重构主控编排与运行时预热链路，统一工作区提示词/专家调度协议并补齐 wiki 记忆注入与写回闭环。

同时收敛启动与运维脚本默认行为（含 wiki worker）、更新 Admin 可观测性与相关测试，降低首轮时延并提高运行稳定性。 Made-with: Cursor
2026-10-11 12:10:45 +08:00 · 2026-04-26 08:34:33 +08:00 · 2026-04-26 08:34:33 +08:00 · dbbe3add6a
commit dbbe3add6a
parent 4a23b715a2
14438 changed files with 2693620 additions and 2546 deletions
--- a/openclaw/docs/concepts/experimental-features.md
+++ b/openclaw/docs/concepts/experimental-features.md
@ -0,0 +1,47 @@
+---
+title: "Experimental Features"
+summary: "What experimental flags mean in OpenClaw and which ones are currently documented"
+read_when:
+  - You see an `.experimental` config key and want to know whether it is stable
+  - You want to try preview runtime features without confusing them with normal defaults
+  - You want one place to find the currently documented experimental flags
+---
+
+# Experimental features
+
+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:
+
+- 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
+  environment before baking them into a shared baseline.
+
+## Currently documented flags
+
+| Surface                  | Key                                                       | Use it when                                                                                                    | More                                                                                          |
+| ------------------------ | --------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- |
+| Local model runtime      | `agents.defaults.experimental.localModelLean`             | A smaller or stricter local backend chokes on OpenClaw's full default tool surface                             | [Local Models](/gateway/local-models)                                                         |
+| Memory search            | `agents.defaults.memorySearch.experimental.sessionMemory` | You want `memory_search` to index prior session transcripts and accept the extra storage/indexing cost         | [Memory configuration reference](/reference/memory-config#session-memory-search-experimental) |
+| Structured planning tool | `tools.experimental.planTool`                             | You want the structured `update_plan` tool exposed for multi-step work tracking in compatible runtimes and UIs | [Gateway configuration reference](/gateway/configuration-reference#toolsexperimental)         |
+
+## Local model lean mode
+
+`agents.defaults.experimental.localModelLean: true` is a pressure-release valve
+for weaker local-model setups. It trims heavyweight default tools like
+`browser`, `cron`, and `message` so the prompt shape is smaller and less brittle
+for small-context or stricter OpenAI-compatible backends.
+
+That is intentionally **not** the normal path. If your backend handles the full
+runtime cleanly, leave this off.
+
+## Experimental does not mean hidden
+
+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.