Duriin-API/workers/coordinatorWorker.js

const os = require('os');
const fs = require('fs');
const path = require('path');
const { openRuntimeDb } = require('../src/db/runtime');
const { initAutonomySchema } = require('../src/autonomy/schema');
const { leaseNextJob, completeJob, failJob } = require('../src/autonomy/jobs');
const { callCoordinator } = require('../src/autonomy/llm');
const { acceptProposal, recordRejectedProposal, INSTRUMENT_RULES } = require('../src/autonomy/coordinator');
const { EVENT_FAMILY_NAMES } = require('../src/autonomy/calibration');
const { buildGraphContext } = require('../src/autonomy/graphContext');

function sleep(ms) { return new Promise((resolve) => setTimeout(resolve, ms)); }

// bumped when the prompt changes in a way that changes what a prediction means.
// autonomy-2 is the first version that can see the relationship graph.
const STRATEGY_VERSION = 'autonomy-2';

function loadConfig() {
  const configPath = path.resolve(process.env.DURIIN_CONFIG || path.join(__dirname, '..', 'config.json'));
  const raw = JSON.parse(fs.readFileSync(configPath, 'utf8'));
  require('dotenv').config({ path: path.resolve(path.dirname(configPath), '.env') });
  raw.openRouter = { ...(raw.openRouter || {}) };
  if (process.env.OPEN_ROUTER_API_KEY) raw.openRouter.apiKey = process.env.OPEN_ROUTER_API_KEY;
  if (process.env.OPEN_ROUTER_LLM_MODEL) raw.openRouter.llmModel = process.env.OPEN_ROUTER_LLM_MODEL;
  return raw;
}

function buildPrompt(event, articles, graphContext = '') {
  const evidence = articles.map((article, index) =>
    `[Evidence ${index + 1}] article_id=${article.id}\nTitle: ${article.title}\n${String(article.content || article.description || '').slice(0, 4000)}`
  ).join('\n\n---\n\n');
  return `Event title: ${event.title}\n\n${evidence}\n\n${graphContext ? `${graphContext}\n\n` : ''}Return JSON only in this shape:\n${JSON.stringify({ predictions: [{
    instrument: '<ticker supported by the articles>', direction: '<positive or negative>',
    event_type: '<one value from the event_type list below>',
    causal_channel: '<short description>', horizon_days: '<one of 1, 5, 10, 20, 30, 60, 90>',
    evidence_article_ids: ['<article_id values from the evidence above>'],
    invalidation_condition: '<what would falsify this>',
  }] }, null, 2)}\n\nEvery value in that shape is a placeholder describing the field. Do not copy them. Choose instrument, direction and horizon_days from the evidence in front of you.\n\nevent_type must be exactly one of: ${EVENT_FAMILY_NAMES.join(', ')}. Pick the closest one. Use "other" only when none of them genuinely apply, and never invent a value outside this list.\n\n${INSTRUMENT_RULES}\n\nUse only instruments and evidence directly supported by the articles. Return an empty predictions array when there is no clear, tradable hypothesis. Never include probabilities, returns, confidence, position sizes, or actions.`;
}

async function runCoordinatorWorker({ archivePath, intelligencePath, workerId = `coordinator-${os.hostname()}-${process.pid}`, pollMs = 1000 } = {}) {
  const archiveDb = openRuntimeDb(archivePath, { schema: 'archive', readonly: true });
  const intelligenceDb = openRuntimeDb(intelligencePath, { schema: 'intelligence' });
  intelligenceDb.pragma('journal_mode = WAL');
  intelligenceDb.pragma('busy_timeout = 5000');
  initAutonomySchema(intelligenceDb);
  const config = loadConfig();
  while (true) {
    const job = leaseNextJob(intelligenceDb, workerId, 180, ['coordinator_event']);
    if (!job) { await sleep(pollMs); continue; }
    try {
      const event = archiveDb.prepare('SELECT id, title FROM events WHERE id = ?').get(job.entity_id);
      if (!event) throw new Error(`event ${job.entity_id} does not exist`);
      const articles = archiveDb.prepare(`
        SELECT id, title, description, content, pub_date_effective
        FROM articles
        WHERE event_id = ? AND content IS NOT NULL AND content != '' AND is_index_page = 0
        ORDER BY pub_date_effective ASC, id ASC LIMIT 25
      `).all(job.entity_id);
      const allowlisted = intelligenceDb.prepare(
        "SELECT 1 FROM autonomy_instruments WHERE active=1 AND tradable=1 LIMIT 1"
      ).get();
      if (!allowlisted) throw new Error('no tradable instruments are allowlisted');
      const historical = job.lane === 'historical';
      const informationCutoff = historical
        ? (articles.map((article) => article.pub_date_effective).filter(Boolean).sort().pop() || new Date().toISOString())
        : new Date().toISOString();
      const graphContext = buildGraphContext(intelligenceDb, event.id, informationCutoff);
      const raw = await callCoordinator(config, buildPrompt(event, articles, graphContext));
      try {
        acceptProposal(intelligenceDb, archiveDb, raw, {
          eventId: event.id,
          informationCutoff,
          model: config.openRouter.llmModel || 'unknown',
          promptVersion: 'coordinator-1',
          strategyVersion: STRATEGY_VERSION,
          // only a genuine live lane job may ever feed learning
          origin: historical ? 'historical' : 'live',
          learningEligible: !historical,
        });
      } catch (validationError) {
        console.error(`[${workerId}] proposal rejected for event ${event.id}:`, validationError.message);
        recordRejectedProposal(intelligenceDb, raw, {
          eventId: event.id,
          informationCutoff,
          model: config.openRouter.llmModel || 'unknown',
          promptVersion: 'coordinator-1',
          origin: historical ? 'historical' : 'live',
          learningEligible: !historical,
        }, validationError.message);
      }
      completeJob(intelligenceDb, job.id, workerId);
    } catch (error) {
      failJob(intelligenceDb, job.id, workerId, error);
    }
    await sleep(pollMs);
  }
}

module.exports = { buildPrompt, runCoordinatorWorker };