chore: release v1.36.0

- Add gemini-3.1-flash-image-preview to supported Google multimodal models
- Improve preferences loading with blocking first-time setup flow
- Add first-time-setup.md reference for guided configuration
- Update model references in SKILL.md and preferences schema

.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Skills shared by Baoyu for improving daily work efficiency",
-    "version": "1.35.0"
+    "version": "1.36.0"
   },
   "plugins": [
     {

CHANGELOG.md

@@ -2,6 +2,15 @@
 
 English | [中文](./CHANGELOG.zh.md)
 
+## 1.36.0 - 2026-02-27
+
+### Features
+- `baoyu-image-gen`: add `gemini-3.1-flash-image-preview` model support for Google multimodal image generation
+- `baoyu-image-gen`: improve first-time setup with blocking preferences flow and guided configuration
+
+### Fixes
+- `baoyu-image-gen`: use curl fallback for Google API when HTTP proxy is detected (by @liye71023326)
+
 ## 1.35.0 - 2026-02-24
 
 ### Features

CHANGELOG.zh.md

@@ -2,6 +2,15 @@
 
 [English](./CHANGELOG.md) | 中文
 
+## 1.36.0 - 2026-02-27
+
+### 新功能
+- `baoyu-image-gen`：新增 `gemini-3.1-flash-image-preview` Google 多模态图片生成模型支持
+- `baoyu-image-gen`：优化首次使用引导流程，支持阻塞式偏好配置
+
+### 修复
+- `baoyu-image-gen`：检测到 HTTP 代理时自动回退使用 curl 调用 Google API (by @liye71023326)
+
 ## 1.35.0 - 2026-02-24
 
 ### 新功能

skills/baoyu-image-gen/SKILL.md

@@ -13,33 +13,28 @@ Official API-based image generation. Supports OpenAI, Google, DashScope (阿里
 1. `SKILL_DIR` = this SKILL.md file's directory
 2. Script path = `${SKILL_DIR}/scripts/main.ts`
 
-## Preferences (EXTEND.md)
+## Step 0: Load Preferences ⛔ BLOCKING
 
-Use Bash to check EXTEND.md existence (priority order):
+**CRITICAL**: This step MUST complete BEFORE any image generation. Do NOT skip or defer.
+
+Check EXTEND.md existence (priority: project → user):
 
 ```bash
-# Check project-level first
 test -f .baoyu-skills/baoyu-image-gen/EXTEND.md && echo "project"
-
-# Then user-level (cross-platform: $HOME works on macOS/Linux/WSL)
 test -f "$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md" && echo "user"
 ```
 
-┌──────────────────────────────────────────────────┬───────────────────┐
-│                       Path                       │     Location      │
-├──────────────────────────────────────────────────┼───────────────────┤
-│ .baoyu-skills/baoyu-image-gen/EXTEND.md          │ Project directory │
-├──────────────────────────────────────────────────┼───────────────────┤
-│ $HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md    │ User home         │
-└──────────────────────────────────────────────────┴───────────────────┘
+| Result | Action |
+|--------|--------|
+| Found | Load, parse, apply settings. If `default_model.[provider]` is null → ask model only (Flow 2) |
+| Not found | ⛔ Run first-time setup ([references/config/first-time-setup.md](references/config/first-time-setup.md)) → Save EXTEND.md → Then continue |
 
-┌───────────┬───────────────────────────────────────────────────────────────────────────┐
-│  Result   │                                  Action                                   │
-├───────────┼───────────────────────────────────────────────────────────────────────────┤
-│ Found     │ Read, parse, apply settings                                               │
-├───────────┼───────────────────────────────────────────────────────────────────────────┤
-│ Not found │ Use defaults                                                              │
-└───────────┴───────────────────────────────────────────────────────────────────────────┘
+**CRITICAL**: If not found, complete the full setup (provider + model + quality + save location) using AskUserQuestion BEFORE generating any images. Generation is BLOCKED until EXTEND.md is created.
+
+| Path | Location |
+|------|----------|
+| `.baoyu-skills/baoyu-image-gen/EXTEND.md` | Project directory |
+| `$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md` | User home |
 
