Skip to content

Job Manufacturing

job_manufacturing — G6 Manufacturing job agent.

Cluster: Job Agents | Type: component | MCP Tools: 26

Overview

Domain-specialist job agent for manufacturing operations. Schedules production runs, optimises processes for throughput, conducts quality inspections, manages supply-chain procurement, tracks output against targets, and analyses defect rates — covering the full manufacturing operations lifecycle within G6's safety-bounded, audit-trailed JobAgentBlock framework.

When to use:

  • Scheduling production runs across multiple lines to meet order demand with minimal changeover
  • Identifying root causes of quality defects and recommending process adjustments
  • Managing supplier procurement against production schedules and inventory buffers
  • Analysing OEE (Overall Equipment Effectiveness) and recommending improvement actions

Example:

from mvp.job_manufacturing import JobManufacturingBlock, JobManufacturingInput

block = JobManufacturingBlock()
result = block.infer(JobManufacturingInput(
    task="Schedule production for 3 product lines over the next 2 weeks to fulfil 1,200 outstanding orders with minimum changeover time",
    context={"plant": "Campbellfield-VIC", "shifts_per_day": 2, "lines": ["L1", "L2", "L3"]},
))
# result.ok → True; result.value → JobManufacturingOutput with result, artifacts

Works well with: job_framework, job_logistics, job_machinery_operator

Public API

JobManufacturingBlock(JobAgentBlock)

G6 Manufacturing job agent — Tier 1 block with MCP delegation.

Field Type Default
name str 'job_manufacturing'
sector SectorClassification field(default_factory=lambda: _SECTOR)
toolkit ToolkitSpec \| None field(default_factory=lambda: JOB_TOOLKITS.get('manufacturing'))
mcp_module str 'mvp.job_manufacturing.manufacturing_mcp.server'
capabilities ClassVar[set[type]] {Extensible, HumanLearnable, Collaborative, ProblemSolvable, KnowledgeGrounded, Memorable, AgentCommunicable, Actuatable}

Methods:

infer(data)

JobManufacturingInput(JobInput)

Input for the Manufacturing job agent.

JobManufacturingOutput(JobOutput)

JobManufacturingMCPBlock(AIBlock[MCPJobManufacturingInput, MCPJobManufacturingOutput, dict])

26-op MCP block for the Manufacturing job agent.

Field Type Default
name str 'job_manufacturing_mcp'
state dict field(default_factory=dict)
db_path str ':memory:'
resource_bounds ResourceBounds field(default_factory=ResourceBounds)
usage ResourceUsage field(default_factory=ResourceUsage)

Methods:

infer(data: MCPJobManufacturingInput) -> Result[MCPJobManufacturingOutput]

MCPJobManufacturingInput(BaseModel)

Input to JobManufacturingMCPBlock — 26-op dispatch.

Field Type Default
op Literal['schedule_production', 'optimize_process', 'inspect_quality', 'manage_supply_chain', 'track_output', 'analyze_defects', 'evaluate_efficiency', 'assess_capacity', 'benchmark_throughput', 'audit_safety', 'create_proposal', 'review_deliverable', 'delegate_task', 'report_status', 'request_feedback', 'store_artifact', 'retrieve_artifact', 'list_artifacts', 'search_artifacts', 'archive', 'plan_sprint', 'track_progress', 'reflect_on_outcome', 'get_capabilities', 'info', 'list_patterns'] required
task str ''
context dict[str, Any] Field(default_factory=dict)
parameters dict[str, Any] Field(default_factory=dict)
artifact_id str ''
query str ''
run_mode str 'beta'
reviewer_signature str ''

MCPJobManufacturingOutput(BaseModel)

Output from JobManufacturingMCPBlock.

Field Type Default
op str required
result str ''
artifacts list[dict[str, Any]] Field(default_factory=list)
records list[dict[str, Any]] Field(default_factory=list)
message str ''
count int 0
found bool False
metadata dict[str, Any] Field(default_factory=dict)
degraded bool False
degradation_reason str \| None None
completion_state CompletionState 'qualified-draft'
warning_card dict[str, Any] \| None None
evidence dict[str, Any] Field(default_factory=dict)

ManufacturingStore(JobStore)

SQLite store for the Manufacturing job agent.

Constructor:

Parameter Type Default
db_path str ':memory:'

Methods:

create_production_order(product: str, quantity: float = 0, due_date: str = '', priority: str = 'normal', bom: list | None = None, routing: list | None = None, data: dict | None = None) -> str

get_production_order(order_id: str) -> dict | None

list_production_orders(status: str = '') -> list[dict]

update_order_status(order_id: str, status: str) -> bool

create_quality_record(order_id: str, inspection_type: str = '', measurements: list | None = None, specification: dict | None = None, pass_fail: str = '', inspector: str = '', inspected_date: str = '') -> str

get_quality_records(order_id: str = '', pass_fail: str = '') -> list[dict]

add_equipment(name: str, line: str = '', oee_availability: float = 0, oee_performance: float = 0, oee_quality: float = 0, last_maintenance: str = '', next_maintenance: str = '', status: str = 'operational', data: dict | None = None) -> str

get_equipment(equip_id: str) -> dict | None

list_equipment(line: str = '', status: str = '') -> list[dict]

update_equipment_oee(equip_id: str, oee_availability: float, oee_performance: float, oee_quality: float) -> bool

add_inventory_item(part_number: str, description: str = '', quantity_on_hand: float = 0, reorder_point: float = 0, lead_time_days: float = 0, unit_cost: float = 0, location: str = '', data: dict | None = None) -> str

get_inventory_item(item_id: str) -> dict | None

list_inventory(location: str = '') -> list[dict]

get_low_stock_items() -> list[dict]

create_nonconformance(order_id: str = '', description: str = '', category: str = '', severity: str = 'minor', root_cause: str = '', corrective_action: str = '', data: dict | None = None) -> str

get_nonconformances(order_id: str = '', status: str = '', severity: str = '') -> list[dict]

close_nonconformance(nc_id: str, root_cause: str = '', corrective_action: str = '') -> bool

Functions

assemble_review_text(output: Any) -> str

Collect the reviewable free text from a JobManufacturingOutput (duck-typed).

assess_manufacturing_output(output: Any, qa_block: Any | None = None, generate: Any | None = None) -> GroundedRunResult

Run grounded four-valued QA over a manufacturing output.

MCP Tools

Operation Source
schedule_production manufacturing_mcp
optimize_process manufacturing_mcp
inspect_quality manufacturing_mcp
manage_supply_chain manufacturing_mcp
track_output manufacturing_mcp
analyze_defects manufacturing_mcp
evaluate_efficiency manufacturing_mcp
assess_capacity manufacturing_mcp
benchmark_throughput manufacturing_mcp
audit_safety manufacturing_mcp
create_proposal manufacturing_mcp
review_deliverable manufacturing_mcp
delegate_task manufacturing_mcp
report_status manufacturing_mcp
request_feedback manufacturing_mcp
store_artifact manufacturing_mcp
retrieve_artifact manufacturing_mcp
list_artifacts manufacturing_mcp
search_artifacts manufacturing_mcp
archive manufacturing_mcp
plan_sprint manufacturing_mcp
track_progress manufacturing_mcp
reflect_on_outcome manufacturing_mcp
get_capabilities manufacturing_mcp
info manufacturing_mcp
list_patterns manufacturing_mcp