Profile img

놀래라

@davidclimbing@hackers.pub · 19 following · 14 followers

레고를 뿌리고 뿌린 레고들을 쌓고 있습니다.

음악 작곡에서 시작해 몽골학을 거쳐, 지금은 컴퓨터 공학과 친해지려고 노력하고 있습니다. 한때 지평선을 넓히는 데 집중했다면, 이제는 뿌리를 내려 깊어지려고 노력 중입니다.

GitHub
@davidclimbing

놀래라 shared the below article:

Claude Code의 거의 모든 것은 Tool Use 입니다. MCP도 subagent도 Skills 역시요.

자손킴 @jasonkim@hackers.pub

이번 글에서는 지난글에 이어서 Claude가 도구를 사용하는 구체적인 방법을 알아본다. Claude가 사용할 수 있는 도구들의 목록은 Tools 섹션에 포함되어 있다. Tools 섹션에 대해서는 이전 글을 참고한다.

Tool Use 란?

Tool Use는 Claude가 외부 도구(함수)를 호출하여 실제 작업을 수행할 수 있게 하는 메커니즘이다. Claude는 텍스트 생성만으로는 수행할 수 없는 작업들, 예를 들어 파일 읽기, 명령어 실행, 웹 검색 등을 도구를 통해 수행한다.

Claude에게 사용 가능한 도구들의 스키마를 알려주면 Claude는 사용자의 요청을 분석하여 적절한 도구를 선택하고 필요한 파라미터와 함께 도구 사용을 요청한다. 에이전트(클라이언트)는 이 요청을 받아 실제로 도구를 실행하고 그 결과를 다시 Claude에게 전달한다.

Tools 섹션: 도구 정의하기

Claude가 도구를 사용하려면 먼저 어떤 도구가 있는지 알아야 한다. 에이전트는 API 요청의 tools 배열에 사용 가능한 도구들을 정의한다. 각 도구는 이름, 설명, 그리고 입력 스키마를 포함한다.

Bash 도구 정의 예시

{
  "name": "Bash",
  "description": "Executes a given bash command in a persistent shell session with optional timeout, ensuring proper handling and security measures.\n\nIMPORTANT: This tool is for terminal operations like git, npm, docker, etc...",
  "input_schema": {
    "type": "object",
    "properties": {
      "command": {
        "type": "string",
        "description": "The command to execute"
      },
      "timeout": {
        "type": "number",
        "description": "Optional timeout in milliseconds (max 600000)"
      },
      "description": {
        "type": "string",
        "description": "Clear, concise description of what this command does in 5-10 words, in active voice."
      }
    },
    "required": ["command"],
    "additionalProperties": false,
    "$schema": "http://json-schema.org/draft-07/schema#"
  }
}

Glob 도구 정의 예시

{
  "name": "Glob",
  "description": "- Fast file pattern matching tool that works with any codebase size\n- Supports glob patterns like \"**/*.js\" or \"src/**/*.ts\"\n- Returns matching file paths sorted by modification time\n- Use this tool when you need to find files by name patterns",
  "input_schema": {
    "type": "object",
    "properties": {
      "pattern": {
        "type": "string",
        "description": "The glob pattern to match files against"
      },
      "path": {
        "type": "string",
        "description": "The directory to search in. If not specified, the current working directory will be used."
      }
    },
    "required": ["pattern"],
    "additionalProperties": false,
    "$schema": "http://json-schema.org/draft-07/schema#"
  }
}

도구 정의에서 description이 중요하다. Claude는 이 설명을 읽고 어떤 상황에서 해당 도구를 사용해야 하는지 판단한다. input_schema는 JSON Schema 형식으로 Claude가 도구를 호출할 때 어떤 파라미터를 어떤 형식으로 전달해야 하는지 정의한다.

Claude가 도구를 선정하는 방법

Claude가 도구를 선택하는 과정은 Messages API의 대화 흐름 속에서 이루어진다. 실제 예시를 통해 살펴보자.