 **EXTEND.md Supports**: Default provider | Default quality | Default aspect ratio | Default image size | Default models
 
@@ -87,12 +82,12 @@ npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "A cat" --image out.png --provi
 | `--promptfiles <files...>` | Read prompt from files (concatenated) |
 | `--image <path>` | Output image path (required) |
 | `--provider google\|openai\|dashscope\|replicate` | Force provider (default: google) |
-| `--model <id>`, `-m` | Model ID (`--ref` with OpenAI requires GPT Image model, e.g. `gpt-image-1.5`) |
+| `--model <id>`, `-m` | Model ID (Google: `gemini-3-pro-image-preview`, `gemini-3.1-flash-image-preview`; OpenAI: `gpt-image-1.5`) |
 | `--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) |
 | `--imageSize 1K\|2K\|4K` | Image size for Google (default: from quality) |
-| `--ref <files...>` | Reference images. Supported by Google multimodal and OpenAI edits (GPT Image models). If provider omitted: Google first, then OpenAI |
+| `--ref <files...>` | Reference images. Supported by Google multimodal (`gemini-3-pro-image-preview`, `gemini-3-flash-preview`, `gemini-3.1-flash-image-preview`) and OpenAI edits (GPT Image models). If provider omitted: Google first, then OpenAI |
 | `--n <count>` | Number of images |
 | `--json` | JSON output |
 
@@ -194,7 +189,7 @@ Supported: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `2.35:1`
 - Missing API key → error with setup instructions
 - Generation failure → auto-retry once
 - Invalid aspect ratio → warning, proceed with default
-- Reference images with unsupported provider/model → error with fix hint (switch to Google multimodal or OpenAI GPT Image edits)
+- Reference images with unsupported provider/model → error with fix hint (switch to Google multimodal: `gemini-3-pro-image-preview`, `gemini-3.1-flash-image-preview`; or OpenAI GPT Image edits)
 
 ## Extension Support
 

skills/baoyu-image-gen/references/config/first-time-setup.md

@@ -0,0 +1,197 @@
+---
+name: first-time-setup
+description: First-time setup and default model selection flow for baoyu-image-gen
+---
+
+# First-Time Setup
+
+## Overview
+
+Triggered when:
+1. No EXTEND.md found → full setup (provider + model + preferences)
+2. EXTEND.md found but `default_model.[provider]` is null → model selection only
+
+## Setup Flow
+
+```
+No EXTEND.md found          EXTEND.md found, model null
+        │                            │
+        ▼                            ▼
+┌─────────────────────┐    ┌──────────────────────┐
+│ AskUserQuestion     │    │ AskUserQuestion      │
+│ (full setup)        │    │ (model only)         │
+└─────────────────────┘    └──────────────────────┘
+        │                            │
+        ▼                            ▼
+┌─────────────────────┐    ┌──────────────────────┐
+│ Create EXTEND.md    │    │ Update EXTEND.md     │
+└─────────────────────┘    └──────────────────────┘
+        │                            │
+        ▼                            ▼
+    Continue                     Continue
+```
+
+## Flow 1: No EXTEND.md (Full Setup)
+
+**Language**: Use user's input language or saved language preference.
+
+Use AskUserQuestion with ALL questions in ONE call:
+
+### Question 1: Default Provider
+
+```yaml
+header: "Provider"
+question: "Default image generation provider?"
+options:
+  - label: "Google (Recommended)"
+    description: "Gemini multimodal - high quality, reference images, flexible sizes"
+  - label: "OpenAI"
+    description: "GPT Image - consistent quality, reliable output"
+  - label: "DashScope"
+    description: "Alibaba Cloud - z-image-turbo, good for Chinese content"
+  - label: "Replicate"
+    description: "Community models - nano-banana-pro, flexible model selection"
+```
+
+### Question 2: Default Google Model
+
+Only show if user selected Google or auto-detect (no explicit provider).
+
+```yaml
+header: "Google Model"
+question: "Default Google image generation model?"
+options:
+  - label: "gemini-3-pro-image-preview (Recommended)"
+    description: "Highest quality, best for production use"
+  - label: "gemini-3.1-flash-image-preview"
+    description: "Fast generation, good quality, lower cost"
+  - label: "gemini-3-flash-preview"
+    description: "Fast generation, balanced quality and speed"
+```
+
+### Question 3: Default Quality
+
+```yaml
+header: "Quality"
+question: "Default image quality?"
+options:
+  - label: "2k (Recommended)"
+    description: "2048px - covers, illustrations, infographics"
+  - label: "normal"
+    description: "1024px - quick previews, drafts"
+```
+
+### Question 4: Save Location
+
+```yaml
+header: "Save"
+question: "Where to save preferences?"
+options:
+  - label: "Project (Recommended)"
+    description: ".baoyu-skills/ (this project only)"
+  - label: "User"
+    description: "~/.baoyu-skills/ (all projects)"
+```
+
+### Save Locations
+
+| Choice | Path | Scope |
+|--------|------|-------|
+| Project | `.baoyu-skills/baoyu-image-gen/EXTEND.md` | Current project |
+| User | `$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md` | All projects |
+
+### EXTEND.md Template
+
+```yaml
+---
+version: 1
+default_provider: [selected provider or null]
+default_quality: [selected quality]
+default_aspect_ratio: null
+default_image_size: null
+default_model:
+  google: [selected google model or null]
+  openai: null
+  dashscope: null
+  replicate: null
+---
+```
+
+## Flow 2: EXTEND.md Exists, Model Null
+
+When EXTEND.md exists but `default_model.[current_provider]` is null, ask ONLY the model question for the current provider.
+
+### Google Model Selection
+
+```yaml
+header: "Google Model"
+question: "Choose a default Google image generation model?"
+options:
+  - label: "gemini-3-pro-image-preview (Recommended)"
+    description: "Highest quality, best for production use"
+  - label: "gemini-3.1-flash-image-preview"
+    description: "Fast generation, good quality, lower cost"
+  - label: "gemini-3-flash-preview"
+    description: "Fast generation, balanced quality and speed"
+```
+
+### OpenAI Model Selection
+
+```yaml
+header: "OpenAI Model"
+question: "Choose a default OpenAI image generation model?"
+options:
+  - label: "gpt-image-1.5 (Recommended)"
+    description: "Latest GPT Image model, high quality"
+  - label: "gpt-image-1"
+    description: "Previous generation GPT Image model"
+```
+
+### DashScope Model Selection
+
+```yaml
+header: "DashScope Model"
+question: "Choose a default DashScope image generation model?"
+options:
+  - label: "z-image-turbo (Recommended)"
+    description: "Fast generation, good quality"
+  - label: "z-image-ultra"
+    description: "Higher quality, slower generation"
+```
+
+### Replicate Model Selection
+
+```yaml
+header: "Replicate Model"
+question: "Choose a default Replicate image generation model?"
+options:
+  - label: "google/nano-banana-pro (Recommended)"
+    description: "Google's fast image model on Replicate"
+  - label: "google/nano-banana"
+    description: "Google's base image model on Replicate"
+```
+
+### Update EXTEND.md
+
+After user selects a model:
+
+1. Read existing EXTEND.md
+2. If `default_model:` section exists → update the provider-specific key
+3. If `default_model:` section missing → add the full section:
+
+```yaml
+default_model:
+  google: [value or null]
+  openai: [value or null]
+  dashscope: [value or null]
+  replicate: [value or null]
+```
+
+Only set the selected provider's model; leave others as their current value or null.
+
+## After Setup
+
+1. Create directory if needed
+2. Write/update EXTEND.md with frontmatter
+3. Confirm: "Preferences saved to [path]"
+4. Continue with image generation

