Hermes-agent
This commit is contained in:
Zakaria
@@ -0,0 +1,334 @@
|
||||
"""xAI image generation backend.
|
||||
|
||||
Exposes xAI's ``grok-imagine-image`` model as an
|
||||
:class:`ImageGenProvider` implementation.
|
||||
|
||||
Features:
|
||||
- Text-to-image generation
|
||||
- Multiple aspect ratios (1:1, 16:9, 9:16, etc.)
|
||||
- Multiple resolutions (1K, 2K)
|
||||
- Base64 output saved to cache
|
||||
|
||||
Selection precedence (first hit wins):
|
||||
1. ``XAI_IMAGE_MODEL`` env var
|
||||
2. ``image_gen.xai.model`` in ``config.yaml``
|
||||
3. :data:`DEFAULT_MODEL`
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
from typing import Any, Dict, List, Optional, Tuple
|
||||
|
||||
import requests
|
||||
|
||||
from agent.image_gen_provider import (
|
||||
DEFAULT_ASPECT_RATIO,
|
||||
ImageGenProvider,
|
||||
error_response,
|
||||
resolve_aspect_ratio,
|
||||
save_b64_image,
|
||||
save_url_image,
|
||||
success_response,
|
||||
)
|
||||
from tools.xai_http import hermes_xai_user_agent, resolve_xai_http_credentials
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Model catalog
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
_MODELS: Dict[str, Dict[str, Any]] = {
|
||||
"grok-imagine-image": {
|
||||
"display": "Grok Imagine Image",
|
||||
"speed": "~5-10s",
|
||||
"strengths": "Fast, high-quality",
|
||||
},
|
||||
"grok-imagine-image-quality": {
|
||||
"display": "Grok Imagine Image (Quality)",
|
||||
"speed": "~10-20s",
|
||||
"strengths": "Higher fidelity / detail; slower than the standard model.",
|
||||
},
|
||||
}
|
||||
|
||||
DEFAULT_MODEL = "grok-imagine-image"
|
||||
|
||||
# xAI aspect ratios (more options than FAL/OpenAI)
|
||||
_XAI_ASPECT_RATIOS = {
|
||||
"landscape": "16:9",
|
||||
"square": "1:1",
|
||||
"portrait": "9:16",
|
||||
"4:3": "4:3",
|
||||
"3:4": "3:4",
|
||||
"3:2": "3:2",
|
||||
"2:3": "2:3",
|
||||
}
|
||||
|
||||
# xAI resolutions
|
||||
_XAI_RESOLUTIONS = {"1k", "2k"}
|
||||
|
||||
DEFAULT_RESOLUTION = "1k"
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Config
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def _load_xai_config() -> Dict[str, Any]:
|
||||
"""Read ``image_gen.xai`` from config.yaml."""
|
||||
try:
|
||||
from hermes_cli.config import load_config
|
||||
|
||||
cfg = load_config()
|
||||
section = cfg.get("image_gen") if isinstance(cfg, dict) else None
|
||||
xai_section = section.get("xai") if isinstance(section, dict) else None
|
||||
return xai_section if isinstance(xai_section, dict) else {}
|
||||
except Exception as exc:
|
||||
logger.debug("Could not load image_gen.xai config: %s", exc)
|
||||
return {}
|
||||
|
||||
|
||||
def _resolve_model() -> Tuple[str, Dict[str, Any]]:
|
||||
"""Decide which model to use and return ``(model_id, meta)``."""
|
||||
env_override = os.environ.get("XAI_IMAGE_MODEL")
|
||||
if env_override and env_override in _MODELS:
|
||||
return env_override, _MODELS[env_override]
|
||||
|
||||
cfg = _load_xai_config()
|
||||
candidate = cfg.get("model") if isinstance(cfg.get("model"), str) else None
|
||||
if candidate and candidate in _MODELS:
|
||||
return candidate, _MODELS[candidate]
|
||||
|
||||
return DEFAULT_MODEL, _MODELS[DEFAULT_MODEL]
|
||||
|
||||
|
||||
def _resolve_resolution() -> str:
|
||||
"""Get configured resolution."""
