""" SQLite persistence layer for portfolio positions, custom patterns, and config. """ import sqlite3 import json import os from datetime import datetime from typing import List, Dict, Any, Optional DB_PATH = os.path.join(os.path.dirname(__file__), "..", "data", "geooptions.db") def get_conn() -> sqlite3.Connection: conn = sqlite3.connect(DB_PATH) conn.row_factory = sqlite3.Row return conn def init_db(): os.makedirs(os.path.dirname(DB_PATH), exist_ok=True) conn = get_conn() c = conn.cursor() c.execute("""CREATE TABLE IF NOT EXISTS portfolio ( id TEXT PRIMARY KEY, title TEXT NOT NULL, underlying TEXT NOT NULL, strategy TEXT NOT NULL, asset_class TEXT, entry_date TEXT NOT NULL, expiry_date TEXT, expiry_days INTEGER, legs TEXT NOT NULL, capital_invested REAL NOT NULL, entry_underlying_price REAL, geo_trigger TEXT, rationale TEXT, status TEXT DEFAULT 'open', close_date TEXT, close_value REAL, notes TEXT, ib_fees_entry REAL DEFAULT 0, ib_fees_exit REAL DEFAULT 0, created_at TEXT DEFAULT (datetime('now')) )""") c.execute("""CREATE TABLE IF NOT EXISTS custom_patterns ( id TEXT PRIMARY KEY, name TEXT NOT NULL, description TEXT, triggers TEXT, keywords TEXT, historical_instances TEXT, suggested_trades TEXT, asset_class TEXT, expected_move_pct REAL, probability REAL, horizon_days INTEGER, ai_quality_score INTEGER, ai_evaluation TEXT, source TEXT DEFAULT 'custom', is_active INTEGER DEFAULT 1, created_at TEXT DEFAULT (datetime('now')), updated_at TEXT DEFAULT (datetime('now')) )""") # Migrations: add columns if not present for _sql in [ "ALTER TABLE custom_patterns ADD COLUMN source TEXT DEFAULT 'custom'", "ALTER TABLE custom_patterns ADD COLUMN counter_thesis TEXT", "ALTER TABLE custom_patterns ADD COLUMN invalidation_trigger TEXT", "ALTER TABLE custom_patterns ADD COLUMN invalidation_probability REAL", "ALTER TABLE pattern_score_history ADD COLUMN predicted_probability REAL", "ALTER TABLE knowledge_base ADD COLUMN expires_at TEXT", "ALTER TABLE knowledge_base ADD COLUMN confidence_decay_days INTEGER DEFAULT 90", # Phase 4.1 — Bayesian posteriors "ALTER TABLE custom_patterns ADD COLUMN bayesian_alpha REAL DEFAULT 1.0", "ALTER TABLE custom_patterns ADD COLUMN bayesian_beta REAL DEFAULT 1.0", "ALTER TABLE custom_patterns ADD COLUMN bayesian_win_rate REAL", "ALTER TABLE custom_patterns ADD COLUMN bayesian_updated_at TEXT", "ALTER TABLE custom_patterns ADD COLUMN bayesian_sample_size INTEGER DEFAULT 0", ]: try: c.execute(_sql) except Exception: pass # Phase 4.2 — Régime clusters (K-Means sur gauges macro) c.execute("""CREATE TABLE IF NOT EXISTS regime_clusters ( id INTEGER PRIMARY KEY AUTOINCREMENT, timestamp TEXT NOT NULL, cluster_id INTEGER NOT NULL, cluster_label TEXT, dominant_regime TEXT, gauges_json TEXT DEFAULT '{}', anomaly_flag INTEGER DEFAULT 0, created_at TEXT DEFAULT (datetime('now')) )""") try: c.execute("CREATE INDEX IF NOT EXISTS idx_rc_ts ON regime_clusters(timestamp DESC)") except Exception: pass # Phase 4.3 — Embeddings sémantiques des patterns c.execute("""CREATE TABLE IF NOT EXISTS pattern_embeddings ( id INTEGER PRIMARY KEY AUTOINCREMENT, pattern_id