docs: refine ModelScope documentation wording

docs/configuration.md

@@ -254,7 +254,7 @@ Tracing covers the providers that go through nanobot's OpenAI-compatible client
 > - **OpenCode Zen / Go**: `providers.opencode` (canonical Zen), the legacy-compatible `providers.opencodeZen`, and `providers.opencodeGo` use the same `OPENCODE_API_KEY`, but route to different OpenCode gateways. These providers use OpenCode's OpenAI-compatible `chat/completions` endpoints; choose model IDs from that endpoint family.
 > - **Zhipu Coding Plan**: If you're on Zhipu's coding plan, set `"apiBase": "https://open.bigmodel.cn/api/coding/paas/v4"` in your zhipu provider config.
 > - **Alibaba Cloud BaiLian**: If you're using Alibaba Cloud BaiLian's OpenAI-compatible endpoint, set `"apiBase": "https://dashscope.aliyuncs.com/compatible-mode/v1"` in your dashscope provider config.
-> - **ModelScope (魔搭社区)**: If you're using ModelScope's OpenAI-compatible endpoint, set `"apiBase": "https://api-inference.modelscope.cn/v1"` in your modelscope provider config.
+> - **ModelScope**: If you're using ModelScope's OpenAI-compatible endpoint, set `"apiBase": "https://api-inference.modelscope.cn/v1"` in your modelscope provider config.
 > - **StepFun Step Plan**: If you're on StepFun's Step Plan subscription, set `"apiBase": "https://api.stepfun.ai/step_plan/v1"` in your stepfun provider config. Supported models include `step-3.5-flash`, `step-3.5-flash-2603`, and `step-router-v1`.
 > - **Step Fun (Mainland China)**: If your API key is from Step Fun's mainland China platform (stepfun.com), set `"apiBase": "https://api.stepfun.com/v1"` in your stepfun provider config.
 > - **Xiaomi MiMo thinking mode**: MiMo models (e.g. `mimo-v2.5-pro`) default to enabled thinking. Use `agents.defaults.reasoningEffort: "none"` to disable it, or `"low"` / `"medium"` / `"high"` to keep it on. Omitting the field preserves the provider's per-model default.
@@ -289,7 +289,7 @@ Tracing covers the providers that go through nanobot's OpenAI-compatible client
 | `siliconflow` | LLM (SiliconFlow/硅基流动) | [siliconflow.cn](https://siliconflow.cn) |
 | `novita` | LLM (Novita AI OpenAI-compatible gateway) | [novita.ai](https://novita.ai) |
 | `dashscope` | LLM (Qwen) | [dashscope.console.aliyun.com](https://dashscope.console.aliyun.com) |
-| `modelscope` | LLM (ModelScope/魔搭) + Image generation | [modelscope.cn](https://modelscope.cn) |
+| `modelscope` | LLM (ModelScope/魔搭社区) + Image generation | [modelscope.cn](https://modelscope.cn) |
 | `moonshot` | LLM (Moonshot/Kimi) | [platform.kimi.com](https://platform.kimi.com?aff=nanobot) |
 | `kimi_coding` | LLM (Kimi Coding Plan, Anthropic Messages API) | [platform.kimi.com](https://platform.kimi.com?aff=nanobot) |
 | `zhipu` | LLM (Zhipu GLM) | [open.bigmodel.cn](https://open.bigmodel.cn) |

docs/image-generation.md

@@ -323,7 +323,7 @@ Other supported models: `cogview-4`, `cogview-4-250304`, `cogview-3-flash`. Refe
 
 ModelScope (魔搭社区) API-Inference supports text-to-image generation and image editing via an async task pattern.
 
-Supported aspect ratios: `1:1`, `16:9`, `9:16`, `3:4`, `4:3`. Sizes can be specified as `WIDTHxHEIGHT` (e.g. `1024x1024`, `1536x1024`) or using aspect ratio presets.
+Supported aspect ratios: `1:1`, `16:9`, `9:16`, `3:4`, `4:3`. Sizes can be specified as `WIDTHxHEIGHT` (e.g. `1024x1024`, `1664x928`) or using aspect ratio presets.
 
 ```json
 {

nanobot/providers/image_generation.py

@@ -1760,11 +1760,11 @@ _MODELSCOPE_TIMEOUT_S = 300.0
 _MODELSCOPE_POLL_INTERVAL_S = 5.0
 _MODELSCOPE_POLL_MAX_ATTEMPTS = 60  # 5 min at 5s intervals
 _MODELSCOPE_ASPECT_RATIOS = {
-    "1:1": "1024x1024",
+    "1:1": "1328x1328",
-    "16:9": "1536x1024",
+    "16:9": "1664x928",
-    "9:16": "1024x1536",
+    "9:16": "928x1664",
-    "3:4": "1024x1536",
+    "3:4": "1140x1472",
-    "4:3": "1536x1024",
+    "4:3": "1472x1140",
 }
 
 

tests/providers/test_image_generation.py

@@ -1633,8 +1633,21 @@ async def test_modelscope_image_generation_with_size() -> None:
     assert body["size"] == "768x1024"
 
 
+@pytest.mark.parametrize(
+    ("aspect_ratio", "expected_size"),
+    [
+        ("1:1", "1328x1328"),
+        ("16:9", "1664x928"),
+        ("9:16", "928x1664"),
+        ("3:4", "1140x1472"),
+        ("4:3", "1472x1140"),
+    ],
+)
 @pytest.mark.asyncio
-async def test_modelscope_image_generation_aspect_ratio_mapping() -> None:
+async def test_modelscope_image_generation_aspect_ratio_mapping(
+    aspect_ratio: str,
+    expected_size: str,
+) -> None:
     submit = FakeResponse({"task_id": "t1"})
     poll = [FakeResponse({"task_status": "SUCCEED", "output_images": ["https://cdn/img.png"]})]
     fake = ModelScopeFakeClient(submit, poll)
@@ -1643,9 +1656,9 @@ async def test_modelscope_image_generation_aspect_ratio_mapping() -> None:
         client=fake,  # type: ignore[arg-type]
     )
 
-    await client.generate(prompt="test", model="m", aspect_ratio="16:9")
+    await client.generate(prompt="test", model="m", aspect_ratio=aspect_ratio)
 
-    assert fake.calls[0]["json"]["size"] == "1536x1024"
+    assert fake.calls[0]["json"]["size"] == expected_size
 
 
 @pytest.mark.asyncio
@@ -1753,4 +1766,3 @@ 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
-