From 06fb9dc1caf7490e017e48378aeebb449350a8a3 Mon Sep 17 00:00:00 2001 From: mateo-berri <277851410+mateo-berri@users.noreply.github.com> Date: Thu, 3 Sep 2026 00:44:53 -0700 Subject: [PATCH] fix(images): stop forwarding the raw image[] and mask[] form keys The /v1/images/edits handler binds the documented image[] and mask[] aliases into their canonical parameters, then re-reads the multipart body, so the raw bracketed keys rode along to the provider next to the values already built from them. OpenAI rejected both: image[] as "Invalid type for 'image[0]'" and mask[] as "Invalid parameter: 'mask'". Drop both aliases from what gets forwarded. --- litellm/proxy/image_endpoints/endpoints.py | 14 +++- .../proxy/image_endpoints/test_endpoints.py | 75 +++++++++++++++++++ 2 files changed, 86 insertions(+), 3 deletions(-) diff --git a/litellm/proxy/image_endpoints/endpoints.py b/litellm/proxy/image_endpoints/endpoints.py index 83caa92ede5..7d6d37c7c75 100644 --- a/litellm/proxy/image_endpoints/endpoints.py +++ b/litellm/proxy/image_endpoints/endpoints.py @@ -21,6 +21,10 @@ from litellm.types.llms.openai import ChatCompletionUserMessage router: Final = APIRouter() +IMAGE_ARRAY_FIELD: Final = "image[]" +MASK_ARRAY_FIELD: Final = "mask[]" +BRACKETED_FILE_FIELDS: Final = frozenset({IMAGE_ARRAY_FIELD, MASK_ARRAY_FIELD}) + async def uploadfile_to_bytesio(upload: UploadFile) -> io.BytesIO: """ @@ -229,9 +233,9 @@ async def image_edit_api( fastapi_response: Response, user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth), image: list[UploadFile] | None = File(None), - image_array: list[UploadFile] | None = File(None, alias="image[]"), + image_array: list[UploadFile] | None = File(None, alias=IMAGE_ARRAY_FIELD), mask: list[UploadFile] | None = File(None), - mask_array: list[UploadFile] | None = File(None, alias="mask[]"), + mask_array: list[UploadFile] | None = File(None, alias=MASK_ARRAY_FIELD), model: str | None = None, ): """ @@ -279,7 +283,11 @@ async def image_edit_api( ######################################################### # Read request body and convert UploadFiles to BytesIO ######################################################### - data: Final = await _read_request_body(request=request) + data: Final = { + key: value + for key, value in (await _read_request_body(request=request)).items() + if key not in BRACKETED_FILE_FIELDS + } image_files: Final = await batch_to_bytesio(image) mask_files: Final = await batch_to_bytesio(mask) if image_files: diff --git a/tests/test_litellm/proxy/image_endpoints/test_endpoints.py b/tests/test_litellm/proxy/image_endpoints/test_endpoints.py index 91a011a8234..65524b54742 100644 --- a/tests/test_litellm/proxy/image_endpoints/test_endpoints.py +++ b/tests/test_litellm/proxy/image_endpoints/test_endpoints.py @@ -5,10 +5,13 @@ from typing import Any, Dict import orjson import pytest +from fastapi import FastAPI +from fastapi.testclient import TestClient from starlette.requests import Request from starlette.responses import Response from litellm.proxy._types import UserAPIKeyAuth +from litellm.proxy.auth.user_api_key_auth import user_api_key_auth from litellm.proxy.image_endpoints import endpoints @@ -115,3 +118,75 @@ async def test_image_generation_prompt_rerouting(monkeypatch): assert captured_route_request_data["prompt"] == "sanitized prompt" assert "messages" not in captured_route_request_data assert response.headers.get("x-callback-test") == "value" + + +def _image_edit_client(monkeypatch, captured: Dict[str, Any]) -> TestClient: + class CaptureProcessing: + def __init__(self, data: Dict[str, Any]) -> None: + captured.update(data) + + async def base_process_llm_request(self, **_: Any) -> Dict[str, Any]: + return {"data": [{"b64_json": "aGk="}]} + + monkeypatch.setattr(endpoints, "ProxyBaseLLMRequestProcessing", CaptureProcessing) + monkeypatch.setattr("litellm.proxy.proxy_server.general_settings", {}) + monkeypatch.setattr("litellm.proxy.proxy_server.user_model", None) + + app = FastAPI() + app.include_router(endpoints.router) + app.dependency_overrides[user_api_key_auth] = lambda: UserAPIKeyAuth() + return TestClient(app) + + +def test_image_edit_image_array_alias_is_not_forwarded(monkeypatch): + """The documented `image[]` alias must reach the provider only as `image`.""" + captured: Dict[str, Any] = {} + + response = _image_edit_client(monkeypatch, captured).post( + "/v1/images/edits", + files={"image[]": ("tree.png", b"\x89PNG\r\n\x1a\ntree", "image/png")}, + data={"model": "gpt-image-1", "prompt": "add a hat"}, + ) + + assert response.status_code == 200 + assert "image[]" not in captured + assert [buffer.getvalue() for buffer in captured["image"]] == [b"\x89PNG\r\n\x1a\ntree"] + assert [buffer.name for buffer in captured["image"]] == ["tree.png"] + + +def test_image_edit_mask_array_alias_is_not_forwarded(monkeypatch): + """`mask[]` has the same shape as `image[]` and must be dropped the same way.""" + captured: Dict[str, Any] = {} + + response = _image_edit_client(monkeypatch, captured).post( + "/v1/images/edits", + files={ + "image": ("tree.png", b"\x89PNG\r\n\x1a\ntree", "image/png"), + "mask[]": ("mask.png", b"\x89PNG\r\n\x1a\nmask", "image/png"), + }, + data={"model": "gpt-image-1", "prompt": "add a hat"}, + ) + + assert response.status_code == 200 + assert "mask[]" not in captured + assert [buffer.getvalue() for buffer in captured["mask"]] == [b"\x89PNG\r\n\x1a\nmask"] + assert [buffer.getvalue() for buffer in captured["image"]] == [b"\x89PNG\r\n\x1a\ntree"] + + +def test_image_edit_canonical_file_fields_still_reach_the_provider(monkeypatch): + """Dropping the bracketed aliases must not touch the canonical fields.""" + captured: Dict[str, Any] = {} + + response = _image_edit_client(monkeypatch, captured).post( + "/v1/images/edits", + files={ + "image": ("tree.png", b"\x89PNG\r\n\x1a\ntree", "image/png"), + "mask": ("mask.png", b"\x89PNG\r\n\x1a\nmask", "image/png"), + }, + data={"model": "gpt-image-1", "prompt": "add a hat"}, + ) + + assert response.status_code == 200 + assert [buffer.getvalue() for buffer in captured["image"]] == [b"\x89PNG\r\n\x1a\ntree"] + assert [buffer.getvalue() for buffer in captured["mask"]] == [b"\x89PNG\r\n\x1a\nmask"] + assert captured["prompt"] == "add a hat"