@@ -127,12 +127,14 @@ Live tests are split into two layers so we can isolate failures:
127127- Embedded agent forwards a multimodal user message to the model
128128- Assertion: reply contains `cat` + the code (OCR tolerance: minor mistakes allowed)
129129130-Tip: to see what you can test on your machine (and the exact `provider/model` ids), run:
130+<Tip>
131+To see what you can test on your machine (and the exact `provider/model` ids), run:
131132132133```bash
133134openclaw models list
134135openclaw models list --json
135136```
137+</Tip>
136138137139## Live: CLI backend smoke (Claude, Codex, Gemini, or other local CLIs)
138140@@ -413,7 +415,9 @@ More providers you can include in the live matrix (if you have creds/config):
413415- Built-in: `openai`, `openai-codex`, `anthropic`, `google`, `google-vertex`, `google-antigravity`, `google-gemini-cli`, `zai`, `openrouter`, `opencode`, `opencode-go`, `xai`, `groq`, `cerebras`, `mistral`, `github-copilot`
414416- Via `models.providers` (custom endpoints): `minimax` (cloud/API), plus any OpenAI/Anthropic-compatible proxy (LM Studio, vLLM, LiteLLM, etc.)
415417416-Tip: don’t try to hardcode “all models” in docs. The authoritative list is whatever `discoverModels(...)` returns on your machine + whatever keys are available.
418+<Tip>
419+Do not hardcode "all models" in docs. The authoritative list is whatever `discoverModels(...)` returns on your machine plus whatever keys are available.
420+</Tip>
417421418422## Credentials (never commit)
419423此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。