managed-agent

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Managed Agent (Anthropic cloud runtime)

托管Agent（Anthropic云端运行时）

ruflo-agent

has two agent runtimes behind one mental model:

Runtime	Tools	Use it when
WASM (local, `rvagent` )	`wasm_agent_` / `wasm_gallery_`	fast, free, ephemeral, offline, untrusted code in a sandbox
Managed (Anthropic cloud)	`managed_agent_*` (this skill)	long-running / async work (minutes–hours), a real cloud container with pre-installed packages + network, persistent filesystem + transcript across turns

This skill drives the managed runtime — Anthropic's Claude Managed Agents (beta). The model: Agent (model + system + tools + MCP servers + skills) → Environment (container template) → Session (running instance) → Events (turns / tool-use / status, persisted server-side). See

docs/adr/0001-wasm-contract.md

and project ADR-115.

ruflo-agent

在统一的概念模型下包含两种Agent运行时：

Runtime	Tools	适用场景
WASM（本地， `rvagent` ）	`wasm_agent_` / `wasm_gallery_`	快速、免费、临时、离线运行，可在沙箱中处理不可信代码
Managed（Anthropic云端）	`managed_agent_*` （本技能）	长时间/异步任务（数分钟至数小时），具备预装软件包与网络能力的真实云端容器，跨轮次持久化文件系统与对话记录

本技能用于驱动托管运行时——Anthropic的Claude托管Agent（测试版）。模型架构：Agent（模型+系统配置+工具+MCP服务器+技能）→ Environment（容器模板）→ Session（运行实例）→ Events（对话轮次/工具调用/状态，服务器端持久化）。详见

docs/adr/0001-wasm-contract.md

与项目ADR-115。

Prerequisites

前置条件

```
ANTHROPIC_API_KEY
```
(or
```
CLAUDE_API_KEY
```
) in the environment, with Claude Managed Agents beta access.
If absent, every
```
managed_agent_*
```
tool returns a structured "use
```
wasm_agent_create
```
for a local no-key runtime" error — fall back to the WASM skill.

环境中需配置
```
ANTHROPIC_API_KEY
```
（或
```
CLAUDE_API_KEY
```
），且拥有Claude托管Agent测试版访问权限。
若未配置，所有
```
managed_agent_*
```
工具将返回结构化错误提示“使用
```
wasm_agent_create
```
启动无需密钥的本地运行时”，并自动回退至WASM技能。

Steps

操作步骤

Create —

mcp__claude-flow__managed_agent_create

{ model?, system?, name?, networking?, packages?, initScript?, mcpServers?, skills? }

→

{ sessionId, agentId, environmentId, status }

. Provisions Agent + Environment + Session. Save the three ids.

```
mcpServers
```
:
```
[{type:"url", url, name, authorization_token?}]
```
— the cloud agent must be able to reach the URL. A local
```
ruflo mcp start
```
is not reachable from Anthropic's cloud; deploy/tunnel an HTTP ruflo MCP server first if you want the cloud agent to have ruflo's tools.

packages

{pip?:[], npm?:[], apt?:[], cargo?:[], gem?:[], go?:[]}

— installed in the container.

Prompt —

mcp__claude-flow__managed_agent_prompt

{ sessionId, message, maxWaitMs? }

→ sends a user turn, polls the event log until the session goes idle (default 180s, capped 600s) →

{ finished, status, stopReason, assistantText, toolUses[], eventCount }

. For very long tasks, raise

maxWaitMs

or follow up with

managed_agent_events

Inspect —
```
mcp__claude-flow__managed_agent_status
```
```
{ sessionId }
```
(idle/running/error) ·
```
mcp__claude-flow__managed_agent_events
```
```
{ sessionId, raw? }
```
(full transcript: user turns, agent thinking, tool_use, tool_result, status — the cloud counterpart of
```
wasm_agent_files
```
).
List —
```
mcp__claude-flow__managed_agent_list
```
```
{ limit? }
```
— every session on the org (so you can see which are still running / billing).
Terminate —
```
mcp__claude-flow__managed_agent_terminate
```
```
{ sessionId, environmentId? }
```
— always do this when done: a cloud session keeps billing container time + tokens until deleted. Pass
```
environmentId
```
to also delete the environment ruflo created.