|
||||
cfg = _load_xai_config()
|
||||
res = cfg.get("resolution") if isinstance(cfg.get("resolution"), str) else None
|
||||
if res and res in _XAI_RESOLUTIONS:
|
||||
return res
|
||||
return DEFAULT_RESOLUTION
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Provider
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class XAIImageGenProvider(ImageGenProvider):
|
||||
"""xAI ``grok-imagine-image`` backend."""
|
||||
|
||||
@property
|
||||
def name(self) -> str:
|
||||
return "xai"
|
||||
|
||||
@property
|
||||
def display_name(self) -> str:
|
||||
return "xAI (Grok)"
|
||||
|
||||
def is_available(self) -> bool:
|
||||
creds = resolve_xai_http_credentials()
|
||||
return bool(creds.get("api_key"))
|
||||
|
||||
def list_models(self) -> List[Dict[str, Any]]:
|
||||
return [
|
||||
{
|
||||
"id": model_id,
|
||||
"display": meta.get("display", model_id),
|
||||
"speed": meta.get("speed", ""),
|
||||
"strengths": meta.get("strengths", ""),
|
||||
}
|
||||
for model_id, meta in _MODELS.items()
|
||||
]
|
||||
|
||||
def get_setup_schema(self) -> Dict[str, Any]:
|
||||
# Auth resolution is delegated to the shared ``xai_grok`` post_setup
|
||||
# hook (``hermes_cli/tools_config.py``); identical to the TTS / video
|
||||
# gen entries so users see the same OAuth-or-API-key choice for every
|
||||
# xAI service.
|
||||
return {
|
||||
"name": "xAI Grok Imagine (image)",
|
||||
"badge": "paid",
|
||||
"tag": "grok-imagine-image — text-to-image; uses xAI Grok OAuth or XAI_API_KEY",
|
||||
"env_vars": [],
|
||||
"post_setup": "xai_grok",
|
||||
}
|
||||
|
||||
def generate(
|
||||
self,
|
||||
prompt: str,
|
||||
aspect_ratio: str = DEFAULT_ASPECT_RATIO,
|
||||
**kwargs: Any,
|
||||
) -> Dict[str, Any]:
|
||||
"""Generate an image using xAI's grok-imagine-image."""
|
||||
creds = resolve_xai_http_credentials()
|
||||
api_key = str(creds.get("api_key") or "").strip()
|
||||
provider_name = str(creds.get("provider") or "xai").strip() or "xai"
|
||||
if not api_key:
|
||||
return error_response(
|
||||
error="No xAI credentials found. Configure xAI OAuth in `hermes model` or set XAI_API_KEY.",
|
||||
error_type="missing_api_key",
|
||||
provider=provider_name,
|
||||
aspect_ratio=aspect_ratio,
|
||||
)
|
||||
|
||||
model_id, meta = _resolve_model()
|
||||
aspect = resolve_aspect_ratio(aspect_ratio)
|
||||
xai_ar = _XAI_ASPECT_RATIOS.get(aspect, "1:1")
|
||||
resolution = _resolve_resolution()
|
||||
xai_res = resolution if resolution in _XAI_RESOLUTIONS else DEFAULT_RESOLUTION
|
||||
|
||||
payload: Dict[str, Any] = {
|
||||
"model": model_id,
|
||||
"prompt": prompt,
|
||||
"aspect_ratio": xai_ar,
|
||||
"resolution": xai_res,
|
||||
}
|
||||
|
||||
headers = {
|
||||
"Authorization": f"Bearer {api_key}",
|
||||
"Content-Type": "application/json",
|
||||
"User-Agent": hermes_xai_user_agent(),
|
||||
}
|
||||
|
||||
base_url = str(creds.get("base_url") or "https://api.x.ai/v1").strip().rstrip("/")
|
||||
|
||||
try:
|
||||
response = requests.post(
|
||||
f"{base_url}/images/generations",
|
||||
headers=headers,
|
||||
json=payload,
|
||||
timeout=120,
|
||||
)
|
||||
response.raise_for_status()
|
||||
except requests.HTTPError as exc:
|
||||
response = exc.response
|
||||
status = response.status_code if response is not None else 0
|
||||
try:
|
||||
err_msg = response.json().get("error", {}).get("message", response.text[:300])
|
||||
except Exception:
|
||||
err_msg = response.text[:300] if response is not None else str(exc)
|
||||
logger.error("xAI image gen failed (%d): %s", status, err_msg)
|
||||
return error_response(
|
