Grayscale/nanobot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(image): honor provider proxy for URL downloads

Browse Source
This commit is contained in:
chengyongru
2026-07-27 10:06:19 +08:00
committed by Xubin Ren
parent cc3dbbe804
commit d73794bc68
4 changed files with 211 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/image-generation.md
+3
View File
@@ -70,6 +70,9 @@ Provider settings reuse normal provider config fields:
| `providers.<name>.apiBase` | Optional custom base URL |
| `providers.<name>.extraHeaders` | Headers merged into provider requests |
| `providers.<name>.extraBody` | Extra JSON fields merged into provider request bodies |
| `providers.<name>.proxy` | Explicit trusted HTTP proxy for provider requests and returned image URL downloads |
For providers that return image URLs, direct downloads use DNS pinning. When an explicit provider `proxy` is configured, nanobot validates the initial URL and every redirect locally, then relies on that trusted proxy for final DNS resolution and network egress. Process-wide proxy environment variables are not used for these downloads.
Both camelCase and snake_case config keys are accepted, but docs use camelCase to match `config.json`.
nanobot/providers/image_generation.py
+54 -27
View File
@@ -16,7 +16,11 @@ import httpx
from loguru import logger
from nanobot.providers.registry import find_by_name
from nanobot.security.network import PinnedDNSAsyncTransport, UnsafeURLRequestError
from nanobot.security.network import (
PinnedDNSAsyncTransport,
UnsafeURLRequestError,
resolve_url_target,
)
from nanobot.utils.helpers import detect_image_mime
_OPENROUTER_ATTRIBUTION_HEADERS = {
@@ -137,19 +141,31 @@ def _aihubmix_model_path(model: str) -> str:
async def _download_image_data_url(
url: str,
*,
proxy: str | None = None,
transport: httpx.AsyncBaseTransport | None = None,
) -> str:
try:
safe_transport = PinnedDNSAsyncTransport(inner=transport)
# Proxies resolve the target independently and would defeat DNS pinning.
async with httpx.AsyncClient(
transport=safe_transport,
follow_redirects=False,
timeout=_DEFAULT_TIMEOUT_S,
trust_env=False,
) as client:
client_kwargs: dict[str, Any] = {
"follow_redirects": False,
"timeout": _DEFAULT_TIMEOUT_S,
"trust_env": False,
}
if proxy:
# An explicit provider proxy is a user-selected trusted egress boundary.
# Validate each URL locally, while the proxy owns final DNS resolution.
client_kwargs["proxy"] = proxy
else:
client_kwargs["transport"] = PinnedDNSAsyncTransport(inner=transport)
async with httpx.AsyncClient(**client_kwargs) as client:
current_url = url
for _ in range(_IMAGE_DOWNLOAD_MAX_REDIRECTS + 1):
if proxy:
ok, error, _ = resolve_url_target(current_url)
if not ok:
raise ImageGenerationError(
f"blocked unsafe generated image URL: {error}"
)
async with client.stream("GET", current_url) as response:
if response.is_redirect:
location = response.headers.get("location")
@@ -302,6 +318,13 @@ class ImageGenerationProvider(ABC):
raise ImageGenerationError(f"{label} returned no images: {provider_error}")
raise ImageGenerationError(f"{label} returned no images for this request")
def _http_client_kwargs(self) -> dict[str, Any]:
kwargs: dict[str, Any] = {"timeout": self.timeout}
if self.proxy:
kwargs["proxy"] = self.proxy
kwargs["trust_env"] = False
return kwargs
async def _http_post(
self,
url: str,
@@ -314,11 +337,7 @@ class ImageGenerationProvider(ABC):
return await client.post(url, headers=headers, json=body)
if self._client is not None:
return await self._client.post(url, headers=headers, json=body)
client_kwargs: dict[str, Any] = {"timeout": self.timeout}
if self.proxy:
client_kwargs["proxy"] = self.proxy
client_kwargs["trust_env"] = False
