voyage/lib/util/research-loop-cap.mjs

// lib/util/research-loop-cap.mjs
// Stateful, default-off cost cap for the /trekresearch bounded conversation
// loop (Phase 4.5 dimension discovery + Phase 5 loop turns).
//
// Three properties the plan review required:
//   (a) Default-off — VOYAGE_STORM_ENABLED must be '1'; otherwise the budget
//       is 0 regardless of effort. This IS the decline branch: doing nothing
//       leaves the mechanism off, and adopt is flipping this one constant.
//   (b) The cap counts itself — allowTurn() derives used-turn count from an
//       append-only JSONL ledger, never from a caller-supplied number. A cap
//       that asks the caller how many turns it has used is not a cap.
//   (c) Correct size bound — worst case is max_conv_turns × max_total_dimensions,
//       where max_total_dimensions is the WHOLE list (interview + discovered)
//       under settings.json:16's cap of 8 — not × discovered-only.
//
// CLAUDE_PLUGIN_DATA absent => fall back to ~/.claude/voyage. The variable is
// EMPTY in the Bash tool's process env (measured in a live plugin-enabled
// session), and the Phase 5 bash snippet is this module's only caller — so
// denying on its absence denied turn 1 of every real run. The root is resolved
// in code rather than demanded of the environment, and hooks/scripts/
// pre-agent-cap.mjs resolves it through the SAME function, so the writer and
// the reader can never disagree about where the ledger lives.
//
// The fail-closed stance covers both directions of ledger IO: a ledger that
// cannot be WRITTEN denies the turn, and a ledger that exists but cannot be
// READ denies it too. Only ENOENT counts as zero turns spent, because that is
// the legitimate first-turn state. This module is a budget control, not
// telemetry — the opposite of lib/stats/event-emit.mjs's fail-open.
//
// CLI shim:
//   node lib/util/research-loop-cap.mjs --run-id ID --dimension D --effort E
//   → JSON: { ok, used, budget, reason? }   (exit 0 = granted, exit 1 = denied)

import { existsSync, mkdirSync, appendFileSync, readFileSync } from 'node:fs';
import { dirname, join } from 'node:path';
import { homedir } from 'node:os';

export const MAX_CONV_TURNS = 3;
export const MAX_TOTAL_DIMENSIONS = 8; // settings.json:16 maxDimensions — whole list, not discovered-only

const LEDGER_FILENAME = 'trekresearch-loop-ledger.jsonl';

export function isStormEnabled(env = process.env) {
  return env.VOYAGE_STORM_ENABLED === '1';
}

/**
 * Coerce TREKRESEARCH_MAX_CONV_TURNS. NaN, empty, negative, zero, Infinity, or
 * any fraction that floors below 1 all fall back to MAX_CONV_TURNS — never to
 * unbounded, and never to 0.
 *
 * The floor is applied BEFORE the `<= 0` guard, not after. Flooring afterwards
 * let '0.5' and '0.9' clear a guard written against the raw value and then
 * become 0, making the budget 0 × MAX_TOTAL_DIMENSIONS = 0: every turn denied
 * and the loop silently dead rather than bounded. A cap of 0 is not a narrower
 * cap, it is an off switch that the documented fallback promises not to be.
 */
export function resolveMaxConvTurns(env = process.env) {
  const raw = env.TREKRESEARCH_MAX_CONV_TURNS;
  if (raw === undefined || raw === null || raw === '') return MAX_CONV_TURNS;
  const n = Math.floor(Number(raw));
  if (!Number.isFinite(n) || n <= 0) return MAX_CONV_TURNS;
  return n;
}

/**
 * The one data root for everything this loop writes: the turn ledger and the
 * PreToolUse scope marker. CLAUDE_PLUGIN_DATA when the harness provides it,
 * ~/.claude/voyage when it does not — which is the case in every Bash tool
 * invocation today.
 */
export function resolveDataRoot(env = process.env) {
  const dir = env.CLAUDE_PLUGIN_DATA;
  if (dir && typeof dir === 'string' && dir.length > 0) return dir;
  const home = env.HOME && env.HOME.length > 0 ? env.HOME : homedir();
  return join(home, '.claude', 'voyage');
}

export function resolveLedgerPath(env = process.env) {
  return join(resolveDataRoot(env), LEDGER_FILENAME);
}