TEXT NOT NULL UNIQUE, embedding_json TEXT NOT NULL, model_version TEXT DEFAULT 'text-embedding-3-small', created_at TEXT DEFAULT (datetime('now')), updated_at TEXT DEFAULT (datetime('now')) )""") try: c.execute("CREATE INDEX IF NOT EXISTS idx_pe_pattern ON pattern_embeddings(pattern_id)") except Exception: pass c.execute("""CREATE TABLE IF NOT EXISTS config ( key TEXT PRIMARY KEY, value TEXT NOT NULL, updated_at TEXT DEFAULT (datetime('now')) )""") c.execute("""CREATE TABLE IF NOT EXISTS pattern_score_history ( id INTEGER PRIMARY KEY AUTOINCREMENT, run_id TEXT NOT NULL, pattern_id TEXT NOT NULL, score INTEGER, confidence INTEGER, summary TEXT, scored_at TEXT NOT NULL )""") try: c.execute("CREATE INDEX IF NOT EXISTS idx_psh_pattern ON pattern_score_history(pattern_id, scored_at DESC)") except Exception: pass c.execute("""CREATE TABLE IF NOT EXISTS cycle_runs ( id INTEGER PRIMARY KEY AUTOINCREMENT, run_id TEXT NOT NULL UNIQUE, started_at TEXT NOT NULL, completed_at TEXT, trigger TEXT DEFAULT 'auto', patterns_suggested INTEGER DEFAULT 0, patterns_added INTEGER DEFAULT 0, patterns_scored INTEGER DEFAULT 0, geo_score INTEGER, dominant_regime TEXT, commentary TEXT, status TEXT DEFAULT 'running' )""") try: c.execute("CREATE INDEX IF NOT EXISTS idx_cr_started ON cycle_runs(started_at DESC)") except Exception: pass c.execute("""CREATE TABLE IF NOT EXISTS macro_regime_history ( id INTEGER PRIMARY KEY AUTOINCREMENT, timestamp TEXT NOT NULL, dominant TEXT NOT NULL, scores_json TEXT NOT NULL, reasons_json TEXT NOT NULL, gauges_summary_json TEXT NOT NULL DEFAULT '{}' )""") try: c.execute("CREATE INDEX IF NOT EXISTS idx_mrh_ts ON macro_regime_history(timestamp DESC)") except Exception: pass c.execute("""CREATE TABLE IF NOT EXISTS geo_alert_history ( id INTEGER PRIMARY KEY AUTOINCREMENT, timestamp TEXT NOT NULL, run_id TEXT NOT NULL, geo_score INTEGER NOT NULL, top_patterns_json TEXT NOT NULL DEFAULT '[]', news_count INTEGER DEFAULT 0 )""") try: c.execute("CREATE INDEX IF NOT EXISTS idx_gah_ts ON geo_alert_history(timestamp DESC)") except Exception: pass c.execute("""CREATE TABLE IF NOT EXISTS trade_entry_prices ( id INTEGER PRIMARY KEY AUTOINCREMENT, run_id TEXT NOT NULL, pattern_id TEXT NOT NULL, pattern_name TEXT, underlying TEXT NOT NULL, strategy TEXT, entry_price REAL, entry_date TEXT NOT NULL, score_at_entry INTEGER DEFAULT 0, latest_score INTEGER, expected_move_pct REAL, horizon_days INTEGER DEFAULT 30, ev_at_entry REAL, ev_net REAL, trade_score REAL, matched_profile TEXT, last_seen_at TEXT )""") for col, definition in [ ("latest_score", "INTEGER"), ("ev_at_entry", "REAL"), ("ev_net", "REAL"), ("trade_score", "REAL"), ("matched_profile", "TEXT"), ("last_seen_at", "TEXT"), ("pnl_pct", "REAL"), ("capital_invested", "REAL"), ("strike_guidance", "TEXT"), ("expiry_days_at_entry", "INTEGER"), ("status", "TEXT DEFAULT 'open'"), ("closed_at", "TEXT"), ("close_reason", "TEXT"), ("close_note", "TEXT"), ("pnl_realized", "REAL"), ("close_price", "REAL"), ("target_pct", "REAL"), ("stop_loss_pct", "REAL"), ("signal_threshold", "REAL"), ("asset_class", "TEXT"), ]: