMax, Replicate, Jimeng, Seedream
 
 ## Quality Presets
 

skills/baoyu-imagine/references/config/first-time-setup.md

@@ -53,6 +53,8 @@ options:
     description: "Router for Gemini/FLUX/OpenAI-compatible image models"
   - label: "DashScope"
     description: "Alibaba Cloud - Qwen-Image, strong Chinese/English text rendering"
+  - label: "Z.AI"
+    description: "GLM-image, strong poster and text-heavy image generation"
   - label: "MiniMax"
     description: "MiniMax image generation with subject-reference character workflows"
   - label: "Replicate"
@@ -119,6 +121,20 @@ options:
     description: "Faster variant, use aspect ratio instead of custom size"
 ```
 
+### Question 2e: Default Z.AI Model
+
+Only show if user selected Z.AI.
+
+```yaml
+header: "Z.AI Model"
+question: "Default Z.AI image generation model?"
+options:
+  - label: "glm-image (Recommended)"
+    description: "Best default for posters, diagrams, and text-heavy images"
+  - label: "cogview-4-250304"
+    description: "Legacy Z.AI image model on the same endpoint"
+```
+
 ### Question 3: Default Quality
 
 ```yaml
@@ -165,6 +181,7 @@ default_model:
   azure: [selected azure deployment or null]
   openrouter: [selected openrouter model or null]
   dashscope: null
+  zai: [selected Z.AI model or null]
   minimax: [selected minimax model or null]
   replicate: null
 ---
@@ -257,6 +274,24 @@ Notes for DashScope setup:
 - `qwen-image-max` / `qwen-image-plus` / `qwen-image` only support five fixed sizes: `1664*928`, `1472*1104`, `1328*1328`, `1104*1472`, `928*1664`.
 - In `baoyu-imagine`, `quality` is a compatibility preset. It is not a native DashScope parameter.
 
+### Z.AI Model Selection
+
+```yaml
+header: "Z.AI Model"
+question: "Choose a default Z.AI image generation model?"
+options:
+  - label: "glm-image (Recommended)"
+    description: "Current flagship image model with better text rendering and poster layouts"
+  - label: "cogview-4-250304"
+    description: "Legacy model on the sync image endpoint"
+```
+
+Notes for Z.AI setup:
+
+- Prefer `glm-image` for posters, diagrams, and Chinese/English text-heavy layouts.
+- In `baoyu-imagine`, Z.AI currently exposes text-to-image only; reference images are not wired for this provider.
+- The sync Z.AI image API returns a downloadable image URL, which the runtime saves locally after download.
+
 ### Replicate Model Selection
 
 ```yaml
@@ -306,6 +341,7 @@ default_model:
   azure: [value or null]
   openrouter: [value or null]
   dashscope: [value or null]
+  zai: [value or null]
   minimax: [value or null]
   replicate: [value or null]
 ```

skills/baoyu-imagine/references/config/preferences-schema.md

@@ -11,7 +11,7 @@ description: EXTEND.md YAML schema for baoyu-imagine user preferences
 ---
 version: 1
 
-default_provider: null      # google|openai|azure|openrouter|dashscope|minimax|replicate|null (null = auto-detect)
+default_provider: null      # google|openai|azure|openrouter|dashscope|zai|minimax|replicate|null (null = auto-detect)
 
 default_quality: null       # normal|2k|null (null = use default: 2k)
 
@@ -25,6 +25,7 @@ default_model:
   azure: null               # Azure deployment name, e.g., "gpt-image-1.5" or "image-prod"
   openrouter: null          # e.g., "google/gemini-3.1-flash-image-preview"
   dashscope: null           # e.g., "qwen-image-2.0-pro"
+  zai: null                 # e.g., "glm-image"
   minimax: null             # e.g., "image-01"
   replicate: null           # e.g., "google/nano-banana-2"
 
@@ -49,6 +50,9 @@ batch:
     dashscope:
       concurrency: 3
       start_interval_ms: 1100
+    zai:
+      concurrency: 3
+      start_interval_ms: 1100
     minimax:
       concurrency: 3
       start_interval_ms: 1100
@@ -69,6 +73,7 @@ batch:
 | `default_model.azure` | string\|null | null | Azure default deployment name |
 | `default_model.openrouter` | string\|null | null | OpenRouter default model |
 | `default_model.dashscope` | string\|null | null | DashScope default model |
+| `default_model.zai` | string\|null | null | Z.AI default model |
 | `default_model.minimax` | string\|null | null | MiniMax default model |
 | `default_model.replicate` | string\|null | null | Replicate default model |
 | `batch.max_workers` | int\|null | 10 | Batch worker cap |
@@ -100,6 +105,7 @@ default_model:
   azure: "gpt-image-1.5"
   openrouter: "google/gemini-3.1-flash-image-preview"
   dashscope: "qwen-image-2.0-pro"
+  zai: "glm-image"
   minimax: "image-01"
   replicate: "google/nano-banana-2"
 batch:
@@ -111,6 +117,9 @@ batch:
     azure:
       concurrency: 3
       start_interval_ms: 1100
+    zai:
+      concurrency: 3
+      start_interval_ms: 1100
     openrouter:
       concurrency: 3
       start_interval_ms: 1100

skills/baoyu-imagine/scripts/main.test.ts

@@ -31,6 +31,7 @@ function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
     size: null,
     quality: null,
     imageSize: null,
+    imageSizeSource: null,
     referenceImages: [],
     n: 1,
     batchFile: null,
@@ -78,7 +79,7 @@ test("parseArgs parses the main baoyu-imagine CLI flags", () => {
     "--image",
     "out/hero",
     "--provider",
-    "openai",
+    "zai",
     "--quality",
     "2k",
     "--imageSize",
@@ -95,9 +96,10 @@ test("parseArgs parses the main baoyu-imagine CLI flags", () => {
 
