hermes-agent/agent/image_gen_provider.py
Teknium 031f9c9edc
fix(image_gen): cache xAI ephemeral URL responses to disk (#26942) (#31759)
xAI's grok-imagine-image API returns ephemeral imgen.x.ai/xai-tmp-* URLs
that 404 within minutes — long before downstream consumers (Telegram
send_photo, browser preview, multi-tier delivery fallback) get a chance
to fetch them.  The xAI image_gen provider was passing those URLs
through unchanged on the elif url: branch; b64 responses were already
cached locally via save_b64_image.  Result: every image_generate call
on a Telegram-routed xai-oauth profile delivered no image, falling
through to text-only.

Adds agent.image_gen_provider.save_url_image() — a sibling helper to
save_b64_image that downloads URL bytes to $HERMES_HOME/cache/images/.
Content-type-aware extension inference with URL-suffix fallback;
oversize cap (25MB default) with partial-write cleanup; empty-body
refusal.  Mirrors the audio_cache pattern used by text_to_speech.

Wires save_url_image into both the xAI and OpenAI providers' URL
branches.  When the download fails (network blip, 404 in-flight) we
log a warning and fall back to the bare URL rather than turning the
tool call into a hard error — the gateway's existing URL-send fallback
then gets a chance to surface the original error legibly.

Test plan:
- tests/agent/test_save_url_image.py — 8 direct tests against a real
  in-process HTTP server: bytes round-trip, content-type → extension,
  URL-suffix fallback, default-to-png, 404 propagation, empty-body
  refusal, oversize cap + cleanup, filename uniqueness.
- tests/plugins/image_gen/test_xai_provider.py — flip
  test_successful_url_response (was asserting the bug), add
  test_url_response_falls_back_to_bare_url_when_download_fails.
- tests/plugins/image_gen/test_openai_provider.py — symmetric pair.

