代理服务器

人工智能 社区

技能解读

当前原文的自动摘译,尚未人工审校。

何时使用

在以下情况下使用此技能: 使用 Claude 代理启动 Agentica 开发 调试 SDK、服务器和代理之间的连接问题 设置新的 Agentica 环境 排除代理工具访问或幻觉问题

环境变量

变量 · 设置者 · 使用者 · 目的 INFERENCE_ENDPOINT_URL · 人类 · Agentica 服务器 · 服务器发送 LLM 推理请求的位置 S_M_BASE_URL · 人类 · Agentica SDK 客户端 · SDK 连接到会话管理器的位置 关键:这些不是同一个端点! SDK连接服务器(2345端口)

启动顺序

必须按此顺序启动(每个都在单独的终端中):

终端 2:Agentica 服务器

必须从其目录运行:

1. 代理生成后出现 APIConnectionError

症状:代理成功生成,但在第一次调用时失败,并出现连接错误。原因:Claude 代理返回纯 JSON,而不是 SSE 格式。修复:代理必须返回服务器发送的事件格式:

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
人工智能
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
88 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@parcadei · 未声明许可证
上下文用量评级
低消耗
接入复杂程度
需简单配置
是否需要外部接口密钥
不需要
兼容的系统
未声明(默认跨平台)
运行环境要求
Python
检测到的文件与系统行为
  • 只读
  • 允许写入 / 修改
  • 命令执行
  • 读取环境变量
网络行为
允许外网请求
安装命令数
无(仅作为资料)

需要注意: 未声明工具权限范围;实际权限由运行环境决定。

作者说明文件(原文) SKILL.md

# Agentica Server + Claude Proxy Setup

Complete reference for running Agentica SDK with a local Claude proxy. This enables Python agents to use Claude CLI as their inference backend.

## When to Use

Use this skill when:
- Starting Agentica development with Claude proxy
- Debugging connection issues between SDK, server, and proxy
- Setting up a fresh Agentica environment
- Troubleshooting agent tool access or hallucination issues

## Architecture

```
Agentica SDK (client code)
    | S_M_BASE_URL=http://localhost:2345
    v
ClientSessionManager
    |
    v
Agentica Server (agentica-server)
    | INFERENCE_ENDPOINT_URL=http://localhost:8080/v1/chat/completions
    v
Claude Proxy (claude_proxy.py)
    |
    v
Claude CLI (claude -p)
```

## Environment Variables

| Variable | Set By | Used By | Purpose |
|----------|--------|---------|---------|
| `INFERENCE_ENDPOINT_URL` | Human | agentica-server | Where server sends LLM inference requests |
| `S_M_BASE_URL` | Human | Agentica SDK client | Where SDK connects to session manager |

**KEY:** These are NOT the same endpoint!
- SDK connects to server (port 2345)
- Server connects to proxy (port 8080)

## Startup Sequence

Must start in this order (each in a separate terminal):

### Terminal 1: Claude Proxy

```bash
uv run python scripts/agentica/claude_proxy.py --port 8080
```

### Terminal 2: Agentica Server

**MUST run from its directory:**

```bash
cd workspace/agentica-research/agentica-server
INFERENCE_ENDPOINT_URL=http://localhost:8080/v1/chat/completions uv run agentica-server --port 2345
```

### Terminal 3: Your Agent Script

```bash
S_M_BASE_URL=http://localhost:2345 uv run python scripts/agentica/your_script.py
```

## Health Checks

```bash
# Claude proxy health
curl http://localhost:8080/health

# Agentica server health
curl http://localhost:2345/health
```

## Common Errors & Fixes

### 1. APIConnectionError after agent spawn

**Symptom:** Agent spawns successfully but fails on first call with connection error.

**Cause:** Claude proxy returning plain JSON instead of SSE format.

**Fix:** Proxy must return Server-Sent Events format:
```
data: {"choices": [...]}\n\n
```

### 2. ModuleNotFoundError for agentica-server

**Symptom:** `ModuleNotFoundError: No module named 'agentica_server'`

**Cause:** Running `uv run agentica-server` from wrong directory.

**Fix:** Must `cd workspace/agentica-research/agentica-server` first.

### 3. Agent can't use Read/Write/Edit tools

**Symptom:** Agent asks for file contents instead of reading them.

**Cause:** Missing `--allowedTools` in claude_proxy.py CLI call.

**Fix:** Proxy must pass tool permissions:
```bash
claude -p ... --allowedTools Read Write Edit Bash
```

### 4. Agent claims success but didn't do task

**Symptom:** Agent says "I've created the file" but file doesn't exist.

**Cause:** Hallucination - agent describing intended actions without executing.

**Fix:** Added emphatic anti-hallucination prompt in REPL_BASELINE:
```
CRITICAL: Use ACTUAL tools. Never DESCRIBE using tools.
```

### 5. Timeout on agent.call()

**Symptom:** Call hangs for 30+ seconds then times out.

**Cause:** Claude CLI taking too long or stuck in a loop.

**Fix:** Check proxy logs for the actual CLI output. May need to simplify prompt.

## Key Files

| File | Purpose |
|------|---------|
| `scripts/agentica/claude_proxy.py` | OpenAI-compatible proxy with SSE streaming |
| `workspace/agentica-research/agentica-server/` | Local agentica-server installation |
| `scripts/agentica/PATTERNS.md` | Multi-agent pattern documentation |

## Quick Verification

Test the full stack:

```bash
# 1. Verify proxy responds
curl http://localhost:8080/health

# 2. Verify server responds
curl http://localhost:2345/health

# 3. Test inference through proxy
curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"claude","messages":[{"role":"user","content":"Say hello"}]}'
```

## Checklist

Before running agents:
- [ ] Claude proxy running on port 8080
- [ ] Agentica server running on port 2345 (from its directory)
- [ ] `S_M_BASE_URL` set for client scripts
- [ ] `INFERENCE_ENDPOINT_URL` set for server
- [ ] Both health checks return 200

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。