skills/baoyu-image-gen/references/config/preferences-schema.md

@@ -20,7 +20,7 @@ default_aspect_ratio: null  # "16:9"|"1:1"|"4:3"|"3:4"|"2.35:1"|null
 default_image_size: null    # 1K|2K|4K|null (Google only, overrides quality)
 
 default_model:
-  google: null              # e.g., "gemini-3-pro-image-preview"
+  google: null              # e.g., "gemini-3-pro-image-preview", "gemini-3.1-flash-image-preview"
   openai: null              # e.g., "gpt-image-1.5"
   dashscope: null           # e.g., "z-image-turbo"
   replicate: null           # e.g., "google/nano-banana-pro"

skills/baoyu-image-gen/scripts/providers/google.ts

@@ -1,9 +1,17 @@
 import path from "node:path";
 import { readFile } from "node:fs/promises";
+import { execSync } from "node:child_process";
 import type { CliArgs } from "../types";
 
-const GOOGLE_MULTIMODAL_MODELS = ["gemini-3-pro-image-preview", "gemini-3-flash-preview"];
-const GOOGLE_IMAGEN_MODELS = ["imagen-3.0-generate-002", "imagen-3.0-generate-001"];
+const GOOGLE_MULTIMODAL_MODELS = [
+  "gemini-3-pro-image-preview",
+  "gemini-3-flash-preview",
+  "gemini-3.1-flash-image-preview",
+];
+const GOOGLE_IMAGEN_MODELS = [
+  "imagen-3.0-generate-002",
+  "imagen-3.0-generate-001",
+];
 
 export function getDefaultModel(): string {
   return process.env.GOOGLE_IMAGE_MODEL || "gemini-3-pro-image-preview";
@@ -33,7 +41,8 @@ function getGoogleImageSize(args: CliArgs): "1K" | "2K" | "4K" {
 }
 
 function getGoogleBaseUrl(): string {
-  const base = process.env.GOOGLE_BASE_URL || "https://generativelanguage.googleapis.com";
+  const base =
+    process.env.GOOGLE_BASE_URL || "https://generativelanguage.googleapis.com";
   return base.replace(/\/+$/g, "");
 }
 