async with httpx.AsyncClient(**client_kwargs) as c:
async with httpx.AsyncClient(**self._http_client_kwargs()) as c:
return await c.post(url, headers=headers, json=body)
@@ -446,7 +465,7 @@ class AIHubMixImageGenerationClient(ImageGenerationProvider):
}
size = _aihubmix_size(aspect_ratio, image_size)
client = self._client or httpx.AsyncClient(timeout=self.timeout)
client = self._client or httpx.AsyncClient(**self._http_client_kwargs())
try:
return await self._generate_with_client(
client,
@@ -506,7 +525,7 @@ class AIHubMixImageGenerationClient(ImageGenerationProvider):
raise ImageGenerationError(f"AIHubMix image generation failed: {detail}") from exc
payload = response.json()
images = await _aihubmix_images_from_payload(payload)
images = await _aihubmix_images_from_payload(payload, proxy=self.proxy)
self._require_images(images, payload)
@@ -882,6 +901,8 @@ def _gemini_flash_supported_image_sizes(model: str) -> set[str]:
async def _aihubmix_images_from_payload(
payload: dict[str, Any],
*,
proxy: str | None = None,
) -> list[str]:
images: list[str] = []
candidates: list[Any] = []
@@ -899,7 +920,7 @@ async def _aihubmix_images_from_payload(
if value.startswith("data:image/"):
images.append(value)
elif value.startswith(("http://", "https://")):
images.append(await _download_image_data_url(value))
images.append(await _download_image_data_url(value, proxy=proxy))
return
if not isinstance(value, dict):
return
@@ -1100,7 +1121,7 @@ class OpenAIImageGenerationClient(ImageGenerationProvider):
return model
async def _parse_images_response(self, payload: dict[str, Any]) -> list[str]:
return await _openai_images_from_payload(payload)
return await _openai_images_from_payload(payload, proxy=self.proxy)
async def _post_image_edit(
self,
@@ -1130,7 +1151,7 @@ class OpenAIImageGenerationClient(ImageGenerationProvider):
data=body,
files=files,
)
async with httpx.AsyncClient(timeout=self.timeout) as c:
async with httpx.AsyncClient(**self._http_client_kwargs()) as c:
return await c.post(
f"{self.api_base}/images/edits",
headers=headers,
@@ -1311,7 +1332,7 @@ class CustomImageGenerationClient(ImageGenerationProvider):
logger.info("Custom Images API response ({}): {}", response.status_code,
{k: v for k, v in payload.items() if k != "data"})
images = await _openai_images_from_payload(payload)
images = await _openai_images_from_payload(payload, proxy=self.proxy)
self._require_images(images, payload)
@@ -1505,6 +1526,8 @@ def _openai_explicit_size_supported(
async def _openai_images_from_payload(
payload: dict[str, Any],
*,
proxy: str | None = None,
) -> list[str]:
"""Extract images from OpenAI Images API response.
@@ -1520,7 +1543,7 @@ async def _openai_images_from_payload(
continue
url = item.get("url")
if isinstance(url, str) and url:
images.append(await _download_image_data_url(url))
images.append(await _download_image_data_url(url, proxy=proxy))
return images
@@ -1800,7 +1823,7 @@ class ZhipuImageGenerationClient(ImageGenerationProvider):
url = f"{self.api_base}/images/generations"
client = self._client or httpx.AsyncClient(timeout=self.timeout)
client = self._client or httpx.AsyncClient(**self._http_client_kwargs())
try:
return await self._generate_with_client(
client,
@@ -1834,7 +1857,7 @@ class ZhipuImageGenerationClient(ImageGenerationProvider):
raise ImageGenerationError(f"Zhipu image generation failed: {detail}") from exc
payload = response.json()
images = await _zhipu_images_from_payload(payload)
images = await _zhipu_images_from_payload(payload, proxy=self.proxy)
self._require_images(images, payload)
@@ -1859,6 +1882,8 @@ def _zhipu_size(
async def _zhipu_images_from_payload(
payload: dict[str, Any],
*,
proxy: str | None = None,
) -> list[str]:
"""Extract image data URLs from Zhipu API response.
