ForexBot2/market_outlook.py

"""
ForexBot2 — AI market outlook (advisory hourly assessment)
===========================================================
Builds a broad XAU/USD market brief and asks DeepSeek whether a good setup
appears to be forming. The result is written to the signal-history database
and may be displayed by consumers, but it is ADVISORY-ONLY: it never changes
signal scoring, gates, grades, or trade setup generation.

The outlook runs outside the replayable signal path. Individual candle/news
failures produce a partial brief; an unavailable LLM, malformed reply, or
locked database never reaches a scan caller as an exception.

The static prompt is intentional: DeepSeek prices byte-identical prompt
prefixes at its cache-hit rate, so timestamps and all other changing evidence
live only in the JSON user payload.
"""

import datetime as _dt
import logging
import math
import os
import sqlite3
import threading
import time
from dataclasses import dataclass
from typing import Any, Dict, List, Optional

from agent_panel import _normalize_candles
from app_config import (get_app_config, market_outlook_enabled,
                        signal_log_path)
from config import PlatformConfig, Timeframe, XAUUSD
from engine import TechnicalEngine
from llm_client import get_llm_client
from providers import base as _provider_base

logger = logging.getLogger(__name__)

DEFAULT_MAX_PER_DAY = 12
DEFAULT_CANDLE_BARS = 20
_OUTLOOK_TFS = (Timeframe.M15, Timeframe.H1, Timeframe.H4)
_VALID_BIASES = ("bullish", "bearish", "neutral")
_VALID_SETUPS = ("buy", "sell", "none")


# STATIC prompt: repeated prompt prefixes are much cheaper with DeepSeek's
# server-side cache. Variable market evidence belongs exclusively in payload.
SYSTEM_PROMPT = """\
You are writing an advisory market outlook for gold (XAU/USD). You receive a
JSON market brief covering recent candle shape, indicator states, price
levels, news, and recent technical signals. Assess what may be forming soon;
you are not a signal generator and must not provide an entry price, stop, or
target.

Gold doctrine: hawkish Fed / rate hikes / rising real yields / strong
dollar are gold-bearish; easing / rate cuts / safe-haven flows /
geopolitical stress / weak dollar are gold-bullish.

Indicator "value" units: rsi 0-100 (above 70 overbought, below 30
oversold); adx 0-100 (above 25 = strong trend); macd = histogram in
dollars (momentum); roc = percent; bollinger = position 0-1 (0 = lower
band, 1 = upper band); keltner = dollar distance from the mid-line;
ema_trend = 0-1 alignment score; divergence and candlestick = pattern
counts. "candles" is per timeframe: {"ref_close", "atr", "bars"}; bars
are oldest-first [open, high, low, close] in ATR units relative to the
latest close. Read their shape, never quote them as prices.

Hard rules: use ONLY the JSON provided. Do not invent numbers, events, or
price levels. Your training data about gold, markets, and current events is
stale and OFF-LIMITS: never use outside knowledge; if a fact is not in the
JSON, treat it as unknown. If evidence is thin or missing, answer "neutral"
with confidence below 30. Use plain everyday English for someone unfamiliar
with markets: short simple sentences, no acronyms or jargon. Keep "watch"
and "note" to at most 25 words each.

Reply with ONLY JSON:
{"bias": "bullish"|"bearish"|"neutral",
 "setup_forming": "buy"|"sell"|"none",
 "confidence": 0-100,
 "watch": "<what to watch for, max 25 words>",
 "note": "<plain-English summary, max 25 words>"}
"""


