// RagSample — entry in exports/rag/playbooks.jsonl. Spec shape exactly,
// plus provenance + success_score (so the index can re-rank by quality).
import {
  ValidationResult, requireString, requireNumber, requireIsoTimestamp, requireProvenance, requireStringArray,
} from "./types";

export const RAG_SAMPLE_SCHEMA_VERSION = 1;

export interface RagSample {
  schema_version: number;
  id: string;
  title: string;
  content: string;
  tags: string[];
  source_run_id: string;
  success_score: "accepted" | "partially_accepted";  // RAG only ships from these two
  embedding_text: string;                            // the text to embed (often == content but can be shorter)
  exported_at: string;
  provenance: { source_file: string; line_offset?: number; sig_hash: string; recorded_at: string };
}

export function validateRagSample(input: unknown): ValidationResult<RagSample> {
  const errors: string[] = [];
  if (typeof input !== "object" || input === null) return { valid: false, errors: ["expected object"] };
  const r = input as Record<string, unknown>;
  let ok = true;

  if (r.schema_version !== RAG_SAMPLE_SCHEMA_VERSION) {
    errors.push(`schema_version: expected ${RAG_SAMPLE_SCHEMA_VERSION}, got ${JSON.stringify(r.schema_version)}`);
    ok = false;
  }
  ok = requireString(r.id, "id", errors) && ok;
  ok = requireString(r.title, "title", errors) && ok;
  ok = requireString(r.content, "content", errors) && ok;
  ok = requireString(r.embedding_text, "embedding_text", errors) && ok;
  ok = requireString(r.source_run_id, "source_run_id", errors) && ok;
  ok = requireIsoTimestamp(r.exported_at, "exported_at", errors) && ok;
  ok = requireStringArray(r.tags, "tags", errors) && ok;
  ok = requireProvenance(r.provenance, "provenance", errors) && ok;

  if (!["accepted", "partially_accepted"].includes(r.success_score as string)) {
    errors.push("success_score: must be accepted|partially_accepted (rejected/needs_human never enter RAG)");
    ok = false;
  }
  if (typeof r.content === "string" && (r.content as string).trim().length === 0) {
    errors.push("content: must be non-whitespace");
    ok = false;
  }

  if (!ok) return { valid: false, errors };
  return { valid: true, value: r as unknown as RagSample };
}