/**
 * Read one run's turn count off the append-only ledger.
 *
 * ENOENT is 0 turns spent — the legitimate first-turn state, and the reason
 * this cannot simply throw on every read failure. Every OTHER read error
 * (EISDIR, EACCES, EIO) THROWS, because returning 0 from an unreadable ledger
 * re-granted the full budget on every call: unbounded, and the exact
 * silently-grant-unlimited failure this module's header argues against three
 * lines above the code that did it. The missing-directory case already failed
 * closed; this makes the unreadable-file case agree with it.
 *
 * The `existsSync` pre-check is deliberately gone: readFileSync's own ENOENT
 * carries the same information without a second syscall that can disagree with
 * the read that follows it.
 *
 * Exported so hooks/scripts/pre-agent-cap.mjs counts through this exact
 * function. A reader and a writer with private copies of the counting rule are
 * how a hook ends up enforcing a different bound than the gate it backs.
 *
 * @param {string} ledgerPath
 * @param {string} runId
 * @returns {{granted: number}}
 * @throws when the ledger exists but cannot be read
 */
export function readLedger(ledgerPath, runId) {
  let text;
  try {
    text = readFileSync(ledgerPath, 'utf-8');
  } catch (e) {
    if (e && e.code === 'ENOENT') return { granted: 0 };
    const err = new Error(`ledger unreadable at ${ledgerPath}: ${e.message}`);
    err.code = 'VOYAGE_LEDGER_UNREADABLE';
    throw err;
  }
  let granted = 0;
  for (const line of text.split('\n')) {
    if (!line) continue;
    try {
      if (JSON.parse(line).runId === runId) granted++;
    } catch { /* skip malformed lines */ }
  }
  return { granted };
}

/**
 * Decide whether one more research-loop turn may run. Append-only: never
 * read-modify-write, because Phase 4.5/5 may spawn multiple agents in a
 * single message and a read-modify-write counter would lose concurrent
 * grants.
 *
 * @param {{runId: string, dimension: string, effort: string}} args
 * @param {{env?: object, now?: Date}} [opts]
 * @returns {{ok: boolean, used: number, budget: number, reason?: string}}
 */
export function allowTurn({ runId, dimension, effort } = {}, opts = {}) {
  const env = opts.env || process.env;
  const now = opts.now || new Date();

  if (!isStormEnabled(env)) {
    return { ok: false, used: 0, budget: 0, reason: 'storm_disabled' };
  }
  if (effort !== 'high') {
    return { ok: false, used: 0, budget: 0, reason: 'effort_not_high' };
  }
  if (!runId || !dimension) {
    return { ok: false, used: 0, budget: 0, reason: 'missing_args' };
  }

  const maxConvTurns = resolveMaxConvTurns(env);
  const budget = maxConvTurns * MAX_TOTAL_DIMENSIONS;

  const ledgerPath = resolveLedgerPath(env);
  let used;
  try {
    used = readLedger(ledgerPath, runId).granted;
  } catch (e) {
    return { ok: false, used: 0, budget, reason: `ledger-read-failed: ${e.message}` };
  }
  if (used >= budget) {
    return { ok: false, used, budget, reason: 'budget_exhausted' };
  }

  try {
    const dir = dirname(ledgerPath);
    if (!existsSync(dir)) mkdirSync(dir, { recursive: true });
    appendFileSync(ledgerPath, JSON.stringify({ ts: now.toISOString(), runId, dimension, effort }) + '\n');
  } catch (e) {
    return { ok: false, used, budget, reason: `ledger-write-failed: ${e.message}` };
  }

  return { ok: true, used: used + 1, budget };
}

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

function parseArgs(argv) {
  const out = {};
  for (let i = 0; i < argv.length; i++) {
    const a = argv[i];
    if (a === '--run-id') out.runId = argv[++i];
    else if (a === '--dimension') out.dimension = argv[++i];
    else if (a === '--effort') out.effort = argv[++i];
  }
  return out;
}

if (import.meta.url === `file://${process.argv[1]}`) {
  const args = parseArgs(process.argv.slice(2));
  if (!args.runId || !args.dimension || !args.effort) {
    process.stdout.write(JSON.stringify({
      ok: false,
      reason: 'usage: research-loop-cap.mjs --run-id ID --dimension D --effort standard|high|low',
    }) + '\n');
    process.exit(1);
  }
  const result = allowTurn(args);
  process.stdout.write(JSON.stringify(result) + '\n');
  process.exit(result.ok ? 0 : 1);
}