pig/apps/piggy/test/config.test.ts

import assert from 'node:assert/strict';
import test from 'node:test';
import { loadPiggyConfig, loadPiggyStallLimits, loadPiggyTurnLimits } from '../src/config';

const minimum = {
  DATABASE_URL: 'postgres://pig:pig@localhost:54330/pig',
  PIGGY_INFERENCE_API_KEY: 'test-key',
  PIGGY_INTERNAL_TOKEN: 'test-internal-token-for-piggy-000000',
};

test('the chat budget is separate from the worker budget, and larger', () => {
  const config = loadPiggyConfig(minimum);

  // The worker extracts; the chat has to quote aggregates back. Sharing one
  // budget meant tuning either one moved both.
  assert.equal(config.PIGGY_MAX_TOKENS, 1_024);
  assert.equal(config.PIGGY_CHAT_MAX_TOKENS, 2_048);
  assert.equal(config.PIGGY_MAX_TURNS, 4);
});

test('a turn has a ceiling on both axes, generous against the measured turn', () => {
  const config = loadPiggyConfig(minimum);

  // Measured on the live stack against the default model: a one-tool turn is
  // 2 model calls and 4,922 tokens, a two-tool turn is 3 and 12,265. The
  // ceilings are roughly three times the busiest of those, which leaves a real
  // multi-step question room to breathe and still stops a `while (true)` in
  // seconds rather than in dollars.
  assert.equal(config.PIGGY_CHAT_MAX_MODEL_CALLS, 8);
  assert.equal(config.PIGGY_CHAT_MAX_TURN_TOKENS, 40_000);
  assert.equal(config.PIGGY_CHAT_DAILY_LIMIT_CENTS, 200);

  // PIGGY_MAX_TURNS is the queue worker's own budget and reaches nothing in the
  // chat path. Keeping them distinct is the point: raising one used to look
  // like it raised the other, which is how the chat came to have no ceiling at
  // all.
  assert.notEqual(config.PIGGY_MAX_TURNS, config.PIGGY_CHAT_MAX_MODEL_CALLS);
});

test('the ceilings can be read without the rest of the environment', () => {
  // The chat server is handed a socket and a token and builds the rest from
  // defaults; it must not start demanding a DATABASE_URL it never uses.
  assert.deepEqual(loadPiggyTurnLimits({}), {
    maxModelCalls: 8,
    maxTurnTokens: 40_000,
    dailyLimitCents: 200,
  });
  assert.deepEqual(
    loadPiggyTurnLimits({
      PIGGY_CHAT_MAX_MODEL_CALLS: '3',
      PIGGY_CHAT_MAX_TURN_TOKENS: '9000',
      PIGGY_CHAT_DAILY_LIMIT_CENTS: '0',
    }),
    { maxModelCalls: 3, maxTurnTokens: 9_000, dailyLimitCents: 0 },
  );
  // A ceiling of zero model calls would answer nothing at all, so it is a
  // configuration error rather than a very strict deployment.
  assert.throws(
    () => loadPiggyTurnLimits({ PIGGY_CHAT_MAX_MODEL_CALLS: '0' }),
    /PIGGY_CHAT_MAX_MODEL_CALLS/,
  );
  assert.throws(
    () => loadPiggyTurnLimits({ PIGGY_CHAT_MAX_TURN_TOKENS: 'plenty' }),
    /PIGGY_CHAT_MAX_TURN_TOKENS/,
  );
});

test('a turn has two deadlines for silence, and they are not one flat deadline', () => {
  const config = loadPiggyConfig(minimum);
  assert.equal(config.PIGGY_CHAT_FIRST_PROGRESS_TIMEOUT_MS, 60_000);
  assert.equal(config.PIGGY_CHAT_IDLE_TIMEOUT_MS, 45_000);
  // Read on their own too: the chat server is handed a socket and a token.
  assert.deepEqual(loadPiggyStallLimits({}), { firstProgressMs: 60_000, idleMs: 45_000 });
  assert.deepEqual(
    loadPiggyStallLimits({
      PIGGY_CHAT_FIRST_PROGRESS_TIMEOUT_MS: '1500',
      PIGGY_CHAT_IDLE_TIMEOUT_MS: '900',
    }),
    { firstProgressMs: 1_500, idleMs: 900 },
  );

  // The idle window is the shorter of the two on purpose. Getting started
  // covers connecting, the endpoint's queue and a slow model's first token;
  // once a turn is under way the gaps are milliseconds, so a long silence
  // mid-answer is a dead socket rather than a thoughtful one. Neither bounds
  // the turn's total duration, which is the whole design: the idle clock
  // restarts on every event.
  assert.ok(
    loadPiggyStallLimits({}).idleMs < loadPiggyStallLimits({}).firstProgressMs,
    'the idle window should not need to be as generous as getting started',
  );

  // A deadline of zero would stall every turn before it began, so it is a
  // configuration error rather than a very impatient deployment.
  assert.throws(
    () => loadPiggyStallLimits({ PIGGY_CHAT_IDLE_TIMEOUT_MS: '0' }),
    /PIGGY_CHAT_IDLE_TIMEOUT_MS/,
  );
  assert.throws(
    () => loadPiggyStallLimits({ PIGGY_CHAT_FIRST_PROGRESS_TIMEOUT_MS: 'patience' }),
    /PIGGY_CHAT_FIRST_PROGRESS_TIMEOUT_MS/,
  );
});

test('reasoning stays off by default', () => {
  // Reasoning tokens are billed like any other and nemotron-nano's are
  // verbose. The knob exists for debugging, not for the default deployment.
  assert.equal(loadPiggyConfig(minimum).PIGGY_REASONING_EFFORT, 'none');
  assert.equal(
    loadPiggyConfig({ ...minimum, PIGGY_REASONING_EFFORT: 'low' }).PIGGY_REASONING_EFFORT,
    'low',
  );
  assert.throws(
    () => loadPiggyConfig({ ...minimum, PIGGY_REASONING_EFFORT: 'maximum' }),
    /PIGGY_REASONING_EFFORT/,
  );
});

test('the default token prices are the published price of the default model', () => {
  const config = loadPiggyConfig(minimum);
  // $0.05/$0.20 per million tokens, carried as cents per million so that
  // tokens x price is already micro-cents.
  assert.equal(config.PIGGY_PRICE_INPUT_CENTS_PER_MTOK, 5);
  assert.equal(config.PIGGY_PRICE_OUTPUT_CENTS_PER_MTOK, 20);
  assert.equal(config.PIGGY_MODEL, 'nvidia/nemotron-3-nano-30b-a3b');
});