Use qwen3.8-max in OpenClaw

Configure qwen3.8-max from ChineseModels in OpenClaw.
Guide: https://chinesemodels.ai/documentation/openclaw/models/qwen3.8-max
Exact model ID: qwen3.8-max

Detect my OS and client version; check the current official configuration reference. Back up existing config and preserve logins, providers, permissions and unrelated settings. Use a secure local key prompt or secret store; never print or commit the key.

Merge models.providers.chinesemodels into the active OpenClaw config. Use models.mode=merge, baseUrl=https://chinesemodels.ai/v1, api=openai-completions, apiKey as a secret/environment reference and models with exact IDs. Preserve existing providers and agent defaults. Inspect model-policy restrictions. Verify openclaw models list --provider chinesemodels, then select chinesemodels/<exact ID>.

Fetch https://chinesemodels.ai/v1/models with my bearer key. Confirm this exact ID exists; do not silently substitute another model. Exclude image/video generators when importing more models. Test text, streaming, a tool call and a tool-result round trip. Only configure verified thinking parameters. Report what was tested, how to select this model, refresh the list and restore the backup. Do not change messaging channels, send messages or publish anything.

{
  "models": {
    "mode": "merge",
    "providers": {
      "chinesemodels": {
        "baseUrl": "https://chinesemodels.ai/v1",
        "api": "openai-completions",
        "apiKey": "${CHINESEMODELS_API_KEY}",
        "models": [
          {
            "id": "qwen3.8-max",
            "name": "qwen3.8-max (ChineseModels)",
            "input": [
              "text"
            ]
          }
        ]
      }
    }
  }
}