Your lightweight open-source personal agent.
Python agent-frameworkai-agentai-agentschatbotchatopsdiscord-botllm-agentsllmslocal-llmmcpmodel-context-protocolmulti-agentopenai-compatibleopenclawpersonal-ai-assistantpythonself-hostedtelegram-bot-ai-assistantwebuiworkflow-automation
fix: harden custom image provider compatibility
chengyongrud435cb0b2171
diff --git a/docs/image-generation.md b/docs/image-generation.mdindex 55250c406..bf34ba620 100644--- a/docs/image-generation.md+++ b/docs/image-generation.md@@ -23,7 +23,7 @@ The feature is disabled by default. Enable it in `~/.nanobot/config.json`, confi}```-See [Provider Notes](#provider-notes) for AIHubMix, MiniMax, Gemini, Ollama, StepFun, and Zhipu configuration examples.+See [Provider Notes](#provider-notes) for Custom, AIHubMix, MiniMax, Gemini, Ollama, StepFun, and Zhipu configuration examples.> [!TIP]> Prefer environment variables for API keys. nanobot resolves `${VAR_NAME}` values from the environment at startup.@@ -86,7 +86,13 @@ Use a model that supports image generation and image editing if you want referen### Custom (OpenAI-compatible)-Any OpenAI-compatible image generation API can be used with the `custom` provider. This includes local Stable Diffusion servers, Replicate, Agnes AI, and similar services that expose the `/v1/images/generations` endpoint.+Use the `custom` provider for services that implement the synchronous OpenAI Images API:++```text+POST /v1/images/generations+```++The response must include generated images in `data[].b64_json` or `data[].url`. Native prediction APIs, such as Replicate's `/v1/models/{owner}/{model}/predictions`, are not directly compatible unless you put an OpenAI-compatible gateway in front of them.Configure:@@ -108,7 +114,15 @@ Configure:}```-The `apiBase` is required. The provider sends requests to `{apiBase}/images/generations` using the OpenAI Images API format with `response_format: "b64_json"`. The `apiKey` is optional for local or unauthenticated endpoints.+The `apiBase` is required. The provider sends requests to `{apiBase}/images/generations` using the OpenAI Images API format with `response_format: "b64_json"`. The `apiKey` is optional for local or unauthenticated endpoints. Reference-image edits are not supported by the generic `custom` provider.++`extraBody` can adapt provider-specific quirks because it is merged last into the request body. Examples:++- Agnes AI documents URL responses, so use `"extraBody": {"response_format": "url"}`.+- Together AI documents `"response_format": "base64"`, so override the default.+- Volcengine Ark Seedream models may require size hints such as `"2K"`, `"3K"`, `"4K"`, or explicit dimensions. Set `tools.imageGeneration.defaultImageSize` or `providers.custom.extraBody.size` to a value supported by the selected model.++For compatibility with the default nanobot setting, custom maps `defaultImageSize: "1K"` to `1024x1024`. Other explicit size hints are passed through unchanged.### AIHubMixdiff --git a/nanobot/providers/image_generation.py b/nanobot/providers/image_generation.pyindex 18f62e26c..a16a17c77 100644--- a/nanobot/providers/image_generation.py+++ b/nanobot/providers/image_generation.py@@ -1046,7 +1046,13 @@ class CustomImageGenerationClient(ImageGenerationProvider):@staticmethoddef _custom_size(aspect_ratio: str | None, image_size: str | None) -> str:- return _openai_size("gpt-image-2", aspect_ratio, image_size)+ if image_size:+ requested = image_size.strip()+ if requested:+ if requested.lower() == "1k":+ return "1024x1024"+ return requested+ return _openai_size("gpt-image-2", aspect_ratio, None)async def generate(self,diff --git a/tests/providers/test_image_generation.py b/tests/providers/test_image_generation.pyindex b7bd29a4b..29890778d 100644--- a/tests/providers/test_image_generation.py+++ b/tests/providers/test_image_generation.py@@ -843,6 +843,67 @@ async def test_custom_generate_success() -> None:assert body["size"] == "1536x1024"+async def test_custom_generate_preserves_provider_size_hint() -> None:+ fake = FakeClient(FakeResponse({"data": [{"b64_json": RAW_B64}]}))+ client = CustomImageGenerationClient(+ api_key="sk-custom-test",+ api_base="https://custom.example/v1",+ client=fake, # type: ignore[arg-type]+ )++ await client.generate(+ prompt="a cat on the moon",+ model="custom-image-model",+ image_size="2K",+ )++ assert fake.calls[0]["json"]["size"] == "2K"+++async def test_custom_generate_maps_one_k_to_openai_dimension() -> None:+ fake = FakeClient(FakeResponse({"data": [{"b64_json": RAW_B64}]}))+ client = CustomImageGenerationClient(+ api_key="sk-custom-test",+ api_base="https://custom.example/v1",+ client=fake, # type: ignore[arg-type]+ )++ await client.generate(+ prompt="a cat on the moon",+ model="custom-image-model",+ image_size="1K",+ )++ assert fake.calls[0]["json"]["size"] == "1024x1024"+++async def test_custom_generate_extra_body_can_override_defaults() -> None:+ fake = FakeClient(FakeResponse({"data": [{"url": "https://images.example/cat.png"}]}))+ fake.get_response = FakeResponse({}, content=PNG_BYTES)+ client = CustomImageGenerationClient(+ api_key="sk-custom-test",+ api_base="https://custom.example/v1",+ extra_body={"response_format": "url", "size": "2K"},+ client=fake, # type: ignore[arg-type]+ )++ response = await client.generate(+ prompt="a cat on the moon",+ model="custom-image-model",+ image_size="1K",+ )++ expected_data_url = f"data:image/png;base64,{base64.b64encode(PNG_BYTES).decode('ascii')}"+ assert response.images == [expected_data_url]+ assert fake.get_calls[0]["url"] == "https://images.example/cat.png"+ body = fake.calls[0]["json"]+ assert body["response_format"] == "url"+ assert body["size"] == "2K"++@pytest.mark.asyncioasync def test_custom_generate_without_api_key_omits_authorization() -> None:fake = FakeClient(FakeResponse({"data": [{"b64_json": RAW_B64}]}))