import { z } from 'zod';

/** Connector manifest (CLAUDE.md §9). Seeds the `sources` table; drives the public /source pages. */
export const ConnectorManifest = z.object({
  id: z.string().regex(/^[a-z0-9-]+$/),
  name: z.string(),
  organization: z.string(),
  category: z.enum(['terminology', 'genes', 'genomics', 'variants', 'epidemiology', 'trials', 'literature', 'drugs', 'regulatory', 'evidence', 'pathways', 'funding', 'guidelines']),
  tier: z.number().int().min(0).max(11),
  description: z.string(),
  homepage: z.string().url(),
  docsUrl: z.string().url().optional(),
  termsUrl: z.string().url().optional(),
  access: z.object({
    type: z.enum(['api', 'bulk', 'rss', 'ftp', 'graphql', 'rest', 'scrape', 'manual']),
    auth: z.enum(['none', 'api_key', 'oauth', 'account', 'controlled']),
    baseUrl: z.string().url().optional(),
  }),
  license: z.string(),
  licenseStatus: z.enum(['review', 'approved', 'restricted', 'blocked']),
  commercialUse: z.enum(['allowed', 'restricted', 'prohibited', 'unknown']),
  redistribution: z.enum(['allowed', 'attribution', 'restricted', 'prohibited', 'unknown']),
  attribution: z.string().optional(),
  termsReviewedAt: z.string().optional(), // YYYY-MM-DD, human review date
  termsNotes: z.string().optional(),
  updateFrequency: z.string(),
  expectedLatency: z.string().optional(),
  supportsIncrementalSync: z.boolean(),
  entities: z.array(z.string()),
  metrics: z.array(z.string()).default([]),
  rateLimits: z.object({
    requestsPerSecond: z.number().positive().optional(),
    requestsPerMinute: z.number().positive().optional(),
    maxConcurrency: z.number().int().positive().default(1),
    notes: z.string().optional(),
  }),
  retryPolicy: z
    .object({
      maxRetries: z.number().int().min(0).default(4),
      baseDelayMs: z.number().int().min(0).default(500),
      maxDelayMs: z.number().int().min(0).default(30_000),
    })
    .default({ maxRetries: 4, baseDelayMs: 500, maxDelayMs: 30_000 }),
  rawRetention: z.enum(['full', 'summary', 'none']).default('full'),
  schemaVersion: z.string().default('1'),
  documentationVerifiedAt: z.string(), // YYYY-MM-DD, the date official docs were checked (CLAUDE.md §224-225)
  owner: z.string().default('cancerindex'),
  status: z.enum(['planned', 'active', 'paused', 'awaiting_credentials', 'review', 'retired']),
  schedule: z.string().optional(), // cron expression for the worker scheduler
  anomalyGuard: z
    .object({
      /** Refuse to mark records source_missing when the fetched count drops below this ratio of the previous run. */
      minRatioOfPrevious: z.number().min(0).max(1).default(0.5),
    })
    .default({ minRatioOfPrevious: 0.5 }),
  /**
   * Mid-run cursor checkpoint (CLAUDE.md §90): `connector_cursors.cursor` is persisted after this many
   * upserted records (or every 60 s) whenever `ctx.cursor` changed, so a killed run resumes from the
   * last completed page instead of from the start of the run. See docs/connectors/README.md.
   */
  checkpointEvery: z.number().int().positive().default(2000),
});
export type ConnectorManifest = z.infer<typeof ConnectorManifest>;

export function defineManifest(m: z.input<typeof ConnectorManifest>): ConnectorManifest {
  return ConnectorManifest.parse(m);
}