||||
error=f"xAI image generation failed ({status}): {err_msg}",
|
||||
error_type="api_error",
|
||||
provider=provider_name,
|
||||
model=model_id,
|
||||
prompt=prompt,
|
||||
aspect_ratio=aspect,
|
||||
)
|
||||
except requests.Timeout:
|
||||
return error_response(
|
||||
error="xAI image generation timed out (120s)",
|
||||
error_type="timeout",
|
||||
provider=provider_name,
|
||||
model=model_id,
|
||||
prompt=prompt,
|
||||
aspect_ratio=aspect,
|
||||
)
|
||||
except requests.ConnectionError as exc:
|
||||
return error_response(
|
||||
error=f"xAI connection error: {exc}",
|
||||
error_type="connection_error",
|
||||
provider=provider_name,
|
||||
model=model_id,
|
||||
prompt=prompt,
|
||||
aspect_ratio=aspect,
|
||||
)
|
||||
|
||||
try:
|
||||
result = response.json()
|
||||
except Exception as exc:
|
||||
return error_response(
|
||||
error=f"xAI returned invalid JSON: {exc}",
|
||||
error_type="invalid_response",
|
||||
provider=provider_name,
|
||||
model=model_id,
|
||||
prompt=prompt,
|
||||
aspect_ratio=aspect,
|
||||
)
|
||||
|
||||
# Parse response — xAI returns data[0].b64_json or data[0].url
|
||||
data = result.get("data", [])
|
||||
if not data:
|
||||
return error_response(
|
||||
error="xAI returned no image data",
|
||||
error_type="empty_response",
|
||||
provider=provider_name,
|
||||
model=model_id,
|
||||
prompt=prompt,
|
||||
aspect_ratio=aspect,
|
||||
)
|
||||
|
||||
first = data[0]
|
||||
b64 = first.get("b64_json")
|
||||
url = first.get("url")
|
||||
|
||||
if b64:
|
||||
try:
|
||||
saved_path = save_b64_image(b64, prefix=f"xai_{model_id}")
|
||||
except Exception as exc:
|
||||
return error_response(
|
||||
error=f"Could not save image to cache: {exc}",
|
||||
error_type="io_error",
|
||||
provider="xai",
|
||||
model=model_id,
|
||||
prompt=prompt,
|
||||
aspect_ratio=aspect,
|
||||
)
|
||||
image_ref = str(saved_path)
|
||||
elif url:
|
||||
# xAI's grok-imagine-image returns ephemeral ``imgen.x.ai/xai-tmp-*``
|
||||
# URLs that 404 within minutes — by the time Telegram's
|
||||
# ``send_photo`` or any downstream consumer fetches them, the
|
||||
# asset is gone (#26942). Materialise the bytes locally at
|
||||
# tool-completion time so the gateway has a stable file path to
|
||||
# upload, mirroring the b64 branch above and the audio_cache
|
||||
# pattern used by text_to_speech.
|
||||
try:
|
||||
saved_path = save_url_image(url, prefix=f"xai_{model_id}")
|
||||
except Exception as exc:
|
||||
logger.warning(
|
||||
"xAI 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="xAI response contained neither b64_json nor URL",
|
||||
error_type="empty_response",
|
||||
provider="xai",
|
||||
model=model_id,
|
||||
prompt=prompt,
|
||||
aspect_ratio=aspect,
|
||||
)
|
||||
|
||||
extra: Dict[str, Any] = {
|
||||
"resolution": xai_res,
|
||||
}
|
||||
|
||||
return success_response(
|
||||
image=image_ref,
|
||||
model=model_id,
|
||||
prompt=prompt,
|
||||
aspect_ratio=aspect,
|
||||
provider="xai",
|
||||
extra=extra,
|
||||
)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Plugin registration
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
def register(ctx: Any) -> None:
|
||||
"""Register this provider with the image gen registry."""
|
||||
ctx.register_image_gen_provider(XAIImageGenProvider())
|
||||
@@ -0,0 +1,7 @@
|
||||
name: xai
|
||||
version: 1.0.0
|
||||
description: "xAI image generation backend (grok-imagine-image). Text-to-image."
|
||||
author: Julien Talbot
|
||||
kind: backend
|
||||
requires_env:
|
||||
- XAI_API_KEY
|
||||
Reference in New Issue
Block a user