@@ -1871,7 +1896,7 @@ async def _zhipu_images_from_payload(
continue
url = item.get("url")
if isinstance(url, str) and url:
images.append(await _download_image_data_url(url))
images.append(await _download_image_data_url(url, proxy=proxy))
return images
@@ -1957,7 +1982,7 @@ class ModelScopeImageGenerationClient(ImageGenerationProvider):
body.update(self.extra_body)
url = f"{self.api_base}/images/generations"
client = self._client or httpx.AsyncClient(timeout=self.timeout)
client = self._client or httpx.AsyncClient(**self._http_client_kwargs())
try:
return await self._generate_with_client(
client,
@@ -2047,8 +2072,8 @@ class ModelScopeImageGenerationClient(ImageGenerationProvider):
f"{_MODELSCOPE_POLL_MAX_ATTEMPTS} polls"
)
@staticmethod
async def _collect_images(
self,
data: dict[str, Any],
) -> list[str]:
images: list[str] = []
@@ -2057,7 +2082,9 @@ class ModelScopeImageGenerationClient(ImageGenerationProvider):
if url.startswith("data:image/"):
images.append(url)
else:
images.append(await _download_image_data_url(url))
images.append(
await _download_image_data_url(url, proxy=self.proxy)
)
return images
tests/providers/test_image_generation.py
+44 -14
View File
@@ -103,19 +103,19 @@ class CodexStreamingCompleteThenErrorResponse(FakeResponse):
@pytest.fixture(autouse=True)
def generated_image_downloads(monkeypatch) -> list[str]:
def generated_image_downloads(monkeypatch) -> list[tuple[str, str | None]]:
"""Keep provider response parsing tests independent from outbound HTTP."""
urls: list[str] = []
downloads: list[tuple[str, str | None]] = []
async def download(url: str) -> str:
urls.append(url)
async def download(url: str, *, proxy: str | None = None) -> str:
downloads.append((url, proxy))
return PNG_DATA_URL
monkeypatch.setattr(
"nanobot.providers.image_generation._download_image_data_url",
download,
)
return urls
return downloads
@pytest.mark.asyncio
@@ -294,19 +294,21 @@ async def test_aihubmix_image_edit_payload_uses_reference_images(tmp_path: Path)
@pytest.mark.asyncio
async def test_aihubmix_image_generation_downloads_url_response(
generated_image_downloads: list[str],
generated_image_downloads: list[tuple[str, str | None]],
) -> None:
fake = FakeClient(FakeResponse({"data": [{"url": "https://cdn.example/image.png"}]}))
fake.get_response = FakeResponse({}, content=PNG_BYTES)
proxy = "http://127.0.0.1:23458"
client = AIHubMixImageGenerationClient(
api_key="sk-ahm-test",
proxy=proxy,
client=fake, # type: ignore[arg-type]
)
response = await client.generate(prompt="draw", model="gpt-image-2-free")
assert response.images[0].startswith("data:image/png;base64,")
assert generated_image_downloads == ["https://cdn.example/image.png"]
assert generated_image_downloads == [("https://cdn.example/image.png", proxy)]
@pytest.mark.asyncio
@@ -836,18 +838,22 @@ async def test_openai_b64_json_response_uses_detected_mime() -> None:
@pytest.mark.asyncio
async def test_openai_url_download_fallback(generated_image_downloads: list[str]) -> None:
async def test_openai_url_download_fallback(
generated_image_downloads: list[tuple[str, str | None]],
) -> None:
fake = FakeClient(FakeResponse({"data": [{"url": "https://cdn.example/image.png"}]}))
fake.get_response = FakeResponse({}, content=PNG_BYTES)
proxy = "http://127.0.0.1:23458"
client = OpenAIImageGenerationClient(
api_key="sk-openai-test",
proxy=proxy,
client=fake, # type: ignore[arg-type]
