voyage/scripts/trekreview-armB.workflow.mjs

// scripts/trekreview-armB.workflow.mjs
// NW2 bake-off — Arm B: /trekreview Phase 5–6 reimplemented as a Workflow.
//
// This is the T2 §5 Arm B substrate: where the prose path (Arm A) has main
// spawn two reviewers, hand-parse their trailing JSON, JS-dedup, then spawn the
// coordinator, Arm B expresses the SAME pipeline as one Workflow —
//   parallel([conformance, correctness]) with a findings SCHEMA (StructuredOutput
//   forces typed findings — no JSON.parse dance, F2 win)
//   → plain-JS dedup by (file,line,rule_key)   [inlined; scripts have no imports]
//   → agent(review-coordinator) with a verdict SCHEMA
//   → return { verdict, findings } structured  (Phase 7 rendering stays shared/prose).
//
// Phases 1–4 (parse/triage) + 7–8 (render/validate/stats) stay prose in BOTH
// arms; the bake-off pins their output and passes it in via `args`. The reviewer
// agents carry Read, so paths are passed (not inlined content):
//   args = { briefPath: <path to brief.md>, diffPath: <path to unified diff>,
//            triage: <"path → treatment" lines>, quick?: bool,
//            enginePayloads?: [<lib/review/engine-findings.mjs payload>, ...],
//            engineNotRun?: [<reviewer name>, ...] }
//
// Ordre 5: the Claude Code engine payloads (Phase 4.7, run in prose before this
// script) are merged with the reviewers' findings; a reviewer or engine that
// returned nothing forbids ALLOW (fail-closed, as on the prose path); and no
// finding is struck for length.
//
// Run via the Workflow tool: Workflow({ scriptPath: this file, args }).
// The structured result is logged as a single JSON line (prefix RESULT_JSON:)
// AND returned, so the bake-off harness can recover {verdict, findings}.

export const meta = {
  name: 'trekreview-armB',
  description: 'NW2 bake-off Arm B — /trekreview Phase 5–6 as a Workflow (schema-validated parallel reviewers, JS triplet-dedup, coordinator verdict)',
  phases: [
    { title: 'Review', detail: 'parallel conformance + correctness reviewers, findings schema-forced' },
    { title: 'Coordinate', detail: 'JS dedup-by-triplet, then review-coordinator verdict' },
  ],
};

const RULE_KEYS = [
  'MISSING_BRIEF_REF', 'UNIMPLEMENTED_CRITERION', 'SCOPE_CREEP_BUILT', 'NON_GOAL_VIOLATED',
  'MISSING_TEST', 'SECURITY_INJECTION', 'PLACEHOLDER_IN_CODE', 'MISSING_ERROR_HANDLING',
  'UNDECLARED_DEPENDENCY', 'PLAN_EXECUTE_DRIFT', 'BROKEN_SUCCESS_CRITERION', 'COVERAGE_SILENT_SKIP',
  'CODE_REVIEW_DEFECT', 'CODE_REVIEW_IMPROVEMENT', 'SECURITY_REVIEW_VULNERABILITY',
];
const SEVERITIES = ['BLOCKER', 'MAJOR', 'MINOR', 'SUGGESTION'];
// Every catalogue rule_key -> its tier (lib/review/rule-catalogue.mjs; scripts
// cannot import, so it is inlined and pinned equal by the workflow test).
const RULE_TIERS = {
  MISSING_BRIEF_REF: 'MAJOR', UNIMPLEMENTED_CRITERION: 'BLOCKER', SCOPE_CREEP_BUILT: 'MAJOR',
  NON_GOAL_VIOLATED: 'BLOCKER', MISSING_TEST: 'MAJOR', SECURITY_INJECTION: 'BLOCKER',
  PLACEHOLDER_IN_CODE: 'MAJOR', MISSING_ERROR_HANDLING: 'MINOR', UNDECLARED_DEPENDENCY: 'MAJOR',
  PLAN_EXECUTE_DRIFT: 'MAJOR', BROKEN_SUCCESS_CRITERION: 'BLOCKER', COVERAGE_SILENT_SKIP: 'MAJOR',
  CODE_REVIEW_DEFECT: 'MAJOR', CODE_REVIEW_IMPROVEMENT: 'MINOR', SECURITY_REVIEW_VULNERABILITY: 'BLOCKER',
};
// Lower number = higher severity; an unknown severity ranks last (as
// lib/review/coordinator-contract.mjs severityRank does).
const sevRank = (s) => (SEVERITIES.includes(s) ? SEVERITIES.indexOf(s) : SEVERITIES.length);
// The catalogue tier of a rule_key, or null when the key is missing or unknown.
const tierOf = (key) => (typeof key === 'string' && Object.prototype.hasOwnProperty.call(RULE_TIERS, key) ? RULE_TIERS[key] : null);

