boardroom-map/startos/actions/configure-grading.ts

import { sdk } from '../sdk'
import { configFile } from '../file-models/config'

const { InputSpec, Value } = sdk

const inputSpec = InputSpec.of({
  bdefOverride: Value.textarea({
    name: 'BDEF Rubric Override (optional)',
    description:
      'Leave EMPTY to grade against the baked-in BDEF v1.1 framework ' +
      '(Girdley + Munger/Buffett). Non-empty text replaces the rubric wholesale, ' +
      'so include the qualitative categories A-H if you customize it.',
    required: false,
    default: null,
    minRows: 5,
    maxRows: 24,
    placeholder: '(empty = the built-in BDEF v1.1 rubric)',
  }),
  extractorModel: Value.text({
    name: 'Extractor Model (optional)',
    description:
      'Catalog alias of the model that runs the stage-1 structured KPI ' +
      'extraction over each deck. Empty = use the first model.',
    required: false,
    default: null,
    placeholder: 'grader-a',
  }),
  networkMode: Value.select({
    name: 'Network Mode',
    description:
      'Air-gapped: graders reach ONLY the on-Spark model proxy — zero internet, ' +
      'board decks never leave your hardware (models must be pre-pulled into the ' +
      'Spark HF cache, all on the head Spark). Local services: graders may also ' +
      'reach LAN services like SearXNG and the second Spark (this network has ' +
      'egress unless you firewall it).',
    default: 'airgapped',
    values: {
      airgapped: 'Air-gapped (no network, recommended)',
      local_services: 'Local services (SearXNG / 2nd Spark)',
    },
  }),
  searxngUrl: Value.text({
    name: 'SearXNG URL (local-services only)',
    description: 'JSON-search endpoint to give graders a web_search tool. Ignored in air-gapped mode. Empty = no web search.',
    required: false,
    default: null,
    placeholder: 'https://searxng.local',
  }),
  adjudicatorEnabled: Value.toggle({
    name: 'Run an Adjudicator',
    description:
      'After the panel finishes, run a local "lead grader" that reads every ' +
      'grade sheet, reconciles disagreements, and settles the qualitative scores ' +
      'the deterministic composite uses. No frontier model — stays on the Sparks.',
    default: true,
  }),
  adjudicatorModel: Value.text({
    name: 'Adjudicator Model (optional)',
    description: 'Catalog alias of the model that adjudicates the panel. Empty = use the first model.',
    required: false,
    default: null,
    placeholder: 'grader-a',
  }),
  adjudicatorPersona: Value.textarea({
    name: 'Adjudicator Instructions (optional)',
    description: 'Override how the adjudicator reconciles the panel. Empty = a sensible built-in default.',
    required: false,
    default: null,
    minRows: 3,
    maxRows: 14,
  }),
  wipeRemoteDocs: Value.toggle({
    name: 'Wipe Decks From Sparks After Grading',
    description:
      'Delete the extracted deck text from the Sparks when a job finishes. ' +
      'Scorecards and ledgers are always kept on this StartOS box. Recommended ' +
      'for confidential board material.',
    default: true,
  }),
  autoRunOnDrop: Value.toggle({
    name: 'Auto-grade When Decks Are Dropped',
    description:
      'Start grading automatically (after a short debounce) whenever new decks ' +
      'land in the inbox. Off by default so you trigger grading explicitly.',
    default: false,
  }),
  preJobStopContainers: Value.text({
    name: 'Stop These Containers Before Grading (optional)',
    description:
      'Space- or comma-separated docker container names stopped on the HEAD ' +
      'Spark at the start of every grading job, so the job gets the GPU to ' +
      'itself (e.g. an always-on vLLM another service runs). They are NOT ' +
      'restarted afterwards — the service that owns them reloads its own ' +
      'models (e.g. the Gazette\'s Fleet job). Empty = stop nothing.',
    required: false,
    default: null,
    placeholder: 'vllm-gemma4-clerk',
  }),
  // --- Deterministic-scorer weights (composite = quant 60 + qual 40 - flags) ---
  profitabilityKpi: Value.number({
    name: 'Weight: Profitability KPIs',
    description: 'Points for the profitability KPI attainment bucket — the heaviest slice of the quant 60. Default 30.',
    required: true,
    default: 30,
    integer: false,
    min: 0,
    max: 100,
  }),
  otherKpi: Value.number({
    name: 'Weight: Other KPIs',
    description: 'Points for the non-profitability measurable-KPI bucket. Default 20.',
    required: true,
    default: 20,
    integer: false,
    min: 0,
    max: 100,
  }),
  forecastIntegrity: Value.number({
    name: 'Weight: Forecast Integrity',
    description: 'Points for deck N actuals hitting what deck N-1 promised. Default 10.',
    required: true,
    default: 10,
    integer: false,
    min: 0,
    max: 100,
  }),
  qualCategoryMax: Value.number({
    name: 'Weight: Max Per Qualitative Category',
    description: 'Max points per BDEF category A-H (8 categories x 5 = the qualitative 40). Default 5.',
    required: true,
    default: 5,
    integer: false,
    min: 0,
    max: 100,
  }),
  redFlagCap: Value.number({
    name: 'Red-flag Penalty Cap',
    description: 'Maximum total points red flags can subtract from the composite. Default 15.',
    required: true,
    default: 15,
    integer: false,
    min: 0,
    max: 100,
  }),
  kpiCreditFloor: Value.number({
    name: 'KPI Credit Floor',
    description: 'actual/target ratio below which a KPI earns zero credit (linear credit above it). Default 0.5.',
    required: true,
    default: 0.5,
    integer: false,
    min: 0,
    max: 1,
  }),
  droppedKpiPenalty: Value.number({
    name: 'Dropped-KPI Penalty',
    description: 'Penalty per KPI that silently disappeared from the deck. Default 2.',
    required: true,
    default: 2,
    integer: false,
    min: 0,
    max: 100,
  }),
  droppedKpiMax: Value.number({
    name: 'Dropped-KPI Flag Limit',
    description: 'Count at most this many dropped-KPI flags per deck. Default 3.',
    required: true,
    default: 3,
    integer: true,
    min: 0,
    max: 50,
  }),
  evidenceFullCredit: Value.number({
    name: 'Evidence Full-credit Threshold',
    description: 'Quote characters a qualitative finding needs for full weight (thinner evidence scales down). Default 400.',
    required: true,
    default: 400,
    integer: true,
    min: 0,
    max: 100000,
  }),
  singleSourceFlagFactor: Value.number({
    name: 'Single-source Flag Damping',
    description: 'Multiplier applied to red flags raised by only one grader. Default 0.5.',
    required: true,
    default: 0.5,
    integer: false,
    min: 0,
    max: 1,
  }),
})

