hermes-admin/hermes-agent
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity
Files
d871cda170e140c227ac437036004a0fe19061b4
hermes-agent/plugins/image_gen/openai/__init__.py
Teknium a23ede5569 fix(secrets): scope image_gen plugin credential reads (openai/deepinfra/krea) 
OPENAI_API_KEY, DEEPINFRA_API_KEY and KREA_API_KEY now resolve via get_secret; the OpenAI client is constructed with the scoped key explicitly instead of relying on the SDK's implicit environ read.
2026-08-02 10:04:48 -07:00

420 lines
14 KiB
Python
Raw Blame History

"""OpenAI image generation backend.
Exposes OpenAI's ``gpt-image-2`` model at three quality tiers as an
:class:`ImageGenProvider` implementation. The tiers are implemented as
three virtual model IDs so the ``hermes tools`` model picker and the
``image_gen.model`` config key behave like any other multi-model backend:
gpt-image-2-low ~15s fastest, good for iteration
gpt-image-2-medium ~40s default — balanced
gpt-image-2-high ~2min slowest, highest fidelity
All three hit the same underlying API model (``gpt-image-2``) with a
different ``quality`` parameter. Output is base64 JSON → saved under
``$HERMES_HOME/cache/images/``.
Selection precedence (first hit wins):
1. ``OPENAI_IMAGE_MODEL`` env var (escape hatch for scripts / tests)
2. ``image_gen.openai.model`` in ``config.yaml``
3. ``image_gen.model`` in ``config.yaml`` (when it's one of our tier IDs)
4. :data:`DEFAULT_MODEL` — ``gpt-image-2-medium``
"""
from __future__ import annotations
import logging
import os
from typing import Any, Dict, List, Optional, Tuple
from agent.secret_scope import get_secret
from agent.image_gen_provider import (
DEFAULT_ASPECT_RATIO,
ImageGenProvider,
error_response,
normalize_reference_images,
resolve_aspect_ratio,
save_b64_image,
save_url_image,
success_response,
)
logger = logging.getLogger(__name__)
# ---------------------------------------------------------------------------
# Model catalog
# ---------------------------------------------------------------------------
#
# All three IDs resolve to the same underlying API model with a different
# ``quality`` setting. ``api_model`` is what gets sent to OpenAI;
# ``quality`` is the knob that changes generation time and output fidelity.
API_MODEL = "gpt-image-2"
_MODELS: Dict[str, Dict[str, Any]] = {
"gpt-image-2-low": {
"display": "GPT Image 2 (Low)",
"speed": "~15s",
"strengths": "Fast iteration, lowest cost",
"quality": "low",
},
"gpt-image-2-medium": {
"display": "GPT Image 2 (Medium)",
"speed": "~40s",
"strengths": "Balanced — default",
"quality": "medium",
},
"gpt-image-2-high": {
"display": "GPT Image 2 (High)",
"speed": "~2min",
"strengths": "Highest fidelity, strongest prompt adherence",
"quality": "high",
},
}
DEFAULT_MODEL = "gpt-image-2-medium"
_SIZES = {
"landscape": "1536x1024",
"square": "1024x1024",
"portrait": "1024x1536",
}
def _load_openai_config() -> Dict[str, Any]:
"""Read ``image_gen`` from config.yaml (returns {} on any failure)."""
try:
from hermes_cli.config import load_config
cfg = load_config()
section = cfg.get("image_gen") if isinstance(cfg, dict) else None
return section if isinstance(section, dict) else {}
except Exception as exc:
logger.debug("Could not load image_gen config: %s", exc)
return {}
def _resolve_model() -> Tuple[str, Dict[str, Any]]:
"""Decide which tier to use and return ``(model_id, meta)``."""
