高物
ae014ac881
Replace uses of the legacy `gpt-image-2-all` model with `gpt-image-2` and standardize image workflows: no-reference generation uses POST /v1/images/generations, any-reference flows use POST /v1/images/edits with multipart `image` parts. Update SKILLs, generation scripts, decision logs, and docs to reflect the contract change and edits-vs-generations guidance. Apply corresponding changes across backend (api-server match3d/puzzle modules, openai image adapter, mappers, telemetry, spacetime client/module), frontend components and services (Match3D, Puzzle, CreativeImageInputPanel, runtime shells), and add new spritesheet/parser files and tests. Also add media/logo.png. These changes align repository code and documentation with the VectorEngine image API contract and update generation/upload handling (green-screen -> alpha processing, spritesheet handling, and related tests).
98 lines
3.5 KiB
Markdown
98 lines
3.5 KiB
Markdown
---
|
|
name: gpt-image-2-apimart
|
|
description: Generate or inspect project image assets through this repository's VectorEngine gpt-image-2 workflow. Use when Codex needs to create puzzle template sample images, reproduce the server-rs gpt-image-2 request body, dry-run image prompts, batch-generate local project thumbnails, or debug VECTOR_ENGINE_BASE_URL / VECTOR_ENGINE_API_KEY image-generation configuration without exposing secrets. The directory name is historical.
|
|
---
|
|
|
|
# gpt-image-2 VectorEngine
|
|
|
|
Use this skill for project-local image asset generation that must match the repository's `server-rs` VectorEngine `gpt-image-2` path. The folder still contains `apimart` in its name for compatibility with existing local plugin references.
|
|
|
|
## Workflow
|
|
|
|
1. Read the local task and decide whether the image is project-bound.
|
|
2. Prefer `scripts/generate-template-samples.mjs` for puzzle template thumbnails or small batches.
|
|
3. Run dry-run first:
|
|
|
|
```powershell
|
|
node .codex/skills/gpt-image-2-apimart/scripts/generate-template-samples.mjs --dry-run
|
|
```
|
|
|
|
4. If dry-run looks correct and the user asked for real assets, run live generation with a small limit:
|
|
|
|
```powershell
|
|
node .codex/skills/gpt-image-2-apimart/scripts/generate-template-samples.mjs --live --limit 6
|
|
```
|
|
|
|
5. Save final project assets under `public/` or another explicitly requested workspace path.
|
|
6. Never print `VECTOR_ENGINE_API_KEY`. Report only whether configuration exists.
|
|
|
|
## Request Contract
|
|
|
|
The repository image path uses:
|
|
|
|
```text
|
|
POST {VECTOR_ENGINE_BASE_URL}/v1/images/generations
|
|
Authorization: Bearer {VECTOR_ENGINE_API_KEY}
|
|
Content-Type: application/json
|
|
```
|
|
|
|
Default body:
|
|
|
|
```json
|
|
{
|
|
"model": "gpt-image-2",
|
|
"prompt": "<prompt>",
|
|
"n": 1,
|
|
"size": "1024x1024"
|
|
}
|
|
```
|
|
|
|
For visual references, use the edit endpoint instead of the create endpoint:
|
|
|
|
```text
|
|
POST {VECTOR_ENGINE_BASE_URL}/v1/images/edits
|
|
Authorization: Bearer {VECTOR_ENGINE_API_KEY}
|
|
Content-Type: multipart/form-data
|
|
```
|
|
|
|
Multipart fields:
|
|
|
|
```text
|
|
model=gpt-image-2
|
|
prompt=<prompt>
|
|
n=1
|
|
size=1024x1024
|
|
image=@reference.png
|
|
```
|
|
|
|
In this repository, calls with no reference images use `POST /v1/images/generations`; calls with any reference image use `POST /v1/images/edits` and pass references as one or more `image` form parts. Match3D container UI generation embeds `public/match3d-background-references/pot-fused-reference.png` into the edit request as an `image` part.
|
|
|
|
Accept image output from `data[].url`, `data[].b64_json`, or direct nested `url` fields. VectorEngine GPT-image-2 currently returns synchronously; do not poll APIMart task endpoints.
|
|
|
|
## Environment
|
|
|
|
Load environment values from process env first, then `.env.secrets.local`, `.env.local`, and `.env.example`.
|
|
|
|
Required for live generation:
|
|
|
|
- `VECTOR_ENGINE_BASE_URL`
|
|
- `VECTOR_ENGINE_API_KEY`
|
|
|
|
Optional:
|
|
|
|
- `VECTOR_ENGINE_IMAGE_REQUEST_TIMEOUT_MS`
|
|
|
|
If the key or base URL is missing, stop after dry-run or explain the missing configuration. Do not ask the user to paste the key in chat.
|
|
|
|
## Prompt Rules
|
|
|
|
- Use Chinese prompts when generating project puzzle templates.
|
|
- Keep template samples square, clear, image-only, and suitable for puzzle thumbnails.
|
|
- Avoid text, watermark, UI chrome, buttons, borders, and tutorial overlays.
|
|
- Include local negative constraints in the prompt instead of relying on provider-specific negative prompt fields.
|
|
|
|
## Resources
|
|
|
|
- `scripts/generate-template-samples.mjs`: dry-run or live-generate puzzle template sample thumbnails.
|
|
- `assets/puzzle-template-prompts.json`: default prompt list consumed by the script.
|