disclosure-bureau/investigator-runtime/src/tools/write_contradiction.ts

/**
 * write_contradiction.ts — Dupin's primary writer.
 *
 * Inserts a row into public.contradictions and renders
 * case/contradictions/R-NNNN.md.
 *
 * Validates:
 *  - topic + at least 2 positions
 *  - each position has a chunk_pk (resolved from doc_id + chunk_id via the DB)
 *  - position.statement is non-empty
 *  - notes ≤ 4000 chars
 *
 * Naming uses the R-NNNN slot from contradiction_id_seq. Note: this CLAUDE.md
 * historically reserved R-NNNN for `relation` artefacts (chief-detective);
 * contradictions are the same conceptual class (a connection between two
 * pieces of evidence in tension), so they share the slot.
 */
import { mkdir, writeFile } from "node:fs/promises";
import path from "node:path";
import { audit } from "../lib/audit";
import { env } from "../lib/env";
import { allocate } from "../lib/ids";
import { query, queryOne } from "../lib/pg";

export interface ContradictionPosition {
  doc_id: string;
  chunk_id: string;
  /** The verbatim or paraphrased claim that puts this chunk on this side. */
  statement: string;
  statement_pt_br?: string;
  /** Optional weight or stance label (e.g. "asserts", "denies"). */
  stance?: string;
}

export interface WriteContradictionArgs {
  topic: string;
  topic_pt_br?: string;
  positions: ContradictionPosition[];
  notes?: string;
  notes_pt_br?: string;
  resolution_status?: "open" | "resolved" | "irreconcilable";
}

export interface WriteContradictionContext {
  job_id: string;
  detective: string;
}

interface ResolvedPosition extends ContradictionPosition {
  chunk_pk: number;
  page: number;
  statement_pt_br: string;
}

/**
 * Strip page-prefix idioms detectives sometimes emit. Canonical chunk_id is
 * just `c0042`. Forms accepted: "c0042", "p007#c0042", "p007/c0042".
 */
function normalizeChunkId(raw: string): string {
  const m = raw.match(/c\d{4,}$/);
  return m ? m[0] : raw;
}

async function resolveChunk(doc_id: string, chunk_id: string): Promise<{ chunk_pk: number; page: number } | null> {
  const cid = normalizeChunkId(chunk_id);
  const row = await queryOne<{ chunk_pk: number; page: number }>(
    `SELECT chunk_pk, page FROM public.chunks WHERE doc_id = $1 AND chunk_id = $2`,
    [doc_id, cid],
  );
  return row ?? null;
}

function renderMd(
  id: string,
  body: WriteContradictionArgs,
  positions: ResolvedPosition[],
  ctx: WriteContradictionContext,
): string {
  const fm = [
    "---",
    `schema_version: "0.1.0"`,
    `type: contradiction`,
    `contradiction_id: ${id}`,
    `topic: ${JSON.stringify(body.topic)}`,
    `resolution_status: ${body.resolution_status ?? "open"}`,
    `detected_by: ${ctx.detective}`,
    `job_id: ${ctx.job_id}`,
    `created_at: ${new Date().toISOString()}`,
    "---",
  ].join("\n");

  const positionBlocks = positions.map((p, i) => {
    const pageStr = String(p.page).padStart(3, "0");
    return [
      `### Position ${i + 1}${p.stance ? ` — ${p.stance}` : ""}`,
      "",
      `**(EN)** > ${p.statement}`,
      "",
      `**(PT-BR)** > ${p.statement_pt_br}`,
      "",
      `Source: [[${p.doc_id}/p${pageStr}#${p.chunk_id}]]`,
    ].join("\n");
  });

  return [
    fm,
    "",
    `# Contradiction ${id}`,
    "",
    `**Topic (EN).** ${body.topic}`,
    `**Tópico (PT-BR).** ${body.topic_pt_br ?? body.topic}`,
    "",
    "## Positions in tension",
    "",
    positionBlocks.join("\n\n"),
    "",
    "## Notes (EN)",
    "",
    body.notes || "_(no commentary recorded)_",
    "",
    "## Notas (PT-BR)",
    "",
    body.notes_pt_br || "_(sem comentário registrado)_",
    "",
  ].join("\n");
}

export async function writeContradiction(
  body: WriteContradictionArgs,
  ctx: WriteContradictionContext,
): Promise<{ contradiction_id: string; case_file: string }> {
  if (!body.topic?.trim()) throw new Error("topic required");
  if (!body.topic_pt_br?.trim()) throw new Error("topic_pt_br required (bilingual contract)");
  if (!Array.isArray(body.positions) || body.positions.length < 2) {
    throw new Error("at least 2 positions required");
  }
  if (body.notes && body.notes.length > 4000) {
    throw new Error(`notes too long (${body.notes.length} > 4000)`);
  }
  if (body.notes && !body.notes_pt_br?.trim()) {
    throw new Error("notes_pt_br required when notes set (bilingual contract)");
  }

  const resolved: ResolvedPosition[] = [];
  for (const p of body.positions) {
    if (!p?.doc_id?.trim() || !p?.chunk_id?.trim()) {
      throw new Error("position requires doc_id + chunk_id");
    }
    if (!p?.statement?.trim()) {
      throw new Error(`position ${p.doc_id}/${p.chunk_id} missing statement`);
    }
    if (!p?.statement_pt_br?.trim()) {
      throw new Error(`position ${p.doc_id}/${p.chunk_id} missing statement_pt_br (bilingual contract)`);
    }
    const chunk = await resolveChunk(p.doc_id, p.chunk_id);
    if (!chunk) {
      throw new Error(`chunk ${p.doc_id}/${p.chunk_id} not found`);
    }
    resolved.push({
      ...p,
      statement: p.statement.trim(),
      statement_pt_br: p.statement_pt_br.trim(),
      chunk_pk: chunk.chunk_pk,
      page: chunk.page,
    });
  }

  // Reject pairs that point at the same chunk on every side — that's not a
  // contradiction, that's a single statement.
  const uniqueChunks = new Set(resolved.map((p) => p.chunk_pk));
  if (uniqueChunks.size < 2) {
    throw new Error("contradiction requires positions from at least 2 distinct chunks");
  }

  const contradiction_id = await allocate.contradictionId();
  const chunkPayload = resolved.map((p) => ({
    chunk_pk: p.chunk_pk,
    doc_id: p.doc_id,
    chunk_id: p.chunk_id,
    page: p.page,
    statement: p.statement,
    statement_pt_br: p.statement_pt_br,
    stance: p.stance ?? null,
  }));

  await query(
    `INSERT INTO public.contradictions
       (contradiction_id, topic, topic_pt_br, chunks, detected_by,
        resolution_status, notes, notes_pt_br)
     VALUES ($1, $2, $3, $4::jsonb, $5, $6, $7, $8)`,
    [
      contradiction_id,
      body.topic.trim(),
      body.topic_pt_br!.trim(),
      JSON.stringify(chunkPayload),
      ctx.detective,
      body.resolution_status ?? "open",
      body.notes ?? null,
      body.notes_pt_br ?? null,
    ],
  );

  const dir = path.join(env.CASE_ROOT, "contradictions");
  await mkdir(dir, { recursive: true });
  const file = path.join(dir, `${contradiction_id}.md`);
  await writeFile(file, renderMd(contradiction_id, body, resolved, ctx), "utf-8");

  await audit({
    event: "write_contradiction",
    job_id: ctx.job_id,
    detective: ctx.detective,
    contradiction_id,
    n_positions: resolved.length,
    distinct_chunks: uniqueChunks.size,
    file,
  });

  return { contradiction_id, case_file: file };
}