polymarket-bot/bot/data/manifold.py

"""
Manifold Markets client — cross-platform prediction market probability signals.

For each Polymarket question, searches Manifold for a matching binary market
by keyword overlap and returns its probability as a calibration signal.

Used for politics and tech markets where Manifold often has independent
probability estimates that diverge from Polymarket.

Cache TTL: 30 minutes (Manifold markets move slowly vs our 60 s cycle).
Match threshold: >= 0.25 keyword overlap ratio between significant tokens.

Weight choice: MANIFOLD_LOGODDS_WEIGHT = 0.6 in bayesian.py means a 30 pp
divergence (Manifold 0.75 vs Poly 0.45) produces edge_gross ≈ 0.19, which
clears the politics far-horizon regime threshold of 0.12 after costs.
"""
import logging
import re
import time
from typing import Optional

import httpx

MANIFOLD_API = "https://api.manifold.markets/v0"
CACHE_TTL_SEC = 1800  # 30 minutes

log = logging.getLogger(__name__)

_MATCH_THRESHOLD = 0.25

_STOP_WORDS = frozenset([
    "will", "the", "a", "an", "is", "are", "was", "were", "be", "been",
    "by", "in", "on", "at", "to", "for", "of", "and", "or", "not",
    "this", "that", "with", "from", "have", "has", "had", "do", "does",
    "did", "can", "could", "would", "should", "may", "might", "shall",
    "win", "lose", "get", "become", "make", "take", "give", "see",
    "any", "who", "what", "when", "where", "which", "how", "over", "under",
    "than", "more", "most", "least", "its", "their", "they",
    "him", "her", "his", "she", "been", "being", "into", "after",
    "before", "during", "until", "against", "between", "through",
])


def _significant_words(text: str) -> set[str]:
    words = re.findall(r"[a-zA-Z]+", text.lower())
    return {w for w in words if w not in _STOP_WORDS and len(w) >= 3}


def _build_search_query(question: str, max_words: int = 6) -> str:
    words = re.findall(r"[a-zA-Z0-9]+", question)
    sig = [w for w in words if w.lower() not in _STOP_WORDS and len(w) >= 3]
    return " ".join(sig[:max_words])


def _best_match(poly_question: str, results: list[dict]) -> Optional[dict]:
    """Return best-matching open binary Manifold market, or None if below threshold."""
    poly_words = _significant_words(poly_question)
    if not poly_words:
        return None

    best_score = 0.0
    best: Optional[dict] = None

    for result in results:
        if result.get("outcomeType") != "BINARY":
            continue
        prob = result.get("probability")
        if prob is None or not (0.02 < float(prob) < 0.98):
            continue
        title = result.get("question", "")
        m_words = _significant_words(title)
        if not m_words:
            continue
        overlap = len(poly_words & m_words)
        score = overlap / min(len(poly_words), len(m_words))
        if score > best_score:
            best_score = score
            best = result

    if best_score >= _MATCH_THRESHOLD and best is not None:
        return best
    return None


class ManifoldClient:
    """Async Manifold Markets client for cross-platform probability signals."""

    def __init__(self) -> None:
        self._client = httpx.AsyncClient(timeout=15)
        # question → (fetched_at_monotonic, probability_or_None)
        self._cache: dict[str, tuple[float, Optional[float]]] = {}

    async def get_probability(self, question: str) -> Optional[float]:
        """
        Return Manifold probability for a matching market, or None.

        Searches by keyword overlap.  Returns None if no match exceeds
        _MATCH_THRESHOLD or on any API error (caller degrades gracefully).
        """
        now = time.monotonic()
        cached = self._cache.get(question)
        if cached and (now - cached[0]) < CACHE_TTL_SEC:
            return cached[1]

        query = _build_search_query(question)
        if not query:
            self._cache[question] = (now, None)
            return None

        try:
            resp = await self._client.get(
                f"{MANIFOLD_API}/search-markets",
                params={"term": query, "limit": 5, "filter": "open"},
            )
            resp.raise_for_status()
            results = resp.json()
            match = _best_match(question, results)
            prob = float(match["probability"]) if match else None
            self._cache[question] = (now, prob)
            if prob is not None:
                log.info(
                    "Manifold match: %-50s → %.3f | %s",
                    question[:50], prob, match.get("question", "")[:60],
                )
            else:
                log.debug("Manifold no match for: %s (query=%r)", question[:50], query)
            return prob

        except Exception as e:
            log.warning("Manifold API error for %r: %s", question[:40], e)
            self._cache[question] = (now, None)
            return None

    async def close(self) -> None:
        await self._client.aclose()