aiwg/agentic/code/addons/nlp-prod/schemas/cost-model.yaml

Deployment tool and support utility for AI context. Copies agents, skills, commands, rules, and behaviors into the paths each AI platform reads (Claude Code, Codex, Copilot, Cursor, Warp, OpenClaw, and 6 more) so one source of truth works across 10 platfo

# Cost Model Schema
# Schema for cost-model.yaml generated by aiwg nlp productionize and cost-analyst agent

$schema: "https://json-schema.org/draft/2020-12/schema"
$id: "https://aiwg.io/schemas/nlp-prod/cost-model/v1"
title: "NLP Pipeline Cost Model"
description: |
  Schema for cost-model.yaml — the TCO model for a production pipeline.
  Generated by the Cost Analyst agent and `aiwg nlp estimate-cost`.
  Stored in the pipeline directory alongside pipeline.config.yaml.

type: object
required:
  - version
  - pipeline
  - analyzed_at
  - steps
  - totals

properties:
  version:
    type: string
    default: "1.0.0"

  pipeline:
    type: string
    description: "Pipeline name"

  analyzed_at:
    type: string
    format: date-time

  monthly_volume:
    type: integer
    description: "Assumed monthly call volume for projections"

  steps:
    type: array
    items:
      $ref: "#/$defs/StepCost"

  totals:
    $ref: "#/$defs/TotalCost"

  recommendations:
    type: array
    items:
      $ref: "#/$defs/CostRecommendation"

$defs:
  StepCost:
    type: object
    required:
      - name
      - model
      - avg_input_tokens
      - avg_output_tokens
      - cost_per_call_usd
    properties:
      name:
        type: string

      model:
        type: string

      avg_input_tokens:
        type: integer

      avg_output_tokens:
        type: integer

      cost_per_call_usd:
        type: number

      cacheable_prefix_tokens:
        type: integer
        default: 0
        description: "Tokens in stable system prompt prefix eligible for caching"

      cache_savings_per_call_usd:
        type: number
        default: 0.0
        description: "Per-call savings if prompt cache enabled"

      parallelizable_with:
        type: array
        items:
          type: string
        description: "Names of steps with no data dependency (can run concurrently)"

  TotalCost:
    type: object
    required:
      - cost_per_call_usd
    properties:
      cost_per_call_usd:
        type: number

      monthly_cost_usd:
        type: number
        description: "Monthly cost without any optimizations"

      monthly_cost_with_caching_usd:
        type: number
        description: "Monthly cost with prompt caching enabled"

      monthly_cost_optimized_usd:
        type: number
        description: "Monthly cost after all recommended optimizations"

      potential_savings_pct:
        type: number
        minimum: 0.0
        maximum: 100.0
        description: "Percentage savings from current to optimized"

  CostRecommendation:
    type: object
    required:
      - type
      - action
      - estimated_savings_pct
    properties:
      type:
        type: string
        enum: [model_downgrade, caching, parallelization, prompt_trim, batching]

      step:
        type: string
        nullable: true
        description: "Step this applies to (null if pipeline-wide)"

      action:
        type: string
        description: "Specific action to take"

      estimated_savings_pct:
        type: number
        minimum: 0.0
        maximum: 100.0

      risk:
        type: string
        enum: [low, medium, high]
        default: low

      validation:
        type: string
        description: "Command or method to verify the optimization doesn't regress quality"

# Example
examples:
  - version: "1.0.0"
    pipeline: product-extractor
    analyzed_at: "2026-04-01T12:00:00Z"
    monthly_volume: 100000
    steps:
      - name: extract
        model: claude-haiku-4-5
        avg_input_tokens: 800
        avg_output_tokens: 200
        cost_per_call_usd: 0.000090
        cacheable_prefix_tokens: 320
        cache_savings_per_call_usd: 0.000029
    totals:
      cost_per_call_usd: 0.000090
      monthly_cost_usd: 9.00
      monthly_cost_with_caching_usd: 6.10
      monthly_cost_optimized_usd: 6.10
      potential_savings_pct: 32.2
    recommendations:
      - type: caching
        step: extract
        action: "Enable prefix caching — system prompt is 320 tokens and stable across all calls"
        estimated_savings_pct: 32.0
        risk: low
        validation: "Enable cache_prefix: true in pipeline.config.yaml; verify output quality unchanged"