사용자의 요청

사용자가 "이 NestJS 프로젝트에서 entity 구조를 탐색해주세요"라고 요청하면 에이전트는 다음과 같은 메시지를 API에 전송한다:

{
  "role": "user",
  "content": [
    {
      "type": "text",
      "text": "이 NestJS TypeScript 프로젝트에서 entity 구조를 탐색해주세요..."
    }
  ]
}

Claude의 도구 사용 요청

Claude는 사용자의 요청을 분석하고 작업 수행에 필요한 도구들을 선택하여 tool_use 블록으로 응답한다:

{
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "이 NestJS 프로젝트의 entity 구조를 철저하게 탐색하겠습니다."
    },
    {
      "type": "tool_use",
      "id": "toolu_01ABC123XYZ",
      "name": "Glob",
      "input": {
        "pattern": "**/*.entity.ts"
      }
    },
    {
      "type": "tool_use",
      "id": "toolu_01DEF456UVW",
      "name": "Bash",
      "input": {
        "command": "find /workspace/my-nestjs-project/src -type f -name \"*.ts\" | grep -E \"(entity|entities)\" | head -20",
        "description": "Find entity files in src directory"
      }
    }
  ]
}

여기서 주목할 점이 있다. Claude는 한 번의 응답에서 여러 도구를 동시에 요청할 수 있다. 위 예시에서는 GlobBash 두 도구를 병렬로 요청했다. 각 도구 요청에는 고유한 id가 부여되어 나중에 결과를 매핑할 때 사용된다.

응답의 stop_reason

Claude가 도구 사용을 요청하면 API 응답의 stop_reason"tool_use"로 설정된다:

{
  "id": "msg_01XYZ789ABC",
  "type": "message",
  "role": "assistant",
  "model": "claude-haiku-4-5-20251001",
  "content": [...],
  "stop_reason": "tool_use",
  "usage": {
    "input_tokens": 714,
    "output_tokens": 314
  }
}

stop_reason은 에이전트에게 "응답이 끝난 것이 아니라 도구 실행이 필요하다"는 신호를 보낸다.

에이전트는 tool_use 요청을 받으면 무엇을 하는가?

에이전트(클라이언트)가 stop_reason: "tool_use" 응답을 받으면 다음 단계를 수행해야 한다:

  1. 도구 요청 파싱: 응답의 content 배열에서 type: "tool_use" 블록들을 추출한다.

  2. 도구 실행: 각 도구 요청에 대해 실제 도구를 실행한다. 예를 들어:

    • Bash 도구 → 시스템에서 실제 bash 명령어 실행
    • Glob 도구 → 파일 시스템에서 패턴 매칭 수행
    • Read 도구 → 파일 내용 읽기
  3. 결과 수집: 각 도구의 실행 결과를 수집하고 tool_use_id와 함께 결과를 구성한다.

  4. 모델에 결과 전달: 수집한 결과를 tool_result 형식으로 모델에 다시 전송한다.

이 과정에서 에이전트는 도구 실행의 성공/실패 여부, 타임아웃 처리, 보안 검증 등을 담당한다. Claude는 도구의 스키마와 용도만 알 뿐 실제 실행은 에이전트의 몫이다.

에이전트가 모델에 도구 실행 결과를 알리는 방법

에이전트가 도구를 실행한 후에는 그 결과를 tool_result 형식으로 모델에 전달한다. 이 결과는 user role의 메시지로 전송된다.