)
response = await client.generate(prompt="draw", model="dall-e-3")
assert response.images[0].startswith("data:image/png;base64,")
assert generated_image_downloads == ["https://cdn.example/image.png"]
assert generated_image_downloads == [("https://cdn.example/image.png", proxy)]
@pytest.mark.asyncio
@@ -1211,14 +1217,16 @@ async def test_custom_generate_maps_one_k_to_openai_dimension() -> None:
@pytest.mark.asyncio
async def test_custom_generate_extra_body_can_override_defaults(
generated_image_downloads: list[str],
generated_image_downloads: list[tuple[str, str | None]],
) -> None:
fake = FakeClient(FakeResponse({"data": [{"url": "https://images.example/cat.png"}]}))
fake.get_response = FakeResponse({}, content=PNG_BYTES)
proxy = "http://127.0.0.1:23458"
client = CustomImageGenerationClient(
api_key="sk-custom-test",
api_base="https://custom.example/v1",
extra_body={"response_format": "url", "size": "2K"},
proxy=proxy,
client=fake, # type: ignore[arg-type]
)
@@ -1229,7 +1237,7 @@ async def test_custom_generate_extra_body_can_override_defaults(
)
assert response.images == [PNG_DATA_URL]
assert generated_image_downloads == ["https://images.example/cat.png"]
assert generated_image_downloads == [("https://images.example/cat.png", proxy)]
body = fake.calls[0]["json"]
assert body["response_format"] == "url"
assert body["size"] == "2K"
@@ -1636,19 +1644,21 @@ async def test_zhipu_image_generation_with_explicit_size() -> None:
@pytest.mark.asyncio
async def test_zhipu_image_generation_downloads_url_response(
generated_image_downloads: list[str],
generated_image_downloads: list[tuple[str, str | None]],
) -> None:
fake = FakeClient(FakeResponse({"data": [{"url": "https://cdn.example/image.png"}]}))
fake.get_response = FakeResponse({}, content=PNG_BYTES)
proxy = "http://127.0.0.1:23458"
client = ZhipuImageGenerationClient(
api_key="sk-zhipu-test",
proxy=proxy,
client=fake, # type: ignore[arg-type]
)
response = await client.generate(prompt="draw", model="glm-image")
assert response.images[0].startswith("data:image/png;base64,")
assert generated_image_downloads == ["https://cdn.example/image.png"]
assert generated_image_downloads == [("https://cdn.example/image.png", proxy)]
@pytest.mark.asyncio
@@ -1728,7 +1738,9 @@ def _modelscope_fast_poll(monkeypatch) -> None:
@pytest.mark.asyncio
async def test_modelscope_image_generation_submit_and_poll() -> None:
async def test_modelscope_image_generation_submit_and_poll(
generated_image_downloads: list[tuple[str, str | None]],
) -> None:
submit = FakeResponse({"task_id": "abc123"})
poll_responses = [
FakeResponse({"task_status": "PENDING"}),
@@ -1738,9 +1750,11 @@ async def test_modelscope_image_generation_submit_and_poll() -> None:
}),
]
fake = ModelScopeFakeClient(submit, poll_responses)
proxy = "http://127.0.0.1:23458"
client = ModelScopeImageGenerationClient(
api_key="ms-token",
api_base="https://api-inference.modelscope.cn/v1",
proxy=proxy,
client=fake, # type: ignore[arg-type]
)
@@ -1750,6 +1764,7 @@ async def test_modelscope_image_generation_submit_and_poll() -> None:
)
assert response.images[0].startswith("data:image/png;base64,")
assert generated_image_downloads == [("https://cdn.example/image.png", proxy)]
# Verify POST request
post_call = fake.calls[0]
@@ -1919,3 +1934,18 @@ async def test_modelscope_image_generation_poll_timeout(monkeypatch) -> None:
# Should have polled up to the (patched) attempt limit.
assert len(fake.get_calls) == 3
def test_image_provider_http_client_kwargs_include_explicit_proxy() -> None:
proxy = "http://127.0.0.1:23458"
client = AIHubMixImageGenerationClient(
api_key="sk-ahm-test",
proxy=proxy,
)
assert client._http_client_kwargs() == {
"timeout": client.timeout,
"proxy": proxy,
"trust_env": False,
}
tests/providers/test_image_generation_security.py
+110 -1
View File
@@ -33,8 +33,16 @@ def _resolve_public(host: str, port: int | None, *args, **kwargs):
["http://127.0.0.1/admin", "http://[::]/admin"],
ids=["ipv4-loopback", "ipv6-unspecified"],
)
@pytest.mark.parametrize(
"proxy",
[None, "http://127.0.0.1:23458"],
ids=["direct", "explicit-proxy"],
)
@pytest.mark.asyncio
async def test_generated_image_download_blocks_unsafe_target(url: str) -> None:
async def test_generated_image_download_blocks_unsafe_target(
url: str,
proxy: str | None,
) -> None:
requested = False
async def handler(request: httpx.Request) -> httpx.Response:
@@ -45,6 +53,7 @@ async def test_generated_image_download_blocks_unsafe_target(url: str) -> None:
with pytest.raises(ImageGenerationError, match="blocked unsafe generated image URL"):
await _download_image_data_url(
url,
proxy=proxy,
transport=httpx.MockTransport(handler),
)
@@ -116,3 +125,103 @@ async def test_generated_image_download_enforces_streaming_size_limit(monkeypatc
"https://cdn.example/image.png",
transport=httpx.MockTransport(handler),
)
class _StreamContext:
def __init__(self, response: httpx.Response) -> None:
self.response = response
async def __aenter__(self) -> httpx.Response:
return self.response
async def __aexit__(self, exc_type, exc, traceback) -> None:
await self.response.aclose()
@pytest.mark.asyncio
async def test_generated_image_download_uses_explicit_provider_proxy(
monkeypatch,
) -> None:
monkeypatch.setattr(
"nanobot.security.network.socket.getaddrinfo",
_resolve_public,
)
captured: dict[str, object] = {}
class FakeAsyncClient:
def __init__(self, **kwargs) -> None:
captured["kwargs"] = kwargs
async def __aenter__(self):
return self
async def __aexit__(self, exc_type, exc, traceback) -> None:
return None
def stream(self, method: str, url: str) -> _StreamContext:
captured["request"] = (method, url)
request = httpx.Request(method, url)
return _StreamContext(httpx.Response(200, content=PNG_BYTES, request=request))
monkeypatch.setattr(image_generation.httpx, "AsyncClient", FakeAsyncClient)
proxy = "http://127.0.0.1:23458"
result = await _download_image_data_url(
"https://cdn.example/image.png",
proxy=proxy,
)
assert result.startswith("data:image/png;base64,")
assert captured["request"] == ("GET", "https://cdn.example/image.png")
assert captured["kwargs"] == {
"follow_redirects": False,
"timeout": image_generation._DEFAULT_TIMEOUT_S,
"trust_env": False,
"proxy": proxy,
}
@pytest.mark.asyncio
async def test_proxied_generated_image_download_revalidates_redirects(
monkeypatch,
) -> None:
original_getaddrinfo = socket.getaddrinfo
def resolve_test_hosts(host: str, port: int | None, *args, **kwargs):
if host == "cdn.example":
return _resolve_public(host, port, *args, **kwargs)
return original_getaddrinfo(host, port, *args, **kwargs)
monkeypatch.setattr("nanobot.security.network.socket.getaddrinfo", resolve_test_hosts)
requested: list[str] = []
class FakeAsyncClient:
def __init__(self, **kwargs) -> None:
pass
async def __aenter__(self):
return self
async def __aexit__(self, exc_type, exc, traceback) -> None:
return None
def stream(self, method: str, url: str) -> _StreamContext:
requested.append(url)
request = httpx.Request(method, url)
return _StreamContext(
httpx.Response(
302,
headers={"location": "http://169.254.169.254/latest"},
request=request,
)
)
monkeypatch.setattr(image_generation.httpx, "AsyncClient", FakeAsyncClient)
with pytest.raises(ImageGenerationError, match="blocked unsafe generated image URL"):
await _download_image_data_url(
"https://cdn.example/image.png",
proxy="http://127.0.0.1:23458",
)
assert requested == ["https://cdn.example/image.png"]