@dataclass
class OutlookResult:
    bias: str
    setup_forming: str
    confidence: float
    watch: str
    note: str
    created_ts: float


def _finite(x: Any) -> Optional[float]:
    """float(x) or None for non-numeric / non-finite JSON values."""
    try:
        value = float(x)
    except (TypeError, ValueError):
        return None
    return value if math.isfinite(value) else None


def _round_finite(x: Any, digits: int) -> Optional[float]:
    value = _finite(x)
    return round(value, digits) if value is not None else None


def _json_safe(value: Any) -> Any:
    """Replace any accidental NaN/inf nested in provider data with null."""
    if isinstance(value, dict):
        return {str(key): _json_safe(item) for key, item in value.items()}
    if isinstance(value, (list, tuple)):
        return [_json_safe(item) for item in value]
    if isinstance(value, bool) or value is None or isinstance(value, str):
        return value
    if isinstance(value, (int, float)):
        return _finite(value)
    return value


def _clamp_confidence(raw: Any) -> Optional[float]:
    value = _finite(raw)
    return max(0.0, min(100.0, value)) if value is not None else None


def _word_limit(text: Any, words: int = 25) -> str:
    """Bound a response field by words as well as a practical char limit."""
    clean = str(text or "").strip()
    return " ".join(clean.split()[:words])[:200]


def _validate_outlook(reply: Any) -> Optional[OutlookResult]:
    """Validate only model replies that fully match the requested contract."""
    if not isinstance(reply, dict):
        return None
    bias = reply.get("bias")
    setup_forming = reply.get("setup_forming")
    confidence = _clamp_confidence(reply.get("confidence"))
    if (bias not in _VALID_BIASES or setup_forming not in _VALID_SETUPS
            or confidence is None):
        return None
    return OutlookResult(
        bias=bias,
        setup_forming=setup_forming,
        confidence=confidence,
        watch=_word_limit(reply.get("watch")),
        note=_word_limit(reply.get("note")),
        created_ts=time.time(),
    )


# ── Data collection ──────────────────────────────────────────────────

_dp: Any = None  # Patchable singleton, mirroring agent_panel._dp.


def _outlook_provider() -> Any:
    """Lazy provider singleton so its closed-bar cache stays warm hourly."""
    global _dp
    if _dp is None:
        from providers import make_data_provider
        _dp = make_data_provider(PlatformConfig())
    return _dp


def _indicator_payload(analysis: Any) -> Dict[str, Dict[str, Any]]:
    """Visible scored indicators with finite, compact values only."""
    out: Dict[str, Dict[str, Any]] = {}
    for name, indicator in (getattr(analysis, "indicators", None) or {}).items():
        if name.startswith("_") or getattr(indicator, "weight", 0) == 0:
            continue
        entry: Dict[str, Any] = {
            "signal": getattr(getattr(indicator, "signal", None), "name", ""),
            "confidence": _round_finite(
                getattr(indicator, "confidence", None), 1),
            "value": _round_finite(getattr(indicator, "value", None), 2),
        }
        out[name] = entry
    return out


def _analysis_payload(analyses: Dict[str, Any]) -> Dict[str, Any]:
    """Pure formatter for the technical portion of the market brief."""
    indicators: Dict[str, Any] = {}
    market_regime: Dict[str, Optional[str]] = {}
    volatility_regime: Dict[str, Optional[str]] = {}
    key_levels: Dict[str, Dict[str, Optional[float]]] = {}
    for tf in _OUTLOOK_TFS:
        name = tf.value
        analysis = analyses.get(name)
        indicators[name] = _indicator_payload(analysis)
        market_regime[name] = getattr(analysis, "market_regime", None)
        volatility_regime[name] = getattr(analysis, "volatility_regime", None)
        key_levels[name] = {
            level: _round_finite(value, 2)
            for level, value in (getattr(analysis, "key_levels", None) or {}).items()
        }
    return {
        "indicators": indicators,
        "market_regime": market_regime,
        "volatility_regime": volatility_regime,
        "key_levels": key_levels,
    }


def _empty_news_payload() -> Dict[str, Any]:
    return {
        "headlines": None,
        "events": None,
        "gold_sentiment": None,
        "remaining_high_impact_events": None,
    }


