按需加载的技能

---
name: custom-cake-order
description: Cakes made to order. Use when a customer wants a cake baked for them — size by guests, flavors, allergies, lead time, deposit.
---

# Custom cake orders

1. Size by guests: up to 12 → 18 cm, up to 24 → 24 cm, more → two tiers.
2. Flavors: chocolate, vanilla, dulce de leche. Nothing else.
3. Nut allergy → the nut-free line. It only bakes on Friday mornings.
4. Check the calendar before you promise a date. Never less than 72 hours.
5. Quote the 50% deposit, and ask before you book. Never book on your own.

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

const checkCalendar = tool({
  name: 'check_calendar',
  description: 'Free baking slots and pickup times for a day, per production line.',
  schema: z.object({ day: z.string(), line: z.enum(['regular', 'nut-free']) }),
  execute: async ({ day, line }) => bakerySlots(day, line), // 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: [checkCalendar],
  // Every folder in ./skills with a SKILL.md is one skill:
  //   skills/custom-cake-order/SKILL.md, skills/catering-quote/SKILL.md, …
  skillSources: [createFileSystemSkillSource({ dir: './skills' })],
  // The default. Only each skill's name and description go in the system prompt,
  // and the agent gets a load_skill tool to fetch a full body when it needs one.
  skillMode: 'on-demand',
  maxTurns: 10,
})

agent.on('tool-end', ({ name, output }) => {
  if (name === 'load_skill') console.log('loaded:', output.slice(0, 60))
})

const last = await agent.run('I need a cake for 20 people this Saturday. Chocolate, and one guest can’t have nuts.')
console.log(last.content)

// On-demand skills, from scratch. Plain fetch and node:fs, no SDK.
import { readdirSync, readFileSync } from 'node:fs'
import { join } from 'node:path'

// 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: 'system' | 'user'; content: string }
  | { role: 'assistant'; content: string | null; tool_calls?: ToolCall[] }
  | { role: 'tool'; tool_call_id: string; content: string }

// 1. Read the skills: one folder per skill, each with a SKILL.md.
//    The frontmatter (the block between the --- lines) holds name and description.
type Skill = { name: string; description: string; body: string }

function readSkill(file: string): Skill {
  const [, front = '', body = ''] = readFileSync(file, 'utf8').match(/^---\n([\s\S]*?)\n---\n?([\s\S]*)$/) ?? []
  const field = (key: string) => front.match(new RegExp(`^${key}:\\s*(.+)$`, 'm'))?.[1]?.trim() ?? ''
  return { name: field('name'), description: field('description'), body: body.trim() }
}

const SKILLS_DIR = './skills'
const skills = new Map(
  readdirSync(SKILLS_DIR, { withFileTypes: true })
    .filter((entry) => entry.isDirectory())
    .map((entry) => readSkill(join(SKILLS_DIR, entry.name, 'SKILL.md')))
    .map((skill) => [skill.name, skill]),
)

// 2. The catalog goes in the system prompt: one line per skill, never the body.
const catalog = [...skills.values()].map((s) => `- \`${s.name}\` — ${s.description}`).join('\n')
const SYSTEM = `You are the order assistant of a bakery.

<available-skills>
When the customer's request matches a skill, call load_skill with its name
before you answer, and follow the instructions it returns.
${catalog}
</available-skills>`

// 3. load_skill is a tool like any other. Its result is the body.
const loadSkill = ({ name }: { name: string }): string => {
  const skill = skills.get(name)
  if (!skill) throw new Error(`Unknown skill "${name}". Available: ${[...skills.keys()].join(', ')}`)
  return `<skill name="${skill.name}">\n${skill.body}\n</skill>`
}

type ToolFn = (args: Record<string, string>) => string | Promise<string>
const tools: Record<string, ToolFn> = {
  load_skill: (args) => loadSkill({ name: args.name ?? '' }),
  check_calendar: checkCalendar, // your code
}
const toolSchemas = [
  {
    type: 'function',
    function: {
      name: 'load_skill',
      description: "Load a skill's full instructions by name. Skills are listed in <available-skills>.",
      parameters: { type: 'object', properties: { name: { type: 'string' } }, required: ['name'] },
    },
  },
  /* check_calendar's schema */
]

