Humano no loop

import { OpenAIProvider, createLocalAgent, createSteeringController, tool } from 'astorlm'
import { z } from 'zod'

// Any OpenAI-compatible endpoint: OpenAI, Ollama, LM Studio, vLLM, a proxy…
const LLM = { baseURL: 'http://localhost:11434/v1', apiKey: 'YOUR_API_KEY' } // local servers usually ignore the key

// Your UI: each of these resolves when the person clicks or types.
declare function approve(what: string): Promise<boolean> // shows YES / NO
declare function answer(question: string): Promise<string> // shows a text box

// 1. ESCALATE: a tool the model calls when it isn't sure. It waits for a person.
const askKid = tool({
  name: 'ask_kid',
  description: 'Ask Tina when you are not sure what she wants. Waits for her answer.',
  schema: z.object({ question: z.string() }),
  execute: async ({ question }) => answer(question),
})

// 2. APPROVE: irreversible tools wait for a yes before they run.
const NEEDS_APPROVAL = new Set(['drop_claw'])
const steering = createSteeringController({
  beforeToolExecution: async ({ toolName, input }) => {
    if (!NEEDS_APPROVAL.has(toolName)) return { authorize: true }
    const ok = await approve(`${toolName}(${JSON.stringify(input)})`) // show the real call
    return ok ? { authorize: true } : { authorize: false, mockResult: 'Tina said no. Ask her what to do.' }
  },
})

const agent = await createLocalAgent({
  provider: new OpenAIProvider({ ...LLM, model: 'your-model' }), // e.g. 'llama3.1', 'gpt-4o-mini'
  systemPrompt: 'You work a claw machine for Tina. If you are not sure which prize she means, ask her before acting.',
  tools: [moveClaw, dropClaw, askKid], // moveClaw, dropClaw: your code
  hooks: steering.hooks, // the steering controller wraps the approval hook
  maxTurns: 20,
})

// 3. STEER: the person can correct the agent at any moment, e.g. from a button.
// The loop cancels the next tool call and hands the model this feedback instead.
onTinaShouts((text) => steering.steer(text)) // your UI: 'No, wait! The penguin!'

const result = await agent.run('Get me the bear!')
console.log(result.content)

// Human in the loop, from scratch. Plain fetch, no SDK.

// Any OpenAI-compatible endpoint: OpenAI, Ollama, LM Studio, vLLM, a proxy…
const LLM = {
  baseURL: 'http://localhost:11434/v1', // e.g. Ollama's default address
  model: 'your-model', // e.g. 'llama3.1', 'gpt-4o-mini'
  apiKey: 'YOUR_API_KEY', // local servers usually ignore it
}

// Your UI: each of these resolves when the person clicks or types.
declare function approve(what: string): Promise<boolean>
declare function answer(question: string): Promise<string>

type ToolFn = (args: Record<string, string | number>) => Promise<string>
const tools: Record<string, ToolFn> = {
  move_claw: moveClaw, // your code
  drop_claw: dropClaw, // your code
  // 1. ESCALATE: the model asks, a person answers.
  ask_kid: ({ question }) => answer(String(question)),
}
const toolSchemas = [/* one JSON Schema per tool: move_claw(to), drop_claw(), ask_kid(question) */]
const NEEDS_APPROVAL = new Set(['drop_claw'])

// 3. STEER: a person can queue a correction at any time, e.g. from a button.
let steer: string | null = null
export const queueCorrection = (text: string) => {
  steer = text
}

type ToolCall = { id: string; function: { name: string; arguments: string } }
type Message =
  | { role: 'system' | 'user'; content: string }
  | { role: 'assistant'; content: string | null; tool_calls?: ToolCall[] }
  | { role: 'tool'; tool_call_id: string; content: string }

