Per-run limits & cost cap

import { createGnl, RunLimitExceededError, type RunLimits } from '@gnldev/durable';

// Checked AFTER each model step is journaled — a single step can OVERSHOOT the ceiling,
// but the run does not proceed to the NEXT step once it is breached.
const limits: RunLimits = { maxTokens: 50_000, maxCostUsd: 0.5, maxToolCalls: 20 };

try {
  await gnl.run('asst', { runId: 'r5', prompt: 'do the task', limits });
} catch (e) {
  if (e instanceof RunLimitExceededError) {
    // e.detail: { kind, value, limit }
    console.log('limit exceeded:', e.detail.kind, e.detail.value, e.detail.limit);
  }
}

// Same tool + identical argsHash repeated 3 times IN A ROW → 'reflect' delivers a nudge
// instead of an immediate block ('block' throws ToolLoopDetectedError right away).
const limits: RunLimits = { loopDetection: { maxRepeats: 3, onRepeat: 'reflect' } };

// The journal stays consistent when RunLimitExceededError is thrown.
// Raise the ceiling and resume the SAME runId to continue past the cut-off point:
await gnl.run('asst', { runId: 'r5', prompt: 'continue', limits: { maxTokens: 200_000 } });

// onBlocked fires for a loop / maxToolCalls / duplicate / tainted BLOCK — you get the
// RAW breach and decide what (if anything) the user sees. GNL does not invent a
// user-facing message.
const result = await gnl.stream('asst', {
  runId: 'r6',
  prompt: 'do the task',
  limits,
  onBlocked: (breach) => {
    // breach.kind identifies which guard fired; breach.message is a raw diagnostic
    // string; breach.detail carries that guard's own structured payload.
    console.log('blocked:', breach.kind, breach.message);
  },
});

try {
  const text = await result.text;
} catch (e) {
  // result.text REJECTS on a block — mirrors runDurable throwing, so a direct
  // consumer of the stream cannot silently miss the breach.
}