docs/QUICKSTART.md

docs/API_REFERENCE.md

# API Reference

This document describes the public Python modules and functions available in AnyCoder.

## `models.py`

### `ModelInfo` dataclass

```python
@dataclass
class ModelInfo:
    name: str
    id: str
    description: str
    default_provider: str = "auto"

AVAILABLE_MODELS: List[ModelInfo]

A list of supported models with metadata.

find_model(identifier: str) -> Optional[ModelInfo]

Lookup a model by name or ID.

---

inference.py

chat_completion(model_id: str, messages: List[Dict[str,str]], provider: Optional[str]=None, max_tokens: int=4096) -> str

Send a one-shot chat completion request.

stream_chat_completion(model_id: str, messages: List[Dict[str,str]], provider: Optional[str]=None, max_tokens: int=4096) -> Generator[str]

Stream partial generation results.

---

hf_client.py

get_inference_client(model_id: str, provider: str="auto") -> InferenceClient

Creates an HF InferenceClient with provider routing logic.

---

docs/ARCHITECTURE.md

# Architecture Overview

Below is a high-level diagram of AnyCoder's components and data flow:

                          +------------+
                          |   User     |
                          +-----+------+
                                |
                                v
                      +---------+----------+
                      |   Gradio UI (app.py)|
                      +---------+----------+
                                |
       +------------------------+------------------------+
       |                         |                        |
       v                         v                        v
 models.py                 inference.py              plugins.py

(model registry) (routing & chat_completion) (extension points) | | | +---------------------+ +------------------------+ | v hf_client.py deploy.py (HF/OpenAI/Gemini/etc routing) (HF Spaces integration)

- **UI Layer** (`app.py` + Gradio): handles inputs, outputs, and state.
- **Model Registry** (`models.py`): metadata-driven list of supported models.
- **Inference Layer** (`inference.py`, `hf_client.py`): abstracts provider selection and API calls.
- **Extensions** (`plugins.py`): plugin architecture for community or custom integrations.
- **Deployment** (`deploy.py`): Helpers to preview in an iframe or push to Hugging Face Spaces.

This separation ensures modularity, testability, and easy extensibility.