대답 옆에 근거를 붙인다 — 설비에 물어보는 LLM 붙이기

plant_server (mcp_server)      assistant (client + server)          태블릿
  equipment.list      ◀──MCP──   plant 의 클라이언트                ──MCP──▶  ui://assistant
  equipment.read                 화면의 서버                                   답 + 호출 기록
  checklist.get                  가운데에 모델

handler: (args) async {
  final id = (args['id'] as String?)?.toUpperCase();
  final m = _machines[id];
  if (m == null) { /* ... */ }

  // 서버는 사실과, 그 사실이 한계와 어떻게 비교되는지를 말한다.
  // 기계가 "괜찮다"고는 말하지 않는다 — 그 단어는 점검표를 든
  // 사람의 것이다.
  final overdue = (m['runHours'] as int) > (m['serviceEveryHours'] as int);
  final vibrationOver =
      (m['vibrationMm'] as num) > (m['vibrationLimitMm'] as num);
  return _json({
    'id': id,
    ...m,
    'serviceOverdue': overdue,
    'vibrationOverLimit': vibrationOver,
  });
}

server.addTool(
  name: 'checklist.get',
  description:
      'Get the plant safety checklist for a machine type (press, conveyor, welder). '
      'These steps are set by the plant engineer and must not be paraphrased.',
  /* ... */
);

// 1. 설비에 붙는다. 특권 채널이 아니라 평범한 MCP 클라이언트다.
final connected = await McpClient.createAndConnect(
  config: McpClient.simpleConfig(name: 'Plant Assistant', version: '1.0.0'),
  transportConfig: const TransportConfig.stdio(
    command: 'dart',
    arguments: ['run', 'bin/server.dart'],
    workingDirectory: '../plant_server',
  ),
);
final mcpClient = connected.get();

// 2. 프로바이더를 등록하고, 둘을 잇는 클라이언트를 만든다.
final bench = BenchProvider();
final llm = McpLlm()..registerProvider('bench', BenchProviderFactory(bench));

final client = await llm.createClient(
  providerName: 'bench',
  config: LlmConfiguration(model: 'bench-1'),
  mcpClient: mcpClient,          // ← 도구가 여기로 들어간다
  systemPrompt: assistantSystemPrompt,
);

// 3. 묻는다. 도구 목록 전달, 도구 호출 실행, 결과 되먹임까지 이 한 줄 안에서 돈다.
final response = await client.chat(question, enableTools: true);

//      llm.registerProvider('claude', ClaudeProviderFactory());
//      final client = await llm.createClient(
//        providerName: 'claude',
//        config: LlmConfiguration(apiKey: Platform.environment['ANTHROPIC_API_KEY'],
//                                 model: 'claude-sonnet-5'),
//        mcpClient: mcpClient,
//        systemPrompt: systemPrompt,
//      );
//
//    Nothing below this point changes.

You help a maintenance technician standing in front of a machine.

Rules:
- Every number you state must have come from a tool result in this conversation.
  If you do not have it, call the tool. Never estimate a reading.
- Safety checklist steps are the plant engineer's. Quote them in order and do
  not paraphrase, shorten or reorder them.
- You do not decide whether a machine is safe to work on. You report what the
  readings are, how they compare to their limits, and what the checklist says.
- If the plant has no tool that answers the question, say so.

// 설비 감사 로그의 현재 지점을 표시해 둔다. 그래야 이 질문이 유발한 호출만
// 귀속시킬 수 있다 — 부팅 이후 전부가 아니라.
final before = await _auditCalls();
final response = await llm.chat(question, enableTools: true);
final after = await _auditCalls();

_answer = response.text.trim();
_toolCalls = after.sublist(before.length);
_notice = _toolCalls.isEmpty
    ? 'No tool was called. Treat this as the assistant talking about '
      'itself, not about the plant.'
    : '';

// audit.log 자체도 도구 호출이지만 그건 우리 것이지 어시스턴트의 것이 아니다 —
// 세면 모든 답의 근거가 하나씩 부풀어 오른다.
return calls.cast<String>().where((c) => !c.startsWith('audit.log')).toList();

// 근거 개수는 근거가 없을 때 안심시키는 얼굴을 하면 안 된다.
// "0 tool calls" 에 초록색은 흘깃 보면 "확인됨, 이상 없음"으로 읽히고,
// 그건 뜻하는 바의 정반대다.
{
  'type': 'conditional',
  'condition': '{{grounded}}',
  'then': { /* 초록, N건 */ },
  'else': {
    'type': 'text',
    'content': 'Not built from any plant data',
    'style': {'fontSize': 13, 'fontWeight': 'bold', 'color': _accent},
  },
},

[+ 2240ms] assistant up — it is a client of the plant and a server to us
[+ 2253ms] assistant offers: assistant.ask, assistant.state
[+ 2722ms] Q: how is CONV-03 doing?
[+ 2723ms]    grounded=true calls=1 equipment.read(id: CONV-03) -> overdue=true vibrationOver=true
[+ 2723ms]    A: CONV-03 needs attention — service is overdue (9310 h against a 8000 h
              interval) and vibration is above limit (5.2 mm against 4.5 mm).
[+ 2894ms] Q: what is the checklist before I work on CONV-03?
[+ 2894ms]    grounded=true calls=1 checklist.get(machineType: conveyor) -> 4 steps
[+ 3028ms] Q: what is the weather like?
[+ 3028ms]    grounded=false calls=0
[+ 3029ms]    A: I can look up machines, their current readings, and the plant checklist
              for a machine type. Ask me about one of those.

# tools offered by the plant: equipment.list, equipment.read, checklist.get, audit.log

# tool calls the plant actually received (4):
#   equipment.list(line: A) -> 2 machines
#   equipment.read(id: CONV-03) -> overdue=true vibrationOver=true
#   checklist.get(machineType: conveyor) -> 4 steps
#   equipment.read(id: PRESS-01) -> overdue=false vibrationOver=false

# provider decisions (9):
#   chose equipment.list(line: A)
#   answer from tool result (141 chars)
#   ...
#   no tool matched — declined to guess

$ dart analyze     # plant_server
No issues found!
$ dart analyze     # assistant
No issues found!
$ bash verify.sh
   [player] open in AppPlayer, ask three questions
plant-assistant: two grounded answers with their calls on screen, one ungrounded answer flagged

# an answer about a machine must have reached the plant
reading = s.call("assistant.ask", {"question": "how is CONV-03 doing?"})
assert reading["grounded"], "a question about a machine must reach the plant"

# an unanswerable question must not have invented tool calls
weather = s.call("assistant.ask", {"question": "what is the weather like?"})
assert not weather["grounded"] and weather["notice"], weather

# and the checklist reaches the screen as a quotation
ap.wait_text("checklist.get")

( cd plant_server && dart pub get )
( cd assistant && dart pub get )

# ask from the CLI
cd assistant
dart run bin/ask.dart                        # five prepared questions
dart run bin/ask.dart "how is PRESS-01 doing?"