try: c.execute(f"ALTER TABLE trade_entry_prices ADD COLUMN {col} {definition}") except Exception: pass try: c.execute("CREATE INDEX IF NOT EXISTS idx_tep_date ON trade_entry_prices(entry_date DESC)") c.execute("CREATE INDEX IF NOT EXISTS idx_tep_status ON trade_entry_prices(status, closed_at DESC)") except Exception: pass c.execute("""CREATE TABLE IF NOT EXISTS risk_profiles ( id INTEGER PRIMARY KEY AUTOINCREMENT, name TEXT NOT NULL, min_score INTEGER NOT NULL DEFAULT 0, min_gain_pct REAL NOT NULL DEFAULT 0, color TEXT DEFAULT '#3b82f6', enabled INTEGER DEFAULT 1, sort_order INTEGER DEFAULT 0, created_at TEXT DEFAULT (datetime('now')) )""") # Default risk profiles (seed only if table is empty) existing_profiles = c.execute("SELECT COUNT(*) FROM risk_profiles").fetchone()[0] if existing_profiles == 0: default_profiles = [ ("Conservateur", 50, 100.0, "#22c55e", 1, 0), ("Équilibré", 30, 250.0, "#3b82f6", 1, 1), ("Agressif", 15, 600.0, "#ef4444", 1, 2), ] c.executemany( "INSERT INTO risk_profiles (name, min_score, min_gain_pct, color, enabled, sort_order) VALUES (?,?,?,?,?,?)", default_profiles ) # Default config defaults = { "openai_api_key": "", "newsapi_key": "", "eia_api_key": "", "fred_api_key": "", "sources": json.dumps({ "reuters_world": {"enabled": True, "url": "https://feeds.reuters.com/reuters/worldNews", "name": "Reuters World"}, "reuters_business": {"enabled": True, "url": "https://feeds.reuters.com/reuters/businessNews", "name": "Reuters Business"}, "reuters_energy": {"enabled": True, "url": "https://feeds.reuters.com/reuters/USenergyNews", "name": "Reuters Commodities"}, "ap_top": {"enabled": True, "url": "https://feeds.apnews.com/rss/apf-topnews", "name": "AP Top News"}, "aljazeera": {"enabled": True, "url": "https://www.aljazeera.com/xml/rss/all.xml", "name": "Al Jazeera"}, "ft": {"enabled": False, "url": "https://www.ft.com/rss/home", "name": "Financial Times"}, "bloomberg": {"enabled": False, "url": "https://feeds.bloomberg.com/markets/news.rss", "name": "Bloomberg Markets"}, "newsapi": {"enabled": False, "url": "", "name": "NewsAPI (clé requise)", "requires_key": "newsapi_key"}, "gdelt": {"enabled": False, "url": "https://api.gdeltproject.org/api/v2/doc/doc?query=geopolitics&mode=artlist&format=json", "name": "GDELT Project (gratuit)"}, "eia": {"enabled": False, "url": "", "name": "EIA Energy (clé requise)", "requires_key": "eia_api_key"}, "fred": {"enabled": False, "url": "", "name": "FRED Macro Fed (clé requise)", "requires_key": "fred_api_key"}, "usda": {"enabled": False, "url": "https://apps.fas.usda.gov/psdonline/api/psd/crops", "name": "USDA Agriculture (gratuit)"}, "who": {"enabled": False, "url": "https://www.who.int/rss-feeds/news-english.xml", "name": "WHO Santé (gratuit)"}, "emdat": {"enabled": False, "url": "", "name": "EM-DAT Catastrophes (inscription requise)"}, "twitter_trump": {"enabled": False, "url": "", "name": "X/Twitter Trump (API payante)"}, }), "ai_enabled": "false", "ai_auto_rescore": "false", "auto_cycle_enabled": "false", "auto_cycle_hours": "3", "auto_cycle_similarity_threshold": "0.30", "min_ev_threshold": "0.0", "min_score_threshold": "0", "exit_defaults": json.dumps({ "target_pct": 30.0, "stop_loss_pct": -50.0, "signal_reversal_mode": "badge_only", "signal_reversal_threshold": 25, }), } for k, v in defaults.items(): c.execute("INSERT OR IGNORE INTO config (key, value) VALUES (?, ?)", (k, v)) c.execute("""CREATE TABLE IF NOT EXISTS ai_reasoning_traces ( id INTEGER PRIMARY KEY AUTOINCREMENT, run_id TEXT NOT NULL, trace_type TEXT NOT NULL, pattern_id TEXT, input_context_json TEXT DEFAULT '{}', output_json TEXT DEFAULT '{}', reasoning_summary TEXT, geo_score INTEGER, macro_dominant TEXT, created_at TEXT NOT NULL DEFAULT (datetime('now')) )""") try: c.execute("CREATE INDEX IF NOT EXISTS idx_art_run ON ai_reasoning_traces(run_id)") c.execute("CREATE INDEX IF NOT EXISTS idx_art_pattern ON ai_reasoning_traces(pattern_id, trace_type)") except Exception: pass c.execute("""CREATE TABLE IF NOT EXISTS ai_reports ( id INTEGER PRIMARY KEY AUTOINCREMENT, report_type TEXT NOT NULL DEFAULT 'portfolio', days INTEGER NOT NULL DEFAULT 30, stats_json TEXT DEFAULT '{}', winners_json TEXT DEFAULT '[]', losers_json TEXT DEFAULT '[]', report_json TEXT DEFAULT '{}', created_at TEXT NOT NULL DEFAULT (datetime('now')) )""") try: c.execute("CREATE INDEX IF NOT EXISTS idx_reports_type_date ON ai_reports(report_type, created_at)") except Exception: pass c.execute("""CREATE TABLE IF NOT EXISTS knowledge_base ( id INTEGER PRIMARY KEY AUTOINCREMENT, category TEXT NOT NULL, title TEXT NOT NULL, content TEXT NOT NULL, confidence INTEGER DEFAULT 50, confirmation_count INTEGER DEFAULT 1, status TEXT DEFAULT 'active', tags TEXT DEFAULT '', first_seen_at TEXT NOT NULL DEFAULT (datetime('now')), last_confirmed_at TEXT NOT NULL DEFAULT (datetime('now')) )""") c.execute("""CREATE TABLE IF NOT EXISTS reasoning_state ( id INTEGER PRIMARY KEY AUTOINCREMENT, version INTEGER NOT NULL DEFAULT 1, narrative TEXT NOT NULL, synthesis_json TEXT DEFAULT '{}', sources_count INTEGER DEFAULT 0, reports_used INTEGER DEFAULT 0, trades_analyzed INTEGER DEFAULT 0, created_at TEXT NOT NULL DEFAULT (datetime('now')) )""") c.execute("""CREATE TABLE IF NOT EXISTS iv_history ( id INTEGER PRIMARY KEY AUTOINCREMENT, ticker TEXT NOT NULL, recorded_date TEXT NOT NULL, iv_current REAL, iv_30d REAL, iv_60d REAL, iv_90d REAL, created_at TEXT DEFAULT (datetime('now')) )""") c.execute("""CREATE TABLE IF NOT EXISTS iv_watchlist ( ticker TEXT PRIMARY KEY, added_date TEXT NOT NULL DEFAULT (date('now')), added_by TEXT DEFAULT 'builtin', is_active INTEGER DEFAULT 1 )""") c.execute("""CREATE TABLE IF NOT EXISTS system_logs ( id INTEGER PRIMARY KEY AUTOINCREMENT, ts TEXT NOT NULL DEFAULT (datetime('now')), level TEXT NOT NULL, source TEXT, cycle_id TEXT, ticker TEXT, message TEXT NOT NULL, details TEXT )""") c.execute("""CREATE TABLE IF NOT EXISTS cycle_context_snapshots ( run_id TEXT PRIMARY KEY, ts TEXT NOT NULL DEFAULT (datetime('now')), context_json TEXT NOT NULL )""") c.execute("""CREATE TABLE IF NOT EXISTS skipped_trades ( id INTEGER PRIMARY KEY AUTOINCREMENT, run_id TEXT, pattern_id TEXT, pattern_name