   assert.deepEqual(args.promptFiles, ["prompts/system.md", "prompts/content.md"]);
   assert.equal(args.imagePath, "out/hero");
-  assert.equal(args.provider, "openai");
+  assert.equal(args.provider, "zai");
   assert.equal(args.quality, "2k");
   assert.equal(args.imageSize, "4K");
+  assert.equal(args.imageSizeSource, "cli");
   assert.deepEqual(args.referenceImages, ["ref/one.png", "ref/two.jpg"]);
   assert.equal(args.n, 3);
   assert.equal(args.jobs, 5);
@@ -124,6 +126,7 @@ default_image_size: 2K
 default_model:
   google: gemini-3-pro-image-preview
   openai: gpt-image-1.5
+  zai: glm-image
   azure: image-prod
   minimax: image-01
 batch:
@@ -134,6 +137,9 @@ batch:
       start_interval_ms: 900
     openai:
       concurrency: 4
+    zai:
+      concurrency: 2
+      start_interval_ms: 1000
     minimax:
       concurrency: 2
       start_interval_ms: 1400
@@ -151,6 +157,7 @@ batch:
   assert.equal(config.default_image_size, "2K");
   assert.equal(config.default_model?.google, "gemini-3-pro-image-preview");
   assert.equal(config.default_model?.openai, "gpt-image-1.5");
+  assert.equal(config.default_model?.zai, "glm-image");
   assert.equal(config.default_model?.azure, "image-prod");
   assert.equal(config.default_model?.minimax, "image-01");
   assert.equal(config.batch?.max_workers, 8);
@@ -161,6 +168,10 @@ batch:
   assert.deepEqual(config.batch?.provider_limits?.openai, {
     concurrency: 4,
   });
+  assert.deepEqual(config.batch?.provider_limits?.zai, {
+    concurrency: 2,
+    start_interval_ms: 1000,
+  });
   assert.deepEqual(config.batch?.provider_limits?.minimax, {
     concurrency: 2,
     start_interval_ms: 1400,
@@ -246,6 +257,19 @@ test("mergeConfig only fills values missing from CLI args", () => {
   assert.equal(merged.quality, "2k");
   assert.equal(merged.aspectRatio, "3:2");
   assert.equal(merged.imageSize, "4K");
+  assert.equal(merged.imageSizeSource, "cli");
+});
+
+test("mergeConfig tags inherited imageSize defaults so providers can ignore incompatible config", () => {
+  const merged = mergeConfig(
+    makeArgs(),
+    {
+      default_image_size: "2K",
+    } satisfies Partial<ExtendConfig>,
+  );
+
+  assert.equal(merged.imageSize, "2K");
+  assert.equal(merged.imageSizeSource, "config");
 });
 
 test("detectProvider rejects non-ref-capable providers and prefers Google first when multiple keys exist", (t) => {
@@ -316,6 +340,27 @@ test("detectProvider selects Azure when only Azure credentials are configured",
   );
 });
 
+test("detectProvider selects Z.AI when credentials are present or the model id matches", (t) => {
+  useEnv(t, {
+    GOOGLE_API_KEY: null,
+    OPENAI_API_KEY: null,
+    AZURE_OPENAI_API_KEY: null,
+    AZURE_OPENAI_BASE_URL: null,
+    OPENROUTER_API_KEY: null,
+    DASHSCOPE_API_KEY: null,
+    ZAI_API_KEY: "zai-key",
+    BIGMODEL_API_KEY: null,
+    MINIMAX_API_KEY: null,
+    REPLICATE_API_TOKEN: null,
+    JIMENG_ACCESS_KEY_ID: null,
+    JIMENG_SECRET_ACCESS_KEY: null,
+    ARK_API_KEY: null,
+  });
+
+  assert.equal(detectProvider(makeArgs()), "zai");
+  assert.equal(detectProvider(makeArgs({ model: "glm-image" })), "zai");
+});
+
 test("detectProvider infers Seedream from model id and allows Seedream reference-image workflows", (t) => {
   useEnv(t, {
     GOOGLE_API_KEY: null,
@@ -375,6 +420,7 @@ test("batch worker and provider-rate-limit configuration prefer env over EXTEND
     BAOYU_IMAGE_GEN_MAX_WORKERS: "12",
     BAOYU_IMAGE_GEN_GOOGLE_CONCURRENCY: "5",
     BAOYU_IMAGE_GEN_GOOGLE_START_INTERVAL_MS: "450",
+    BAOYU_IMAGE_GEN_ZAI_CONCURRENCY: "4",
   });
 
   const extendConfig: Partial<ExtendConfig> = {
@@ -385,6 +431,10 @@ test("batch worker and provider-rate-limit configuration prefer env over EXTEND
           concurrency: 2,
           start_interval_ms: 900,
         },
+        zai: {
+          concurrency: 1,
+          start_interval_ms: 1200,
+        },
         minimax: {
           concurrency: 1,
           start_interval_ms: 1500,
@@ -398,6 +448,10 @@ test("batch worker and provider-rate-limit configuration prefer env over EXTEND
     concurrency: 5,
     startIntervalMs: 450,
   });
+  assert.deepEqual(getConfiguredProviderRateLimits(extendConfig).zai, {
+    concurrency: 4,
+    startIntervalMs: 1200,
+  });
   assert.deepEqual(getConfiguredProviderRateLimits(extendConfig).minimax, {
     concurrency: 1,
     startIntervalMs: 1500,
@@ -464,5 +518,11 @@ test("path normalization, worker count, and retry classification follow expected
   assert.equal(getWorkerCount(5, 0, 4), 1);
 
