Agentica Agent → S_M_BASE_URL → Claude Proxy → claude -p → Claude CLI (with tools)
                 (localhost:2345)   (localhost:8080)

subprocess.run([
    "claude", "-p", prompt,
    "--append-system-prompt", system_prompt,
    "--allowedTools", "Read", "Write", "Edit", "Bash",  # REQUIRED
])

# Response format
yield f"data: {json.dumps(chunk)}\n\n"
yield "data: [DONE]\n\n"

return "your result here"

## ANTI-HALLUCINATION WARNING

**STOP AND READ THIS CAREFULLY:**

You have access to these tools: Read, Write, Edit, Bash

When the task asks you to create/modify/run something:
1. FIRST: Actually invoke the tool (Read, Write, Edit, or Bash)
2. SECOND: Wait for the tool result
3. THIRD: Then return your answer based on what actually happened

**DO NOT** skip the tool invocation and just claim success!

If you didn't invoke a tool, you CANNOT claim the action succeeded.

cat logs/agent-<N>.log

curl -s http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "claude", "messages": [{"role": "user", "content": "Create file at workspace/test.txt"}], "stream": false}'

# After agent claims to create file
ls -la workspace/test.txt
cat workspace/test.txt

# Terminal 1: Proxy
uv run python scripts/agentica/claude_proxy.py --port 8080

# Terminal 2: Agentica Server
cd workspace/agentica-research/agentica-server
INFERENCE_ENDPOINT_URL=http://localhost:8080/v1/chat/completions uv run agentica-server --port 2345

S_M_BASE_URL=http://localhost:2345 uv run python your_script.py

curl http://localhost:8080/health  # Proxy
curl http://localhost:2345/health  # Agentica