答えの横に根拠を付ける — 設備に問い合わせる LLM をつなぐ

plant_server (mcp_server)      assistant (client + server)          tablet
  equipment.list      ◀──MCP──   a client of the plant              ──MCP──▶  ui://assistant
  equipment.read                 a server to the screen                        answer + call record
  checklist.get                  the model in the middle

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

  // The server states facts, and how those facts compare to their limits.
  // It does not say the machine is "fine" — that word belongs to the person
  // holding the checklist.
  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.',
  /* ... */
);

  final llm = McpLlm()..registerProvider('bench', BenchProviderFactory(bench));

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

  // 3. Ask.
  for (final q in questions) {
    stdout.writeln('\n> $q');
    final response = await client.chat(q, enableTools: true);
    stdout.writeln(response.text.trim());
  }

  // 4. What the plant was actually asked. An assistant's answer is only worth
  //    what the record behind it is worth.
  final audit = await mcpClient.callTool('audit.log', const {});
  final first = audit.content.first;
  if (first is TextContent) {
    final calls = (jsonDecode(first.text) as Map<String, dynamic>)['calls'] as List;
    stdout.writeln('\n# tool calls the plant actually received (${calls.length}):');

//      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.

            ? 'No tool was called. Treat this as the assistant talking about '
              'itself, not about the plant.'
            : '';
        return _state();
      },
    );

    server.addTool(
      name: 'assistant.state',
      description: 'Current question, answer and the tool calls behind it',
      inputSchema: const {'type': 'object', 'properties': {}},

    // audit.log is itself a tool call, but it is ours, not the assistant's —
    // counting it would inflate every answer's evidence by one.

            'style': {'fontSize': 13, 'fontWeight': 'bold', 'color': _accent},
          },
        },
        {
          'type': 'box',
          'width': 720,
          'height': 110,
          'child': {
            'type': 'list',
            'items': '{{toolCalls}}',
            'shrinkWrap': true,
            'spacing': 4,

[+ 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?"