Update cloud plugin 2026 04 03

apps/MemOS-Cloud-OpenClaw-Plugin/.gitignore

@@ -4,6 +4,7 @@ node_modules
 # Environment variables
 .env
 .env.*
+.memos_arms_uid
 
 # NPM
 .npmrc

apps/MemOS-Cloud-OpenClaw-Plugin/HOOK.md

@@ -0,0 +1,22 @@
+---
+name: memos-cloud-openclaw-plugin
+description: "OpenClaw lifecycle plugin for MemOS Cloud (add + recall memory)"
+homepage: https://github.com/MemTensor/MemOS-Cloud-OpenClaw-Plugin
+metadata: {
+  "openclaw": {
+    "emoji": "🧠",
+    "events": ["before_agent_start", "agent_end", "command:new"],
+    "requires": {
+      "bins": ["node"]
+    }
+  }
+}
+---
+
+# MemOS Cloud OpenClaw Plugin Hooks
+
+This plugin registers the following OpenClaw lifecycle hooks to interact with MemOS Cloud:
+
+- `before_agent_start`: Intercepts the agent startup sequence to recall relevant memories from MemOS Cloud and injects them into the agent's context.
+- `agent_end`: Intercepts the agent termination sequence to capture the completed conversation turn and saves it to MemOS Cloud.
+- `command:new`: Increments a numeric conversation suffix when the `/new` command is issued to keep MemOS contexts distinct.

apps/MemOS-Cloud-OpenClaw-Plugin/README.md

@@ -7,8 +7,18 @@ A minimal OpenClaw lifecycle plugin that **recalls** memories from MemOS Cloud b
 ## Features
 - **Recall**: `before_agent_start` → `/search/memory`
 - **Add**: `agent_end` → `/add/message`
+- **Config UI**: starting the gateway also starts a local plugin config page for editing `plugins.entries.memos-cloud-openclaw-plugin.config`
 - Uses **Token** auth (`Authorization: Token <MEMOS_API_KEY>`)
 
+## Config UI
+- On gateway start, the plugin launches a local config page and prints the URL in the terminal (default: `http://127.0.0.1:38463`).
+- The page reads and writes the host config file directly:
+  - OpenClaw: `~/.openclaw/openclaw.json`
+  - Moltbot: `~/.moltbot/moltbot.json`
+  - ClawDBot: `~/.clawdbot/clawdbot.json`
+- If the preferred UI port is already in use, the plugin automatically picks the next free port.
+- Saving changes writes `plugins.entries.memos-cloud-openclaw-plugin.config`. (Note: you may need to manually restart the gateway after saving for settings to take effect).
+
 ## Install
 
 ### Option A — NPM (Recommended)
@@ -55,9 +65,8 @@ Make sure it’s enabled in `~/.openclaw/openclaw.json`:
 Restart the gateway after config changes.
 
 ## Environment Variables
-The plugin resolves runtime config in this order: **plugin config → env files → process environment**.
-Among env files, it tries them in order (**openclaw → moltbot → clawdbot**). For each key, the first file with a value wins.
-If none of these files exist (or the key is missing), it falls back to the process environment.
+The plugin resolves runtime config in this order: **plugin config → env files**. Due to strict security sandboxing, it **does not** read credentials from process environment variables.
+For env files, it tries them in order (**openclaw → moltbot → clawdbot**). For each key, the first file with a value wins.
 
 **Where to configure**
 - Files (priority order):
@@ -66,19 +75,9 @@ If none of these files exist (or the key is missing), it falls back to the proce
   - `~/.clawdbot/.env`
 - Each line is `KEY=value`
 
-**Quick setup (shell)**
+**Quick setup (shell / Windows)**
 ```bash
-echo 'export MEMOS_API_KEY="mpg-..."' >> ~/.zshrc
-source ~/.zshrc
-# or
-
-echo 'export MEMOS_API_KEY="mpg-..."' >> ~/.bashrc
-source ~/.bashrc
-```
-
-**Quick setup (Windows PowerShell)**
-```powershell
-[System.Environment]::SetEnvironmentVariable("MEMOS_API_KEY", "mpg-...", "User")
+echo 'MEMOS_API_KEY="mpg-..."' >> ~/.openclaw/.env
 ```
 
 If `MEMOS_API_KEY` is missing, the plugin will warn with setup instructions and the API key URL.
@@ -306,7 +305,7 @@ MEMOS_AGENT_OVERRIDES='{"research-agent": {"memoryLimitNumber": 12, "relativity"
 - **What it does**: when enabled, session keys like `agent:main:<provider>:direct:<peer-id>` reuse `<peer-id>` as MemOS `user_id`.
 - **What it does not do**: non-direct session keys such as `agent:main:<provider>:channel:<channel-id>` keep using the configured fallback `userId`.
 - **Request paths affected**: the same resolver is used by both `buildSearchPayload()` and `buildAddMessagePayload()`, so recall and add stay consistent.
-- **Config precedence**: runtime config still follows the same rule as the rest of the plugin - plugin config first, then `.env` files (`~/.openclaw/.env` -> `~/.moltbot/.env` -> `~/.clawdbot/.env`), then process env.
+- **Config precedence**: runtime config still follows the same rule as the rest of the plugin - plugin config first, then `.env` files (`~/.openclaw/.env` -> `~/.moltbot/.env` -> `~/.clawdbot/.env`).
 