   assert.equal(isRetryableGenerationError(new Error("API error (401): denied")), false);
+  assert.equal(
+    isRetryableGenerationError(
+      new Error("Replicate returned 2 outputs, but baoyu-imagine currently supports saving exactly one image per request."),
+    ),
+    false,
+  );
   assert.equal(isRetryableGenerationError(new Error("socket hang up")), true);
 });

skills/baoyu-imagine/scripts/main.ts

@@ -58,6 +58,7 @@ const DEFAULT_PROVIDER_RATE_LIMITS: Record<Provider, ProviderRateLimit> = {
   openai: { concurrency: 3, startIntervalMs: 1100 },
   openrouter: { concurrency: 3, startIntervalMs: 1100 },
   dashscope: { concurrency: 3, startIntervalMs: 1100 },
+  zai: { concurrency: 3, startIntervalMs: 1100 },
   minimax: { concurrency: 3, startIntervalMs: 1100 },
   jimeng: { concurrency: 3, startIntervalMs: 1100 },
   seedream: { concurrency: 3, startIntervalMs: 1100 },
@@ -76,7 +77,7 @@ Options:
   --image <path>            Output image path (required in single-image mode)
   --batchfile <path>        JSON batch file for multi-image generation
   --jobs <count>            Worker count for batch mode (default: auto, max from config, built-in default 10)
-  --provider google|openai|openrouter|dashscope|minimax|replicate|jimeng|seedream|azure  Force provider (auto-detect by default)
+  --provider google|openai|openrouter|dashscope|zai|minimax|replicate|jimeng|seedream|azure  Force provider (auto-detect by default)
   -m, --model <id>          Model ID
   --ar <ratio>              Aspect ratio (e.g., 16:9, 1:1, 4:3)
   --size <WxH>              Size (e.g., 1024x1024)
@@ -114,6 +115,8 @@ Environment variables:
   GOOGLE_API_KEY            Google API key
   GEMINI_API_KEY            Gemini API key (alias for GOOGLE_API_KEY)
   DASHSCOPE_API_KEY         DashScope API key
+  ZAI_API_KEY               Z.AI API key
+  BIGMODEL_API_KEY          Backward-compatible alias for Z.AI API key
   MINIMAX_API_KEY           MiniMax API key
   REPLICATE_API_TOKEN       Replicate API token
   JIMENG_ACCESS_KEY_ID      Jimeng Access Key ID
@@ -123,6 +126,8 @@ Environment variables:
   OPENROUTER_IMAGE_MODEL    Default OpenRouter model (google/gemini-3.1-flash-image-preview)
   GOOGLE_IMAGE_MODEL        Default Google model (gemini-3-pro-image-preview)
   DASHSCOPE_IMAGE_MODEL     Default DashScope model (qwen-image-2.0-pro)
+  ZAI_IMAGE_MODEL           Default Z.AI model (glm-image)
+  BIGMODEL_IMAGE_MODEL      Backward-compatible alias for Z.AI model (glm-image)
   MINIMAX_IMAGE_MODEL       Default MiniMax model (image-01)
   REPLICATE_IMAGE_MODEL     Default Replicate model (google/nano-banana-2)
   JIMENG_IMAGE_MODEL        Default Jimeng model (jimeng_t2i_v40)
@@ -134,6 +139,8 @@ Environment variables:
   OPENROUTER_TITLE          Optional app name for OpenRouter attribution
   GOOGLE_BASE_URL           Custom Google endpoint
   DASHSCOPE_BASE_URL        Custom DashScope endpoint
+  ZAI_BASE_URL              Custom Z.AI endpoint
+  BIGMODEL_BASE_URL         Backward-compatible alias for Z.AI endpoint
   MINIMAX_BASE_URL          Custom MiniMax endpoint
   REPLICATE_BASE_URL        Custom Replicate endpoint
   JIMENG_BASE_URL           Custom Jimeng endpoint
@@ -161,6 +168,7 @@ export function parseArgs(argv: string[]): CliArgs {
     size: null,
     quality: null,
     imageSize: null,
+    imageSizeSource: null,
     referenceImages: [],
     n: 1,
     batchFile: null,
@@ -240,6 +248,7 @@ export function parseArgs(argv: string[]): CliArgs {
         v !== "openai" &&
         v !== "openrouter" &&
         v !== "dashscope" &&
+        v !== "zai" &&
         v !== "minimax" &&
         v !== "replicate" &&
         v !== "jimeng" &&
@@ -284,6 +293,7 @@ export function parseArgs(argv: string[]): CliArgs {
       const v = argv[++i]?.toUpperCase();
       if (v !== "1K" && v !== "2K" && v !== "4K") throw new Error(`Invalid imageSize: ${v}`);
       out.imageSize = v;
+      out.imageSizeSource = "cli";
       continue;
     }
 
