dsh 接入都三方的模型，如何调整思考强度？

{
                  id: gpt-5.6-sol,
                  contextWindow: 272000,
                  maxTokens: 128000,
                  reasoningEfforts: { "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" }
                }

更改DeepSeek渠道的API地址为你的网关地址

或者“添加提供方”选择 opencode-go

或者修改配置文件添加reasoningEfforts

类似这么改一下 ~/.dsh/settings.yaml 就可以了```
ui-onboarding:
welcomeNoticeVersion: 2026-08-13.1
llm-pi-ai:
providers:
aether:
displayName: Aether
apiKeyEnv: AETHER_API_KEY
api: openai-responses
baseURL: http://172.18.80.1:8084/v1
models:
- id: gpt-5.6-luna
name: GPT-5.6 Luna
contextWindow: 272000
maxTokens: 128000
reasoningEfforts:
low: low
medium: medium
high: high
xhigh: xhigh
max: max
- id: gpt-5.6-terra
name: GPT-5.6 Terra
contextWindow: 272000
maxTokens: 128000
reasoningEfforts:
low: low
medium: medium
high: high
xhigh: xhigh
max: max
- id: gpt-5.6-sol
name: GPT-5.6 Sol
contextWindow: 272000
maxTokens: 128000
reasoningEfforts:
low: low
medium: medium
high: high
xhigh: xhigh
max: max
agent-default-model:
provider: aether
model: gpt-5.6-luna
reasoningEffort: high

晚上发布了，白天搜了好几次都没发布

改了但好像也没生效呢±=