@agnic/wallet-skills 1.3.0 → 1.3.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@agnic/wallet-skills",
3
- "version": "1.3.0",
3
+ "version": "1.3.1",
4
4
  "description": "Vercel AI SDK skills for AgnicPay wallet — balance, payments, trading, x402, and agent identity",
5
5
  "keywords": [
6
6
  "agnic",
@@ -95,7 +95,7 @@ npx agnic@latest ai image --prompt 'Logo design' --aspect-ratio 16:9 --output lo
95
95
  ```
96
96
 
97
97
  340+ models from OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, and more.
98
- Model format: `provider/model-name` (e.g., `openai/gpt-4o`, `google/gemini-2.0-flash`)
98
+ Model format: `provider/model-name` (e.g., `openai/gpt-4o`, `google/gemini-2.5-flash-image`)
99
99
  Free models: `meta-llama/*`, `google/gemma-*`, `mistralai/*`
100
100
 
101
101
  ### Workflow: Sign Up + Pay + Report
@@ -46,7 +46,7 @@ Models use `provider/model-name` format:
46
46
  | ----------- | ----------------------------------------- |
47
47
  | openai | `openai/gpt-4o`, `openai/gpt-4-turbo` |
48
48
  | anthropic | `anthropic/claude-3.5-sonnet` |
49
- | google | `google/gemini-2.0-flash`, `google/gemma-*` |
49
+ | google | `google/gemini-2.5-flash-image`, `google/gemma-*` |
50
50
  | meta-llama | `meta-llama/llama-3.3-70b` |
51
51
  | mistralai | `mistralai/mistral-large-latest` |
52
52
  | deepseek | `deepseek/deepseek-chat` |
@@ -79,7 +79,7 @@ Free models: `meta-llama/*`, `google/gemma-*`, `mistralai/*`
79
79
  | Option | Description |
80
80
  | ------------------------- | ---------------------------------------- |
81
81
  | `--prompt <text>` | Image description (required) |
82
- | `--model <id>` | Model (default: google/gemini-2.0-flash) |
82
+ | `--model <id>` | Model (default: google/gemini-2.5-flash-image) |
83
83
  | `--aspect-ratio <ratio>` | 1:1, 16:9, 9:16, 4:3, 3:2 (default: 1:1)|
84
84
  | `--output <path>` | Save image to file |
85
85
  | `--json` | Output as JSON |
@@ -123,6 +123,10 @@ npx agnic@latest ai image --prompt 'A sunset over mountains' --output sunset.png
123
123
  # Generate widescreen image
124
124
  npx agnic@latest ai image --prompt 'Cyberpunk cityscape' --aspect-ratio 16:9 --output city.png
125
125
 
126
+ # Use a specific image model
127
+ npx agnic@latest ai image --prompt 'A portrait painting' --model openai/gpt-5-image --output portrait.png
128
+ npx agnic@latest ai image --prompt 'Abstract art' --model black-forest-labs/flux.2-max --output art.png
129
+
126
130
  # Get image as JSON (base64)
127
131
  npx agnic@latest ai image --prompt 'Logo design for a tech startup' --json
128
132
  ```
@@ -131,7 +135,13 @@ npx agnic@latest ai image --prompt 'Logo design for a tech startup' --json
131
135
 
132
136
  - Must be authenticated (`npx agnic@latest status` to check)
133
137
  - Wallet must have USDC balance (free models available for testing)
134
- - Image generation requires a model with image output support (default: google/gemini-2.0-flash)
138
+ - Image generation models:
139
+ - `google/gemini-2.5-flash-image` (default) — fast, good quality
140
+ - `google/gemini-3-pro-image-preview` — highest quality Google model
141
+ - `google/gemini-3.1-flash-image-preview` — latest flash preview
142
+ - `openai/gpt-5-image` — OpenAI image generation
143
+ - `black-forest-labs/flux.2-max` — Flux high quality
144
+ - `black-forest-labs/flux.2-klein-4b` — Flux lightweight/fast
135
145
 
136
146
  ## Error Handling
137
147