@@ -396,6 +406,7 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
           openai: null,
           openrouter: null,
           dashscope: null,
+          zai: null,
           minimax: null,
           replicate: null,
           jimeng: null,
@@ -424,6 +435,7 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
           key === "openai" ||
           key === "openrouter" ||
           key === "dashscope" ||
+          key === "zai" ||
           key === "minimax" ||
           key === "replicate" ||
           key === "jimeng" ||
@@ -442,6 +454,7 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
           key === "openai" ||
           key === "openrouter" ||
           key === "dashscope" ||
+          key === "zai" ||
           key === "minimax" ||
           key === "replicate" ||
           key === "jimeng" ||
@@ -531,12 +544,16 @@ export async function loadExtendConfig(
 }
 
 export function mergeConfig(args: CliArgs, extend: Partial<ExtendConfig>): CliArgs {
+  const imageSize = args.imageSize ?? extend.default_image_size ?? null;
   return {
     ...args,
     provider: args.provider ?? extend.default_provider ?? null,
     quality: args.quality ?? extend.default_quality ?? null,
     aspectRatio: args.aspectRatio ?? extend.default_aspect_ratio ?? null,
-    imageSize: args.imageSize ?? extend.default_image_size ?? null,
+    imageSize,
+    imageSizeSource:
+      args.imageSizeSource ??
+      (args.imageSize !== null ? "cli" : (imageSize !== null ? "config" : null)),
   };
 }
 
@@ -572,13 +589,14 @@ export function getConfiguredProviderRateLimits(
     openai: { ...DEFAULT_PROVIDER_RATE_LIMITS.openai },
     openrouter: { ...DEFAULT_PROVIDER_RATE_LIMITS.openrouter },
     dashscope: { ...DEFAULT_PROVIDER_RATE_LIMITS.dashscope },
+    zai: { ...DEFAULT_PROVIDER_RATE_LIMITS.zai },
     minimax: { ...DEFAULT_PROVIDER_RATE_LIMITS.minimax },
     jimeng: { ...DEFAULT_PROVIDER_RATE_LIMITS.jimeng },
     seedream: { ...DEFAULT_PROVIDER_RATE_LIMITS.seedream },
     azure: { ...DEFAULT_PROVIDER_RATE_LIMITS.azure },
   };
 
-  for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "minimax", "jimeng", "seedream", "azure"] as Provider[]) {
+  for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "zai", "minimax", "jimeng", "seedream", "azure"] as Provider[]) {
     const envPrefix = `BAOYU_IMAGE_GEN_${provider.toUpperCase()}`;
     const extendLimit = extendConfig.batch?.provider_limits?.[provider];
     configured[provider] = {
@@ -630,6 +648,7 @@ function inferProviderFromModel(model: string | null): Provider | null {
   const normalized = model.trim();
   if (normalized.includes("seedream") || normalized.includes("seededit")) return "seedream";
   if (normalized === "image-01" || normalized === "image-01-live") return "minimax";
+  if (normalized === "glm-image" || normalized === "cogview-4-250304") return "zai";
   return null;
 }
 
@@ -657,6 +676,7 @@ export function detectProvider(args: CliArgs): Provider {
   const hasOpenai = !!process.env.OPENAI_API_KEY;
   const hasOpenrouter = !!process.env.OPENROUTER_API_KEY;
   const hasDashscope = !!process.env.DASHSCOPE_API_KEY;
+  const hasZai = !!(process.env.ZAI_API_KEY || process.env.BIGMODEL_API_KEY);
   const hasMinimax = !!process.env.MINIMAX_API_KEY;
   const hasReplicate = !!process.env.REPLICATE_API_TOKEN;
   const hasJimeng = !!(process.env.JIMENG_ACCESS_KEY_ID && process.env.JIMENG_SECRET_ACCESS_KEY);
@@ -677,6 +697,13 @@ export function detectProvider(args: CliArgs): Provider {
     return "minimax";
   }
 
+  if (modelProvider === "zai") {
+    if (!hasZai) {
+      throw new Error("Model looks like a Z.AI image model, but ZAI_API_KEY is not set.");
+    }
+    return "zai";
+  }
+
   if (args.referenceImages.length > 0) {
     if (hasGoogle) return "google";
     if (hasOpenai) return "openai";
@@ -696,6 +723,7 @@ export function detectProvider(args: CliArgs): Provider {
     hasAzure && "azure",
     hasOpenrouter && "openrouter",
     hasDashscope && "dashscope",
+    hasZai && "zai",
     hasMinimax && "minimax",
     hasReplicate && "replicate",
     hasJimeng && "jimeng",
@@ -706,7 +734,7 @@ export function detectProvider(args: CliArgs): Provider {
   if (available.length > 1) return available[0]!;
 
