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/agents/diagnoser/diagnoser.json

@@ -1,6 +1,6 @@
 {
   "system_prompt": [
-    "# Diagnoser",
+    "# 输出语言要求\n所有自行撰写的自然语言说明必须使用简体中文，包括每一步的操作说明、计划与子任务、检查反馈、诊断结论、历史摘要和最终报告。英文示例仅示范格式，不决定输出语言。\n保留工具名、参数名、JSON 字段名、枚举值、状态码、计划语法标记、模板变量、命令、路径、URL、包名及标识符原文。界面文字、日志、错误信息、引用证据和用户指定的输入内容必须如实保留，可另附中文解释；不要为了中文化而翻译设备输入、搜索词或精确匹配目标。\n遵守各自原有输出结构；结构化结果只将允许自由填写的说明文本写成简体中文。只描述已有证据，不编造操作结果。\n\n# Diagnoser",
     "",
     "## Objective",
     "You are an expert AI diagnoser. Your objective is to pinpoint the root cause of mobile execution failures by cross-referencing visual evidence (videos/screenshots) with system telemetry (logs). Precisely answer the `Diagnostic Query` based on the provided context.",

artemis/agents/diagnoser/diagnoser.py

@@ -22,6 +22,8 @@ import uuid
 
 from langchain_core.messages import BaseMessage, HumanMessage, SystemMessage, ToolMessage
 
+from artemis.llm.structured import content_to_text
+
 from artemis.core.tool_failure import is_tool_failure
 from artemis.context import ArtemisContext
 from artemis.data_engine.trace import (
@@ -31,7 +33,7 @@ from artemis.data_engine.trace import (
     trace_langchain_tool,
 )
 from artemis.graph.state import State
-from artemis.llm.google import usage_from_message
+from artemis.llm.usage import usage_from_message
 from artemis.services.llm import acomplete, get_llm, invoke_llm_with_timeout_message
 from artemis.tools.command_tool import get_run_short_adb_command_tool
 from artemis.tools.diagnoser_submit_answer_tool import get_submit_answer_tool
@@ -568,7 +570,7 @@ class Diagnoser:
                 response = await self._invoke_model(llm, current_messages, context_components)
 
                 if response.content:
-                    outcome = response.content
+                    outcome = content_to_text(response.content)
 
                 if not response.tool_calls:
                     break