TEXT, underlying TEXT, strategy TEXT, score INTEGER DEFAULT 0, expected_move_pct REAL, skip_reason TEXT DEFAULT 'no_profile', skip_detail TEXT, asset_class TEXT, created_at TEXT DEFAULT (strftime('%Y-%m-%dT%H:%M:%S', 'now')) )""") try: c.execute("CREATE INDEX IF NOT EXISTS idx_skipped_date ON skipped_trades(created_at DESC)") except Exception: pass c.execute("""CREATE TABLE IF NOT EXISTS var_snapshots ( id INTEGER PRIMARY KEY AUTOINCREMENT, computed_at TEXT NOT NULL, confidence REAL NOT NULL DEFAULT 0.95, horizon_days INTEGER NOT NULL DEFAULT 1, lookback_days INTEGER NOT NULL DEFAULT 252, default_iv REAL NOT NULL DEFAULT 0.20, hist_var_1d_pct REAL, hist_cvar_pct REAL, hist_var_1d_eur REAL, param_var_1d_pct REAL, param_cvar_pct REAL, mc_var_1d_pct REAL, mc_cvar_pct REAL, n_positions INTEGER, total_notional_eur REAL, data_source TEXT, breach_rate_pct REAL, kupiec_ok INTEGER, macro_regime TEXT, ticker_prices TEXT, full_result TEXT )""") try: c.execute("CREATE INDEX IF NOT EXISTS idx_var_snap_ts ON var_snapshots(computed_at DESC)") except Exception: pass c.execute("""CREATE TABLE IF NOT EXISTS pnl_snapshots ( id INTEGER PRIMARY KEY AUTOINCREMENT, snapped_at TEXT NOT NULL, n_open INTEGER, n_closed INTEGER, total_capital_eur REAL, total_pnl_pct REAL, total_pnl_eur REAL, ticker_prices TEXT, macro_regime TEXT, trades_snapshot TEXT )""") try: c.execute("CREATE INDEX IF NOT EXISTS idx_pnl_snap_ts ON pnl_snapshots(snapped_at DESC)") except Exception: pass c.execute("""CREATE TABLE IF NOT EXISTS cycle_reports ( id INTEGER PRIMARY KEY AUTOINCREMENT, run_id TEXT NOT NULL UNIQUE, generated_at TEXT NOT NULL, macro_dominant TEXT, geo_score INTEGER, patterns_added INTEGER DEFAULT 0, trades_logged INTEGER DEFAULT 0, trades_closed INTEGER DEFAULT 0, pnl_snapshot_id INTEGER, var_snapshot_id INTEGER, full_report_json TEXT )""") try: c.execute("CREATE INDEX IF NOT EXISTS idx_cycle_reports_ts ON cycle_reports(generated_at DESC)") except Exception: pass c.execute("""CREATE TABLE IF NOT EXISTS options_trade_assessments ( id INTEGER PRIMARY KEY AUTOINCREMENT, run_id TEXT NOT NULL, trade_id INTEGER, ticker TEXT, strategy TEXT, assessed_at TEXT, iv_rank REAL, iv_current_pct REAL, skew_pct REAL, term_structure TEXT, fit_score INTEGER, verdict TEXT, issues_json TEXT, optimal_strategy TEXT, analysis TEXT, when_to_enter TEXT )""") try: c.execute("CREATE INDEX IF NOT EXISTS idx_ota_run ON options_trade_assessments(run_id)") c.execute("CREATE INDEX IF NOT EXISTS idx_ota_trade ON options_trade_assessments(trade_id)") except Exception: pass try: c.execute("CREATE INDEX IF NOT EXISTS idx_kb_category ON knowledge_base(category, status)") c.execute("CREATE INDEX IF NOT EXISTS idx_rs_version ON reasoning_state(version DESC)") c.execute("CREATE UNIQUE INDEX IF NOT EXISTS idx_iv_history_ticker_date ON iv_history(ticker, recorded_date)") c.execute("CREATE INDEX IF NOT EXISTS idx_syslog_ts ON system_logs(ts DESC)") c.execute("CREATE INDEX IF NOT EXISTS idx_syslog_level ON system_logs(level, ts DESC)") c.execute("CREATE INDEX IF NOT EXISTS idx_syslog_cycle ON system_logs(cycle_id, ts DESC)") except