创建 —
```
mcp__claude-flow__managed_agent_create
```
```
{ model?, system?, name?, networking?, packages?, initScript?, mcpServers?, skills? }
```
→
```
{ sessionId, agentId, environmentId, status }
```
。完成Agent、Environment与Session的部署。请保存这三个ID。
- ```
mcpServers
```
  :
```
[{type:"url", url, name, authorization_token?}]
```
  — 云端Agent必须能够访问该URL。本地启动的
```
ruflo mcp start
```
  无法被Anthropic云端访问；若需让云端Agent使用ruflo工具，请先部署或通过隧道暴露HTTP版ruflo MCP服务器。
- ```
packages
```
  :
```
{pip?:[], npm?:[], apt?:[], cargo?:[], gem?:[], go?:[]}
```
  — 将在容器中安装的软件包。
发起提示 —
```
mcp__claude-flow__managed_agent_prompt
```
```
{ sessionId, message, maxWaitMs? }
```
→ 发送用户对话轮次，轮询事件日志直至Session进入空闲状态（默认180秒，上限600秒）→
```
{ finished, status, stopReason, assistantText, toolUses[], eventCount }
```
。对于超长任务，可提高
```
maxWaitMs
```
或后续使用
```
managed_agent_events
```
跟进。
检查状态 —
```
mcp__claude-flow__managed_agent_status
```
```
{ sessionId }
```
（返回idle/running/error状态）·
```
mcp__claude-flow__managed_agent_events
```
```
{ sessionId, raw? }
```
（完整对话记录：用户轮次、Agent思考过程、tool_use、tool_result、状态——对应本地
```
wasm_agent_files
```
的云端版本）。
列出会话 —
```
mcp__claude-flow__managed_agent_list
```
```
{ limit? }
```
— 列出组织下所有会话（可查看哪些会话仍在运行/计费）。
终止会话 —
```
mcp__claude-flow__managed_agent_terminate
```
```
{ sessionId, environmentId? }
```
— 完成任务后务必执行此操作：云端会话会持续产生容器时长与令牌费用，直至删除。传入
```
environmentId
```
可同时删除ruflo创建的环境。

Cost & safety

成本与安全

Managed Agents bill per session (LM tokens + container time) and are rate-limited per org. Estimate before a long run; record completed sessions to the
```
cost-tracking
```
namespace.
Treat orphaned sessions like leaked resources —
```
managed_agent_list
```
then
```
managed_agent_terminate
```
anything stale.
Beta API (
```
managed-agents-2026-04-01
```
);
```
multiagent
```
/
```
define-outcomes
```
on the agent config are research preview.

托管Agent按会话计费（包含大模型令牌费用+容器时长），且按组织设置速率限制。执行长任务前请估算成本；将已完成会话记录至
```
cost-tracking
```
命名空间。
孤立会话视为资源泄漏——使用
```
managed_agent_list
```
列出会话，再用
```
managed_agent_terminate
```
清理过期会话。
测试版API（
```
managed-agents-2026-04-01
```
）；Agent配置中的
```
multiagent
```
/
```
define-outcomes
```
为研究预览功能。

Quick example

快速示例

managed_agent_create  { "model": "claude-haiku-4-5-20251001", "system": "Terse. Do exactly what is asked.", "name": "scratch" }
  → { sessionId: "sesn_…", agentId: "agent_…", environmentId: "env_…", status: "idle" }
managed_agent_prompt  { "sessionId": "sesn_…", "message": "echo hello > /tmp/x && cat /tmp/x — then stop." , "maxWaitMs": 60000 }
  → { finished: true, status: "idle", stopReason: "end_turn", assistantText: "Done.", toolUses: [{name:"bash", input:{command:"echo hello > /tmp/x && cat /tmp/x"}}] }
managed_agent_terminate { "sessionId": "sesn_…", "environmentId": "env_…" }
  → { sessionDeleted: true, environmentDeleted: true }

managed_agent_create  { "model": "claude-haiku-4-5-20251001", "system": "Terse. Do exactly what is asked.", "name": "scratch" }
  → { sessionId: "sesn_…", agentId: "agent_…", environmentId: "env_…", status: "idle" }
managed_agent_prompt  { "sessionId": "sesn_…", "message": "echo hello > /tmp/x && cat /tmp/x — then stop." , "maxWaitMs": 60000 }
  → { finished: true, status: "idle", stopReason: "end_turn", assistantText: "Done.", toolUses: [{name:"bash", input:{command:"echo hello > /tmp/x && cat /tmp/x"}}] }
managed_agent_terminate { "sessionId": "sesn_…", "environmentId": "env_…" }
  → { sessionDeleted: true, environmentDeleted: true }