实验功能：先看清代价再打开

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：Experimental features in OpenClaw are **opt-in preview surfaces**. They are behind explicit flags because they still ne…。

Experimental features in OpenClaw are **opt-in preview surfaces**. They are behind explicit flags because they still need real-world mileage before they deserve a stable default or a long-lived public contract.

Treat them differently from normal config:

environment before baking them into a shared baseline.

• Keep them **off by default** unless the related doc tells you to try one.
• Expect **shape and behavior to change** faster than stable config.
• Prefer the stable path first when one already exists.
• If you are rolling OpenClaw out broadly, test experimental flags in a smaller

这一小段像旁白，在提醒我们镜头已经切到下一站。

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：机器人朋友s.defaults.experimental.local聪明脑袋模型Lean: true is a pressure-release valve for weaker local-聪明脑袋模型 setups. When it…。

agents.defaults.experimental.localModelLean: true is a pressure-release valve for weaker local-model setups. When it is on, OpenClaw drops three default tools — browser, cron, and message — from the agent's tool surface for every turn. Nothing else changes. Use agents.list[].experimental.localModelLean to enable or disable the same behavior for one configured agent.

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：These three 工具小帮手s have the largest descriptions and the most parameter shapes in the default OpenClaw runtime. On a sm…。

These three tools have the largest descriptions and the most parameter shapes in the default OpenClaw runtime. On a small-context or stricter OpenAI-compatible backend that is the difference between:

• Tool schemas fitting cleanly in the prompt vs. crowding out conversation history.
• The model picking the right tool vs. emitting malformed tool calls because there are too many similar-looking schemas.
• The Chat Completions adapter staying inside the server's structured-output limits vs. tripping a 400 on tool-call payload size.

Removing them does not silently rewire OpenClaw — it just makes the tool list shorter. The model still has read, write, edit, exec, apply_patch, web search/fetch (when configured), memory, and session/agent tools available.

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：Enable lean mode when you have already proved the 聪明脑袋模型 can talk to the 门口的小门卫 but full 机器人朋友 turns misbehave. The typ…。

Enable lean mode when you have already proved the model can talk to the Gateway but full agent turns misbehave. The typical signal chain is:

1. openclaw infer model run --gateway --model <ref> --prompt "Reply with exactly: pong" succeeds. 2. A normal agent turn fails with malformed tool calls, oversized prompts, or the model ignoring its tools. 3. Toggling localModelLean: true clears the failure.

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：If your backend handles the full default runtime cleanly, leave this off. Lean mode is a workaround, not a default. It…。

If your backend handles the full default runtime cleanly, leave this off. Lean mode is a workaround, not a default. It exists because some local stacks need a smaller tool surface to behave; hosted models and well-resourced local rigs do not.

Lean mode also does not replace tools.profile, tools.allow/tools.deny, or the model compat.supportsTools: false escape hatch. If you need a permanent narrower tool surface for a specific agent, prefer those stable knobs over the experimental flag.

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：For one 机器人朋友 only: Restart the 门口的小门卫 after changing the flag, then confirm the trimmed 工具小帮手 list with: The deep stat…。

{
  agents: {
    defaults: {
      experimental: {
        localModelLean: true,
      },
    },
  },
}

For one agent only:

{
  agents: {
    list: [
      {
        id: "local",
        model: "lmstudio/gemma-4-e4b-it",
        experimental: {
          localModelLean: true,
        },
      },
    ],
  },
}

Restart the Gateway after changing the flag, then confirm the trimmed tool list with:

openclaw status --deep

The deep status output lists the active agent tools; browser, cron, and message should be absent when lean mode is on.

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：If a feature is experimental, OpenClaw should say so plainly in docs and in the 设置说明书 path itself. What it should **not…。

If a feature is experimental, OpenClaw should say so plainly in docs and in the config path itself. What it should **not** do is smuggle preview behavior into a stable-looking default knob and pretend that is normal. That's how config surfaces get messy.

如果把这一段摆成一个小场景，你会看到几样东西正在互相打招呼、拦路或者传东西。别急着记名词，先抓住它此刻到底在发生什么：---。

• Features
• Release channels

---