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(image): scope Gemini image sizes by model
Xubin Rena8604a317206
diff --git a/nanobot/providers/image_generation.py b/nanobot/providers/image_generation.pyindex f9d76e288..9e9332fd1 100644--- a/nanobot/providers/image_generation.py+++ b/nanobot/providers/image_generation.py@@ -40,9 +40,11 @@ _GEMINI_IMAGEN_ASPECT_RATIOS = {"1:1", "9:16", "16:9", "3:4", "4:3"}_GEMINI_FLASH_ASPECT_RATIOS = {"1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9",}-# Image-size tokens accepted by Gemini 3+ image models (earlier Flash image-# models expose only a single fixed resolution).-_GEMINI_FLASH_IMAGE_SIZES = {"512", "1K", "2K", "4K"}+# Gemini 3 Pro image models accept these sizes. Gemini 3.1 Flash adds 512,+# while Gemini 3.1 Flash Lite supports only 1K.+_GEMINI_3_IMAGE_SIZES = {"1K", "2K", "4K"}+_GEMINI_31_FLASH_IMAGE_SIZES = {"512", *_GEMINI_3_IMAGE_SIZES}+_GEMINI_31_FLASH_LITE_IMAGE_SIZES = {"1K"}_OLLAMA_DEFAULT_SIDE = 1024_OLLAMA_SIZE_PRESETS = {"1K": 1024,@@ -782,21 +784,27 @@ def _gemini_flash_image_config(config: dict[str, str] = {}if aspect_ratio and aspect_ratio in _GEMINI_FLASH_ASPECT_RATIOS:config["aspectRatio"] = aspect_ratio- if image_size and _gemini_flash_supports_image_size(model):+ if image_size:normalized = image_size.strip().upper()- if normalized in _GEMINI_FLASH_IMAGE_SIZES:+ if normalized in _gemini_flash_supported_image_sizes(model):config["imageSize"] = normalizedreturn config-def _gemini_flash_supports_image_size(model: str) -> bool:- """Return whether the model honors ``imageSize``.+def _gemini_flash_supported_image_sizes(model: str) -> set[str]:+ """Return the ``imageSize`` values documented for a Flash-path model.- Only Gemini 3+ image models expose a configurable image size; earlier Flash- image models (2.0, 2.5) generate at a single fixed resolution, so ``imageSize``- is identified positively rather than by excluding a single version.+ Earlier Flash image models (2.0, 2.5) expose no configurable size. Gemini+ 3.1 Flash Lite is intentionally checked before the broader Flash match."""- return "gemini-3" in model.lower()+ normalized = model.lower()+ if "gemini-3.1-flash-lite-image" in normalized:+ return _GEMINI_31_FLASH_LITE_IMAGE_SIZES+ if "gemini-3.1-flash-image" in normalized:+ return _GEMINI_31_FLASH_IMAGE_SIZES+ if "gemini-3" in normalized:+ return _GEMINI_3_IMAGE_SIZES+ return set()async def _aihubmix_images_from_payload(diff --git a/tests/providers/test_image_generation.py b/tests/providers/test_image_generation.pyindex 19f5eb4d8..7fe63e430 100644--- a/tests/providers/test_image_generation.py+++ b/tests/providers/test_image_generation.py@@ -480,6 +480,34 @@ async def test_gemini_flash_2_0_drops_image_size() -> None:assert image_config == {"aspectRatio": "16:9"}+ ("model", "image_size", "expected"),+ [+ ("gemini-3-pro-image", "512", None),+ ("gemini-3.1-flash-lite-image", "2K", None),+ ("gemini-3.1-flash-lite-image", "1K", {"imageSize": "1K"}),+ ("gemini-3.1-flash-image", "512", {"imageSize": "512"}),+ ],+)+async def test_gemini_flash_scopes_image_size_by_model(+ model: str,+ image_size: str,+ expected: dict[str, str] | None,+) -> None:+ fake = FakeClient(_gemini_flash_image_response())+ client = GeminiImageGenerationClient(api_key="AIza-test", client=fake) # type: ignore[arg-type]++ await client.generate(+ prompt="draw a cat",+ model=model,+ image_size=image_size,+ )++ response_format = fake.calls[0]["json"]["generationConfig"].get("responseFormat")+ assert response_format == ({"image": expected} if expected else None)++@pytest.mark.asyncioasync def test_gemini_flash_ignores_unsupported_hints() -> None:fake = FakeClient(_gemini_flash_image_response())