Merge pull request #584 from NA-Wen/main

Enable OpenClaw Integration with ChatDev Backend Workflow Support

Author: zxrys

Makefile

@@ -10,7 +10,7 @@ dev: ## Run both backend and frontend development servers
 .PHONY: server
 server: ## Start the backend server in the background
 	@echo "Starting server in background..."
-	@uv run python server_main.py --port 6400 --reload &
+	@uv run python server_main.py --port 6400 &
 
 .PHONY: client
 client: ## Start the frontend development server

README-zh.md

@@ -170,6 +170,33 @@ make dev
     ```
     检查所有 YAML 文件的语法与 schema 错误。
 
+### 🦞 使用 OpenClaw 运行
+
+OpenClaw 可以与 ChatDev 集成，通过 **调用已有的 agent 团队**，或在 ChatDev 中 **动态创建新的 agent 团队** 来完成任务。
+
+开始使用：
+
+1. 启动 ChatDev 2.0 后端。
+2. 为你的 OpenClaw 实例安装所需的技能：
+
+    ```bash
+    clawdhub install chatdev
+    ```
+
+3. 让 OpenClaw 创建一个 ChatDev 工作流。例如：
+
+  * **自动化信息收集与内容发布**
+
+    ```
+    创建一个 ChatDev 工作流，用于自动收集热点信息，生成一篇小红书文案，并发布该内容
+    ```
+
+  * **多智能体地缘政治模拟**
+
+    ```
+    创建一个 ChatDev 工作流，构建多个 agent，用于模拟中东局势未来可能的发展
+    ```
+
 
 ### 🐳 使用 Docker 运行
 你也可以通过 Docker Compose 运行整个应用。该方式可简化依赖管理，并提供一致的运行环境。

README.md

@@ -182,6 +182,29 @@ make dev
     ```
     Checks all YAML files for syntax and schema errors.
 
+### 🦞 Run with OpenClaw
+OpenClaw can integrate with ChatDev by invoking existing agent teams or dynamically creating new agent teams within ChatDev.
+To get started:
+1. Start the ChatDev 2.0 backend.
+2. Install the required skills for your OpenClaw instance:
+    ```bash
+    clawdhub install chatdev
+    ```
+
+3. Ask your OpenClaw to create a ChatDev workflow. For example:
+
+* **Automated information collection and content publishing**
+
+  ```
+  Create a ChatDev workflow to automatically collect trending information, generate a Xiaohongshu post, and publish it.
+  ```
+
+* **Multi-agent geopolitical simulation**
+  ```
+  Create a ChatDev workflow with multiple agents to simulate possible future developments of the Middle East situation.
+  ```
+
+
 ### 🐳 Run with Docker
 Alternatively, you can run the entire application using Docker Compose. This method simplifies dependency management and provides a consistent environment.
 

entity/configs/node/tooling.py

@@ -312,6 +312,8 @@ class McpRemoteConfig(BaseConfig):
     server: str
     headers: Dict[str, str] = field(default_factory=dict)
     timeout: float | None = None
+    cache_ttl: float = 0.0
+    tool_sources: List[str] | None = None
 
     FIELD_SPECS = {
         "server": ConfigFieldSpec(
@@ -337,6 +339,22 @@ class McpRemoteConfig(BaseConfig):
             description="Per-request timeout in seconds",
             advance=True,
         ),
+        "cache_ttl": ConfigFieldSpec(
+            name="cache_ttl",
+            display_name="Tool Cache TTL",
+            type_hint="float",
+            required=False,
+            description="Seconds to cache MCP tool list; 0 disables cache for hot updates",
+            advance=True,
+        ),
+        "tool_sources": ConfigFieldSpec(
+            name="tool_sources",
+            display_name="Tool Sources Filter",
+            type_hint="list[str]",
+            required=False,
+            description="Only include MCP tools whose meta.source is in this list; omit to default to ['mcp_tools'].",
+            advance=True,
+        ),
     }
 
     @classmethod
@@ -360,7 +378,40 @@ def from_dict(cls, data: Mapping[str, Any], *, path: str) -> "McpRemoteConfig":
         else:
             raise ConfigError("timeout must be numeric", extend_path(path, "timeout"))
 
-        return cls(server=server, headers=headers, timeout=timeout, path=path)
+        cache_ttl_value = mapping.get("cache_ttl", 0.0)
+        if cache_ttl_value is None:
+            cache_ttl = 0.0
+        elif isinstance(cache_ttl_value, (int, float)):
+            cache_ttl = float(cache_ttl_value)
+        else:
+            raise ConfigError("cache_ttl must be numeric", extend_path(path, "cache_ttl"))
+
+        tool_sources_raw = mapping.get("tool_sources")
+        tool_sources: List[str] | None = None
+        if tool_sources_raw is not None:
+            entries = ensure_list(tool_sources_raw)
+            normalized: List[str] = []
+            for idx, entry in enumerate(entries):
+                if not isinstance(entry, str):
+                    raise ConfigError(
+                        "tool_sources must be a list of strings",
+                        extend_path(path, f"tool_sources[{idx}]"),
+                    )
+                value = entry.strip()
+                if value:
+                    normalized.append(value)
+            tool_sources = normalized
+        else:
+            tool_sources = ["mcp_tools"]
+
+        return cls(
+            server=server,
+            headers=headers,
+            timeout=timeout,
+            cache_ttl=cache_ttl,
+            tool_sources=tool_sources,
+            path=path,
+        )
 
     def cache_key(self) -> str:
         payload = (
@@ -380,6 +431,7 @@ class McpLocalConfig(BaseConfig):
     inherit_env: bool = True
     startup_timeout: float = 10.0
     wait_for_log: str | None = None
+    cache_ttl: float = 0.0
 
     FIELD_SPECS = {
         "command": ConfigFieldSpec(
@@ -438,6 +490,14 @@ class McpLocalConfig(BaseConfig):
             description="Regex that marks readiness when matched against stdout",
             advance=True,
         ),
+        "cache_ttl": ConfigFieldSpec(
+            name="cache_ttl",
+            display_name="Tool Cache TTL",
+            type_hint="float",
+            required=False,
+            description="Seconds to cache MCP tool list; 0 disables cache for hot updates",
+            advance=True,
+        ),
     }
 
     @classmethod
@@ -474,6 +534,13 @@ def from_dict(cls, data: Mapping[str, Any], *, path: str) -> "McpLocalConfig":
             raise ConfigError("startup_timeout must be numeric", extend_path(path, "startup_timeout"))
 
         wait_for_log = optional_str(mapping, "wait_for_log", path)
+        cache_ttl_value = mapping.get("cache_ttl", 0.0)
+        if cache_ttl_value is None:
+            cache_ttl = 0.0
+        elif isinstance(cache_ttl_value, (int, float)):
+            cache_ttl = float(cache_ttl_value)
+        else:
+            raise ConfigError("cache_ttl must be numeric", extend_path(path, "cache_ttl"))
         return cls(
             command=command,
             args=normalized_args,
@@ -482,6 +549,7 @@ def from_dict(cls, data: Mapping[str, Any], *, path: str) -> "McpLocalConfig":
             inherit_env=bool(inherit_env),
             startup_timeout=startup_timeout,
             wait_for_log=wait_for_log,
+            cache_ttl=cache_ttl,
             path=path,
         )