voyage/lib/review/plan-review-dedup.mjs

// lib/review/plan-review-dedup.mjs
// Phase-9 dedup helper for /trekplan adversarial review:
// merges plan-critic + scope-guardian findings into a single deduplicated
// stream, preserving provenance (which agent originally raised each finding).
//
// Two dedup signals:
//   1. Exact match  — identical computeFindingId(file:line:rule_key) → merge.
//   2. Jaccard ≥ 0.7 on text-token sets → merge (catches near-duplicates).
//
// Provenance is preserved on the surviving finding's `raised_by` array.
//
// CLI shim — two input modes:
//   file mode:  node lib/review/plan-review-dedup.mjs \
//                    --plan-critic /tmp/x.json --scope-guardian /tmp/y.json
//   stdin mode: node lib/review/plan-review-dedup.mjs --stdin   (reads fd 0:
//                    one object {plan_critic, scope_guardian} of agent payloads)
//   → stdout: deduped JSON, exit 0 on success.
//
// File mode tolerates empty / missing inputs (single-agent review still works).
// stdin mode is the Phase-9 path: the read-only reviewers (plan-critic,
// scope-guardian) cannot write temp files, so /trekplan pipes their inline JSON
// blocks here. Malformed stdin exits NON-ZERO — a broken hand-off must surface
// loudly, never collapse into a silent empty merge.

import { readFileSync } from 'node:fs';
import { jaccardSimilarity, meetsThreshold } from '../parsers/jaccard.mjs';
import { computeFindingId } from '../parsers/finding-id.mjs';

export const DEFAULT_THRESHOLD = 0.7;

/**
 * Tokenize a finding's text for Jaccard comparison: lowercase, split on
 * non-word, drop empties. Stable + deterministic.
 */
export function tokenize(text) {
  if (typeof text !== 'string' || text.length === 0) return [];
  return text.toLowerCase().split(/\W+/).filter(t => t.length > 0);
}

/**
 * Normalize a single agent payload into an array of {agent, finding} pairs.
 * Tolerates missing payload (returns []).
 */
function normalizeAgentPayload(payload, fallbackAgent) {
  if (!payload || typeof payload !== 'object') return [];
  const agent = (typeof payload.agent === 'string' && payload.agent.length > 0)
    ? payload.agent
    : fallbackAgent;
  const findings = Array.isArray(payload.findings) ? payload.findings : [];
  return findings.map(f => ({ agent, finding: f }));
}

function annotate(finding, agent) {
  const id = computeFindingId(
    String(finding.file ?? 'unknown'),
    finding.line ?? 0,
    String(finding.rule_key ?? 'unknown'),
  );
  return {
    id,
    file: finding.file ?? null,
    line: finding.line ?? null,
    rule_key: finding.rule_key ?? null,
    text: typeof finding.text === 'string' ? finding.text : '',
    raised_by: [agent],
  };
}

/**
 * Dedup an arbitrary collection of agent payloads.
 *
 * @param {Array<{agent: string, payload: object | null | undefined}>} sources
 * @param {{ threshold?: number }} [opts]
 * @returns {{
 *   findings: Array<object>,
 *   dedup_stats: { total_in: number, total_out: number,
 *                  exact_id_dups: number, jaccard_dups: number }
 * }}
 */
export function dedupFindings(sources, opts = {}) {
  const threshold = typeof opts.threshold === 'number' ? opts.threshold : DEFAULT_THRESHOLD;

  const incoming = [];
  for (const s of sources) {
    for (const pair of normalizeAgentPayload(s.payload, s.agent)) {
      incoming.push(annotate(pair.finding, pair.agent));
    }
  }

  const total_in = incoming.length;

  // Pass 1 — exact id dedup
  const byId = new Map();
  let exact_id_dups = 0;
  for (const f of incoming) {
    const existing = byId.get(f.id);
    if (existing) {
      for (const a of f.raised_by) {
        if (!existing.raised_by.includes(a)) existing.raised_by.push(a);
      }
      exact_id_dups += 1;
    } else {
      byId.set(f.id, f);
    }
  }

  // Pass 2 — jaccard on text tokens; merge near-duplicates
  const survivors = [];
  let jaccard_dups = 0;
  for (const f of byId.values()) {
    const tokens = tokenize(f.text);
    let merged = false;
    for (const s of survivors) {
      const sim = jaccardSimilarity(tokens, tokenize(s.text));
      if (meetsThreshold(sim, threshold)) {
        for (const a of f.raised_by) {
          if (!s.raised_by.includes(a)) s.raised_by.push(a);
        }
        jaccard_dups += 1;
        merged = true;
        break;
      }
    }
    if (!merged) survivors.push(f);
  }

  return {
    findings: survivors,
    dedup_stats: {
      total_in,
      total_out: survivors.length,
      exact_id_dups,
      jaccard_dups,
    },
  };
}

// ---- CLI shim ----------------------------------------------------------------

function parseArgs(argv) {
  const out = {};
  for (let i = 0; i < argv.length; i++) {
    const a = argv[i];
    if (a === '--plan-critic') out.planCritic = argv[++i];
    else if (a === '--scope-guardian') out.scopeGuardian = argv[++i];
    else if (a === '--threshold') out.threshold = Number(argv[++i]);
    else if (a === '--stdin') out.stdin = true;
  }
  return out;
}

function readJsonOrNull(path) {
  if (!path) return null;
  try {
    return JSON.parse(readFileSync(path, 'utf-8'));
  } catch {
    return null;
  }
}

// --stdin mode reads ONE object {plan_critic, scope_guardian} from fd 0. Unlike
// the file path mode (which tolerates absent files so single-agent review still
// works), malformed stdin is a hard error: --stdin means the caller intended to
// pipe both inline review blocks, so a parse failure is a broken hand-off that
// must surface loudly — not collapse into a silent empty merge (the original
// Phase-9 defect: read-only reviewers never wrote the temp files, the helper
// swallowed the absence, and the dedup ran on nothing).
function readStdinSourcesOrExit() {
  let raw;
  try {
    raw = readFileSync(0, 'utf-8');
  } catch (err) {
    process.stderr.write(`plan-review-dedup --stdin: cannot read stdin: ${err.message}\n`);
    process.exit(1);
  }
  let parsed;
  try {
    parsed = JSON.parse(raw);
  } catch (err) {
    process.stderr.write(`plan-review-dedup --stdin: malformed JSON on stdin: ${err.message}\n`);
    process.exit(1);
  }
  if (!parsed || typeof parsed !== 'object' || Array.isArray(parsed)) {
    process.stderr.write('plan-review-dedup --stdin: expected an object {plan_critic, scope_guardian}\n');
    process.exit(1);
  }
  return [
    { agent: 'plan-critic', payload: parsed.plan_critic ?? null },
    { agent: 'scope-guardian', payload: parsed.scope_guardian ?? null },
  ];
}

if (import.meta.url === `file://${process.argv[1]}`) {
  const args = parseArgs(process.argv.slice(2));
  const sources = args.stdin
    ? readStdinSourcesOrExit()
    : [
        { agent: 'plan-critic', payload: readJsonOrNull(args.planCritic) },
        { agent: 'scope-guardian', payload: readJsonOrNull(args.scopeGuardian) },
      ];
  const opts = {};
  if (Number.isFinite(args.threshold)) opts.threshold = args.threshold;
  const result = dedupFindings(sources, opts);
  process.stdout.write(JSON.stringify(result, null, 2) + '\n');
  process.exit(0);
}