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/sdk/examples/video_transcription_example.py

@@ -20,7 +20,7 @@ and analyze video content from a mobile device screen.
 The agent can:
 1. Start a screen recording
 2. Perform actions while recording
-3. Stop the recording and analyze its content using Gemini models
+3. Stop the recording and analyze its content using sampled frames with Responses
 
 Use case: Recording a video playing on the screen and transcribing its content.
 """
@@ -28,6 +28,7 @@ Use case: Recording a video playing on the screen and transcribing its content.
 import asyncio
 
 from artemis.config import LLM, LLMConfig, LLMConfigUtils, LLMWithFallback
+from artemis.config import settings
 from artemis.sdk.agent import Agent
 from artemis.sdk.builders.agent_config_builder import AgentConfigBuilder
 from artemis.sdk.types.agent import AgentConfig
@@ -37,35 +38,29 @@ from artemis.sdk.types.task import AgentProfile, TaskRequest
 def get_video_capable_llm_config() -> LLMConfig:
     """Returns an LLM config with video_analyzer configured.
 
-    The video_analyzer must use a video-capable Gemini model:
-    - gemini-3.8-flash (recommended - fast and capable)
-    - gemini-3.7-flash
-    - gemini-3-pro-preview
-    - gemini-2.5-flash
-    - gemini-2.5-pro
-    - gemini-2.0-flash
+    Set OPENAI_MODEL to a Responses model with image input support.
     """
     return LLMConfig(
         planner=LLMWithFallback(
             provider="openai",
-            model="gpt-5-nano",
-            fallback=LLM(provider="openai", model="gpt-5-mini"),
+            model=settings.OPENAI_MODEL,
+            fallback=LLM(provider="openai", model=settings.OPENAI_MODEL),
         ),
         utils=LLMConfigUtils(
             outputter=LLMWithFallback(
                 provider="openai",
-                model="gpt-5-nano",
-                fallback=LLM(provider="openai", model="gpt-5-mini"),
+                model=settings.OPENAI_MODEL,
+                fallback=LLM(provider="openai", model=settings.OPENAI_MODEL),
             ),
             hopper=LLMWithFallback(
                 provider="openai",
-                model="gpt-5-nano",
-                fallback=LLM(provider="openai", model="gpt-5-mini"),
+                model=settings.OPENAI_MODEL,
+                fallback=LLM(provider="openai", model=settings.OPENAI_MODEL),
             ),
             video_analyzer=LLMWithFallback(
-                provider="google",
-                model="gemini-3.8-flash",
-                fallback=LLM(provider="google", model="gemini-3.7-flash"),
+                provider="openai",
+                model=settings.OPENAI_MODEL,
+                fallback=LLM(provider="openai", model=settings.OPENAI_MODEL),
             ),
         ),
     )