From 08fe9f7b3ae895c87044d1b3c10ca35f0d58fbdf Mon Sep 17 00:00:00 2001
From: arcdrake22 <arcdrake22@users.noreply.github.com>
Date: Sun, 2 Aug 2026 22:25:59 +0200
Subject: [PATCH] fix(image): send Gemini Flash hints via
 generationConfig.imageConfig

The live v1beta API rejects the legacy responseFormat.image block
(enum-based aspectRatio/imageSize fields) for gemini-3.1-flash-lite-image
with INVALID_ARGUMENT, even for documented plain-string values. Gemini
Flash image models accept plain-string hints under
generationConfig.imageConfig instead (e.g. aspectRatio 16:9, imageSize
1K), which the API accepts. Switch the flash path to imageConfig and
update the provider tests accordingly. Other providers (aihubmix,
ollama, imagen) are untouched.
---
 nanobot/providers/image_generation.py    | 17 ++++++++++++-----
 tests/providers/test_image_generation.py | 16 ++++++++--------
 2 files changed, 20 insertions(+), 13 deletions(-)

diff --git a/nanobot/providers/image_generation.py b/nanobot/providers/image_generation.py
index 2a28a0fc3..996e63b9b 100644
--- a/nanobot/providers/image_generation.py
+++ b/nanobot/providers/image_generation.py
@@ -808,7 +808,12 @@ class GeminiImageGenerationClient(ImageGenerationProvider):
         generation_config: dict[str, Any] = {"responseModalities": ["TEXT", "IMAGE"]}
         image_config = _gemini_flash_image_config(model, aspect_ratio, image_size)
         if image_config:
-            generation_config["responseFormat"] = {"image": image_config}
+            # Gemini Flash image models accept plain-string values under
+            # ``generationConfig.imageConfig``. The legacy
+            # ``responseFormat.image`` block is rejected with INVALID_ARGUMENT
+            # by gemini-3.1-flash-lite-image (enum-based fields), so it is not
+            # used here.
+            generation_config["imageConfig"] = image_config
 
         body: dict[str, Any] = {
             "contents": [{"role": "user", "parts": parts}],
@@ -864,11 +869,13 @@ def _gemini_flash_image_config(
     aspect_ratio: str | None,
     image_size: str | None,
 ) -> dict[str, str]:
-    """Build the ``responseFormat.image`` config for Gemini Flash image models.
+    """Build the ``generationConfig.imageConfig`` config for Gemini Flash image models.
 
-    Capabilities are model-specific: Gemini 3.1 Flash variants support four
-    additional extreme ratios, while configurable image sizes are limited to
-    the documented Gemini 3 image model families.
+    Values are the documented plain strings (e.g. ``16:9``, ``1K``) that the
+    live v1beta API accepts under ``imageConfig``. Capabilities are
+    model-specific: Gemini 3.1 Flash variants support four additional extreme
+    ratios, while configurable image sizes are limited to the documented
+    Gemini 3 image model families.
     """
     config: dict[str, str] = {}
     if aspect_ratio and aspect_ratio in _gemini_flash_supported_aspect_ratios(model):
diff --git a/tests/providers/test_image_generation.py b/tests/providers/test_image_generation.py
index 8181ab1d5..a116f4dd8 100644
--- a/tests/providers/test_image_generation.py
+++ b/tests/providers/test_image_generation.py
@@ -464,7 +464,7 @@ async def test_gemini_flash_forwards_aspect_ratio_and_image_size() -> None:
         image_size="2K",
     )
 
-    image_config = fake.calls[0]["json"]["generationConfig"]["responseFormat"]["image"]
+    image_config = fake.calls[0]["json"]["generationConfig"]["imageConfig"]
     assert image_config == {"aspectRatio": "16:9", "imageSize": "2K"}
 
 
@@ -480,7 +480,7 @@ async def test_gemini_flash_2_5_drops_image_size() -> None:
         image_size="1K",
     )
 
-    image_config = fake.calls[0]["json"]["generationConfig"]["responseFormat"]["image"]
+    image_config = fake.calls[0]["json"]["generationConfig"]["imageConfig"]
     assert image_config == {"aspectRatio": "4:3"}
 
 
@@ -496,7 +496,7 @@ async def test_gemini_flash_2_0_drops_image_size() -> None:
         image_size="1K",
     )
 
-    image_config = fake.calls[0]["json"]["generationConfig"]["responseFormat"]["image"]
+    image_config = fake.calls[0]["json"]["generationConfig"]["imageConfig"]
     assert image_config == {"aspectRatio": "16:9"}
 
 
@@ -524,8 +524,8 @@ async def test_gemini_flash_scopes_extreme_aspect_ratios_by_model(
         aspect_ratio=aspect_ratio,
     )
 
-    response_format = fake.calls[0]["json"]["generationConfig"].get("responseFormat")
-    assert response_format == ({"image": expected} if expected else None)
+    image_config = fake.calls[0]["json"]["generationConfig"].get("imageConfig")
+    assert image_config == expected
 
 
 @pytest.mark.parametrize(
@@ -553,8 +553,8 @@ async def test_gemini_flash_scopes_image_size_by_model(
         image_size=image_size,
     )
 
-    response_format = fake.calls[0]["json"]["generationConfig"].get("responseFormat")
-    assert response_format == ({"image": expected} if expected else None)
+    image_config = fake.calls[0]["json"]["generationConfig"].get("imageConfig")
+    assert image_config == expected
 
 
 @pytest.mark.asyncio
@@ -571,7 +571,7 @@ async def test_gemini_flash_ignores_unsupported_hints() -> None:
         image_size="1024x1024",
     )
 
-    assert "responseFormat" not in fake.calls[0]["json"]["generationConfig"]
+    assert "imageConfig" not in fake.calls[0]["json"]["generationConfig"]
 
 
 @pytest.mark.asyncio