Image Generation Provider Plugins

plugins/image_gen/my-backend/
├── __init__.py      # ImageGenProvider subclass + register()
└── plugin.yaml      # Manifest with kind: backend

# plugins/image_gen/my-backend/__init__.py
from typing import Any, Dict, List, Optional


from agent.image_gen_provider import (
    DEFAULT_ASPECT_RATIO,
    ImageGenProvider,
    error_response,
    normalize_reference_images,
    resolve_aspect_ratio,
    save_b64_image,
    success_response,
)


class MyBackendImageGenProvider(ImageGenProvider):
    @property
    def name(self) -> str:
        # Stable id used in image_gen.provider config. Lowercase, no spaces.
        return "my-backend"

    @property
    def display_name(self) -> str:
        # Human label shown in `hermes tools`. Defaults to name.title() if omitted.
        return "My Backend"

    def is_available(self) -> bool:
        # Return False if credentials or deps are missing.
        # The tool's availability gate calls this before dispatch.
        if not os.environ.get("MY_BACKEND_API_KEY"):
            return False
        try:
            import my_backend_sdk  # noqa: F401
        except ImportError:
            return False
        return True

    def list_models(self) -> List[Dict[str, Any]]:
        # Catalog shown in `hermes tools` model picker.
        return [
            {
                "id": "my-model-fast",
                "display": "My Model (Fast)",
                "speed": "~5s",
                "strengths": "Quick iteration",
                "price": "$0.01/image",
            },
            {
                "id": "my-model-hq",
                "display": "My Model (HQ)",
                "speed": "~30s",
                "strengths": "Highest fidelity",
                "price": "$0.04/image",
            },
        ]

    def default_model(self) -> Optional[str]:
        return "my-model-fast"

    def get_setup_schema(self) -> Dict[str, Any]:
        # Metadata for the `hermes tools` picker — keys to prompt for at setup.
        return {
            "name": "My Backend",
            "badge": "paid",        # optional; shown as a short tag in the picker
            "tag": "One-line description shown under the name",
            "env_vars": [
                {
                    "key": "MY_BACKEND_API_KEY",
                    "prompt": "My Backend API key",
                    "url": "https://my-backend.example.com/api-keys",
                },
            ],
        }

    def capabilities(self) -> Dict[str, Any]:
        # Declare whether this backend supports image-to-image / editing.
        # The tool layer surfaces this in the dynamic schema so the model
        # knows when `image_url` is honored. Default (if you omit this) is
        # text-only: {"modalities": ["text"], "max_reference_images": 0}.
        return {"modalities": ["text", "image"], "max_reference_images": 4}

    def generate(
        self,
        prompt: str,
        aspect_ratio: str = DEFAULT_ASPECT_RATIO,
        *,
        image_url: Optional[str] = None,
        reference_image_urls: Optional[List[str]] = None,
        **kwargs: Any,
    ) -> Dict[str, Any]:
        prompt = (prompt or "").strip()
        aspect_ratio = resolve_aspect_ratio(aspect_ratio)

        if not prompt:
            return error_response(
                error="Prompt is required",
                error_type="invalid_input",
                provider=self.name,
                prompt="",
                aspect_ratio=aspect_ratio,
            )

        # Routing: if image_url (or reference_image_urls) is set, the call is
        # an image-to-image / edit request; otherwise text-to-image. Report
        # which path you took via the `modality` field of success_response.
        sources = []
        if image_url:
            sources.append(image_url)
        sources.extend(normalize_reference_images(reference_image_urls) or [])
        modality = "image" if sources else "text"

        # Model selection precedence: env var → config → default. The helper
        # _resolve_model() in the built-in openai plugin is a good reference.
        model_id = kwargs.get("model") or self.default_model() or "my-model-fast"

        try:
            import my_backend_sdk
            client = my_backend_sdk.Client(api_key=os.environ["MY_BACKEND_API_KEY"])
            if modality == "image":
                result = client.edit(
                    prompt=prompt,
                    model=model_id,
                    image_urls=sources,
                )
            else:
                result = client.generate(
                    prompt=prompt,
                    model=model_id,
                    aspect_ratio=aspect_ratio,
                )

            # Two shapes supported:
            #   - URL string: return it as `image`
            #   - base64 data: save under $HERMES_HOME/cache/images/ via save_b64_image()
            if result.get("image_b64"):
                path = save_b64_image(
                    result["image_b64"],
                    prefix=self.name,
                    extension="png",
                )
                image = str(path)
            else:
                image = result["image_url"]

            return success_response(
                image=image,
                model=model_id,
                prompt=prompt,
                aspect_ratio=aspect_ratio,
                provider=self.name,
                modality=modality,
            )
        except Exception as exc:
            return error_response(
                error=str(exc),
                error_type=type(exc).__name__,
                provider=self.name,
                model=model_id,
                prompt=prompt,
                aspect_ratio=aspect_ratio,
            )


def register(ctx) -> None:
    """Plugin entry point — called once at load time."""
    ctx.register_image_gen_provider(MyBackendImageGenProvider())

name: my-backend
version: 1.0.0
description: My image backend — text-to-image via My Backend SDK
author: Your Name
kind: backend
requires_env:
  - MY_BACKEND_API_KEY

success_response(
    image=<url-or-absolute-path>,
    model=<model-id>,
    prompt=<echoed-prompt>,
    aspect_ratio="landscape" | "square" | "portrait",
    provider=<your-provider-name>,
    extra={...},  # optional backend-specific fields
)

error_response(
    error="human-readable message",
    error_type="provider_error" | "invalid_input" | "<exception class name>",
    provider=<your-provider-name>,
    model=<model-id>,
    prompt=<prompt>,
    aspect_ratio=<resolved aspect>,
)

export HERMES_HOME=/tmp/hermes-imggen-test
mkdir -p $HERMES_HOME/plugins/image_gen/my-backend
# …copy __init__.py + plugin.yaml into that dir…

export MY_BACKEND_API_KEY=your-test-key
hermes plugins enable my-backend

# Pick it as the active provider
echo "image_gen:" >> $HERMES_HOME/config.yaml
echo "  provider: my-backend" >> $HERMES_HOME/config.yaml

# Exercise it
hermes -z "Generate an image of a corgi in a spacesuit"

# pyproject.toml
[project.entry-points."hermes_agent.plugins"]
my-backend-imggen = "my_backend_imggen_package"