1---
2name: preferences-schema
3description: EXTEND.md YAML schema for baoyu-image-gen user preferences
4---
5 
6# Preferences Schema
7 
8## Full Schema
9 
10```yaml
11---
12version: 1
13 
14default_provider: null      # google|openai|azure|openrouter|dashscope|zai|minimax|replicate|jimeng|seedream|codex-cli|agnes|null (null = auto-detect; codex-cli is never auto-detected — pin it here or via --provider)
15 
16default_quality: null       # normal|2k|null (null = use default: 2k)
17 
18default_aspect_ratio: null  # "16:9"|"1:1"|"4:3"|"3:4"|"2.35:1"|null
19 
20default_image_size: null    # 1K|2K|4K|null (Google/OpenRouter, overrides quality)
21 
22default_image_api_dialect: null  # openai-native|ratio-metadata|null (OpenAI-compatible gateways; null = use env/default)
23 
24default_model:
25  google: null              # e.g., "gemini-3-pro-image", "gemini-3.1-flash-image"
26  openai: null              # e.g., "gpt-image-2", "gpt-image-1.5", "gpt-image-1"
27  azure: null               # Azure deployment name, e.g., "gpt-image-2" or "image-prod"
28  openrouter: null          # e.g., "google/gemini-3.1-flash-image"
29  dashscope: null           # e.g., "qwen-image-2.0-pro"
30  zai: null                 # e.g., "glm-image"
31  minimax: null             # e.g., "image-01"
32  replicate: null           # e.g., "google/nano-banana-2"
33  codex-cli: null           # Logical label only — Codex image_gen has no user-selectable model. Default: "codex-image-gen"
34  agnes: null               # e.g., "agnes-image-2.1-flash"
35 
36batch:
37  max_workers: 10
38  provider_limits:
39    replicate:
40      concurrency: 5
41      start_interval_ms: 700
42    google:
43      concurrency: 3
44      start_interval_ms: 1100
45    openai:
46      concurrency: 3
47      start_interval_ms: 1100
48    azure:
49      concurrency: 3
50      start_interval_ms: 1100
51    openrouter:
52      concurrency: 3
53      start_interval_ms: 1100
54    dashscope:
55      concurrency: 3
56      start_interval_ms: 1100
57    zai:
58      concurrency: 3
59      start_interval_ms: 1100
60    minimax:
61      concurrency: 3
62      start_interval_ms: 1100
63    codex-cli:
64      concurrency: 1
65      start_interval_ms: 2000
66    agnes:
67      concurrency: 3
68      start_interval_ms: 1100
69---
70```
71 
72## Field Reference
73 
74| Field | Type | Default | Description |
75|-------|------|---------|-------------|
76| `version` | int | 1 | Schema version |
77| `default_provider` | string\|null | null | Default provider (null = auto-detect) |
78| `default_quality` | string\|null | null | Default quality (null = 2k) |
79| `default_aspect_ratio` | string\|null | null | Default aspect ratio |
80| `default_image_size` | string\|null | null | Google/OpenRouter image size (overrides quality) |
81| `default_image_api_dialect` | string\|null | null | OpenAI-compatible image dialect (`openai-native` or `ratio-metadata`) |
82| `default_model.google` | string\|null | null | Google default model |
83| `default_model.openai` | string\|null | null | OpenAI default model |
84| `default_model.azure` | string\|null | null | Azure default deployment name |
85| `default_model.openrouter` | string\|null | null | OpenRouter default model |
86| `default_model.dashscope` | string\|null | null | DashScope default model |
87| `default_model.zai` | string\|null | null | Z.AI default model |
88| `default_model.minimax` | string\|null | null | MiniMax default model |
89| `default_model.replicate` | string\|null | null | Replicate default model |
90| `default_model.codex-cli` | string\|null | null | Codex-CLI logical label (Codex image_gen has no user-selectable model) |
91| `default_model.agnes` | string\|null | null | Agnes default model |
92| `batch.max_workers` | int\|null | 10 | Batch worker cap |
93| `batch.provider_limits.<provider>.concurrency` | int\|null | provider default | Max simultaneous requests per provider |
94| `batch.provider_limits.<provider>.start_interval_ms` | int\|null | provider default | Minimum gap between request starts per provider |
95 
96## Examples
97 
98**Minimal**:
99```yaml
100---
101version: 1
102default_provider: google
103default_quality: 2k
104default_image_api_dialect: null
105---
106```
107 
108**Full**:
109```yaml
110---
111version: 1
112default_provider: google
113default_quality: 2k
114default_aspect_ratio: "16:9"
115default_image_size: 2K
116default_image_api_dialect: null
117default_model:
118  google: "gemini-3-pro-image"
119  openai: "gpt-image-2"
120  azure: "gpt-image-2"
121  openrouter: "google/gemini-3.1-flash-image"
122  dashscope: "qwen-image-2.0-pro"
123  zai: "glm-image"
124  minimax: "image-01"
125  replicate: "google/nano-banana-2"
126  agnes: "agnes-image-2.1-flash"
127batch:
128  max_workers: 10
129  provider_limits:
130    replicate:
131      concurrency: 5
132      start_interval_ms: 700
133    azure:
134      concurrency: 3
135      start_interval_ms: 1100
136    zai:
137      concurrency: 3
138      start_interval_ms: 1100
139    openrouter:
140      concurrency: 3
141      start_interval_ms: 1100
142    minimax:
143      concurrency: 3
144      start_interval_ms: 1100
145    agnes:
146      concurrency: 3
147      start_interval_ms: 1100
148---
149```
150