trumpsignal-backend/app/services/analysis.py

import json
import logging
from typing import Optional

from openai import AsyncOpenAI
from app.config import settings

logger = logging.getLogger(__name__)

_client: Optional[AsyncOpenAI] = None

SYSTEM_PROMPT = """You are an expert macro trader analyzing Trump's Truth Social posts for real-time crypto trading signals.

CORE ASSUMPTION: Treat every post as BREAKING NEWS. Do not assume anything is already priced in — you have no knowledge of what happened before or after this post. Your job is to evaluate the post content only.

=== BULLISH TRANSMISSION CHAINS (BTC/ETH go UP) ===
• Ceasefire / peace deal / de-escalation / conflict ending
  → war-risk premium unwinds → oil stabilizes → USD softens → risk-on → BTC/ETH rally
• Pro-crypto executive action / legislation / reserve
  → regulatory tailwind + direct demand → BTC up immediately
• Dollar weakness (deficit spending, tariff concessions, Fed rate cut signals)
  → hard asset bid → BTC as digital gold
• Trade deal / tariff reduction announcement
  → global growth outlook improves → risk appetite rises → BTC/ETH up
• Strait of Hormuz open / oil supply stable
  → energy prices moderate → inflation fears drop → risk-on

=== BEARISH TRANSMISSION CHAINS (BTC/ETH go DOWN) ===
• War escalation / military strikes / ceasefire violation
  → risk-off panic → crypto liquidations → sharp BTC/ETH drop
• Strait of Hormuz threatened / blocked / mined
  → oil price spike → inflation surge → Fed tightening fears → risk-off
• SEC/DOJ crypto enforcement / new crypto regulation
  → direct selling pressure → BTC/ETH down
• Tariff escalation / new sanctions / trade war
  → growth fears + USD safe-haven bid → crypto outflows
• New military front / ally breakdown / nuclear threat
  → extreme risk-off → everything sells

=== WHAT IS NOT RELEVANT ===
• Retweets with only a URL and no added comment (RT: https://...)
• Media/political attacks with no policy content
• Personal endorsements, rallies, awards, domestic court cases
• Pure domestic politics (abortion, immigration) with no macro angle
• UFO files, sports, entertainment, holidays

=== SIGNAL TAXONOMY (CRITICAL — do not conflate) ===
Each signal is a distinct trading action. Choose exactly one.

• "buy"  — OPEN A NEW LONG. Use when the post is a FRESH bullish catalyst that
           is likely to push price UP in the next 5–60 minutes. Example:
           "Confirmed ceasefire with Iran", "Crypto reserve executive order signed."
           → Expected move: price rises. Directional accuracy = price > entry.

• "sell" — CLOSE AN EXISTING LONG / DE-RISK. Use when the post WEAKENS a prior
           bullish thesis but is NOT strong enough to justify an active short.
           Think: "take profit / step aside." Examples:
           "Ceasefire talks delayed", "Hinting at new tariffs (vague)",
           "Crypto-friendly nominee withdrawn." Ambiguous bearish.
           → Use ONLY if you would exit longs but not open shorts.
           → Directional accuracy = price < entry (same as short, but lower conviction).

• "short"— OPEN A NEW SHORT. Use only for a FRESH bearish catalyst strong enough
           that you would actively bet on price falling. Examples:
           "Military strike on Iran launched", "Strait of Hormuz mined",
           "SEC lawsuit against major exchange announced."
           → Expected move: price drops hard. Reserve for high-conviction bearish.

• "hold" — NO TRADE. Post is irrelevant, or macro-relevant but ambiguous in
           direction, or confidence too low to act. DEFAULT when in doubt.

Decision tree:
  1. Is there a concrete macro/crypto event? NO → hold.
  2. Is the direction clear? NO → hold.
  3. BULLISH: confidence ≥ 60 → buy. Else → hold.
  4. BEARISH: strong/explicit (war, ban, sanctions, enforcement) → short.
              weak/vague/partial walkback of bullish → sell.
              otherwise → hold.

NEVER use "sell" for a strong bearish event — that is "short".
NEVER use "short" for a vague/ambiguous negative — that is "sell" or "hold".

=== CONFIDENCE CALIBRATION ===
80-100: Explicit crypto/monetary policy action; confirmed ceasefire with named parties; Strait of Hormuz status confirmed; named trade deal signed
60-79: Clear new geopolitical event with specific details (named countries, named actions); direct risk-on/off chain
40-59: Probable macro relevance but vague details or highly indirect effect
20-39: Possible relevance, highly uncertain
0-19: Mark as not relevant instead

=== SIGNAL CALIBRATION (critical — read before deciding) ===
DEFAULT is HOLD. Only 5–10% of posts should receive buy or short.
The overwhelming majority of Trump's posts are domestic politics, rhetoric, personal attacks, or vague boasts — these are HOLD.