   throw new Error(
-    "No API key found. Set GOOGLE_API_KEY, GEMINI_API_KEY, OPENAI_API_KEY, AZURE_OPENAI_API_KEY+AZURE_OPENAI_BASE_URL, OPENROUTER_API_KEY, DASHSCOPE_API_KEY, MINIMAX_API_KEY, REPLICATE_API_TOKEN, JIMENG keys, or ARK_API_KEY.\n" +
+    "No API key found. Set GOOGLE_API_KEY, GEMINI_API_KEY, OPENAI_API_KEY, AZURE_OPENAI_API_KEY+AZURE_OPENAI_BASE_URL, OPENROUTER_API_KEY, DASHSCOPE_API_KEY, ZAI_API_KEY, MINIMAX_API_KEY, REPLICATE_API_TOKEN, JIMENG keys, or ARK_API_KEY.\n" +
       "Create ~/.baoyu-skills/.env or <cwd>/.baoyu-skills/.env with your keys."
   );
 }
@@ -738,6 +766,7 @@ export function isRetryableGenerationError(error: unknown): boolean {
     "API error (403)",
     "API error (404)",
     "temporarily disabled",
+    "supports saving exactly one image",
   ];
   return !nonRetryableMarkers.some((marker) => msg.includes(marker));
 }
@@ -745,6 +774,7 @@ export function isRetryableGenerationError(error: unknown): boolean {
 async function loadProviderModule(provider: Provider): Promise<ProviderModule> {
   if (provider === "google") return (await import("./providers/google")) as ProviderModule;
   if (provider === "dashscope") return (await import("./providers/dashscope")) as ProviderModule;
+  if (provider === "zai") return (await import("./providers/zai")) as ProviderModule;
   if (provider === "minimax") return (await import("./providers/minimax")) as ProviderModule;
   if (provider === "replicate") return (await import("./providers/replicate")) as ProviderModule;
   if (provider === "openrouter") return (await import("./providers/openrouter")) as ProviderModule;
@@ -776,6 +806,7 @@ function getModelForProvider(
       return extendConfig.default_model.openrouter;
     }
     if (provider === "dashscope" && extendConfig.default_model.dashscope) return extendConfig.default_model.dashscope;
+    if (provider === "zai" && extendConfig.default_model.zai) return extendConfig.default_model.zai;
     if (provider === "minimax" && extendConfig.default_model.minimax) return extendConfig.default_model.minimax;
     if (provider === "replicate" && extendConfig.default_model.replicate) return extendConfig.default_model.replicate;
     if (provider === "jimeng" && extendConfig.default_model.jimeng) return extendConfig.default_model.jimeng;
@@ -852,6 +883,7 @@ export function createTaskArgs(baseArgs: CliArgs, task: BatchTaskInput, batchDir
     size: task.size ?? baseArgs.size ?? null,
     quality: task.quality ?? baseArgs.quality ?? null,
     imageSize: task.imageSize ?? baseArgs.imageSize ?? null,
+    imageSizeSource: task.imageSize != null ? "task" : (baseArgs.imageSizeSource ?? null),
     referenceImages: task.ref ? task.ref.map((filePath) => resolveBatchPath(batchDir, filePath)) : [],
     n: task.n ?? baseArgs.n,
     batchFile: null,
@@ -1000,7 +1032,7 @@ async function runBatchTasks(
   const acquireProvider = createProviderGate(providerRateLimits);
   const workerCount = getWorkerCount(tasks.length, jobs, maxWorkers);
   console.error(`Batch mode: ${tasks.length} tasks, ${workerCount} workers, parallel mode enabled.`);
-  for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "jimeng", "seedream", "azure"] as Provider[]) {
+  for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "zai", "minimax", "jimeng", "seedream", "azure"] as Provider[]) {
     const limit = providerRateLimits[provider];
     console.error(`- ${provider}: concurrency=${limit.concurrency}, startIntervalMs=${limit.startIntervalMs}`);
   }

skills/baoyu-imagine/scripts/providers/replicate.test.ts

@@ -22,6 +22,7 @@ function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
     size: null,
     quality: null,
     imageSize: null,
+    imageSizeSource: null,
     referenceImages: [],
     n: 1,
     batchFile: null,
@@ -220,6 +221,22 @@ test("Replicate validateArgs blocks misleading multi-output and unsupported fami
     /compatibility list/,
   );
 
+  assert.doesNotThrow(() =>
+    validateArgs(
+      "google/nano-banana-2",
+      makeArgs({ imageSize: "2K", imageSizeSource: "config" }),
+    ),
+  );
+
+  assert.throws(
+    () =>
+      validateArgs(
+        "google/nano-banana-2",
+        makeArgs({ imageSize: "2K", imageSizeSource: "cli" }),
+      ),
+    /do not use --imageSize/,
+  );
+
   assert.doesNotThrow(() =>
     validateArgs(
       "stability-ai/sdxl",

skills/baoyu-imagine/scripts/providers/replicate.ts

@@ -361,7 +361,7 @@ export function validateArgs(model: string, args: CliArgs): void {
     throw new Error("Replicate integration currently supports exactly one output image per request. Remove --n or use --n 1.");
   }
 
-  if (args.imageSize) {
+  if (args.imageSize && args.imageSizeSource !== "config") {
     throw new Error("Replicate models in baoyu-imagine do not use --imageSize. Use --quality, --ar, or --size instead.");
   }
 