 
 ## Notes

apps/MemOS-Cloud-OpenClaw-Plugin/README_ZH.md

@@ -9,8 +9,18 @@
 ## 功能
 - **Recall**：`before_agent_start` → `/search/memory`
 - **Add**：`agent_end` → `/add/message`
+- **Config UI**：启动 gateway 时同时启动本地插件配置页面，用来编辑 `plugins.entries.memos-cloud-openclaw-plugin.config`
 - 使用 **Token** 认证（`Authorization: Token <MEMOS_API_KEY>`）
 
+## 配置页面
+- Gateway 启动后，插件会同时拉起一个本地配置页面，并在终端输出访问地址（默认：`http://127.0.0.1:38463`）。
+- 页面会直接读取并写回当前宿主的配置文件：
+  - OpenClaw：`~/.openclaw/openclaw.json`
+  - Moltbot：`~/.moltbot/moltbot.json`
+  - ClawDBot：`~/.clawdbot/clawdbot.json`
+- 如果默认端口被占用，插件会自动顺延到下一个可用端口。
+- 页面保存后会写回 `plugins.entries.memos-cloud-openclaw-plugin.config`。（注意：保存后可能需要手动重启 Gateway 以使配置生效）
+
 ## 安装
 
 ### 方式 A — NPM（推荐）
@@ -57,9 +67,8 @@ openclaw gateway restart
 修改配置后需要重启 gateway。
 
 ## 环境变量
-插件运行时配置的优先级是：**插件 config → env 文件 → 进程环境变量**。
+插件运行时配置的优先级是：**插件 config → env 文件**。为符合纯粹的安全沙箱规范，插件不再支持回退到进程环境变量去读取敏感凭证。
 在 env 文件层，按顺序读取（**openclaw → moltbot → clawdbot**），每个键优先使用最先匹配到的值。
-若三个文件都不存在（或该键未找到），才会回退到进程环境变量。
 
 **配置位置**
 - 文件（优先级顺序）：
@@ -68,19 +77,9 @@ openclaw gateway restart
   - `~/.clawdbot/.env`
 - 每行格式：`KEY=value`
 
-**快速配置（Shell）**
+**快速配置（Shell / Windows）**
 ```bash
-echo 'export MEMOS_API_KEY="mpg-..."' >> ~/.zshrc
-source ~/.zshrc
-# 或者
-
-echo 'export MEMOS_API_KEY="mpg-..."' >> ~/.bashrc
-source ~/.bashrc
-```
-
-**快速配置（Windows PowerShell）**
-```powershell
-[System.Environment]::SetEnvironmentVariable("MEMOS_API_KEY", "mpg-...", "User")
+echo 'MEMOS_API_KEY="mpg-..."' >> ~/.openclaw/.env
 ```
 
 若未读取到 `MEMOS_API_KEY`，插件会提示配置方式并附 API Key 获取地址。
@@ -311,7 +310,7 @@ MEMOS_AGENT_OVERRIDES='{"research-agent": {"memoryLimitNumber": 12, "relativity"
 - **行为说明**：开启后，像 `agent:main:<provider>:direct:<peer-id>` 这样的私聊 sessionKey，会把 `<peer-id>` 当作 MemOS `user_id`。
 - **不会影响的场景**：像 `agent:main:<provider>:channel:<channel-id>` 这类非私聊 sessionKey，仍继续使用配置好的 fallback `userId`。
 - **作用范围**：同一套解析逻辑同时作用于 `buildSearchPayload()` 和 `buildAddMessagePayload()`，保证 recall 与 add 一致。
-- **配置优先级**：仍遵循插件现有规则——插件 config 优先，其次是 `.env` 文件（`~/.openclaw/.env` -> `~/.moltbot/.env` -> `~/.clawdbot/.env`），最后才回退到进程环境变量。
+- **配置优先级**：仍遵循插件现有规则——插件 config 优先，其次是 `.env` 文件（`~/.openclaw/.env` -> `~/.moltbot/.env` -> `~/.clawdbot/.env`）。
 