env_override = os.environ.get("OPENAI_IMAGE_MODEL")
if env_override and env_override in _MODELS:
return env_override, _MODELS[env_override]
cfg = _load_openai_config()
openai_cfg = cfg.get("openai") if isinstance(cfg.get("openai"), dict) else {}
candidate: Optional[str] = None
if isinstance(openai_cfg, dict):
value = openai_cfg.get("model")
if isinstance(value, str) and value in _MODELS:
candidate = value
if candidate is None:
top = cfg.get("model")
if isinstance(top, str) and top in _MODELS:
candidate = top
if candidate is not None:
return candidate, _MODELS[candidate]
return DEFAULT_MODEL, _MODELS[DEFAULT_MODEL]
# ---------------------------------------------------------------------------
# Source-image loading (for image-to-image / edit)
# ---------------------------------------------------------------------------
def _load_image_bytes(ref: str) -> Tuple[bytes, str]:
"""Load image bytes from a URL or local file path.
Returns ``(data, filename)``. Raises on any network / IO error so the
caller can surface a clean error_response.
"""
ref = ref.strip()
lower = ref.lower()
if lower.startswith(("http://", "https://")):
import requests
resp = requests.get(ref, timeout=60)
resp.raise_for_status()
name = ref.split("?", 1)[0].rsplit("/", 1)[-1] or "image.png"
return resp.content, name
if lower.startswith("data:"):
import base64
header, _, b64 = ref.partition(",")
ext = "png"
if "image/" in header:
ext = header.split("image/", 1)[1].split(";", 1)[0] or "png"
return base64.b64decode(b64), f"image.{ext}"
# Local file path — enforce the shared credential-read guard before reading.
from agent.file_safety import raise_if_read_blocked
raise_if_read_blocked(ref)
with open(ref, "rb") as fh:
data = fh.read()
name = os.path.basename(ref) or "image.png"
return data, name
# ---------------------------------------------------------------------------
# Provider
# ---------------------------------------------------------------------------
class OpenAIImageGenProvider(ImageGenProvider):
"""OpenAI ``images.generate`` / ``images.edit`` backend — gpt-image-2."""
@property
def name(self) -> str:
return "openai"
@property
def display_name(self) -> str:
return "OpenAI"
def is_available(self) -> bool:
if not get_secret("OPENAI_API_KEY"):
return False
try:
import openai # noqa: F401
except ImportError:
return False
return True
def list_models(self) -> List[Dict[str, Any]]:
return [
{
"id": model_id,
"display": meta["display"],
"speed": meta["speed"],
"strengths": meta["strengths"],
"price": "varies",
}
for model_id, meta in _MODELS.items()
]
def default_model(self) -> Optional[str]:
return DEFAULT_MODEL
def get_setup_schema(self) -> Dict[str, Any]:
return {
"name": "OpenAI",
"badge": "paid",
"tag": "gpt-image-2 at low/medium/high quality tiers — text-to-image & image editing",
"env_vars": [
{
"key": "OPENAI_API_KEY",
"prompt": "OpenAI API key",
"url": "https://platform.openai.com/api-keys",
},
],
}
def capabilities(self) -> Dict[str, Any]:
# gpt-image-2 supports editing via images.edit() with up to 16 source
# images.
return {"modalities": ["text", "image"], "max_reference_images": 16}
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 = resolve_aspect_ratio(aspect_ratio)
if not prompt:
return error_response(
error="Prompt is required and must be a non-empty string",
error_type="invalid_argument",
provider="openai",
aspect_ratio=aspect,
)
api_key = get_secret("OPENAI_API_KEY")
if not api_key:
return error_response(
error=(
"OPENAI_API_KEY not set. Run `hermes tools` → Image "
"Generation → OpenAI to configure, or `hermes setup` "
"to add the key."