// Findings schema — mirrors lib/review/findings-schema.mjs (NW1). The enum on
// rule_key enforces the catalogue at the StructuredOutput layer (stronger than
// NW1's post-hoc check: the agent cannot emit an out-of-catalogue key at all).
const FINDINGS_SCHEMA = {
  type: 'object',
  additionalProperties: true,
  required: ['reviewer', 'findings'],
  properties: {
    reviewer: { type: 'string' },
    findings: {
      type: 'array',
      items: {
        type: 'object',
        additionalProperties: true,
        required: ['severity', 'rule_key', 'file', 'line', 'title', 'detail'],
        properties: {
          severity: { type: 'string', enum: SEVERITIES },
          rule_key: { type: 'string', enum: RULE_KEYS },
          file: { type: 'string', minLength: 1 },
          line: { type: 'integer', minimum: 0 },
          brief_ref: { type: 'string' },
          title: { type: 'string', minLength: 1 },
          detail: { type: 'string' },
          recommended_action: { type: 'string' },
        },
      },
    },
  },
};

const VERDICT_SCHEMA = {
  type: 'object',
  additionalProperties: true,
  required: ['verdict', 'findings'],
  properties: {
    verdict: { type: 'string', enum: ['BLOCK', 'WARN', 'ALLOW'] },
    rationale: { type: 'string' },
    findings: {
      type: 'array',
      items: {
        type: 'object',
        additionalProperties: true,
        required: ['severity', 'rule_key', 'file', 'line'],
        properties: {
          severity: { type: 'string', enum: SEVERITIES },
          rule_key: { type: 'string', enum: RULE_KEYS },
          file: { type: 'string', minLength: 1 },
          line: { type: 'integer', minimum: 0 },
          title: { type: 'string' },
          detail: { type: 'string' },
          engine: { type: 'string', enum: ['code-review', 'security-review'] },
          contradicts_brief: { type: 'string' },
          brief_lowered_from: { type: 'string', enum: ['MAJOR'] },
        },
      },
    },
  },
};

// Inlined dedup by (file,line,rule_key) — the JS-side replacement for the
// coordinator's pass-1 triplet dedup (T2 §5 / lib/review/plan-review-dedup.mjs
// pattern; scripts cannot import, so the triplet key is inlined). On a
// repeated triplet the higher severity stays; at equal severity a reviewer
// finding (no `engine`) stays over an engine finding, so an engine's mark never
// lowers what a reviewer agent asserted (decision 13, operator 12.10, as
// coordinator-contract Pass 1); otherwise the first-seen one stays.
function dedupByTriplet(findings) {
  const seen = new Map();
  for (const f of findings) {
    const key = `${f.file}\u0000${f.line}\u0000${f.rule_key}`;
    if (!seen.has(key)) { seen.set(key, f); continue; }
    const kept = seen.get(key);
    const higher = sevRank(f.severity) < sevRank(kept.severity);
    const tieToReviewer = sevRank(f.severity) === sevRank(kept.severity) && !f.engine && Boolean(kept.engine);
    if (higher || tieToReviewer) seen.set(key, f);
  }
  return [...seen.values()];
}

function reviewerPrompt(kind, a) {
  return [
    `You are reviewing delivered code for /trekreview (bake-off Arm B, ${kind}).`,
    `Read the brief (the contract) at: ${a.briefPath}`,
    `Read the unified diff (the delivered change under review) at: ${a.diffPath}`,
    'Emit findings via the StructuredOutput tool, conforming to the provided schema.',
    'Only emit findings whose rule_key is in the catalogue. Cite file:line from the diff.',
    '',
    '=== TRIAGE MAP (respect skip decisions) ===',
    a.triage || '(no triage map supplied — treat all changed files as summary-only)',
  ].join('\n');
}

