c762564d40
- Fix 71 invalid-syntax files (class-body newline-broken assignments) - Add from/None chain to 307 B904 raise-without-from sites - Add B008 ignore to ruff.toml (already in pyproject.toml) - Noqa F401 on __init__.py re-exports (137 sites) - Noqa E402 on deferred imports (63 sites) - Bulk-add stdlib/FastAPI/project imports for F821 (127 sites) - Replace ×→x, –→-, …→... in docstrings (4093 chars) - Manual refactor of 5 SIM103/SIM116 patterns Tests: 791 passed (66 deselected due to pre-existing Redis issues in test_rag.py) Co-authored-by: opencode <opencode@rugmunch.io>
445 lines
16 KiB
Python
445 lines
16 KiB
Python
"""
|
|
RugCharts Social Intelligence
|
|
==============================
|
|
KOL tracking, shill detection, scam monitoring, social metrics.
|
|
|
|
Features:
|
|
- KOL Performance Score - track historical calls, success rate
|
|
- Shill Campaign Detection - coordinated posting patterns
|
|
- Scam Channel Monitor - Telegram/Discord intelligence
|
|
- Social Sentiment - aggregate market mood from multiple platforms
|
|
- Daily Intel Report - Groq-powered market briefing
|
|
"""
|
|
|
|
import hashlib
|
|
import logging
|
|
import os
|
|
import time
|
|
from collections import Counter, defaultdict
|
|
from datetime import UTC, datetime
|
|
|
|
import httpx
|
|
|
|
logger = logging.getLogger("social_intel")
|
|
|
|
GROQ_KEY = os.getenv("GROQ_API_KEY", "")
|
|
|
|
# ═══════════════════════════════════════════════════════════════════════
|
|
# KOL PERFORMANCE TRACKER
|
|
# ═══════════════════════════════════════════════════════════════════════
|
|
|
|
KOL_DATABASE: dict[str, dict] = {} # handle → {calls: [...], metrics: {...}}
|
|
|
|
|
|
def _kol_key(handle: str) -> str:
|
|
return f"kol:{handle.lower().lstrip('@')}"
|
|
|
|
|
|
async def track_kol_call(
|
|
handle: str,
|
|
token: str,
|
|
call_type: str = "buy",
|
|
price_at_call: float = 0,
|
|
chain: str = "solana",
|
|
**kw,
|
|
) -> dict:
|
|
"""Record a KOL making a call on a token.
|
|
|
|
call_type: buy, sell, shill, warning, analysis
|
|
"""
|
|
key = _kol_key(handle)
|
|
if key not in KOL_DATABASE:
|
|
KOL_DATABASE[key] = {
|
|
"calls": [],
|
|
"metrics": {
|
|
"total_calls": 0,
|
|
"buy_calls": 0,
|
|
"sell_calls": 0,
|
|
"shills": 0,
|
|
"warnings": 0,
|
|
"analyses": 0,
|
|
"tokens_mentioned": set(),
|
|
"avg_roi": 0,
|
|
"win_rate": 0,
|
|
"followers": 0,
|
|
},
|
|
}
|
|
|
|
call = {
|
|
"handle": handle,
|
|
"token": token,
|
|
"type": call_type,
|
|
"price_at_call": price_at_call,
|
|
"chain": chain,
|
|
"timestamp": datetime.now(UTC).isoformat(),
|
|
"id": hashlib.sha256(f"{handle}{token}{time.time()}".encode()).hexdigest()[:8],
|
|
}
|
|
|
|
KOL_DATABASE[key]["calls"].append(call)
|
|
m = KOL_DATABASE[key]["metrics"]
|
|
m["total_calls"] += 1
|
|
m[f"{call_type}_calls"] = m.get(f"{call_type}_calls", 0) + 1
|
|
m["tokens_mentioned"].add(token)
|
|
|
|
return {"status": "tracked", "call": call}
|
|
|
|
|
|
async def get_kol_profile(handle: str, **kw) -> dict:
|
|
"""Get a KOL's performance profile - call history, success rate, risk score."""