export async function runAgent(prompt: string, maxTurns = 20): Promise<string> {
  const messages: Message[] = [
    { role: 'system', content: 'You work a claw machine for Tina. If you are not sure which prize she means, ask her before acting.' },
    { role: 'user', content: prompt },
  ]
  for (let turn = 1; turn <= maxTurns; turn++) {
    const res = await fetch(`${LLM.baseURL}/chat/completions`, {
      method: 'POST',
      headers: { 'content-type': 'application/json', authorization: `Bearer ${LLM.apiKey}` },
      body: JSON.stringify({ model: LLM.model, messages, tools: toolSchemas }),
    })
    const [choice] = (await res.json()).choices
    const reply: Message = choice.message
    messages.push(reply)
    if (choice.finish_reason !== 'tool_calls') return reply.content ?? ''

    for (const call of reply.tool_calls ?? []) {
      const name = call.function.name
      const args = JSON.parse(call.function.arguments)
      let output: string
      if (steer !== null) {
        // The tool boundary: a queued correction cancels this call, and the model reads it instead.
        output = `Cancelled. The person says: ${steer}`
        steer = null
      } else if (NEEDS_APPROVAL.has(name) && !(await approve(`${name}(${call.function.arguments})`))) {
        // 2. APPROVE: irreversible tools wait here for a yes.
        output = 'Tina said no. Ask her what to do.'
      } else {
        output = tools[name] ? await tools[name](args) : `Unknown tool: ${name}`
      }
      messages.push({ role: 'tool', tool_call_id: call.id, content: output })
    }
  }
  throw new Error(`No answer after ${maxTurns} turns`)
}

console.log(await runAgent('Get me the bear!'))

# Human in the loop, from scratch. Standard library only, no SDK.
import json
import queue
import urllib.request

# Any OpenAI-compatible endpoint: OpenAI, Ollama, LM Studio, vLLM, a proxy...
LLM = {
    "base_url": "http://localhost:11434/v1",  # e.g. Ollama's default address
    "model": "your-model",  # e.g. "llama3.1", "gpt-4o-mini"
    "api_key": "YOUR_API_KEY",  # local servers usually ignore it
}


def post(path, payload):
    request = urllib.request.Request(
        f"{LLM['base_url']}{path}",
        data=json.dumps(payload).encode(),
        headers={"Content-Type": "application/json", "Authorization": f"Bearer {LLM['api_key']}"},
    )
    with urllib.request.urlopen(request) as response:
        return json.load(response)


# In a terminal the person is input(); in an app, whatever your UI sends back.
def approve(what):
    return input(f"Approve {what}? [y/N] ").strip().lower() == "y"


def ask_kid(question):  # 1. ESCALATE: the model asks, a person answers.
    return input(f"The agent asks: {question}\n> ")


TOOLS = {"move_claw": move_claw, "drop_claw": drop_claw, "ask_kid": ask_kid}  # move_claw, drop_claw: your code
TOOL_SCHEMAS = [...]  # one JSON Schema per tool: move_claw(to), drop_claw(), ask_kid(question)
NEEDS_APPROVAL = {"drop_claw"}

# 3. STEER: another thread (a UI, a chat) can queue a correction at any time.
CORRECTIONS = queue.Queue()


def run_agent(prompt, max_turns=20):
    messages = [
        {"role": "system", "content": "You work a claw machine for Tina. If you are not sure which prize she means, ask her before acting."},
        {"role": "user", "content": prompt},
    ]
    for _ in range(max_turns):
        choice = post("/chat/completions", {"model": LLM["model"], "messages": messages, "tools": TOOL_SCHEMAS})["choices"][0]
        reply = choice["message"]
        messages.append(reply)
        if choice["finish_reason"] != "tool_calls":
            return reply.get("content") or ""

        for call in reply.get("tool_calls", []):
            name = call["function"]["name"]
            args = json.loads(call["function"]["arguments"])
            if not CORRECTIONS.empty():
                # The tool boundary: a queued correction cancels this call, and the model reads it instead.
                output = f"Cancelled. The person says: {CORRECTIONS.get()}"
            elif name in NEEDS_APPROVAL and not approve(f"{name}({args})"):
                # 2. APPROVE: irreversible tools wait here for a yes.
                output = "Tina said no. Ask her what to do."
            else:
                output = TOOLS[name](**args)
            messages.append({"role": "tool", "tool_call_id": call["id"], "content": output})

    raise RuntimeError(f"No answer after {max_turns} turns")


print(run_agent("Get me the bear!"))