Cuándo parar

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

const searchBlocks = tool({
  name: 'search_blocks',
  description: 'Search the ? blocks in one area of the level. Returns what each one hides.',
  schema: z.object({ area: z.string() }),
  execute: async ({ area }) => level.search(area), // your code
})

// The answer as data. Its schema is checked before the loop is allowed to stop.
const markStar = tool({
  name: 'mark_star',
  description: 'Put a marker on the level map where the star is. Call it once, at the end.',
  schema: z.object({ item: z.literal('star'), block: z.number().int().positive() }),
  execute: async ({ block }) => map.addMarker(block), // your code
})

const agent = await createLocalAgent({
  // Any OpenAI-compatible endpoint: OpenAI, Ollama, LM Studio, vLLM, a proxy…
  provider: new OpenAIProvider({
    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
  }),
  tools: [searchBlocks, markStar],
  appendSystemPrompt:
    'When you know where the star is, deliver it with mark_star. ' +
    "If a few searches come back empty, say you couldn't find it.",
  maxTurns: 10, // the clock. Without it, the default is 25.
  stopOnToolNames: ['mark_star'], // the warp pipe
})

const last = await agent.run('Is there a hidden star in this level?')

// The loop hands back its last message whichever way it ended. Read it to find out which.
const call = last.content.find((block) => block.type === 'tool_use')
if (!call) {
  console.log('end_turn:', last.content) // the flag: a plain text answer
} else if (call.name === 'mark_star') {
  console.log('answer:', call.input) // the warp pipe: { item, block }, schema-checked
} else {
  // The clock: maxTurns ran out while the model was still asking for tools.
  throw new Error(`No answer: the run stopped while asking for ${call.name}`)
}

// The three exits of an agent 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
}

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

type ToolFn = (args: Record<string, unknown>) => Promise<string>
const tools: Record<string, ToolFn> = { search_blocks: searchBlocks, mark_star: markStar }
const toolSchemas = [/* one JSON Schema per tool */]
// Terminal tools: once one runs without error, the loop is over.
const stopOn = new Set(['mark_star'])

// Say how the run ended, so the caller can tell an answer from a timeout.
type Outcome =
  | { stop: 'end_turn'; text: string }
  | { stop: 'terminal_tool'; input: Record<string, unknown> }
  | { stop: 'max_turns'; turns: number }

export async function runAgent(prompt: string, maxTurns = 10): Promise<Outcome> {
  const messages: Message[] = [{ 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)

    // Exit 1, the flag: no tool calls, the model is done.
    if (choice.finish_reason !== 'tool_calls') return { stop: 'end_turn', text: reply.content ?? '' }

    for (const call of reply.tool_calls ?? []) {
      const run = tools[call.function.name]
      let input: Record<string, unknown> = {}
      let output = `Unknown tool: ${call.function.name}`
      let failed = true
      if (run) {
        try {
          input = JSON.parse(call.function.arguments)
          output = await run(input)
          failed = false
        } catch (err) {
          output = `Error: ${err instanceof Error ? err.message : err}`
        }
      }
      messages.push({ role: 'tool', tool_call_id: call.id, content: output })

      // Exit 2, the warp pipe: a terminal tool ran fine. Its input is the answer.
      // If it failed, the error goes back to the model and the loop keeps going.
      if (stopOn.has(call.function.name) && !failed) return { stop: 'terminal_tool', input }
    }
  }
  // Exit 3, the clock: out of turns. Say so out loud; don't pass a tool call off as an answer.
  return { stop: 'max_turns', turns: maxTurns }
}

# The three exits of an agent loop, from scratch. Standard library only, no SDK.
import json
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
}

TOOLS = {"search_blocks": search_blocks, "mark_star": mark_star}
TOOL_SCHEMAS = [...]  # one JSON Schema per tool
# Terminal tools: once one runs without error, the loop is over.
STOP_ON = {"mark_star"}


def chat(messages):
    request = urllib.request.Request(
        f"{LLM['base_url']}/chat/completions",
        data=json.dumps({"model": LLM["model"], "messages": messages, "tools": TOOL_SCHEMAS}).encode(),
        headers={"Content-Type": "application/json", "Authorization": f"Bearer {LLM['api_key']}"},
    )
    with urllib.request.urlopen(request) as response:
        return json.load(response)["choices"][0]


def run_agent(prompt, max_turns=10):
    """Returns how the run ended, so the caller can tell an answer from a timeout."""
    messages = [{"role": "user", "content": prompt}]

    for _ in range(max_turns):
        choice = chat(messages)
        reply = choice["message"]
        messages.append(reply)

        # Exit 1, the flag: no tool calls, the model is done.
        if choice["finish_reason"] != "tool_calls":
            return {"stop": "end_turn", "text": reply.get("content") or ""}

        for call in reply.get("tool_calls", []):
            name = call["function"]["name"]
            args = json.loads(call["function"]["arguments"])
            run = TOOLS.get(name)
            failed = run is None
            try:
                output = run(**args) if run else f"Unknown tool: {name}"
            except Exception as err:
                failed = True
                output = f"Error: {err}"
            messages.append({"role": "tool", "tool_call_id": call["id"], "content": output})

            # Exit 2, the warp pipe: a terminal tool ran fine. Its input is the answer.
            # If it failed, the error goes back to the model and the loop keeps going.
            if name in STOP_ON and not failed:
                return {"stop": "terminal_tool", "input": args}

    # Exit 3, the clock: out of turns. Say so out loud; don't pass a tool call off as an answer.
    return {"stop": "max_turns", "turns": max_turns}