|
|
key = _kol_key(handle)
|
|
data = KOL_DATABASE.get(key, {"calls": [], "metrics": {}})
|
|
m = data["metrics"]
|
|
|
|
# Calculate risk score
|
|
total = m.get("total_calls", 0)
|
|
shills = m.get("shills", 0)
|
|
warnings = m.get("warnings", 0)
|
|
|
|
if total > 0:
|
|
shill_ratio = shills / total
|
|
warnings / total
|
|
trust_score = max(0, 100 - shill_ratio * 60 - (1 - m.get("win_rate", 0)) * 40)
|
|
else:
|
|
trust_score = 50
|
|
|
|
return {
|
|
"handle": handle,
|
|
"metrics": {
|
|
**{k: v for k, v in m.items() if k != "tokens_mentioned"},
|
|
"tokens_mentioned": len(m.get("tokens_mentioned", set())),
|
|
},
|
|
"trust_score": round(trust_score, 1),
|
|
"risk_level": "HIGH" if trust_score < 30 else "MEDIUM" if trust_score < 60 else "LOW",
|
|
"recent_calls": data["calls"][-10:],
|
|
"source": "kol_tracker",
|
|
}
|
|
|
|
|
|
async def get_kol_leaderboard(limit: int = 20, **kw) -> dict:
|
|
"""Leaderboard of top KOLs by trust score and call accuracy."""
|
|
kols = []
|
|
for key, _data in KOL_DATABASE.items():
|
|
handle = key.replace("kol:", "")
|
|
profile = await get_kol_profile(handle)
|
|
kols.append(
|
|
{
|
|
"handle": handle,
|
|
"trust_score": profile["trust_score"],
|
|
"risk_level": profile["risk_level"],
|
|
"total_calls": profile["metrics"]["total_calls"],
|
|
}
|
|
)
|
|
|
|
kols.sort(key=lambda k: -k["trust_score"])
|
|
|
|
return {
|
|
"leaderboard": kols[:limit],
|
|
"total_tracked": len(kols),
|
|
"source": "kol_leaderboard",
|
|
}
|
|
|
|
|
|
# ═══════════════════════════════════════════════════════════════════════
|
|
# SHILL CAMPAIGN DETECTION
|
|
# ═══════════════════════════════════════════════════════════════════════
|
|
|
|
SHILL_PATTERNS = {
|
|
"coordinated_posts": {
|
|
"description": "Multiple KOLs posting same token within short window",
|
|
"severity": "HIGH",
|
|
"indicators": ["same_token", "time_window_lt_1h", "similar_wording"],
|
|
},
|
|
"paid_promotion": {
|
|
"description": "Disclosure language suggesting paid content",
|
|
"severity": "MEDIUM",
|
|
"indicators": ["sponsored", "ad", "partner", "#ad", "paid partnership"],
|
|
},
|
|
"pump_and_dump": {
|
|
"description": "Buy call followed by rapid sell within hours",
|
|
"severity": "CRITICAL",
|
|
"indicators": ["buy_then_sell", "price_spike_then_crash", "short_hold_time"],
|
|
},
|
|
"bot_engagement": {
|
|
"description": "Abnormal engagement patterns suggesting bot farms",
|
|
"severity": "HIGH",
|
|
"indicators": ["like_spike", "generic_comments", "low_follower_quality"],
|
|
},
|
|
"affiliate_farming": {
|
|
"description": "Repeated promotion of same platform for referral rewards",
|
|
"severity": "LOW",
|
|
"indicators": ["referral_link", "repeated_platform", "affiliate_pattern"],
|
|
},
|
|
}
|
|
|
|
DETECTED_CAMPAIGNS: list[dict] = []
|
|
|
|
|
|
async def detect_shill_campaigns(posts: list[dict] | None = None, **kw) -> dict:
|
|
"""Scan recent posts for coordinated shill campaigns.
|
|
|
|
If posts not provided, checks against accumulated KOL call data.
|
|
"""
|
|
campaigns = []
|
|
|
|
# Check for coordinated posting (same token, tight window)
|
|
token_windows = defaultdict(list)
|
|
for _key, data in KOL_DATABASE.items():
|
|
for call in data.get("calls", []):
|
|
if call["type"] in ("shill", "buy"):
|
|
token_windows[call["token"]].append(call)
|
|
|
|
for token, calls in token_windows.items():
|
|
if len(calls) >= 3:
|
|
# Check time clustering
|
|
times = sorted(c.get("timestamp", "") for c in calls)
|
|
if len(times) >= 3:
|
|
try:
|
|
t0 = datetime.fromisoformat(times[0].replace("Z", "+00:00"))
|
|
t_last = datetime.fromisoformat(times[-1].replace("Z", "+00:00"))
|
|
window_hours = (t_last - t0).total_seconds() / 3600
|
|
|
|
if window_hours < 2:
|
|
kols_involved = list({c["handle"] for c in calls})
|
|
campaigns.append(
|
|
{
|
|
"type": "coordinated_shill",
|
|
"token": token,
|
|
"severity": "CRITICAL" if len(kols_involved) >= 5 else "HIGH",
|
|
"kols_involved": kols_involved,
|
|
"time_window_hours": round(window_hours, 1),
|
|
"call_count": len(calls),
|
|
"detected_at": datetime.now(UTC).isoformat(),
|
|
}
|
|
)
|
|
except Exception:
|
|
pass
|
|
|
|
# Store detected campaigns
|
|
DETECTED_CAMPAIGNS.extend(campaigns)
|
|
DETECTED_CAMPAIGNS[:] = DETECTED_CAMPAIGNS[-100:] # Keep last 100
|
|
|
|
return {
|
|
"active_campaigns": campaigns,
|
|
"total_detected": len(campaigns),
|
|
"patterns_available": list(SHILL_PATTERNS.keys()),
|
|
"source": "shill_detector",
|
|
}
|
|
|
|
|
|
async def get_shill_alerts(**kw) -> dict:
|
|
"""Get recent shill campaign alerts."""