tool_result 구조

{
  "role": "user",
  "content": [
    {
      "tool_use_id": "toolu_01DEF456UVW",
      "type": "tool_result",
      "content": "/workspace/my-nestjs-project/src/modules/chat/entities/dm-unlock.entity.ts\n/workspace/my-nestjs-project/src/modules/agora/entities/call-session.entity.ts\n/workspace/my-nestjs-project/src/modules/user/entities/user.entity.ts\n/workspace/my-nestjs-project/src/modules/user/entities/user-profile.entity.ts\n/workspace/my-nestjs-project/src/modules/item/entities/item.entity.ts\n...",
      "is_error": false
    },
    {
      "tool_use_id": "toolu_01ABC123XYZ",
      "type": "tool_result",
      "content": "/workspace/my-nestjs-project/src/modules/agora/entities/agora-event-log.entity.ts\n/workspace/my-nestjs-project/src/modules/agora/entities/call-participant.entity.ts\n/workspace/my-nestjs-project/src/modules/item/entities/item.entity.ts\n...",
      "cache_control": {
        "type": "ephemeral"
      }
    }
  ]
}

tool_result의 핵심 필드는 다음과 같다:

필드 설명
tool_use_id Claude가 요청한 도구의 고유 ID. 어떤 요청에 대한 결과인지 매핑
type 항상 "tool_result"
content 도구 실행의 실제 결과 (문자열)
is_error 도구 실행 실패 시 true
cache_control (선택) 프롬프트 캐싱을 위한 제어 옵션

전체 대화 흐름

tool_result를 받은 Claude는 결과를 분석하고 추가 도구가 필요하면 다시 tool_use를 요청한다. 충분한 정보가 모이면 최종 응답을 생성한다. 이 과정이 반복되면서 복잡한 작업도 단계별로 수행할 수 있다:

User → Claude: "entity 구조를 탐색해주세요"
Claude → Agent: tool_use (Glob, Bash)
Agent → Claude: tool_result (파일 목록)
Claude → Agent: tool_use (Read - 여러 파일)
Agent → Claude: tool_result (파일 내용들)
Claude → User: 최종 분석 결과

실제 예시에서 Claude는 먼저 GlobBash로 entity 파일 목록을 찾고 그 결과를 받은 후 Read 도구로 개별 파일들을 읽어 분석했다:

{
  "type": "text",
  "text": "좋습니다. 이제 주요 entity 파일들을 읽겠습니다."
},
{
  "type": "tool_use",
  "id": "toolu_01GHI789RST",
  "name": "Read",
  "input": {
    "file_path": "/workspace/my-nestjs-project/src/modules/user/entities/user.entity.ts"
  }
},
{
  "type": "tool_use",
  "id": "toolu_01JKL012MNO",
  "name": "Read",
  "input": {
    "file_path": "/workspace/my-nestjs-project/src/modules/user/entities/user-profile.entity.ts"
  }
}

마무리

Claude Code와 같은 에이전트는 모델에 사용할 수 있는 도구를 알려주어 도구를 능동적으로 사용하게 만듦으로써 유저의 실행환경과 상호 협력하여 도구를 실행한다. 유저에게 질문을 하는 AskUserQuestion도 도구이고 심지어 계획 모드를 빠져나가는 ExitPlanMode도 도구다.

MCP(Model Context Protocol) 서버가 제공하는 기능들도 결국 도구로 노출되며 Subagent 호출도 도구를 통해 이루어진다. Skills도 마찬가지다. 결국 Claude Code의 거의 모든 확장 기능은 Tool Use라는 하나의 메커니즘 위에서 동작한다.

이 구조를 이해하면 Claude Code가 어떻게 파일을 읽고, 코드를 실행하고, 웹을 검색하는지 명확해진다. 그리고 새로운 도구를 추가하거나 MCP 서버를 연동할 때도 같은 패턴이 적용된다는 것을 알 수 있다.

Read more →
8

놀래라 shared the below article:

Stop writing if statements for your CLI flags

洪 民憙 (Hong Minhee) @hongminhee@hackers.pub

If you've built CLI tools, you've written code like this:

if (opts.reporter === "junit" && !opts.outputFile) {
  throw new Error("--output-file is required for junit reporter");
}
if (opts.reporter === "html" && !opts.outputFile) {
  throw new Error("--output-file is required for html reporter");
}
if (opts.reporter === "console" && opts.outputFile) {
  console.warn("--output-file is ignored for console reporter");
}

A few months ago, I wrote Stop writing CLI validation. Parse it right the first time. about parsing individual option values correctly. But it didn't cover the relationships between options.