@@ -49,11 +58,46 @@ function toModelPath(model: string): string {
   return `models/${modelId}`;
 }
 
-async function postGoogleJson<T>(pathname: string, body: unknown): Promise<T> {
-  const apiKey = getGoogleApiKey();
-  if (!apiKey) throw new Error("GOOGLE_API_KEY or GEMINI_API_KEY is required");
+function getHttpProxy(): string | null {
+  return (
+    process.env.https_proxy ||
+    process.env.HTTPS_PROXY ||
+    process.env.http_proxy ||
+    process.env.HTTP_PROXY ||
+    process.env.ALL_PROXY ||
+    null
+  );
+}
 
-  const res = await fetch(buildGoogleUrl(pathname), {
+async function postGoogleJsonViaCurl<T>(
+  url: string,
+  apiKey: string,
+  body: unknown,
+): Promise<T> {
+  const proxy = getHttpProxy();
+  const bodyStr = JSON.stringify(body);
+  const proxyArgs = proxy ? `-x "${proxy}"` : "";
+
+  const result = execSync(
+    `curl -s --connect-timeout 30 --max-time 300 ${proxyArgs} "${url}" -H "Content-Type: application/json" -H "x-goog-api-key: ${apiKey}" -d @-`,
+    { input: bodyStr, maxBuffer: 100 * 1024 * 1024, timeout: 310000 },
+  );
+
+  const parsed = JSON.parse(result.toString()) as any;
+  if (parsed.error) {
+    throw new Error(
+      `Google API error (${parsed.error.code}): ${parsed.error.message}`,
+    );
+  }
+  return parsed as T;
+}
+
+async function postGoogleJsonViaFetch<T>(
+  url: string,
+  apiKey: string,
+  body: unknown,
+): Promise<T> {
+  const res = await fetch(url, {
     method: "POST",
     headers: {
       "Content-Type": "application/json",
@@ -70,7 +114,30 @@ async function postGoogleJson<T>(pathname: string, body: unknown): Promise<T> {
   return (await res.json()) as T;
 }
 
-function buildPromptWithAspect(prompt: string, ar: string | null, quality: CliArgs["quality"]): string {
+async function postGoogleJson<T>(pathname: string, body: unknown): Promise<T> {
+  const apiKey = getGoogleApiKey();
+  if (!apiKey) throw new Error("GOOGLE_API_KEY or GEMINI_API_KEY is required");
+
+  const url = buildGoogleUrl(pathname);
+  const proxy = getHttpProxy();
+
+  // When an HTTP proxy is detected, use curl instead of fetch.
+  // Bun's fetch has a known issue where long-lived connections through
+  // HTTP proxies get their sockets closed unexpectedly, causing image
+  // generation requests to fail with "socket connection was closed
+  // unexpectedly". Using curl as the HTTP client works around this.
+  if (proxy) {
+    return postGoogleJsonViaCurl<T>(url, apiKey, body);
+  }
+
+  return postGoogleJsonViaFetch<T>(url, apiKey, body);
+}
+
+function buildPromptWithAspect(
+  prompt: string,
+  ar: string | null,
+  quality: CliArgs["quality"],
+): string {
   let result = prompt;
   if (ar) {
     result += ` Aspect ratio: ${ar}.`;
@@ -86,7 +153,9 @@ function addAspectRatioToPrompt(prompt: string, ar: string | null): string {
   return `${prompt} Aspect ratio: ${ar}.`;
 }
 