function coordinatorPrompt(merged, a) {
  return [
    'You are the review-coordinator (Judge Agent) for /trekreview, Arm B.',
    'The reviewers have already run and their findings are PRE-DEDUPLICATED by',
    '(file,line,rule_key) in JS. Do NOT re-dedup. Apply ONLY bounded operations:',
    'HubSpot Judge filters (accuracy / actionability; succinctness NEVER removes a',
    'finding — trim only MINOR/SUGGESTION text, keep BLOCKER/MAJOR whole), Cloudflare',
    'reasonableness (drop speculative or catalogue-violating findings), then compute',
    'the verdict (BLOCK if any BLOCKER; WARN if any MAJOR; else ALLOW).',
    'Return {verdict, findings} via StructuredOutput. Synthesis across files is forbidden.',
    `The brief (the contract) is at: ${a.briefPath} — Read it if needed for context.`,
    '',
    '=== BRIEF CHOICES (the brief-conflict rule) ===',
    `Read the brief's choices at ${a.briefPath}: \`## Non-Goals\`, \`## Constraints\`, \`## Preferences\`,`,
    'and the operator decisions in `## Open Questions / Assumptions`.',
    'Only an engine finding (`engine`: code-review or security-review) whose recommended action',
    'contradicts one of those choices is marked, with `contradicts_brief: "<the Non-Goal or choice, verbatim>"`.',
    'Only a /code-review finding at the MAJOR tier and at severity MAJOR then drops to MINOR, with',
    "`brief_lowered_from: 'MAJOR'`. Every other marked finding keeps its severity. A reviewer-agent finding",
    '(no `engine`) and a finding whose rule_key is not in the catalogue are never marked. A brief-conflicting',
    'finding is kept and marked, never removed. Each returned finding keeps its `engine` and `rule_key`.',
    '',
    '=== PRE-DEDUPED FINDINGS (JSON) ===',
    JSON.stringify(merged, null, 2),
  ].join('\n');
}

let a = args || {};
if (typeof a === 'string') {
  try { a = JSON.parse(a); } catch { a = {}; }
}
log(`Arm B args: type=${typeof args}; keys=${Object.keys(a || {}).join(',') || '(none)'}`);
if (!a || !a.briefPath || !a.diffPath) {
  throw new Error('trekreview-armB: args must include { briefPath, diffPath } (pinned Phase 1-4 output)');
}

phase('Review');
const reviewerThunks = [
  () => agent(reviewerPrompt('brief-conformance', a), {
    agentType: 'voyage:brief-conformance-reviewer', schema: FINDINGS_SCHEMA, label: 'conformance', phase: 'Review',
  }),
  () => agent(reviewerPrompt('code-correctness', a), {
    agentType: 'voyage:code-correctness-reviewer', schema: FINDINGS_SCHEMA, label: 'correctness', phase: 'Review',
  }),
];
const toRun = a.quick ? [reviewerThunks[1]] : reviewerThunks;
const rawResults = await parallel(toRun);
const reviewerResults = rawResults.filter(Boolean);
// A reviewer that returned nothing is an absent one, not a clean one. The
// engines that were due are counted from what actually arrived, never from
// what the caller remembered to list as not run.
const enginePayloads = Array.isArray(a.enginePayloads) ? a.enginePayloads.filter(Boolean) : [];
const expectedEngines = a.quick ? ['claude-code-review'] : ['claude-code-review', 'claude-security-review'];
const arrivedEngines = new Set(enginePayloads.map((p) => p.reviewer));
const missingEngines = expectedEngines.filter((name) => !arrivedEngines.has(name));
const missingReviewers = (rawResults.length - reviewerResults.length) + missingEngines.length;
// Provenance, before dedup: "came from an engine" is read from the source,
// never from an `engine` field. A reviewer finding loses any `engine` it
// carries; an engine payload's findings get `engine` from its `reviewer`
// (the names lib/review/engine-findings.mjs writes); any other payload gives
// its findings no `engine`. So an `engine` in `merged` means an engine payload.
const engineOf = (reviewer) => (reviewer === 'claude-code-review' ? 'code-review'
  : reviewer === 'claude-security-review' ? 'security-review' : null);
const withEngine = (f, eng) => {
  if (!f || typeof f !== 'object') return f;
  const { engine: _dropped, ...rest } = f;
  return eng ? { ...rest, engine: eng } : rest;
};
const allFindings = [
  ...reviewerResults.flatMap((r) => (Array.isArray(r?.findings) ? r.findings : []).map((f) => withEngine(f, null))),
  ...enginePayloads.flatMap((p) => (Array.isArray(p?.findings) ? p.findings : []).map((f) => withEngine(f, engineOf(p?.reviewer)))),
];
const merged = dedupByTriplet(allFindings);
log(`Arm B: ${reviewerResults.length} reviewer(s); ${allFindings.length} raw → ${merged.length} after triplet-dedup`);