|
|
return {
|
|
"alerts": DETECTED_CAMPAIGNS[-20:],
|
|
"total": len(DETECTED_CAMPAIGNS),
|
|
"high_severity": sum(1 for c in DETECTED_CAMPAIGNS if c.get("severity") == "CRITICAL"),
|
|
"source": "shill_alerts",
|
|
}
|
|
|
|
|
|
# ═══════════════════════════════════════════════════════════════════════
|
|
# SCAM CHANNEL MONITOR (Telegram/Discord)
|
|
# ═══════════════════════════════════════════════════════════════════════
|
|
|
|
SCAM_INDICATORS = [
|
|
"100x",
|
|
"1000x",
|
|
"guaranteed",
|
|
"no risk",
|
|
"send sol",
|
|
"send eth",
|
|
"airdrop now",
|
|
"claim now",
|
|
"only 100 spots",
|
|
"presale live",
|
|
"whitelist open",
|
|
"private sale",
|
|
"insider",
|
|
"team doxxed",
|
|
"liquidity locked",
|
|
"renounced",
|
|
"no tax",
|
|
"moon",
|
|
"gem",
|
|
"next 1000x",
|
|
"early entry",
|
|
"before listing",
|
|
"launching in",
|
|
]
|
|
|
|
|
|
async def scan_scam_channels(**kw) -> dict:
|
|
"""Scan known scam channels for active campaigns.
|
|
|
|
In production, this would connect to Telegram API.
|
|
For now, provides the detection framework.
|
|
"""
|
|
return {
|
|
"status": "monitoring",
|
|
"indicators_tracked": SCAM_INDICATORS[:10],
|
|
"channels_monitored": ["telegram_scam_patterns"],
|
|
"note": "Telegram scanning infrastructure being provisioned. Detection patterns active.",
|
|
"source": "scam_monitor",
|
|
}
|
|
|
|
|
|
# ═══════════════════════════════════════════════════════════════════════
|
|
# DAILY INTELLIGENCE REPORT - Groq-powered
|
|
# ═══════════════════════════════════════════════════════════════════════
|
|
|
|
|
|
async def generate_daily_intel(**kw) -> dict:
|
|
"""Generate a comprehensive Daily Intelligence Report using Groq AI.
|
|
|
|
Combines: market data, fear/greed, news headlines, CT sentiment,
|
|
prediction markets, on-chain activity into a single briefing.
|
|
"""
|
|
# Gather all data sources
|
|
try:
|
|
from app.databus.news_provider import get_market_brief
|
|
|
|
brief = await get_market_brief()
|
|
except Exception:
|
|
brief = {}
|
|
|
|
try:
|
|
from app.databus.news_intel import aggregate_all_news
|
|
|
|
news = await aggregate_all_news(limit=15)
|
|
except Exception:
|
|
news = {"articles": []}
|
|
|
|
try:
|
|
from app.databus.x_intel import fetch_ct_rundown
|
|
|
|
ct = await fetch_ct_rundown(limit=10)
|
|
except Exception:
|
|
ct = {"rundown": []}
|
|
|
|
# Build context for Groq
|
|
market_context = brief.get("brief", "Market data unavailable")
|
|
news_headlines = [a.get("title", "") for a in news.get("articles", [])[:10]]
|
|
ct_stories = [s.get("text", "")[:100] for s in ct.get("rundown", [])[:5]]
|
|
fear = brief.get("fear_greed", {}).get("value", 50)
|
|
fear_label = brief.get("fear_greed", {}).get("classification", "Neutral")
|
|
|
|
context = f"""MARKET DATA:
|
|
{market_context}
|
|
|
|
FEAR & GREED INDEX: {fear}/100 - {fear_label}
|
|
|
|
TOP NEWS HEADLINES:
|
|
{chr(10).join(f"• {h}" for h in news_headlines[:8])}
|
|
|
|
CRYPTO TWITTER PULSE:
|
|
{chr(10).join(f"• {s}" for s in ct_stories[:5])}
|
|
|
|
Generate a professional Daily Intelligence Report for crypto investors."""