),
error_type="auth_required",
provider="openai",
aspect_ratio=aspect,
)
try:
import openai
except ImportError:
return error_response(
error="openai Python package not installed (pip install openai)",
error_type="missing_dependency",
provider="openai",
aspect_ratio=aspect,
)
tier_id, meta = _resolve_model()
size = _SIZES.get(aspect, _SIZES["square"])
# Collect source images (primary + references) for image-to-image.
sources: List[str] = []
if isinstance(image_url, str) and image_url.strip():
sources.append(image_url.strip())
for ref in (normalize_reference_images(reference_image_urls) or []):
sources.append(ref)
sources = sources[:16] # gpt-image-2 edit caps at 16 images
is_edit = bool(sources)
modality = "image" if is_edit else "text"
client = openai.OpenAI(api_key=api_key)
if is_edit:
# images.edit() expects file-like objects. Download/read each
# source into a named BytesIO so the SDK sends correct multipart.
import io
try:
files = []
for ref in sources:
data, fname = _load_image_bytes(ref)
bio = io.BytesIO(data)
bio.name = fname
files.append(bio)
except Exception as exc:
return error_response(
error=f"Could not load source image for editing: {exc}",
error_type="io_error",
provider="openai",
model=tier_id,
prompt=prompt,
aspect_ratio=aspect,
)
try:
response = client.images.edit(
model=API_MODEL,
image=files if len(files) > 1 else files[0],
prompt=prompt,
size=size, # type: ignore[arg-type] # _SIZES values are valid gpt-image sizes
quality=meta["quality"],
n=1,
)
except Exception as exc:
logger.debug("OpenAI image edit failed", exc_info=True)
return error_response(
error=f"OpenAI image editing failed: {exc}",
error_type="api_error",
provider="openai",
model=tier_id,
prompt=prompt,
aspect_ratio=aspect,
)
else:
# gpt-image-2 returns b64_json unconditionally and REJECTS
# ``response_format`` as an unknown parameter. Don't send it.
payload: Dict[str, Any] = {
"model": API_MODEL,
"prompt": prompt,
"size": size,
"n": 1,
"quality": meta["quality"],
}
try:
response = client.images.generate(**payload)
except Exception as exc:
logger.debug("OpenAI image generation failed", exc_info=True)
return error_response(
error=f"OpenAI image generation failed: {exc}",
error_type="api_error",
provider="openai",
model=tier_id,
prompt=prompt,
aspect_ratio=aspect,
)
data = getattr(response, "data", None) or []
if not data:
return error_response(
error="OpenAI returned no image data",
error_type="empty_response",
provider="openai",
model=tier_id,
prompt=prompt,
aspect_ratio=aspect,
)
first = data[0]
b64 = getattr(first, "b64_json", None)
url = getattr(first, "url", None)
revised_prompt = getattr(first, "revised_prompt", None)
if b64:
try:
saved_path = save_b64_image(b64, prefix=f"openai_{tier_id}")
except Exception as exc:
return error_response(
error=f"Could not save image to cache: {exc}",
error_type="io_error",
provider="openai",
model=tier_id,
prompt=prompt,
aspect_ratio=aspect,
)
image_ref = str(saved_path)
elif url:
# Defensive — gpt-image-2 returns b64 today, but OpenAI's API
# has previously returned URLs. Cache the bytes locally so the
# gateway never tries to fetch an ephemeral / signed URL after
# it expires — same rationale as the xAI provider (#26942).
try:
saved_path = save_url_image(url, prefix=f"openai_{tier_id}")
except Exception as exc:
logger.warning(
"OpenAI image URL %s could not be cached (%s); falling back to bare URL.",
url,
exc,
)
image_ref = url
else:
image_ref = str(saved_path)
else:
return error_response(
error="OpenAI response contained neither b64_json nor URL",
error_type="empty_response",
provider="openai",
model=tier_id,
prompt=prompt,
aspect_ratio=aspect,
)
extra: Dict[str, Any] = {"size": size, "quality": meta["quality"]}
if revised_prompt:
extra["revised_prompt"] = revised_prompt
return success_response(
image=image_ref,
model=tier_id,
prompt=prompt,
aspect_ratio=aspect,
provider="openai",
modality=modality,
extra=extra,
)
# ---------------------------------------------------------------------------
# Plugin entry point
# ---------------------------------------------------------------------------
def register(ctx) -> None:
"""Plugin entry point — wire ``OpenAIImageGenProvider`` into the registry."""
ctx.register_image_gen_provider(OpenAIImageGenProvider())
Reference in New Issue View Git Blame Copy Permalink