def _news_payload() -> Dict[str, Any]:
    """Collect current news without allowing any news failure to block us."""
    try:
        from news_engine import NewsEngine

        news = NewsEngine(PlatformConfig().news)
        context = news.get_fundamental_context()
        headlines = [str(getattr(h, "headline", ""))
                     for h in (context.news_headlines or [])[:10]
                     if getattr(h, "headline", None)]
        events = [
            {
                "event": getattr(event, "event", None),
                "currency": getattr(event, "currency", None),
                "actual": getattr(event, "actual", None),
                "forecast": getattr(event, "forecast", None),
                "released": not event.is_upcoming,
            }
            for event in (context.events_today or [])
            if event.is_high_impact
        ][:8]
        gold_sentiment, _ = news.get_pair_sentiment(XAUUSD, context)
        remaining = sum(
            1 for event in news.get_week_events()
            if event.is_high_impact and event.is_upcoming
        )
        return {
            "headlines": headlines,
            "events": events,
            "gold_sentiment": _round_finite(gold_sentiment, 2),
            "remaining_high_impact_events": remaining,
        }
    except Exception as exc:
        logger.debug("market outlook: news context unavailable: %s", exc)
        return _empty_news_payload()


def _recent_signals() -> List[Dict[str, Any]]:
    """Read the latest signal history through SQLite's immutable URI."""
    try:
        path = os.path.abspath(signal_log_path())
        # mode=ro (not immutable=1): immutable ignores the WAL, so the
        # newest rows written by the live loggers were invisible here.
        uri = f"file:{path}?mode=ro"
        con = sqlite3.connect(uri, uri=True)
        try:
            rows = con.execute(
                "SELECT logged_at, timeframe, signal, quality, panel_verdict "
                "FROM signals ORDER BY id DESC LIMIT 10").fetchall()
        finally:
            con.close()
        return [
            {
                "logged_at": row[0],
                "timeframe": row[1],
                "signal": row[2],
                "quality": row[3],
                "panel_verdict": row[4],
            }
            for row in reversed(rows)
        ]
    except Exception as exc:
        logger.debug("market outlook: signal history unavailable: %s", exc)
        return []


def _build_payload(
    analyses: Dict[str, Any],
    candles: Dict[str, Any],
    news: Dict[str, Any],
    recent_signals: List[Dict[str, Any]],
    as_of: _dt.datetime,
) -> Dict[str, Any]:
    """Pure market-brief formatter. Every numeric field is finite or null."""
    technical = _analysis_payload(analyses)
    return _json_safe({
        "as_of": as_of.astimezone(_dt.timezone.utc).isoformat(),
        "candles": candles,
        **technical,
        "news": news,
        "recent_signals": recent_signals,
    })


def _collect_payload(settings: Dict[str, Any]) -> Dict[str, Any]:
    """Fetch closed bars and turn them into a structured market brief."""
    analyses: Dict[str, Any] = {}
    candles: Dict[str, Any] = {tf.value: None for tf in _OUTLOOK_TFS}
    bars = int(settings.get("candles_bars", DEFAULT_CANDLE_BARS))
    provider = _outlook_provider()
    engine = TechnicalEngine(PlatformConfig().technical)

    for tf in _OUTLOOK_TFS:
        try:
            df = provider.fetch_ohlcv(XAUUSD, tf)
            analysis = engine.analyze(df, XAUUSD, tf.value)
            analyses[tf.value] = analysis
            atr = _finite(getattr(
                (getattr(analysis, "indicators", None) or {}).get("atr"),
                "value", None))
            if atr is not None and atr > 0 and df is not None and len(df) >= 2:
                candles[tf.value] = _normalize_candles(df, atr, bars)
        except Exception as exc:
            logger.debug("market outlook: %s data unavailable: %s", tf.value, exc)

    return _build_payload(
        analyses=analyses,
        candles=candles,
        news=_news_payload(),
        recent_signals=_recent_signals(),
        as_of=_dt.datetime.now(_dt.timezone.utc),
    )