In the code above, --output-file only makes sense when --reporter is junit or html. When it's console, the option shouldn't exist at all.

We're using TypeScript. We have a powerful type system. And yet, here we are, writing runtime checks that the compiler can't help with. Every time we add a new reporter type, we need to remember to update these checks. Every time we refactor, we hope we didn't miss one.

The state of TypeScript CLI parsers

The old guard—Commander, yargs, minimist—were built before TypeScript became mainstream. They give you bags of strings and leave type safety as an exercise for the reader.

But we've made progress. Modern TypeScript-first libraries like cmd-ts and Clipanion (the library powering Yarn Berry) take types seriously:

// cmd-ts
const app = command({
  args: {
    reporter: option({ type: string, long: 'reporter' }),
    outputFile: option({ type: string, long: 'output-file' }),
  },
  handler: (args) => {
    // args.reporter: string
    // args.outputFile: string
  },
});
// Clipanion
class TestCommand extends Command {
  reporter = Option.String('--reporter');
  outputFile = Option.String('--output-file');
}

These libraries infer types for individual options. --port is a number. --verbose is a boolean. That's real progress.

But here's what they can't do: express that --output-file is required when --reporter is junit, and forbidden when --reporter is console. The relationship between options isn't captured in the type system.

So you end up writing validation code anyway:

handler: (args) => {
  // Both cmd-ts and Clipanion need this
  if (args.reporter === "junit" && !args.outputFile) {
    throw new Error("--output-file required for junit");
  }
  // args.outputFile is still string | undefined
  // TypeScript doesn't know it's definitely string when reporter is "junit"
}

Rust's clap and Python's Click have requires and conflicts_with attributes, but those are runtime checks too. They don't change the result type.

If the parser configuration knows about option relationships, why doesn't that knowledge show up in the result type?

Modeling relationships with conditional()

Optique treats option relationships as a first-class concept. Here's the test reporter scenario:

import { conditional, object } from "@optique/core/constructs";
import { option } from "@optique/core/primitives";
import { choice, string } from "@optique/core/valueparser";
import { run } from "@optique/run";

const parser = conditional(
  option("--reporter", choice(["console", "junit", "html"])),
  {
    console: object({}),
    junit: object({
      outputFile: option("--output-file", string()),
    }),
    html: object({
      outputFile: option("--output-file", string()),
      openBrowser: option("--open-browser"),
    }),
  }
);

const [reporter, config] = run(parser);

The conditional() combinator takes a discriminator option (--reporter) and a map of branches. Each branch defines what other options are valid for that discriminator value.

TypeScript infers the result type automatically:

type Result =
  | ["console", {}]
  | ["junit", { outputFile: string }]
  | ["html", { outputFile: string; openBrowser: boolean }];

When reporter is "junit", outputFile is string—not string | undefined. The relationship is encoded in the type.

Now your business logic gets real type safety:

const [reporter, config] = run(parser);

switch (reporter) {
  case "console":
    runWithConsoleOutput();
    break;
  case "junit":
    // TypeScript knows config.outputFile is string
    writeJUnitReport(config.outputFile);
    break;
  case "html":
    // TypeScript knows config.outputFile and config.openBrowser exist
    writeHtmlReport(config.outputFile);
    if (config.openBrowser) openInBrowser(config.outputFile);
    break;
}

No validation code. No runtime checks. If you add a new reporter type and forget to handle it in the switch, the compiler tells you.