skills/baoyu-imagine/scripts/providers/zai.test.ts

@@ -0,0 +1,180 @@
+import assert from "node:assert/strict";
+import test, { type TestContext } from "node:test";
+
+import type { CliArgs } from "../types.ts";
+import {
+  buildRequestBody,
+  buildZaiUrl,
+  extractImageFromResponse,
+  getDefaultModel,
+  getModelFamily,
+  parseAspectRatio,
+  parseSize,
+  resolveSizeForModel,
+  validateArgs,
+} from "./zai.ts";
+
+function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
+  return {
+    prompt: null,
+    promptFiles: [],
+    imagePath: null,
+    provider: null,
+    model: null,
+    aspectRatio: null,
+    size: null,
+    quality: null,
+    imageSize: null,
+    referenceImages: [],
+    n: 1,
+    batchFile: null,
+    jobs: null,
+    json: false,
+    help: false,
+    ...overrides,
+  };
+}
+
+function useEnv(
+  t: TestContext,
+  values: Record<string, string | null>,
+): void {
+  const previous = new Map<string, string | undefined>();
+  for (const [key, value] of Object.entries(values)) {
+    previous.set(key, process.env[key]);
+    if (value == null) {
+      delete process.env[key];
+    } else {
+      process.env[key] = value;
+    }
+  }
+
+  t.after(() => {
+    for (const [key, value] of previous.entries()) {
+      if (value == null) {
+        delete process.env[key];
+      } else {
+        process.env[key] = value;
+      }
+    }
+  });
+}
+
+test("Z.AI default model prefers env override and otherwise uses glm-image", (t) => {
+  useEnv(t, {
+    ZAI_IMAGE_MODEL: null,
+    BIGMODEL_IMAGE_MODEL: null,
+  });
+  assert.equal(getDefaultModel(), "glm-image");
+
+  process.env.BIGMODEL_IMAGE_MODEL = "cogview-4-250304";
+  assert.equal(getDefaultModel(), "cogview-4-250304");
+});
+
+test("Z.AI URL builder normalizes host, v4 base, and full endpoint inputs", (t) => {
+  useEnv(t, { ZAI_BASE_URL: "https://api.z.ai" });
+  assert.equal(buildZaiUrl(), "https://api.z.ai/api/paas/v4/images/generations");
+
+  process.env.ZAI_BASE_URL = "https://proxy.example.com/api/paas/v4/";
+  assert.equal(buildZaiUrl(), "https://proxy.example.com/api/paas/v4/images/generations");
+
+  process.env.ZAI_BASE_URL = "https://proxy.example.com/custom/images/generations";
+  assert.equal(buildZaiUrl(), "https://proxy.example.com/custom/images/generations");
+});
+
+test("Z.AI model family and parsing helpers recognize documented formats", () => {
+  assert.equal(getModelFamily("glm-image"), "glm");
+  assert.equal(getModelFamily("cogview-4-250304"), "legacy");
+  assert.deepEqual(parseAspectRatio("16:9"), { width: 16, height: 9 });
+  assert.equal(parseAspectRatio("wide"), null);
+  assert.deepEqual(parseSize("1280x1280"), { width: 1280, height: 1280 });
+  assert.deepEqual(parseSize("1472*1088"), { width: 1472, height: 1088 });
+  assert.equal(parseSize("big"), null);
+});
+
+test("Z.AI size resolution follows documented recommended ratios and validates custom sizes", () => {
+  assert.equal(
+    resolveSizeForModel("glm-image", makeArgs({ aspectRatio: "16:9", quality: "2k" })),
+    "1728x960",
+  );
+  assert.equal(
+    resolveSizeForModel("cogview-4-250304", makeArgs({ aspectRatio: "4:3", quality: "normal" })),
+    "1152x864",
+  );
+  assert.equal(
+    resolveSizeForModel("glm-image", makeArgs({ size: "1568x1056", quality: "2k" })),
+    "1568x1056",
+  );
+
+  const uncommon = resolveSizeForModel(
+    "glm-image",
+    makeArgs({ aspectRatio: "5:2", quality: "normal" }),
+  );
+  const parsed = parseSize(uncommon);
+  assert.ok(parsed);
+  assert.ok(parsed.width % 32 === 0);
+  assert.ok(parsed.height % 32 === 0);
+  assert.ok(parsed.width * parsed.height <= 2 ** 22);
+
+  assert.throws(
+    () => resolveSizeForModel("glm-image", makeArgs({ size: "1000x1000", quality: "2k" })),
+    /between 1024 and 2048/,
+  );
+  assert.throws(
+    () => resolveSizeForModel("glm-image", makeArgs({ size: "1280x1260", quality: "2k" })),
+    /divisible by 32/,
+  );
+  assert.throws(
+    () => resolveSizeForModel("cogview-4-250304", makeArgs({ size: "2048x2048", quality: "2k" })),
+    /must not exceed 2\^21 total pixels/,
+  );
+});
+
+test("Z.AI validation rejects unsupported refs and multi-image requests", () => {
+  assert.throws(
+    () => validateArgs("glm-image", makeArgs({ referenceImages: ["ref.png"] })),
+    /text-to-image only/,
+  );
+  assert.throws(
+    () => validateArgs("glm-image", makeArgs({ n: 2 })),
+    /single image per request/,
+  );
+});
+
+test("Z.AI request body maps skill quality and resolved size into provider fields", () => {
+  const body = buildRequestBody(
+    "A cinematic science poster",
+    "glm-image",
+    makeArgs({ aspectRatio: "4:3", quality: "normal" }),
+  );
+
+  assert.deepEqual(body, {
+    model: "glm-image",
+    prompt: "A cinematic science poster",
+    quality: "standard",
+    size: "1472x1088",
+  });
+});
+
+test("Z.AI response extraction downloads the returned image URL", async (t) => {
+  const originalFetch = globalThis.fetch;
+  t.after(() => {
+    globalThis.fetch = originalFetch;
+  });
+
+  globalThis.fetch = async () =>
+    new Response(Uint8Array.from([1, 2, 3]), {
+      status: 200,
+      headers: { "Content-Type": "image/png" },
+    });
+
+  const image = await extractImageFromResponse({
+    data: [{ url: "https://cdn.example.com/glm-image.png" }],
+  });
+  assert.deepEqual([...image], [1, 2, 3]);
+
+  await assert.rejects(
+    () => extractImageFromResponse({ data: [{}] }),
+    /No image URL/,
+  );
+});