Exception: pass # Seed default config values if not already set for _key, _val in [ ("journal_retention_days", "90"), ("maturity_threshold_pct", "35"), # IV Gate — blocks ALERT trades before they are logged ("iv_gate_enabled", "true"), # enable/disable the IV gate entirely ("iv_gate_ivr_high", "60"), # IVR above this = "high vol" (no naked long) ("iv_gate_ivr_extreme", "80"), # IVR above this = "extreme vol" (sell vol only) ("iv_gate_skew_threshold", "8"), # put skew above this = protect is expensive ]: existing = c.execute("SELECT value FROM config WHERE key=?", (_key,)).fetchone() if not existing: c.execute( "INSERT OR IGNORE INTO config (key, value, updated_at) VALUES (?, ?, datetime('now'))", (_key, _val) ) # Seed built-in watchlist tickers (idempotent) _builtin_tickers = [ "SPY", "QQQ", "GLD", "SLV", "USO", "BNO", "UNG", "XLE", "UUP", "TLT", "GDX", "EWJ", "FEZ", "XOM", "CVX", "LMT", "RTX", "BA", ] for _t in _builtin_tickers: c.execute( "INSERT OR IGNORE INTO iv_watchlist (ticker, added_by) VALUES (?, 'builtin')", (_t,) ) conn.commit() conn.close() # ── Config ──────────────────────────────────────────────────────────────────── def get_config(key: str) -> Optional[str]: conn = get_conn() row = conn.execute("SELECT value FROM config WHERE key=?", (key,)).fetchone() conn.close() return row["value"] if row else None def set_config(key: str, value: str): conn = get_conn() conn.execute( "INSERT OR REPLACE INTO config (key, value, updated_at) VALUES (?, ?, datetime('now'))", (key, value) ) conn.commit() conn.close() if key == "openai_api_key": os.environ["OPENAI_API_KEY"] = value def get_all_config() -> Dict[str, str]: conn = get_conn() rows = conn.execute("SELECT key, value FROM config").fetchall() conn.close() result = {r["key"]: r["value"] for r in rows} if "openai_api_key" in result and result["openai_api_key"]: result["openai_api_key_set"] = True result["openai_api_key"] = "***" return result def get_sources() -> Dict[str, Any]: raw = get_config("sources") return json.loads(raw) if raw else {} def update_sources(sources: Dict[str, Any]): set_config("sources", json.dumps(sources)) def save_pattern_scores(scores: List[Dict[str, Any]], meta: Dict[str, Any] = None) -> str: """Persist last AI scores and append a history snapshot. Returns run_id.""" from datetime import datetime as _dt run_id = _dt.utcnow().isoformat() data = {"scores": scores, "meta": meta or {}, "scored_at": run_id, "run_id": run_id} set_config("last_pattern_scores", json.dumps(data)) conn = get_conn() for sp in scores: pid = sp.get("pattern_id", "") if pid: # Look up predicted_probability from custom_patterns row = conn.execute("SELECT probability FROM custom_patterns WHERE id=?", (pid,)).fetchone() predicted_prob = float(row["probability"]) if row and row["probability"] is not None else None conn.execute( "INSERT INTO pattern_score_history (run_id, pattern_id, score, confidence, summary, scored_at, predicted_probability) VALUES (?,?,?,?,?,?,?)", (run_id, pid, sp.get("score"), sp.get("confidence"), sp.get("summary", ""), run_id, predicted_prob), ) # Keep only the last 30 runs