Use "buy" only when ALL of the following are true:
  1. The event is CONCRETE (named countries, named action, specific policy)
  2. The macro transmission chain to BTC/ETH is DIRECT and SHORT (< 2 steps)
  3. Your confidence is ≥ 75

Use "short" only when ALL of the following are true:
  1. A hard bearish event is CONFIRMED (not speculated): verified military strike, enacted tariff, filed lawsuit
  2. The transmission chain to BTC/ETH down is DIRECT
  3. Your confidence is ≥ 80

Use "sell" only for mild walkback of a prior bullish event — NOT for strong bearish news.

When in doubt between buy and hold → choose HOLD.
When in doubt between short and sell → choose SELL or HOLD, not short.

Return ONLY valid JSON. No markdown.

Return ONLY valid JSON. No markdown."""

USER_PROMPT_TEMPLATE = """Analyze this Trump Truth Social post for BTC/ETH trading signals.
Treat it as breaking news — evaluate only what is written.

POST TEXT:
{text}

Respond with JSON:
{{
  "relevant": <true if post contains ANY concrete macro/geopolitical/crypto information>,
  "asset": "BTC" | "ETH" | "BOTH" | null,
  "sentiment": "bullish" | "bearish" | "neutral",
  "signal": "buy" | "sell" | "short" | "hold",
  "confidence": <0-100>,
  "reasoning": "<What specific event is described → macro transmission chain → expected market direction → WHY this signal and NOT the adjacent one (e.g. 'short not sell because strike is confirmed', 'sell not short because only a walkback of prior bullish headline')>"
}}

If post is only a URL, only a retweet link, or purely personal/domestic with zero macro angle: set relevant=false, signal=hold, confidence=0."""

ANALYSIS_VERSION = "v4-selective"

_FALLBACK = {
    "relevant": False,
    "asset": None,
    "sentiment": "neutral",
    "signal": "hold",
    "confidence": 0,
    "reasoning": "",
    "prefilter_reason": None,
    "analysis_version": ANALYSIS_VERSION,
}


def _fallback(prefilter: Optional[str] = None, reasoning: str = "") -> dict:
    out = dict(_FALLBACK)
    out["prefilter_reason"] = prefilter
    out["reasoning"] = reasoning
    return out


def _get_client() -> AsyncOpenAI:
    global _client
    if _client is None:
        _client = AsyncOpenAI(
            api_key=settings.ai_api_key,
            base_url=settings.ai_base_url,
        )
    return _client


async def analyze_post(text: str) -> dict:
    # Fast pre-filter: pure RT/URL with no content
    stripped = text.strip()
    if stripped.startswith("RT: https://") and len(stripped) < 60:
        return _fallback("rt_only", "Pre-filtered: retweet with no added commentary.")
    if stripped.startswith("https://") and " " not in stripped:
        return _fallback("url_only", "Pre-filtered: bare URL with no text content.")
    if not stripped:
        return _fallback("empty", "Pre-filtered: empty post body.")

    try:
        client = _get_client()
        response = await client.chat.completions.create(
            model=settings.ai_model,
            max_tokens=450,
            temperature=0.1,
            messages=[
                {"role": "system", "content": SYSTEM_PROMPT},
                {"role": "user", "content": USER_PROMPT_TEMPLATE.format(text=text[:2000])},
            ],
        )
        raw = response.choices[0].message.content.strip()

        if raw.startswith("```"):
            lines = raw.split("\n")
            raw = "\n".join(lines[1:-1] if lines[-1].strip() == "```" else lines[1:])

        result = json.loads(raw)

        sentiment = result.get("sentiment", "neutral")
        if sentiment not in ("bullish", "bearish", "neutral"):
            sentiment = "neutral"

        signal = result.get("signal", "hold")
        if signal not in ("buy", "sell", "short", "hold"):
            signal = "hold"

        confidence = int(result.get("confidence", 0))
        confidence = max(0, min(100, confidence))

        relevant = bool(result.get("relevant", False))

        asset = result.get("asset")
        if asset == "BOTH":
            asset = "BTC"
        if asset not in ("BTC", "ETH", None):
            asset = None

        reasoning = str(result.get("reasoning", ""))[:600]

        return {
            "relevant": relevant,
            "asset": asset,
            "sentiment": sentiment,
            "signal": signal,
            "confidence": confidence,
            "reasoning": reasoning,
            "prefilter_reason": None,
            "analysis_version": ANALYSIS_VERSION,
        }

    except json.JSONDecodeError as exc:
        logger.error("Failed to parse AI JSON: %s", exc)
        return _fallback("parse_error", f"AI returned unparseable JSON: {exc}")
    except Exception as exc:
        logger.error("analyze_post error: %s", exc)
        return _fallback("api_error", f"AI API error: {exc}")