Files
justvitamin/scripts/generate-source-cost-scenarios.ts
Omair Saleh 056c47581f feat: editorial review dashboard + elite-grade pilot batch (5 SKUs)
Ships the second dashboard surface — a Pattern Library + Preview Theatre — that
presents the 4-section PDP pilot batch back to Umar, compliance, and the board
in an editorial format. Adds the full data layer that drives it: 5 source-backed
per-SKU drafts at QA 100/100, 15 competitor PDP semantic extracts, PubMed
evidence packs, EFSA claims library extension, JV brand voice guide, hand-curated
product FAQs, and the Matrixify-ready CSV exports for Lewis.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-06-02 18:50:09 +08:00

150 lines
7.1 KiB
TypeScript

#!/usr/bin/env bun
import { mkdirSync, readFileSync, existsSync, writeFileSync } from 'fs'
import { join } from 'path'
const root = process.cwd()
const outRoot = join(root, 'content_population_exports')
mkdirSync(outRoot, { recursive: true })
function readJson(path: string, fallback: any = null) {
if (!existsSync(path)) return fallback
return JSON.parse(readFileSync(path, 'utf8').replace(/^\uFEFF/, ''))
}
function csv(rows: any[], headers: string[]) {
const esc = (value: any) => {
if (value === undefined || value === null) value = ''
if (Array.isArray(value)) value = value.join(' | ')
value = String(value)
return /[",\n\r]/.test(value) ? `"${value.replace(/"/g, '""')}"` : value
}
return [headers.join(','), ...rows.map(row => headers.map(header => esc(row[header])).join(','))].join('\n') + '\n'
}
const generatedAt = new Date().toISOString()
const refs = readJson(join(outRoot, 'source_acquisition_pricing_references.json'), { references: [] })
const pilot = readJson(join(outRoot, 'dataforseo_pilot_manifest.json'), {})
const apify = readJson(join(outRoot, 'apify_gapfill_manifest.json'), {})
const budgetGate = readJson(join(outRoot, 'source_acquisition_budget_gate.json'), {})
const taskCount = Number(pilot.counts?.stageOneTargets || 9)
const depth = Number(pilot.guardrails?.recommendedDepth || 10)
const reviewBlocksPerTask = Math.ceil(depth / 10)
const standardUnitUsd = 0.00075
const priorityUnitUsd = 0.0015
const apifyCuUsd = 0.2
const apifyFirstTargets = Number(apify.counts?.firstBatchTargets || 3)
const apifyRequestsPerBrand = Number((apify.targets || [])[0]?.MaxRequestsPerBrand || 3)
const apifyRunCount = 1
const rows = [
{
Provider: 'DataForSEO',
Stage: '1',
Scenario: 'standard_queue_exact_9_asin_depth_10',
Formula: `${taskCount} ASIN tasks x ${reviewBlocksPerTask} ten-review block x $${standardUnitUsd}`,
EstimatedUsd: +(taskCount * reviewBlocksPerTask * standardUnitUsd).toFixed(6),
SuggestedCapUsd: 1,
SpendStatus: 'blocked_until_asins_budget_cost_plan_approval_preflight',
Use: 'Recommended first paid pilot if all 9 ASINs are confirmed. The suggested cap is deliberately much larger than the exact API estimate to allow provider/account minimums while still preventing broad spend.',
SourceUrl: 'https://dataforseo.com/apis/reviews-api/amazon-reviews-api'
},
{
Provider: 'DataForSEO',
Stage: '1',
Scenario: 'priority_queue_reference_only',
Formula: `${taskCount} ASIN tasks x ${reviewBlocksPerTask} ten-review block x $${priorityUnitUsd}`,
EstimatedUsd: +(taskCount * reviewBlocksPerTask * priorityUnitUsd).toFixed(6),
SuggestedCapUsd: 1,
SpendStatus: 'not_recommended_without_explicit_speed_need',
Use: 'Reference only. Priority doubles the unit price; standard queue is enough for cost-controlled evidence collection.',
SourceUrl: 'https://dataforseo.com/apis/reviews-api/amazon-reviews-api'
},
{
Provider: 'DataForSEO',
Stage: '1',
Scenario: 'depth_safety_rule',
Formula: `depth ${depth} stays at ${reviewBlocksPerTask} ten-review block; depth 11 would round to 2 blocks`,
EstimatedUsd: +(taskCount * reviewBlocksPerTask * standardUnitUsd).toFixed(6),
SuggestedCapUsd: 1,