A more complex example: database connections

Test reporters are a nice example, but let's try something with more variation. Database connection strings:

myapp --db=sqlite --file=./data.db
myapp --db=postgres --host=localhost --port=5432 --user=admin
myapp --db=mysql --host=localhost --port=3306 --user=root --ssl

Each database type needs completely different options:

  • SQLite just needs a file path
  • PostgreSQL needs host, port, user, and optionally password
  • MySQL needs host, port, user, and has an SSL flag

Here's how you model this:

import { conditional, object } from "@optique/core/constructs";
import { withDefault, optional } from "@optique/core/modifiers";
import { option } from "@optique/core/primitives";
import { choice, string, integer } from "@optique/core/valueparser";

const dbParser = conditional(
  option("--db", choice(["sqlite", "postgres", "mysql"])),
  {
    sqlite: object({
      file: option("--file", string()),
    }),
    postgres: object({
      host: option("--host", string()),
      port: withDefault(option("--port", integer()), 5432),
      user: option("--user", string()),
      password: optional(option("--password", string())),
    }),
    mysql: object({
      host: option("--host", string()),
      port: withDefault(option("--port", integer()), 3306),
      user: option("--user", string()),
      ssl: option("--ssl"),
    }),
  }
);

The inferred type:

type DbConfig =
  | ["sqlite", { file: string }]
  | ["postgres", { host: string; port: number; user: string; password?: string }]
  | ["mysql", { host: string; port: number; user: string; ssl: boolean }];

Notice the details: PostgreSQL defaults to port 5432, MySQL to 3306. PostgreSQL has an optional password, MySQL has an SSL flag. Each database type has exactly the options it needs—no more, no less.

With this structure, writing dbConfig.ssl when the mode is sqlite isn't a runtime error—it's a compile-time impossibility.

Try expressing this with requires_if attributes. You can't. The relationships are too rich.

The pattern is everywhere

Once you see it, you find this pattern in many CLI tools:

Authentication modes:

const authParser = conditional(
  option("--auth", choice(["none", "basic", "token", "oauth"])),
  {
    none: object({}),
    basic: object({
      username: option("--username", string()),
      password: option("--password", string()),
    }),
    token: object({
      token: option("--token", string()),
    }),
    oauth: object({
      clientId: option("--client-id", string()),
      clientSecret: option("--client-secret", string()),
      tokenUrl: option("--token-url", url()),
    }),
  }
);

Deployment targets, output formats, connection protocols—anywhere you have a mode selector that determines what other options are valid.

Why conditional() exists

Optique already has an or() combinator for mutually exclusive alternatives. Why do we need conditional()?

The or() combinator distinguishes branches based on structure—which options are present. It works well for subcommands like git commit vs git push, where the arguments differ completely.

But in the reporter example, the structure is identical: every branch has a --reporter flag. The difference lies in the flag's value, not its presence.

// This won't work as intended
const parser = or(
  object({ reporter: option("--reporter", choice(["console"])) }),
  object({ 
    reporter: option("--reporter", choice(["junit", "html"])),
    outputFile: option("--output-file", string())
  }),
);

When you pass --reporter junit, or() tries to pick a branch based on what options are present. Both branches have --reporter, so it can't distinguish them structurally.

conditional() solves this by reading the discriminator's value first, then selecting the appropriate branch. It bridges the gap between structural parsing and value-based decisions.

The structure is the constraint

Instead of parsing options into a loose type and then validating relationships, define a parser whose structure is the constraint.

Traditional approach Optique approach
Parse → Validate → Use Parse (with constraints) → Use
Types and validation logic maintained separately Types reflect the constraints
Mismatches found at runtime Mismatches found at compile time

The parser definition becomes the single source of truth. Add a new reporter type? The parser definition changes, the inferred type changes, and the compiler shows you everywhere that needs updating.

Try it

If this resonates with a CLI you're building:

  • Documentation
  • Tutorial
  • conditional() reference
  • GitHub

Next time you're about to write an if statement checking option relationships, ask: could the parser express this constraint instead?

The structure of your parser is the constraint. You might not need that validation code at all.

