import type { RewardSpec } from '@/lib/demo-kit';
import rewardSource from '../../../envs/alert_triage/alert_triage/reward.py?raw';

/**
 * The reward, mirrored from `envs/alert_triage/alert_triage/reward.py`.
 *
 * The labels are for the BSA officer, not the variable names. `caught` is a
 * fair identifier and says nothing to someone deciding a budget; "nothing
 * slipped through" is the same quantity in the words they already use.
 *
 * The constants are restated here as literals rather than imported, because
 * `check-demos` reads the weights off the page beside the code. If reward.py
 * changes, the receipt panel shows the change and these must follow it.
 */

export const reward: RewardSpec = {
  components: [
    {
      key: 'caught',
      label: 'Nothing slipped through',
      description:
        'One point for any correct call. Half a point if a clean customer was escalated — nothing slipped, but a report was filed on them. Nothing if a suspicious alert was closed or no call was made. This is the counterweight, and it is over half the reward: a miss also zeroes the other two, so one miss costs more than every hour a policy could save.',
      weight: 0.55,
      role: 'counterweight',
    },
    {
      key: 'hours',
      label: 'Cleared it in the hours budgeted',
      description:
        'Analyst-hours spent — 0.50 to read the screen, 0.05 per reply, 0.40 per lookup, 0.10 for the documents — as a ratio against the cheapest shipped analyst that got this same alert right. Capped at one. A fast wrong answer saves nothing.',
      weight: 0.25,
      role: 'objective',
    },
    {
      key: 'evidence',
      label: 'Named the facts that decide it',
      description:
        'F1 between the ids the run cited and the facts the generator planted: the explaining KYC or document fact on a clean alert, the transactions that constitute the typology on a suspicious one. Cite everything and precision pays you what it thinks of that. Zero if the call was wrong. The narrative prose is never read.',
      weight: 0.2,
      role: 'objective',
    },
  ],
  metrics: [
    { key: 'hours_spent', label: 'Hours spent', description: 'Screen, replies and lookups, at the generator’s prices.' },
    {
      key: 'reference_hours',
      label: 'Reference took',
      description: 'Hours the cheapest shipped analyst needed to get this same alert right.',
    },
    { key: 'lookups', label: 'Lookups made', description: 'History months, counterparties, prior alerts, documents.' },
    { key: 'turns_used', label: 'Replies spent', description: 'Accepted or refused. Eight ends the episode.' },
    {
      key: 'rejected_replies',
      label: 'Replies refused',
      description: 'No JSON object, an unknown action, an empty cites list, an id never shown, or a repeated lookup. Costs a turn.',
    },
    {
      key: 'false_escalation',
      label: 'Escalated a clean customer',
      description: 'One if a report was filed on a benign alert.',
    },
    { key: 'missed', label: 'Closed a suspicious alert', description: 'One if the alert should have been escalated and was closed instead.' },
    {
      key: 'typology_match',
      label: 'Named the right typology',
      description: 'One if the escalation named what the generator planted. Diagnostic only; not scored, because it would double-count the call with an enum the agent can guess.',
    },
  ],
  source: {
    path: 'envs/alert_triage/alert_triage/reward.py',
    code: rewardSource,
    marker: 'reward',
  },
};