160/160 in the broader image_gen test surface.
2026-05-24 18:10:47 -07:00

324 lines
10 KiB
Python

"""
Image Generation Provider ABC
=============================
Defines the pluggable-backend interface for image generation. Providers register
instances via ``PluginContext.register_image_gen_provider()``; the active one
(selected via ``image_gen.provider`` in ``config.yaml``) services every
``image_generate`` tool call.
Providers live in ``<repo>/plugins/image_gen/<name>/`` (built-in, auto-loaded
as ``kind: backend``) or ``~/.hermes/plugins/image_gen/<name>/`` (user, opt-in
via ``plugins.enabled``).
Response shape
--------------
All providers return a dict that :func:`success_response` / :func:`error_response`
produce. The tool wrapper JSON-serializes it. Keys:
success bool
image str | None URL or absolute file path
model str provider-specific model identifier
prompt str echoed prompt
aspect_ratio str "landscape" | "square" | "portrait"
provider str provider name (for diagnostics)
error str only when success=False
error_type str only when success=False
"""
from __future__ import annotations
import abc
import base64
import datetime
import logging
import uuid
from pathlib import Path
from typing import Any, Dict, List, Optional, Tuple
logger = logging.getLogger(__name__)
VALID_ASPECT_RATIOS: Tuple[str, ...] = ("landscape", "square", "portrait")
DEFAULT_ASPECT_RATIO = "landscape"
# ---------------------------------------------------------------------------
# ABC
# ---------------------------------------------------------------------------
class ImageGenProvider(abc.ABC):
"""Abstract base class for an image generation backend.
Subclasses must implement :meth:`generate`. Everything else has sane
defaults — override only what your provider needs.
"""
@property
@abc.abstractmethod
def name(self) -> str:
"""Stable short identifier used in ``image_gen.provider`` config.
Lowercase, no spaces. Examples: ``fal``, ``openai``, ``replicate``.
"""
@property
def display_name(self) -> str:
"""Human-readable label shown in ``hermes tools``. Defaults to ``name.title()``."""
return self.name.title()
def is_available(self) -> bool:
"""Return True when this provider can service calls.
Typically checks for a required API key. Default: True
(providers with no external dependencies are always available).
"""
return True
def list_models(self) -> List[Dict[str, Any]]:
"""Return catalog entries for ``hermes tools`` model picker.
Each entry::
{
"id": "gpt-image-1.5", # required
"display": "GPT Image 1.5", # optional; defaults to id
"speed": "~10s", # optional
"strengths": "...", # optional
"price": "$...", # optional
}
Default: empty list (provider has no user-selectable models).
"""
return []
def get_setup_schema(self) -> Dict[str, Any]:
"""Return provider metadata for the ``hermes tools`` picker.
Used by ``tools_config.py`` to inject this provider as a row in
the Image Generation provider list. Shape::
{
"name": "OpenAI", # picker label
"badge": "paid", # optional short tag
"tag": "One-line description...", # optional subtitle
"env_vars": [ # keys to prompt for
{"key": "OPENAI_API_KEY",
"prompt": "OpenAI API key",
"url": "https://platform.openai.com/api-keys"},
],
}
Default: minimal entry derived from ``display_name``. Override to
expose API key prompts and custom badges.
"""
return {
"name": self.display_name,
"badge": "",
"tag": "",
"env_vars": [],
}
def default_model(self) -> Optional[str]:
"""Return the default model id, or None if not applicable."""
models = self.list_models()
if models:
return models[0].get("id")
return None
@abc.abstractmethod
def generate(
self,
prompt: str,
aspect_ratio: str = DEFAULT_ASPECT_RATIO,
**kwargs: Any,
) -> Dict[str, Any]:
"""Generate an image.
Implementations should return the dict from :func:`success_response`
or :func:`error_response`. ``kwargs`` may contain forward-compat
parameters future versions of the schema will expose — implementations
should ignore unknown keys.
"""
# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------
def resolve_aspect_ratio(value: Optional[str]) -> str:
"""Clamp an aspect_ratio value to the valid set, defaulting to landscape.
Invalid values are coerced rather than rejected so the tool surface is
forgiving of agent mistakes.
"""
if not isinstance(value, str):
return DEFAULT_ASPECT_RATIO
v = value.strip().lower()
if v in VALID_ASPECT_RATIOS:
return v
return DEFAULT_ASPECT_RATIO
def _images_cache_dir() -> Path:
"""Return ``$HERMES_HOME/cache/images/``, creating parents as needed."""
from hermes_constants import get_hermes_home
path = get_hermes_home() / "cache" / "images"
path.mkdir(parents=True, exist_ok=True)
return path
def save_b64_image(
b64_data: str,
*,
prefix: str = "image",
extension: str = "png",
) -> Path:
"""Decode base64 image data and write it under ``$HERMES_HOME/cache/images/``.
Returns the absolute :class:`Path` to the saved file.
Filename format: ``<prefix>_<YYYYMMDD_HHMMSS>_<short-uuid>.<ext>``.
"""
raw = base64.b64decode(b64_data)
ts = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
short = uuid.uuid4().hex[:8]
path = _images_cache_dir() / f"{prefix}_{ts}_{short}.{extension}"
path.write_bytes(raw)
return path
# Extension inference for save_url_image — keep small and explicit. We don't
# want to import mimetypes for a handful of formats every image_gen provider
# actually returns, and we never want to inherit a content-type that points
# at HTML or JSON when the API gives us a degenerate response.
_URL_IMAGE_CONTENT_TYPES = {
"image/png": "png",
"image/jpeg": "jpg",
"image/jpg": "jpg",
"image/webp": "webp",
"image/gif": "gif",
}
def save_url_image(
url: str,
*,
prefix: str = "image",
timeout: float = 60.0,
max_bytes: int = 25 * 1024 * 1024,
) -> Path:
"""Download an image URL and write it under ``$HERMES_HOME/cache/images/``.
Used by providers (xAI, fallback OpenAI) whose API returns an *ephemeral*
URL instead of inline base64 — those URLs frequently expire before a
downstream consumer (Telegram ``send_photo``, browser fetch) can resolve
them, so we materialise the bytes locally at tool-completion time.
Mirrors :func:`save_b64_image`'s shape so providers can swap in one line.
Returns the absolute :class:`Path` to the saved file. Raises on any
network / HTTP / oversize / non-image-content-type error so callers can
fall back to returning the bare URL with a clear error message.
"""
import requests
response = requests.get(url, timeout=timeout, stream=True)
response.raise_for_status()
# Infer extension from the response content-type, falling back to the
# URL suffix when xAI / OpenAI omit a precise type (some CDNs return
# ``application/octet-stream``). Defaults to ``png``.
content_type = (response.headers.get("Content-Type") or "").split(";", 1)[0].strip().lower()
extension = _URL_IMAGE_CONTENT_TYPES.get(content_type)
if extension is None:
url_path = url.split("?", 1)[0].lower()
for ext in ("png", "jpg", "jpeg", "webp", "gif"):
if url_path.endswith(f".{ext}"):
extension = "jpg" if ext == "jpeg" else ext
break
if extension is None:
extension = "png"
ts = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
short = uuid.uuid4().hex[:8]
path = _images_cache_dir() / f"{prefix}_{ts}_{short}.{extension}"
bytes_written = 0
with path.open("wb") as fh:
for chunk in response.iter_content(chunk_size=64 * 1024):
if not chunk:
continue
bytes_written += len(chunk)
if bytes_written > max_bytes:
fh.close()
try:
path.unlink()
except OSError:
pass
raise ValueError(
f"Image at {url} exceeds {max_bytes // (1024 * 1024)}MB cap; refusing to cache."
)
fh.write(chunk)
if bytes_written == 0:
try:
path.unlink()
except OSError:
pass
raise ValueError(f"Image at {url} returned 0 bytes; refusing to cache.")
return path
def success_response(
*,
image: str,
model: str,
prompt: str,
aspect_ratio: str,
provider: str,
extra: Optional[Dict[str, Any]] = None,
) -> Dict[str, Any]:
"""Build a uniform success response dict.
``image`` may be an HTTP URL or an absolute filesystem path (for b64
providers like OpenAI). Callers that need to pass through additional
backend-specific fields can supply ``extra``.
"""
payload: Dict[str, Any] = {
"success": True,
"image": image,
"model": model,
"prompt": prompt,
"aspect_ratio": aspect_ratio,
"provider": provider,
}
if extra:
for k, v in extra.items():
payload.setdefault(k, v)
return payload
def error_response(
*,
error: str,
error_type: str = "provider_error",
provider: str = "",
model: str = "",
prompt: str = "",
aspect_ratio: str = DEFAULT_ASPECT_RATIO,
) -> Dict[str, Any]:
"""Build a uniform error response dict."""
return {
"success": False,
"image": None,
"error": error,
"error_type": error_type,
"model": model,
"prompt": prompt,
"aspect_ratio": aspect_ratio,
"provider": provider,
}