-async function readImageAsBase64(p: string): Promise<{ data: string; mimeType: string }> {
+async function readImageAsBase64(
+  p: string,
+): Promise<{ data: string; mimeType: string }> {
   const buf = await readFile(p);
   const ext = path.extname(p).toLowerCase();
   let mimeType = "image/png";
@@ -97,7 +166,9 @@ async function readImageAsBase64(p: string): Promise<{ data: string; mimeType: s
 }
 
 function extractInlineImageData(response: {
-  candidates?: Array<{ content?: { parts?: Array<{ inlineData?: { data?: string } }> } }>;
+  candidates?: Array<{
+    content?: { parts?: Array<{ inlineData?: { data?: string } }> };
+  }>;
 }): string | null {
   for (const candidate of response.candidates || []) {
     for (const part of candidate.content?.parts || []) {
@@ -112,16 +183,21 @@ function extractPredictedImageData(response: {
   predictions?: Array<any>;
   generatedImages?: Array<any>;
 }): string | null {
-  const candidates = [...(response.predictions || []), ...(response.generatedImages || [])];
+  const candidates = [
+    ...(response.predictions || []),
+    ...(response.generatedImages || []),
+  ];
   for (const candidate of candidates) {
     if (!candidate || typeof candidate !== "object") continue;
     if (typeof candidate.imageBytes === "string") return candidate.imageBytes;
-    if (typeof candidate.bytesBase64Encoded === "string") return candidate.bytesBase64Encoded;
+    if (typeof candidate.bytesBase64Encoded === "string")
+      return candidate.bytesBase64Encoded;
     if (typeof candidate.data === "string") return candidate.data;
     const image = candidate.image;
     if (image && typeof image === "object") {
       if (typeof image.imageBytes === "string") return image.imageBytes;
-      if (typeof image.bytesBase64Encoded === "string") return image.bytesBase64Encoded;
+      if (typeof image.bytesBase64Encoded === "string")
+        return image.bytesBase64Encoded;
       if (typeof image.data === "string") return image.data;
     }
   }
@@ -131,10 +207,13 @@ function extractPredictedImageData(response: {
 async function generateWithGemini(
   prompt: string,
   model: string,
-  args: CliArgs
+  args: CliArgs,
 ): Promise<Uint8Array> {
   const promptWithAspect = addAspectRatioToPrompt(prompt, args.aspectRatio);
-  const parts: Array<{ text?: string; inlineData?: { data: string; mimeType: string } }> = [];
+  const parts: Array<{
+    text?: string;
+    inlineData?: { data: string; mimeType: string };
+  }> = [];
   for (const refPath of args.referenceImages) {
     const { data, mimeType } = await readImageAsBase64(refPath);
     parts.push({ inlineData: { data, mimeType } });
@@ -147,7 +226,9 @@ async function generateWithGemini(
 
   console.log("Generating image with Gemini...", imageConfig);
   const response = await postGoogleJson<{
-    candidates?: Array<{ content?: { parts?: Array<{ inlineData?: { data?: string } }> } }>;
+    candidates?: Array<{
+      content?: { parts?: Array<{ inlineData?: { data?: string } }> };
+    }>;
   }>(`${toModelPath(model)}:generateContent`, {
     contents: [
       {
@@ -171,12 +252,18 @@ async function generateWithGemini(
 async function generateWithImagen(
   prompt: string,
   model: string,
-  args: CliArgs
+  args: CliArgs,
 ): Promise<Uint8Array> {
-  const fullPrompt = buildPromptWithAspect(prompt, args.aspectRatio, args.quality);
+  const fullPrompt = buildPromptWithAspect(
+    prompt,
+    args.aspectRatio,
+    args.quality,
+  );
   const imageSize = getGoogleImageSize(args);
   if (imageSize === "4K") {
-    console.error("Warning: Imagen models do not support 4K imageSize, using 2K instead.");
+    console.error(
+      "Warning: Imagen models do not support 4K imageSize, using 2K instead.",
+    );
   }
 
   const parameters: Record<string, unknown> = {
@@ -212,12 +299,12 @@ async function generateWithImagen(
 export async function generateImage(
   prompt: string,
   model: string,
-  args: CliArgs
+  args: CliArgs,
 ): Promise<Uint8Array> {
   if (isGoogleImagen(model)) {
     if (args.referenceImages.length > 0) {
       throw new Error(
-        "Reference images are not supported with Imagen models. Use gemini-3-pro-image-preview or gemini-3-flash-preview."
+        "Reference images are not supported with Imagen models. Use gemini-3-pro-image-preview, gemini-3-flash-preview, or gemini-3.1-flash-image-preview.",
       );
     }
     return generateWithImagen(prompt, model, args);
@@ -225,7 +312,7 @@ export async function generateImage(
 
   if (!isGoogleMultimodal(model) && args.referenceImages.length > 0) {
     throw new Error(
-      "Reference images are only supported with Gemini multimodal models. Use gemini-3-pro-image-preview or gemini-3-flash-preview."
+      "Reference images are only supported with Gemini multimodal models. Use gemini-3-pro-image-preview, gemini-3-flash-preview, or gemini-3.1-flash-image-preview.",
     );
   }