// 4. The loop from level 2. Nothing in it knows about skills.
export async function runAgent(prompt: string, maxTurns = 10): Promise<string> {
  const messages: Message[] = [
    { role: 'system', content: SYSTEM },
    { 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 run = tools[call.function.name]
      let output = `Unknown tool: ${call.function.name}`
      try {
        if (run) output = await run(JSON.parse(call.function.arguments))
      } catch (err) {
        output = `Error: ${err instanceof Error ? err.message : err}`
      }
      // A loaded body lands here, in the history, and every later turn resends it.
      messages.push({ role: 'tool', tool_call_id: call.id, content: output })
    }
  }
  throw new Error(`No answer after ${maxTurns} turns`)
}

console.log(await runAgent('I need a cake for 20 people this Saturday. Chocolate, and one guest can’t have nuts.'))

# On-demand skills, from scratch. Standard library only, no SDK.
import json
import re
import urllib.request
from pathlib import Path

# 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
}


# 1. Read the skills: one folder per skill, each with a SKILL.md.
#    The frontmatter (the block between the --- lines) holds name and description.
def read_skill(path):
    match = re.match(r"^---\n(.*?)\n---\n?(.*)$", path.read_text(encoding="utf-8"), re.S)
    front, body = match.groups() if match else ("", "")

    def field(key):
        found = re.search(rf"^{key}:\s*(.+)$", front, re.M)
        return found.group(1).strip() if found else ""

    return {"name": field("name"), "description": field("description"), "body": body.strip()}


SKILLS = {
    skill["name"]: skill
    for skill in (read_skill(folder / "SKILL.md") for folder in Path("skills").iterdir() if folder.is_dir())
}

# 2. The catalog goes in the system prompt: one line per skill, never the body.
CATALOG = "\n".join(f"- `{s['name']}` — {s['description']}" for s in SKILLS.values())
SYSTEM = f"""You are the order assistant of a bakery.

<available-skills>
When the customer's request matches a skill, call load_skill with its name
before you answer, and follow the instructions it returns.
{CATALOG}
</available-skills>"""


# 3. load_skill is a tool like any other. Its result is the body.
def load_skill(name):
    if name not in SKILLS:
        raise ValueError(f'Unknown skill "{name}". Available: {", ".join(SKILLS)}')
    return f'<skill name="{name}">\n{SKILLS[name]["body"]}\n</skill>'


TOOLS = {"load_skill": load_skill, "check_calendar": check_calendar}  # check_calendar: your code
TOOL_SCHEMAS = [
    {
        "type": "function",
        "function": {
            "name": "load_skill",
            "description": "Load a skill's full instructions by name. Skills are listed in <available-skills>.",
            "parameters": {"type": "object", "properties": {"name": {"type": "string"}}, "required": ["name"]},
        },
    },
    # check_calendar's schema
]


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]


# 4. The loop from level 2. Nothing in it knows about skills.
def run_agent(prompt, max_turns=10):
    messages = [{"role": "system", "content": SYSTEM}, {"role": "user", "content": prompt}]

    for _ in range(max_turns):
        choice = chat(messages)
        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"]
            try:
                output = TOOLS[name](**json.loads(call["function"]["arguments"]))
            except Exception as err:
                output = f"Error: {err}"
            # A loaded body lands here, in the history, and every later turn resends it.
            messages.append({"role": "tool", "tool_call_id": call["id"], "content": output})

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


print(run_agent("I need a cake for 20 people this Saturday. Chocolate, and one guest can't have nuts."))