# ── Orchestration, hourly dedup, and request budget ──────────────────

_state_lock = threading.Lock()
_last_run_hour: Optional[int] = None   # UTC hour bucket of the last attempt
_outlook_day: Optional[_dt.date] = None
_outlook_count = 0
_warned_budget = False


def _skip(reason: str) -> None:
    """Heartbeat for every silent early return — a dark outlook feature
    (zero rows for 15 days, 2026-08/09) must be visible in the log."""
    logger.info("market outlook: skipped (%s)", reason)


def reset_outlook_state() -> None:
    """Drop hourly and daily state (tests / deployment config reloads)."""
    global _last_run_hour, _outlook_day, _outlook_count
    global _warned_budget
    with _state_lock:
        _last_run_hour = None
        _outlook_day = None
        _outlook_count = 0
        _warned_budget = False


def _begin_attempt(cap: int, force: bool) -> bool:
    """Atomically apply hourly dedup, then reserve a daily attempt.

    Hourly dedup is by UTC hour BUCKET, not ``now - last < 3600``: the
    H1 loop calls this at boundary+10 s+scan time, so consecutive hours
    were routinely 3,590 s apart and every other hour was dropped."""
    global _last_run_hour, _outlook_day, _outlook_count
    global _warned_budget
    now = time.time()
    hour_bucket = int(now // 3600)
    today = _dt.datetime.now(_dt.timezone.utc).date()
    with _state_lock:
        if not force and _last_run_hour == hour_bucket:
            _skip(f"hour bucket {hour_bucket} already attempted")
            return False
        if _outlook_day != today:
            _outlook_day = today
            _outlook_count = 0
            _warned_budget = False
        if _outlook_count >= cap:
            if not _warned_budget:
                _warned_budget = True
                logger.warning(
                    "market outlook: daily budget (%d) exhausted — no more "
                    "outlooks until UTC midnight", cap)
            else:
                _skip("daily budget exhausted")
            return False
        _outlook_count += 1
        _last_run_hour = hour_bucket
        return True


def run_outlook(settings: Dict[str, Any],
                surface: str = "live") -> Optional[OutlookResult]:
    """Build, ask, validate, and persist one advisory outlook."""
    try:
        payload = _collect_payload(settings)
        reply = get_llm_client().chat_json(SYSTEM_PROMPT, payload)
        result = _validate_outlook(reply)
        if result is None:
            logger.warning(
                "market outlook: no outlook produced (%s)",
                "LLM returned nothing — cap/timeout/disabled" if reply is None
                else "reply failed validation")
            return None
        try:
            from signal_log import log_outlook
            log_outlook(result, surface=surface, payload=payload)
        except Exception:
            logger.debug("market outlook: persistence unavailable", exc_info=True)
        return result
    except Exception:
        logger.warning("market outlook: run failed", exc_info=True)
        return None


def maybe_run_outlook(surface: str, force: bool = False) -> Optional[OutlookResult]:
    """Best-effort public entry point. It NEVER raises to a scan caller.

    ``force`` is for explicit CLI use: it bypasses enabled, surface, and
    hourly gates, but not the independent outlook budget or shared LLM cap.
    """
    try:
        settings = get_app_config().market_outlook_settings
        if not force:
            if not market_outlook_enabled():
                _skip("disabled")
                return None
            if surface == "telegram" and not settings.get("telegram", False):
                _skip("telegram surface off")
                return None
        if _provider_base._is_forex_weekend():
            _skip("weekend")
            return None
        cap = int(settings.get("max_per_day", DEFAULT_MAX_PER_DAY))
        if cap < 1:
            _skip("max_per_day < 1")
            return None
        if not _begin_attempt(cap, force):
            return None
        return run_outlook(settings, surface=surface)
    except Exception:
        logger.warning("market outlook: unavailable", exc_info=True)
        return None