skills/baoyu-imagine/scripts/providers/zai.ts

@@ -0,0 +1,306 @@
+import type { CliArgs, Quality } from "../types";
+
+type ZaiModelFamily = "glm" | "legacy";
+
+type ZaiRequestBody = {
+  model: string;
+  prompt: string;
+  quality: "hd" | "standard";
+  size: string;
+};
+
+type ZaiResponse = {
+  data?: Array<{ url?: string }>;
+};
+
+const DEFAULT_MODEL = "glm-image";
+const GLM_MAX_PIXELS = 2 ** 22;
+const LEGACY_MAX_PIXELS = 2 ** 21;
+const GLM_SIZE_STEP = 32;
+const LEGACY_SIZE_STEP = 16;
+
+const GLM_RECOMMENDED_SIZES: Record<string, string> = {
+  "1:1": "1280x1280",
+  "3:2": "1568x1056",
+  "2:3": "1056x1568",
+  "4:3": "1472x1088",
+  "3:4": "1088x1472",
+  "16:9": "1728x960",
+  "9:16": "960x1728",
+};
+
+const LEGACY_RECOMMENDED_SIZES: Record<string, string> = {
+  "1:1": "1024x1024",
+  "9:16": "768x1344",
+  "3:4": "864x1152",
+  "16:9": "1344x768",
+  "4:3": "1152x864",
+  "2:1": "1440x720",
+  "1:2": "720x1440",
+};
+
+export function getDefaultModel(): string {
+  return process.env.ZAI_IMAGE_MODEL || process.env.BIGMODEL_IMAGE_MODEL || DEFAULT_MODEL;
+}
+
+function getApiKey(): string | null {
+  return process.env.ZAI_API_KEY || process.env.BIGMODEL_API_KEY || null;
+}
+
+export function buildZaiUrl(): string {
+  const base = (process.env.ZAI_BASE_URL || process.env.BIGMODEL_BASE_URL || "https://api.z.ai/api/paas/v4")
+    .replace(/\/+$/g, "");
+  if (base.endsWith("/images/generations")) return base;
+  if (base.endsWith("/api/paas/v4")) return `${base}/images/generations`;
+  if (base.endsWith("/v4")) return `${base}/images/generations`;
+  return `${base}/api/paas/v4/images/generations`;
+}
+
+export function getModelFamily(model: string): ZaiModelFamily {
+  return model.trim().toLowerCase() === "glm-image" ? "glm" : "legacy";
+}
+
+export function parseAspectRatio(ar: string): { width: number; height: number } | null {
+  const match = ar.match(/^(\d+(?:\.\d+)?):(\d+(?:\.\d+)?)$/);
+  if (!match) return null;
+  const width = Number(match[1]);
+  const height = Number(match[2]);
+  if (!Number.isFinite(width) || !Number.isFinite(height) || width <= 0 || height <= 0) {
+    return null;
+  }
+  return { width, height };
+}
+
+export function parseSize(size: string): { width: number; height: number } | null {
+  const match = size.trim().match(/^(\d+)\s*[xX*]\s*(\d+)$/);
+  if (!match) return null;
+  const width = parseInt(match[1]!, 10);
+  const height = parseInt(match[2]!, 10);
+  if (!Number.isFinite(width) || !Number.isFinite(height) || width <= 0 || height <= 0) {
+    return null;
+  }
+  return { width, height };
+}
+
+function formatSize(width: number, height: number): string {
+  return `${width}x${height}`;
+}
+
+function roundToStep(value: number, step: number): number {
+  return Math.max(step, Math.round(value / step) * step);
+}
+
+function getRatioValue(ar: string): number | null {
+  const parsed = parseAspectRatio(ar);
+  if (!parsed) return null;
+  return parsed.width / parsed.height;
+}
+
+function findClosestRatioKey(ar: string, candidates: string[]): string | null {
+  const targetRatio = getRatioValue(ar);
+  if (targetRatio == null) return null;
+
+  let bestKey: string | null = null;
+  let bestDiff = Infinity;
+  for (const candidate of candidates) {
+    const candidateRatio = getRatioValue(candidate);
+    if (candidateRatio == null) continue;
+    const diff = Math.abs(candidateRatio - targetRatio);
+    if (diff < bestDiff) {
+      bestDiff = diff;
+      bestKey = candidate;
+    }
+  }
+
+  return bestDiff <= 0.05 ? bestKey : null;
+}
+
+function getTargetPixels(quality: Quality): number {
+  return quality === "normal" ? 1024 * 1024 : 1536 * 1536;
+}
+
+function fitToPixelBudget(
+  width: number,
+  height: number,
+  targetPixels: number,
+  maxPixels: number,
+  step: number,
+): { width: number; height: number } {
+  let nextWidth = width;
+  let nextHeight = height;
+  const pixels = nextWidth * nextHeight;
+
+  if (pixels > maxPixels) {
+    const scale = Math.sqrt(maxPixels / pixels);
+    nextWidth *= scale;
+    nextHeight *= scale;
+  } else {
+    const scale = Math.sqrt(targetPixels / pixels);
+    nextWidth *= scale;
+    nextHeight *= scale;
+  }
+
+  let roundedWidth = roundToStep(nextWidth, step);
+  let roundedHeight = roundToStep(nextHeight, step);
+  let roundedPixels = roundedWidth * roundedHeight;
+
+  while (roundedPixels > maxPixels && (roundedWidth > step || roundedHeight > step)) {
+    if (roundedWidth >= roundedHeight && roundedWidth > step) {
+      roundedWidth -= step;
+    } else if (roundedHeight > step) {
+      roundedHeight -= step;
+    } else {
+      break;
+    }
+    roundedPixels = roundedWidth * roundedHeight;
+  }
+
+  return { width: roundedWidth, height: roundedHeight };
+}
+
+function validateCustomSize(
+  size: string,
+  family: ZaiModelFamily,
+): string {
+  const parsed = parseSize(size);
+  if (!parsed) {
+    throw new Error("Z.AI --size must be in WxH format, for example 1280x1280.");
+  }
+
