| # Architecture |
|
|
| ## V2 foundation |
|
|
| This repository is the first safe foundation for a Hugging Face-native Agentic Space Factory. |
|
|
| ```text |
| User |
| β |
| Gradio orchestrator Space with HF OAuth |
| β |
| HF Job launched with the user's OAuth token |
| β |
| Mounted private Storage Bucket at /output |
| β |
| Optional private target Space creation |
| β |
| Live Gradio API validation |
| β |
| Bucket report + state + events |
| ``` |
|
|
| ## Current phases |
|
|
| ### Phase 1 β Hello Job |
|
|
| Validates: |
|
|
| ```text |
| OAuth β Jobs scope β HF Job β mounted Bucket β readback UI |
| ``` |
|
|
| ### Phase 2 β Private target Space |
|
|
| Validates: |
|
|
| ```text |
| OAuth β HF Job β create private Gradio Space β upload files β live API test β report |
| ``` |
|
|
| The target Space is private by default and must be created in the signed-in user's namespace. |
|
|
| ## Why Phase 2 is intentionally simple |
|
|
| Before adding Pi, model-card analysis, or ZeroGPU, we need to prove that the system can safely create a target Space and validate it through the live API. |
|
|
| That live API validation gate will later remain the core success criterion. |
|
|