 
 ## 说明

apps/MemOS-Cloud-OpenClaw-Plugin/clawdbot.plugin.json

@@ -2,7 +2,7 @@
   "id": "memos-cloud-openclaw-plugin",
   "name": "MemOS Cloud OpenClaw Plugin",
   "description": "MemOS Cloud recall + add memory via lifecycle hooks",
-  "version": "0.1.11",
+  "version": "0.1.12",
   "kind": "lifecycle",
   "main": "./index.js",
   "configSchema": {
@@ -18,8 +18,7 @@
       },
       "userId": {
         "type": "string",
-        "description": "MemOS user_id (default: openclaw-user)",
-        "default": "openclaw-user"
+        "description": "MemOS user_id (default: openclaw-user)"
       },
       "conversationId": {
         "type": "string",
@@ -38,17 +37,14 @@
         "enum": [
           "none",
           "counter"
-        ],
-        "default": "none"
+        ]
       },
       "useDirectSessionUserId": {
         "type": "boolean",
-        "description": "When enabled, direct-session keys like agent:main:<provider>:direct:<id> use the direct id as MemOS user_id instead of the default configured userId.",
-        "default": false
+        "description": "When enabled, direct-session keys like agent:main:<provider>:direct:<id> use the direct id as MemOS user_id instead of the default configured userId."
       },
       "resetOnNew": {
-        "type": "boolean",
-        "default": true
+        "type": "boolean"
       },
       "queryPrefix": {
         "type": "string",
@@ -63,8 +59,37 @@
         "default": true
       },
       "recallGlobal": {
-        "type": "boolean",
-        "default": true
+        "type": "boolean"
+      },
+      "recallFilterEnabled": {
+        "type": "boolean"
+      },
+      "recallFilterBaseUrl": {
+        "type": "string",
+        "description": "OpenAI-compatible base URL for recall filter model"
+      },
+      "recallFilterApiKey": {
+        "type": "string",
+        "description": "API key for recall filter model endpoint"
+      },
+      "recallFilterModel": {
+        "type": "string",
+        "description": "Model name used to filter recall candidates"
+      },
+      "recallFilterTimeoutMs": {
+        "type": "integer"
+      },
+      "recallFilterRetries": {
+        "type": "integer"
+      },
+      "recallFilterCandidateLimit": {
+        "type": "integer"
+      },
+      "recallFilterMaxItemChars": {
+        "type": "integer"
+      },
+      "recallFilterFailOpen": {
+        "type": "boolean"
       },
       "addEnabled": {
         "type": "boolean",
@@ -75,26 +100,23 @@
         "enum": [
           "last_turn",
           "full_session"
-        ],
-        "default": "last_turn"
+        ]
       },
       "maxMessageChars": {
         "type": "integer",
-        "description": "Max chars per message when adding",
-        "default": 20000
+        "description": "Max chars per message when adding"
       },
       "maxItemChars": {
         "type": "integer",
         "description": "Max chars per memory item when injecting prompt",
         "default": 8000
       },
       "includeAssistant": {
-        "type": "boolean",
-        "default": true
+        "type": "boolean"
       },
       "memoryLimitNumber": {
         "type": "integer",
-        "default": 6
+        "default": 9
       },
       "preferenceLimitNumber": {
         "type": "integer",
@@ -112,50 +134,15 @@
         "type": "integer",
         "default": 6
       },
+      "relativity": {
+        "type": "number",
+        "description": "Minimum relativity score required before a recalled item is injected"
+      },
       "filter": {
         "type": "object",
         "description": "MemOS search filter",
         "additionalProperties": true
       },
-      "relativity": {
-        "type": "number",
-        "description": "Search relativity threshold",
-        "default": 0.45
-      },
-      "recallFilterEnabled": {
-        "type": "boolean",
-        "default": false
-      },
-      "recallFilterBaseUrl": {
-        "type": "string",
-        "description": "OpenAI-compatible API base URL for recall filtering"
-      },
-      "recallFilterApiKey": {
-        "type": "string"
-      },
-      "recallFilterModel": {
-        "type": "string"
-      },
-      "recallFilterTimeoutMs": {
-        "type": "integer",
-        "default": 30000
-      },
-      "recallFilterRetries": {
-        "type": "integer",
-        "default": 1
-      },
-      "recallFilterCandidateLimit": {
-        "type": "integer",
-        "default": 30
-      },
-      "recallFilterMaxItemChars": {
-        "type": "integer",
-        "default": 500
-      },
-      "recallFilterFailOpen": {
-        "type": "boolean",
-        "default": true
-      },
       "knowledgebaseIds": {
         "type": "array",
         "items": {
@@ -176,8 +163,7 @@
         "type": "string"
       },
       "multiAgentMode": {
-        "type": "boolean",
-        "default": false
+        "type": "boolean"
       },
       "allowedAgents": {
         "type": "array",
@@ -200,6 +186,9 @@
         }
       },
       "asyncMode": {
+        "type": "boolean"
+      },
+      "rumEnabled": {
         "type": "boolean",
         "default": true
       },
@@ -212,8 +201,7 @@
         "default": 1
       },
       "throttleMs": {
-        "type": "integer",
-        "default": 0
+        "type": "integer"
       },
       "agentOverrides": {
         "type": "object",