+  const widthStep = family === "glm" ? GLM_SIZE_STEP : LEGACY_SIZE_STEP;
+  const minEdge = family === "glm" ? 1024 : 512;
+  const maxPixels = family === "glm" ? GLM_MAX_PIXELS : LEGACY_MAX_PIXELS;
+
+  if (parsed.width < minEdge || parsed.width > 2048 || parsed.height < minEdge || parsed.height > 2048) {
+    throw new Error(
+      family === "glm"
+        ? "GLM-image custom size requires width and height between 1024 and 2048."
+        : "Z.AI legacy image models require width and height between 512 and 2048."
+    );
+  }
+
+  if (parsed.width % widthStep !== 0 || parsed.height % widthStep !== 0) {
+    throw new Error(
+      family === "glm"
+        ? "GLM-image custom size requires width and height divisible by 32."
+        : "Z.AI legacy image models require width and height divisible by 16."
+    );
+  }
+
+  if (parsed.width * parsed.height > maxPixels) {
+    throw new Error(
+      family === "glm"
+        ? "GLM-image custom size must not exceed 2^22 total pixels."
+        : "Z.AI legacy image size must not exceed 2^21 total pixels."
+    );
+  }
+
+  return formatSize(parsed.width, parsed.height);
+}
+
+export function resolveSizeForModel(
+  model: string,
+  args: Pick<CliArgs, "size" | "aspectRatio" | "quality">,
+): string {
+  const family = getModelFamily(model);
+  const quality = args.quality === "normal" ? "normal" : "2k";
+
+  if (args.size) {
+    return validateCustomSize(args.size, family);
+  }
+
+  const recommended = family === "glm" ? GLM_RECOMMENDED_SIZES : LEGACY_RECOMMENDED_SIZES;
+  const defaultSize = family === "glm" ? "1280x1280" : "1024x1024";
+
+  if (!args.aspectRatio) return defaultSize;
+
+  const recommendedRatio = findClosestRatioKey(args.aspectRatio, Object.keys(recommended));
+  if (recommendedRatio) {
+    return recommended[recommendedRatio]!;
+  }
+
+  const parsedRatio = parseAspectRatio(args.aspectRatio);
+  if (!parsedRatio) return defaultSize;
+
+  const targetPixels = getTargetPixels(quality);
+  const maxPixels = family === "glm" ? GLM_MAX_PIXELS : LEGACY_MAX_PIXELS;
+  const step = family === "glm" ? GLM_SIZE_STEP : LEGACY_SIZE_STEP;
+  const fit = fitToPixelBudget(
+    parsedRatio.width,
+    parsedRatio.height,
+    targetPixels,
+    maxPixels,
+    step,
+  );
+  return formatSize(fit.width, fit.height);
+}
+
+function getZaiQuality(quality: CliArgs["quality"]): "hd" | "standard" {
+  return quality === "normal" ? "standard" : "hd";
+}
+
+export function validateArgs(_model: string, args: CliArgs): void {
+  if (args.referenceImages.length > 0) {
+    throw new Error("Z.AI GLM-image currently supports text-to-image only in baoyu-imagine. Remove --ref or choose another provider.");
+  }
+
+  if (args.n > 1) {
+    throw new Error("Z.AI image generation currently returns a single image per request in baoyu-imagine.");
+  }
+}
+
+export function buildRequestBody(
+  prompt: string,
+  model: string,
+  args: CliArgs,
+): ZaiRequestBody {
+  validateArgs(model, args);
+  return {
+    model,
+    prompt,
+    quality: getZaiQuality(args.quality),
+    size: resolveSizeForModel(model, args),
+  };
+}
+
+export async function extractImageFromResponse(result: ZaiResponse): Promise<Uint8Array> {
+  const url = result.data?.[0]?.url;
+  if (!url) {
+    throw new Error("No image URL in Z.AI response");
+  }
+
+  const imageResponse = await fetch(url);
+  if (!imageResponse.ok) {
+    throw new Error(`Failed to download image from Z.AI: ${imageResponse.status}`);
+  }
+
+  return new Uint8Array(await imageResponse.arrayBuffer());
+}
+
+export async function generateImage(
+  prompt: string,
+  model: string,
+  args: CliArgs,
+): Promise<Uint8Array> {
+  const apiKey = getApiKey();
+  if (!apiKey) {
+    throw new Error("ZAI_API_KEY is required. Get one from https://docs.z.ai/.");
+  }
+
+  const response = await fetch(buildZaiUrl(), {
+    method: "POST",
+    headers: {
+      "Content-Type": "application/json",
+      Authorization: `Bearer ${apiKey}`,
+    },
+    body: JSON.stringify(buildRequestBody(prompt, model, args)),
+  });
+
+  if (!response.ok) {
+    const err = await response.text();
+    throw new Error(`Z.AI API error (${response.status}): ${err}`);
+  }
+
+  const result = (await response.json()) as ZaiResponse;
+  return extractImageFromResponse(result);
+}

skills/baoyu-imagine/scripts/types.ts

@@ -3,6 +3,7 @@ export type Provider =
   | "openai"
   | "openrouter"
   | "dashscope"
+  | "zai"
   | "minimax"
   | "replicate"
   | "jimeng"
@@ -20,6 +21,7 @@ export type CliArgs = {
   size: string | null;
   quality: Quality | null;
   imageSize: string | null;
+  imageSizeSource?: "cli" | "task" | "config" | null;
   referenceImages: string[];
   n: number;
   batchFile: string | null;
@@ -61,6 +63,7 @@ export type ExtendConfig = {
     openai: string | null;
     openrouter: string | null;
     dashscope: string | null;
+    zai: string | null;
     minimax: string | null;
     replicate: string | null;
     jimeng: string | null;