export const configureGrading = sdk.Action.withInput(
  'configure-grading',

  async ({ effects }) => ({
    name: 'Configure Grading',
    description: 'Set the BDEF rubric, air-gap mode, adjudication, retention, and the scoring weights.',
    warning: null,
    allowedStatuses: 'any',
    group: 'Grading',
    visibility: 'enabled',
  }),

  inputSpec,

  async ({ effects }) => {
    const cfg = await configFile.read().const(effects)
    if (!cfg) return {}
    return {
      bdefOverride: cfg.bdefOverride || undefined,
      extractorModel: cfg.extractorModel || undefined,
      networkMode: cfg.networkMode,
      searxngUrl: cfg.searxngUrl || undefined,
      adjudicatorEnabled: cfg.adjudicatorEnabled,
      adjudicatorModel: cfg.adjudicatorModel || undefined,
      adjudicatorPersona: cfg.adjudicatorPersona || undefined,
      wipeRemoteDocs: cfg.wipeRemoteDocs,
      autoRunOnDrop: cfg.autoRunOnDrop,
      preJobStopContainers: cfg.preJobStopContainers || undefined,
      profitabilityKpi: cfg.weights.profitabilityKpi,
      otherKpi: cfg.weights.otherKpi,
      forecastIntegrity: cfg.weights.forecastIntegrity,
      qualCategoryMax: cfg.weights.qualCategoryMax,
      redFlagCap: cfg.weights.redFlagCap,
      kpiCreditFloor: cfg.weights.kpiCreditFloor,
      droppedKpiPenalty: cfg.weights.droppedKpiPenalty,
      droppedKpiMax: cfg.weights.droppedKpiMax,
      evidenceFullCredit: cfg.weights.evidenceFullCredit,
      singleSourceFlagFactor: cfg.weights.singleSourceFlagFactor,
    }
  },

  async ({ effects, input }) => {
    await configFile.merge(effects, {
      bdefOverride: input.bdefOverride ?? '',
      extractorModel: input.extractorModel ?? '',
      networkMode: input.networkMode,
      searxngUrl: input.searxngUrl ?? '',
      adjudicatorEnabled: input.adjudicatorEnabled,
      adjudicatorModel: input.adjudicatorModel ?? '',
      adjudicatorPersona: input.adjudicatorPersona ?? '',
      wipeRemoteDocs: input.wipeRemoteDocs,
      autoRunOnDrop: input.autoRunOnDrop,
      preJobStopContainers: input.preJobStopContainers ?? '',
      weights: {
        profitabilityKpi: input.profitabilityKpi,
        otherKpi: input.otherKpi,
        forecastIntegrity: input.forecastIntegrity,
        qualCategoryMax: input.qualCategoryMax,
        redFlagCap: input.redFlagCap,
        kpiCreditFloor: input.kpiCreditFloor,
        droppedKpiPenalty: input.droppedKpiPenalty,
        droppedKpiMax: input.droppedKpiMax,
        evidenceFullCredit: input.evidenceFullCredit,
        singleSourceFlagFactor: input.singleSourceFlagFactor,
      },
    })

    return {
      version: '1',
      title: 'Grading Settings Saved',
      message:
        input.networkMode === 'airgapped'
          ? 'Saved. Graders will run air-gapped (no internet). Ensure all models are on the head Spark and pre-pulled into its HF cache.'
          : 'Saved. Graders run in local-services mode and may reach the network — make sure that is acceptable for these board decks.',
      result: { type: 'single', value: input.networkMode, copyable: false, qr: false, masked: false },
    }
  },
)