SpendStatus: 'keep_depth_10',
Use: 'Protects against accidental review-depth cost increase. Do not change depth without updating the cost plan and approval.',
SourceUrl: 'https://dataforseo.com/help-center/get-amazon-reviews'
},
{
Provider: 'Apify',
Stage: '2',
Scenario: 'one_actor_first_3_targets_reference_cap',
Formula: `${apifyRunCount} actor run x first ${apifyFirstTargets} targets x ${apifyRequestsPerBrand} requests/brand; CU cost depends on actual run`,
EstimatedUsd: 0,
SuggestedCapUsd: 5,
SpendStatus: 'blocked_until_dataforseo_review_names_gap',
Use: 'Suggested small cap for the first dataset inspection only. Actual actor/proxy/storage cost must be read from Apify run usage before any second run.',
SourceUrl: 'https://docs.apify.com/platform/actors/running/usage-and-resources'
},
{
Provider: 'Apify',
Stage: '2',
Scenario: 'compute_unit_reference',
Formula: `$${apifyCuUsd} per CU; exact CU = memory x runtime plus platform usage`,
EstimatedUsd: 0,
SuggestedCapUsd: 5,
SpendStatus: 'reference_only',
Use: 'CU reference for filling the cost plan after choosing the actor and before one first-batch run.',
SourceUrl: 'https://apify.com/pricing/creator-plan'
}
]
const standard = rows[0]
const manifest = {
generatedAt,
ready: true,
note: 'No-spend scenario estimates for choosing a small local max-spend cap. This does not enable provider spend.',
counts: {
scenarios: rows.length,
dataforseoScenarios: rows.filter(row => row.Provider === 'DataForSEO').length,
apifyScenarios: rows.filter(row => row.Provider === 'Apify').length,
stageOneTasks: taskCount,
reviewDepth: depth,
pricingReferences: refs.counts?.references || 0
},
recommendation: {
providerOrder: 'DataForSEO first; Apify only after a named post-pilot gap.',
dataforseoStage1: `Use standard queue for ${taskCount} ASINs at depth ${depth}; exact official-reference estimate is $${standard.EstimatedUsd}, but set any local max-spend cap manually after checking account minimums/billing.`,
apifyStage2: 'Do not fund Apify yet. If needed later, cap the first run tightly and inspect actual usage before any second run.'
},
guardrails: [
'Scenario estimates are not approval and do not unlock spend.',
'DataForSEO payload remains empty until ASINs are confirmed.',
'Apify remains blocked until DataForSEO review selects run_apify_gapfill and names a gap.',
'Use these rows to fill source-acquisition-cost-plan.json; then rerun cost, approval, preflight, and spend gates.'
],
scenarios: rows,
budgetState: budgetGate.budgetAllowed || {}
}
writeFileSync(join(outRoot, 'source_acquisition_cost_scenarios.json'), JSON.stringify(manifest, null, 2) + '\n', 'utf8')
writeFileSync(join(outRoot, 'source_acquisition_cost_scenarios.csv'), csv(rows, ['Provider', 'Stage', 'Scenario', 'Formula', 'EstimatedUsd', 'SuggestedCapUsd', 'SpendStatus', 'Use', 'SourceUrl']), 'utf8')
writeFileSync(join(outRoot, 'source_acquisition_cost_scenarios.md'), [
'# Source acquisition cost scenarios',
'',
`Generated: ${generatedAt}`,
'',
manifest.note,
'',
`Recommendation: ${manifest.recommendation.providerOrder}`,
'',
'## Guardrails',
...manifest.guardrails.map(item => `- ${item}`),
'',
'## Scenarios',
...rows.map(row => `- ${row.Provider} Stage ${row.Stage} / ${row.Scenario}: ${row.Formula} => estimate $${row.EstimatedUsd}; suggested local cap reference $${row.SuggestedCapUsd}. Status: ${row.SpendStatus}.`),
'',
'## Next use',
'- Keep spend blocked until ASINs/payload are ready.',
'- If choosing to subscribe later, fill `data/sources/budgets/source-acquisition-cost-plan.json` from these scenarios and current account pricing, then rerun all gates.',
''
].join('\n'), 'utf8')
console.log(`Source acquisition cost scenarios ready: ${manifest.ready}`)
console.log(`Scenarios: ${manifest.counts.scenarios}`)
console.log(`DataForSEO standard estimate USD: ${standard.EstimatedUsd}`)