Read more →
7
2

놀래라 shared the below article:

도커로 구축한 랩에서 혼자 실습하며 배우는 네트워크 프로토콜 입문 #3-1

자손킴 @jasonkim@hackers.pub

이 글은 네트워크 계층(L3) 프로토콜의 핵심인 IP에 대해 심도 있게 다룬다. L3 라우터의 역할부터 시작하여, IPv4의 구조, IP 단편화 과정, 그리고 PMTUD(Path MTU Discovery)의 중요성을 설명한다. IP 헤더의 각 필드(버전, 헤더 길이, ToS, 패킷 길이 등)에 대한 자세한 분석을 제공하며, IP 주소와 서브넷 마스크를 통해 네트워크와 호스트를 구분하는 방법을 설명한다. 클래스풀 주소 지정 방식과 클래스리스 주소 지정 방식의 차이점을 비교하고, 공인 IP 주소와 사설 IP 주소의 개념을 명확히 한다. 마지막으로, ICMP(Internet Control Message Protocol)를 통해 IP 레벨의 통신 상태를 확인하고 오류를 알리는 방법을 소개한다. 이 글을 통해 독자는 IP 프로토콜의 기본 원리를 이해하고, 네트워크 문제 해결 능력을 향상시킬 수 있을 것이다.

Read more →
4

대용량 트래픽 처리를 어떻게 경험하냐 물어보는데 사실 이정도만 해도 됨.

1. 큐 시스템 지연을 해결해본 경험 (예: 8시간까지 큐 지연이 있는걸 확인했고 이걸 구조 변경을 통해 해결한 경험)

2. 정적 데이터 요청은 최대한 근원 프로세스까지 도달하지 않게 캐시하여 네트워크 전송 비용 절감 및 응답속도 향상 경험

3. 불특정 다수가 참여하는 텍스트 메시징 서비스에 동영상이 포함되는 경우, 온전하게 동영상 처리하면서도 메시지 교환을 지연시키지 않는 경험

4. 새해 등 기념일에 늘어나는 메시지로 인해 다른 서버가 터져도 내 서버만은 비용 상승이나 큐 지연 없이 서비스 제공해본 경험.

이정도만 모의로 집에서 해보길 강추드림.

5

NPM에 8만6천 회 이상 다운로드된 악성 패키지 대량 유포
------------------------------
- NPM 저장소에서 *100개 이상 자격 증명 탈취용 악성 패키지* 가 8월 이후 탐지되지 않은 채 업로드되어, 총 8만6천 회 이상 다운로드된 사실이 확인됨
- 보안업체
Koi 는 ‘PhantomRaven ’으로 명명한 공격 캠페인이 NPM의 *Remote Dynamic Dependencies(RDD)* 기능을 악용해 126개의 악성 패키지를 배포했…
------------------------------
https://news.hada.io/topic?id=24053&utm_source=googlechat&utm_medium=bot&utm_campaign=1834

0
1

Learn Your Way: 생성형 AI로 교과서를 재구성하기
------------------------------
- 교과서는 본질적으로 *일률적 매체* 라는 한계를 지니며, Google은 생성형 AI로 *대안적 표현과 개인화 예시* 를 자동 생성해 학습 효과와 몰입을 높이는 방식을 탐색 중
- 연구 실험
Learn Your Way 는 교과서를 학습자 수준과 관심사에 맞게 재가공하고, *다중 표현(멀티모달) 컨텐츠* 로 변환해 능동적 학습…
------------------------------
https://news.hada.io/topic?id=23178&utm_source=googlechat&utm_medium=bot&utm_campaign=1834

0
1
30
1
7
6
0
0

Claude에 따르면 대부분의 JavaScript 엔진에서 배열을 비울 때 a.length = 0과 같이 대입하는 게 가장 빠르고 최적화가 잘 된다고 하는데, 이걸 믿어야 할 지 말아야 할 지… 이게 사실이라고 해도 참 답이 없다고 느낀다. 🤦

5
2