phase('Coordinate');
let coord = null;
if (merged.length === 0) {
  coord = { verdict: missingReviewers > 0 ? 'WARN' : 'ALLOW', findings: [] };
  log(`Arm B: zero findings → verdict ${coord.verdict} (coordinator skipped; ${missingReviewers} reviewer(s) missing)`);
} else {
  coord = await agent(coordinatorPrompt(merged, a), {
    agentType: 'voyage:review-coordinator', schema: VERDICT_SCHEMA, label: 'coordinator', phase: 'Coordinate',
  });
}

// The verdict is mechanical: recompute its floor from the findings the
// coordinator returned, so an LLM-written ALLOW over a BLOCKER cannot pass.
const returned = Array.isArray(coord?.findings) ? coord.findings : merged;
// The brief-conflict floor: every returned finding is judged from its
// counterpart in the coordinator's input (`merged`, same file/line/rule_key),
// never from the labels the coordinator wrote. The raise is written into
// `returned`, the mark kept, so the rendered review.md carries it.
const counterparts = new Map(merged
  .filter((m) => m && typeof m === 'object')
  .map((m) => [`${m.file}\u0000${m.line}\u0000${m.rule_key}`, m]));
const present = (f, field) => f[field] !== undefined && f[field] !== null;
const raiseTo = (f, sev) => { if (sevRank(sev) < sevRank(f.severity)) f.severity = sev; };
for (const f of returned) {
  if (!f || typeof f !== 'object') continue;
  const c = counterparts.get(`${f.file}\u0000${f.line}\u0000${f.rule_key}`);
  const labelled = present(f, 'engine') || present(f, 'contradicts_brief') || present(f, 'brief_lowered_from');
  if (c && c.engine) {
    // (1) an engine counterpart: raised to its severity, unless the one legal lowering.
    const legal = c.engine === 'code-review' && c.severity === 'MAJOR' && tierOf(c.rule_key) === 'MAJOR' &&
      f.severity === 'MINOR' && typeof f.contradicts_brief === 'string' && f.contradicts_brief.trim().length > 0 &&
      f.brief_lowered_from === 'MAJOR';
    if (!legal) raiseTo(f, c.severity);
    f.engine = c.engine;
  } else if (labelled) {
    // (2) a reviewer counterpart, (3) no counterpart: an unknown key raises to BLOCKER.
    raiseTo(f, tierOf(f.rule_key) ?? 'BLOCKER');
    if (c) raiseTo(f, c.severity);
    delete f.engine;
  }
}
const has = (sev) => returned.some((f) => f && f.severity === sev);
let verdict = coord?.verdict ?? null;
if (has('BLOCKER')) verdict = 'BLOCK';
else if (has('MAJOR') && verdict !== 'BLOCK') verdict = 'WARN';
if (verdict === 'ALLOW' && missingReviewers > 0) verdict = 'WARN';

const result = {
  verdict,
  missing_reviewers: missingReviewers,
  missing_engines: missingEngines,
  findings: returned,
  raw_reviewer_count: reviewerResults.length,
  raw_finding_count: allFindings.length,
  deduped_count: merged.length,
};
log(`RESULT_JSON:${JSON.stringify(result)}`);
return result;