feat: add Chinese UI, Responses models, and mirrored Windows setup

Localize the web console and persist custom model and capability settings.
Use OpenAI Responses exclusively and move runtime limits into environment configuration.
Bootstrap uv and the virtual environment on Windows, support optional China mirrors,
and package source distributions without environments, build output, or credentials.

Update regression tests and repository quality checks for the new behavior.

artemis/tools/video_tool.py

@@ -12,9 +12,9 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-"""Video Analyzer utility for analyzing video content using Gemini models.
+"""Video Analyzer utility for analyzing video content using OpenAI Responses models.
 
-This utility sends video files to video-capable Gemini models for analysis
+This utility sends sampled video frames to image-capable Responses models for analysis
 and returns text descriptions based on the provided prompt.
 It also exposes a tool for agents to perform structured video analysis.
 """
@@ -111,7 +111,7 @@ DIAGNOSER_VIDEO_ANALYZER_DOCSTRING = (
 
 
 class VideoAnalyzerTool(ArtemisTool):
-    """Universal tool for analyzing video content using Gemini models."""
+    """Universal tool for analyzing video content using OpenAI Responses models."""
 
     def __init__(
         self,