Build the application

## Build
Evaluate machine tooling wear and work-in-progress queue accumulation across simulated manufacturing cells. Synthesize dynamic lot rerouting proposals to bypass impending tooling changes.

## User
Production Shift Coordinator

## Workflow
1. Extract tooling life counters and buffer wait queues from simulated open62541 server endpoints.
2. Predict upcoming tooling change lockouts that will interrupt line flow within two hours.
3. Evaluate alternative routing lines against current work-in-progress queue depths.
4. Generate an optimized lot dispatch schedule that minimizes line idle time during tooling swaps.

## Interface
Production dispatch dashboard highlighting machine tool life countdowns, buffer bottlenecks, and re-routing suggestions.

## Data
JSON streams detailing CNC tool wear percentages, remaining cycle life, and queue counts from open62541 servers.
Starter examples below are synthetic. They are not downloaded records.

## Source
[open62541 OPC UA](https://raw.githubusercontent.com/open62541/open62541/master/README.md)
Extracts tool usage indices and queue attributes from open62541 server information models.

## Tools
anthropic-claude, pandas, fastapi.
Claude Sonnet provides rapid and nuanced multi-constraint scheduling trade-off evaluation via hosted API.
Hosted Claude API using Anthropic Python SDK to reason over shop floor schedules and tooling constraints.

## Deliverables
Submit runnable source, pinned dependencies, setup commands, a working interface, example outputs, and a recorded end-to-end demo. Include tests and an action log.

## Acceptance
- Identifies machines within 10% of mandatory tooling replacement lockouts.
- Proposes lot dispatches that divert high-volume parts away from impending changeovers.
- Produces a validated dispatch table ready for shift supervisor review.

## Starter Examples
```json
[
  {
    "input": {
      "machines": [
        {
          "machine_id": "CNC-01",
          "tool_life_remaining_cycles": 12,
          "wip_queue": 15,
          "cycle_time_min": 3
        },
        {
          "machine_id": "CNC-02",
          "tool_life_remaining_cycles": 150,
          "wip_queue": 2,
          "cycle_time_min": 3.2
        }
      ],
      "incoming_batch": {
        "batch_id": "BATCH-707",
        "lot_count": 8
      }
    },
    "expected_output": {
      "critical_machine": "CNC-01",
      "recommended_action": "DIVERT_TO_CNC-02",
      "dispatch_explanation": "CNC-01 will reach tool lockout in 12 cycles, causing WIP blockage; CNC-02 has capacity and tool life.",
      "projected_downtime_avoided_min": 25.6
    }
  },
  {
    "input": {
      "machines": [
        {
          "machine_id": "CNC-01",
          "tool_life_remaining_cycles": 200,
          "wip_queue": 1,
          "cycle_time_min": 3
        },
        {
          "machine_id": "CNC-02",
          "tool_life_remaining_cycles": 180,
          "wip_queue": 1,
          "cycle_time_min": 3.2
        }
      ],
      "incoming_batch": {
        "batch_id": "BATCH-708",
        "lot_count": 4
      }
    },
    "expected_output": {
      "critical_machine": "NONE",
      "recommended_action": "ROUTE_TO_CNC-01",
      "dispatch_explanation": "CNC-01 provides faster cycle time and ample tool life remaining.",
      "projected_downtime_avoided_min": 0
    }
  }
]
```

## Safety
Generates advisory routing proposals; actual machine dispatch commands are executed solely by human operators.
Use mock external writes. Require human review before any real deployment.