|
|
|
|
report = ""
|
|
if GROQ_KEY:
|
|
try:
|
|
async with httpx.AsyncClient(timeout=45) as c:
|
|
r = await c.post(
|
|
"https://api.groq.com/openai/v1/chat/completions",
|
|
headers={
|
|
"Authorization": f"Bearer {GROQ_KEY}",
|
|
"Content-Type": "application/json",
|
|
},
|
|
json={
|
|
"model": "llama-3.3-70b-versatile",
|
|
"messages": [
|
|
{
|
|
"role": "system",
|
|
"content": """You are a senior crypto intelligence analyst at RugCharts.
|
|
Write a Daily Intelligence Report with these sections:
|
|
1. MARKET SNAPSHOT - 2-3 sentences on today's market
|
|
2. TOP 3 STORIES - the most important developments
|
|
3. SENTIMENT ANALYSIS - what the market is feeling
|
|
4. RISK RADAR - things to watch out for (scams, hacks, regulatory)
|
|
5. BOTTOM LINE - actionable takeaway for investors
|
|
|
|
Be direct, data-driven, no fluff. Use emojis sparingly. Format cleanly.""",
|
|
},
|
|
{"role": "user", "content": context},
|
|
],
|
|
"temperature": 0.4,
|
|
"max_tokens": 800,
|
|
},
|
|
)
|
|
if r.status_code == 200:
|
|
report = r.json()["choices"][0]["message"]["content"]
|
|
except Exception as e:
|
|
report = f"AI report generation unavailable: {str(e)[:100]}"
|
|
|
|
if not report:
|
|
report = f"""DAILY INTELLIGENCE REPORT
|
|
|
|
MARKET SNAPSHOT: {market_context}
|
|
|
|
Fear & Greed: {fear}/100 ({fear_label})
|
|
|
|
TOP HEADLINES:
|
|
{chr(10).join(f"{i + 1}. {h}" for i, h in enumerate(news_headlines[:5]))}
|
|
|
|
BOTTOM LINE: Data-driven. No AI available for narrative synthesis."""
|
|
|
|
return {
|
|
"report": report,
|
|
"generated_at": datetime.now(UTC).isoformat(),
|
|
"data_sources": [
|
|
"CoinGecko (prices)",
|
|
"Alternative.me (Fear & Greed)",
|
|
"Polymarket (predictions)",
|
|
"200+ RSS (news)",
|
|
"CT Rundown (Crypto Twitter)",
|
|
"Arkham (entity intel)",
|
|
],
|
|
"ai_model": "Groq Llama 3.3 70B (free tier)" if GROQ_KEY else "Rule-based (no Groq key)",
|
|
"source": "daily_intel_report",
|
|
}
|
|
|
|
|
|
# ═══════════════════════════════════════════════════════════════════════
|
|
# SOCIAL METRICS AGGREGATOR
|
|
# ═══════════════════════════════════════════════════════════════════════
|
|
|
|
|
|
async def get_social_metrics(**kw) -> dict:
|
|
"""Aggregate social metrics across platforms.
|
|
|
|
Tracks: trending topics, sentiment shifts, KOL activity, meme velocity.
|
|
"""
|
|
# Gather data
|
|
try:
|
|
from app.databus.news_intel import aggregate_all_news
|
|
|
|
news = await aggregate_all_news(limit=50)
|
|
except Exception:
|
|
news = {"articles": [], "stats": {}}
|
|
|
|
# Trending topics from categories
|
|
cat_counter = Counter()
|
|
for a in news.get("articles", []):
|
|
for cat in a.get("categories", []):
|
|
cat_counter[cat] += 1
|
|
|
|
# Sentiment aggregate
|
|
sentiments = Counter()
|
|
for a in news.get("articles", []):
|
|
s = a.get("sentiment", {}).get("sentiment", "neutral")
|
|
sentiments[s] += 1
|
|
|
|
return {
|
|
"trending_topics": dict(cat_counter.most_common(15)),
|
|
"market_sentiment": {
|
|
"aggregate": dict(sentiments),
|
|
"dominant": sentiments.most_common(1)[0][0] if sentiments else "neutral",
|
|
},
|
|
"kol_activity": {
|
|
"tracked": len(KOL_DATABASE),
|
|
"active_campaigns": len(DETECTED_CAMPAIGNS),
|
|
"high_risk_signals": sum(1 for c in DETECTED_CAMPAIGNS if c.get("severity") == "CRITICAL"),
|
|
},
|
|
"source_breakdown": news.get("stats", {}).get("sources", {}),
|
|
"source": "social_metrics",
|
|
}
|