IMBENJI.NET/Duriin-API
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add autonomous paper-trading and calibration pipeline

Browse Source
This commit is contained in:
ImBenji
2026-08-03 14:03:27 +01:00
parent 5a9a2e4c6d
commit c4028cc394
46 changed files with 2246 additions and 115 deletions
Download Patch File Download Diff File Expand all files Collapse all files
workers/augorWorker.js
+111 -12
View File
@@ -2,6 +2,11 @@ const https = require("https");
const http = require("http");
const { findMatchedCompaniesByEmbedding } = require("./embeddings");
const { getPriceContext, formatPriceContext } = require("./priceContext");
const REPROCESS_MIN_NEW_ARTICLES = 3;
const REPROCESS_COOLDOWN_HOURS = 6;
async function runAugorWorker(archiveDb, intelligenceDb, config) {
const loopDelay = config.workers?.augorLoopDelayMs ?? 1500;
@@ -11,6 +16,26 @@ async function runAugorWorker(archiveDb, intelligenceDb, config) {
SELECT * FROM article_queue WHERE status = 'pending' LIMIT 1
`);
const getProcessingState = intelligenceDb.prepare(
"SELECT last_processed_at, articles_at_last_run FROM event_processing_state WHERE event_id = ?"
);
const upsertProcessingState = intelligenceDb.prepare(`
INSERT INTO event_processing_state (event_id, last_processed_at, articles_at_last_run)
VALUES (?, CURRENT_TIMESTAMP, ?)
ON CONFLICT(event_id) DO UPDATE SET
last_processed_at = CURRENT_TIMESTAMP,
articles_at_last_run = excluded.articles_at_last_run
`);
const getCompanyAccuracy = intelligenceDb.prepare(`
SELECT
COUNT(*) as total,
SUM(correct_10d) as correct
FROM prediction_outcomes
WHERE company_id = ? AND correct_10d IS NOT NULL
`);
const recordEvent = intelligenceDb.prepare(
`INSERT INTO worker_events (worker) VALUES ('augor')`
);
@@ -45,8 +70,8 @@ async function runAugorWorker(archiveDb, intelligenceDb, config) {
VALUES (?, ?, ?, ?, ?)
`);
const insertPrediction = intelligenceDb.prepare(`
INSERT INTO event_predictions (event_id, company_id, type, direction, magnitude, timeframe, rationale, event_date)
VALUES (?, ?, ?, ?, ?, ?, ?, ?)
INSERT INTO event_predictions (event_id, company_id, type, direction, magnitude, timeframe, rationale, probability, event_date)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)
`);
const getEventDate = archiveDb.prepare(`
@@ -66,7 +91,6 @@ async function runAugorWorker(archiveDb, intelligenceDb, config) {
const queueRow = getPending.get();
if (!queueRow) {
await sleep(loopDelay);
continue;
}
@@ -98,12 +122,29 @@ async function runAugorWorker(archiveDb, intelligenceDb, config) {
const eventArticleIds = eventArticles.map(a => a.id);
// event-level batching guard — skip re-processing if we already ran on this event recently
// and not enough new articles have arrived to justify another LLM call
const state = getProcessingState.get(eventId);
if (state && state.last_processed_at) {
const newArticles = eventArticles.length - state.articles_at_last_run;
const lastRunMs = new Date(state.last_processed_at + "Z").getTime();
const hoursSince = (Date.now() - lastRunMs) / 3_600_000;
if (newArticles < REPROCESS_MIN_NEW_ARTICLES && hoursSince < REPROCESS_COOLDOWN_HOURS) {
for (const r of getEventArticleIds.all(eventId)) setStatusByArticleId.run(r.id);
console.log(`[augor] event ${eventId} — only ${newArticles} new articles in ${hoursSince.toFixed(1)}h, skipping re-process`);
continue;
}
}
const matchedCompanies = findMatchedCompaniesByEmbedding(
eventArticleIds, archiveDb, intelligenceDb, config
);
if (matchedCompanies.length === 0) {
for (const r of getEventArticleIds.all(eventId)) setStatusByArticleId.run(r.id);
upsertProcessingState.run(eventId, eventArticles.length);
console.log(`[augor] event ${eventId} — no company match, skipped`);
continue;
}
@@ -114,6 +155,7 @@ async function runAugorWorker(archiveDb, intelligenceDb, config) {
const eventDateRow = getEventDate.get(eventId);
const eventDate = eventDateRow ? eventDateRow.pub_date_effective : null;
const eventDateOnly = eventDate ? eventDate.slice(0, 10) : null;
const articleText = eventArticles.map((a, i) => {
const body = (a.content || a.description || "").slice(0, 2000);
@@ -130,9 +172,30 @@ async function runAugorWorker(archiveDb, intelligenceDb, config) {
factsBlock = `Known facts about ${company.name}:\n${lines}`;
}
const result = await callLlm(llmConfig, buildPrompt(company.name, event.title, articleText, factsBlock));
// pull live market context for the company at the time of the event
let priceBlock = null;
if (company.ticker && eventDateOnly) {
try {
const snapshot = await getPriceContext(intelligenceDb, company.ticker, eventDateOnly);
priceBlock = formatPriceContext(snapshot, company.ticker);
} catch (_) {}
}
// historical accuracy of past predictions for this company
let accuracyBlock = null;
const acc = getCompanyAccuracy.get(company.id);
if (acc && acc.total >= 5) {
const pct = (acc.correct / acc.total * 100).toFixed(0);
accuracyBlock = `Past prediction accuracy for ${company.name}: ${pct}% over ${acc.total} evaluated calls.`;
}
const result = await callLlm(llmConfig, buildPrompt(company.name, event.title, articleText, factsBlock, priceBlock, accuracyBlock));
if (result) {
const seenPreds = new Set();
const writeAll = intelligenceDb.transaction(() => {
for (const r of (result.knowledge?.relationships || [])) {
insertKnowledge.run(eventId, company.id, "relationship", JSON.stringify(r), eventDate);
@@ -145,7 +208,21 @@ async function runAugorWorker(archiveDb, intelligenceDb, config) {
}
for (const p of (result.predictions || [])) {
insertPrediction.run(eventId, company.id, p.type, p.direction, p.magnitude, p.timeframe, p.rationale, eventDate);
// hard filter — neutral predictions are dead weight, skip them
if (p.direction === "neutral") continue;
if (p.direction !== "positive" && p.direction !== "negative") continue;
const key = `${p.type}|${p.direction}|${p.magnitude}|${p.timeframe}`;
if (seenPreds.has(key)) continue;
seenPreds.add(key);
const prob = typeof p.probability === "number" && p.probability >= 0 && p.probability <= 1
? p.probability
: null;
insertPrediction.run(
eventId, company.id, p.type, p.direction, p.magnitude, p.timeframe, p.rationale, prob, eventDate
);
}
});
@@ -158,6 +235,7 @@ async function runAugorWorker(archiveDb, intelligenceDb, config) {
}
for (const r of getEventArticleIds.all(eventId)) setStatusByArticleId.run(r.id);
upsertProcessingState.run(eventId, eventArticles.length);
recordEvent.run();
pruneCounter++;
if (pruneCounter >= 100) { pruneEvents.run(); pruneCounter = 0; }
@@ -165,23 +243,44 @@ async function runAugorWorker(archiveDb, intelligenceDb, config) {
} catch (err) {
console.error("[augor] error:", err.message);
} finally {
// Enforce pacing on every path, including the many early `continue`
// branches for skipped or already-processed events.
await sleep(loopDelay);
}
}
}
function buildPrompt(companyName, eventTitle, articleText, factsBlock) {
function buildPrompt(companyName, eventTitle, articleText, factsBlock, priceBlock, accuracyBlock) {
const factsPart = factsBlock ? `${factsBlock}\n\n` : "";
const pricePart = priceBlock ? `Market context for ${companyName}:\n${priceBlock}\n\n` : "";
const accPart = accuracyBlock ? `${accuracyBlock}\n\n` : "";
return `You are a financial intelligence analyst focused on ${companyName}. Always respond in English regardless of the language of the input articles.
return `You are a financial intelligence analyst. Always respond in English.
${factsPart}Assess the impact of the following news event on ${companyName} given what you already know about the company.
Event: ${eventTitle}
${factsPart}${pricePart}${accPart}Event: ${eventTitle}
${articleText}
Return JSON only — no explanation. Shape:
Analyze the impact of this event on ${companyName}. Return JSON only — no explanation.
Strict rules — read carefully:
- predictions must be directly caused by THIS specific event — no speculation, no priced-in narrative
- only emit a prediction if the evidence is unambiguous AND the effect on ${companyName} is concrete and quantifiable
- the default answer is no prediction. an empty predictions array is the correct output for most news. only emit one when the event clearly moves the needle
- never emit two predictions that share type+direction+magnitude+timeframe — collapse them into one
- direction must be "positive" or "negative" only — no neutral predictions, ever. if the impact is unclear, emit nothing
- magnitude:
"high" = major revenue/market-share shift, expected >5% stock move
"medium" = measurable but limited, expected 1-5% stock move
omit any prediction that doesnt clear the medium bar
- timeframe:
"short" = days to 2 weeks (use sparingly — short-horizon predictions are unreliable)
"medium" = 2 weeks to 3 months
"long" = 3+ months — preferred when the thesis is structural
- probability: your honest calibrated probability that the directional call is correct over the stated timeframe, as a number between 0.5 and 0.95. if you cant honestly assign >= 0.6, dont emit the prediction
- if the market context shows the stock has already moved sharply (>10% in 30 days), be sceptical that this event adds new information — the move may already be priced in
{
"knowledge": {
"relationships": [
@@ -195,7 +294,7 @@ Return JSON only — no explanation. Shape:
]
},
"predictions": [
{ "type": "market_share|stock_price|competitive_position|other", "direction": "positive|negative|neutral", "magnitude": "high|medium|low", "timeframe": "short|medium|long", "rationale": "string" }
{ "type": "market_share|stock_price|competitive_position|other", "direction": "positive|negative", "magnitude": "high|medium", "timeframe": "short|medium|long", "probability": 0.0, "rationale": "string" }
]
}