conn.execute("""DELETE FROM pattern_score_history WHERE run_id NOT IN ( SELECT DISTINCT run_id FROM pattern_score_history ORDER BY scored_at DESC LIMIT 30 )""") conn.commit() conn.close() return run_id def get_pattern_scores() -> Dict[str, Any]: """Return last persisted AI scores.""" raw = get_config("last_pattern_scores") if raw: try: return json.loads(raw) except Exception: pass return {"scores": [], "meta": {}, "scored_at": None} def get_score_deltas() -> Dict[str, int]: """Compute score change per pattern between the two most recent scoring runs.""" conn = get_conn() runs = conn.execute( "SELECT DISTINCT run_id FROM pattern_score_history ORDER BY scored_at DESC LIMIT 2" ).fetchall() if len(runs) < 2: conn.close() return {} latest_run, prev_run = runs[0]["run_id"], runs[1]["run_id"] latest = {r["pattern_id"]: r["score"] for r in conn.execute("SELECT pattern_id, score FROM pattern_score_history WHERE run_id=?", (latest_run,)).fetchall()} prev = {r["pattern_id"]: r["score"] for r in conn.execute("SELECT pattern_id, score FROM pattern_score_history WHERE run_id=?", (prev_run,)).fetchall()} conn.close() return { pid: score - prev[pid] for pid, score in latest.items() if pid in prev and score is not None and prev[pid] is not None } def get_score_history(pattern_id: str, limit: int = 10) -> List[Dict[str, Any]]: """Return the last N score snapshots for a given pattern.""" conn = get_conn() rows = conn.execute( "SELECT score, confidence, summary, scored_at FROM pattern_score_history WHERE pattern_id=? ORDER BY scored_at DESC LIMIT ?", (pattern_id, limit), ).fetchall() conn.close() return [dict(r) for r in rows] def compute_pattern_similarity(patterns: List[Dict[str, Any]], threshold: float = 0.25) -> List[Dict[str, Any]]: """Return pairs of patterns with Jaccard keyword similarity above threshold.""" results = [] for i, p1 in enumerate(patterns): kw1 = set(kw.lower() for kw in (p1.get("keywords") or [])) for j, p2 in enumerate(patterns): if i >= j: continue kw2 = set(kw.lower() for kw in (p2.get("keywords") or [])) if not kw1 or not kw2: continue common = kw1 & kw2 union = kw1 | kw2 sim = len(common) / len(union) if union else 0.0 if sim >= threshold: results.append({ "id_a": p1.get("id"), "name_a": p1.get("name"), "id_b": p2.get("id"), "name_b": p2.get("name"), "similarity": round(sim, 2), "common_keywords": sorted(common)[:8], }) return sorted(results, key=lambda x: -x["similarity"]) def get_analysis_config() -> Dict[str, Any]: """Return the AI analysis config: template, top_n, category_filter.""" raw = get_config("analysis_config") if raw: try: return json.loads(raw) except Exception: pass return {"top_n": 10, "category_filter": "all", "template": None} def save_analysis_config(cfg: Dict[str, Any]): set_config("analysis_config", json.dumps(cfg)) # ── Portfolio ───────────────────────────────────────────────────────────────── IB_OPTIONS_FEE_PER_CONTRACT = 0.65 IB_MIN_FEE = 1.0 def compute_ib_fees(num_contracts: int) -> float: return max(IB_MIN_FEE, num_contracts * IB_OPTIONS_FEE_PER_CONTRACT) def add_position(pos: Dict[str, Any]) -> str: import uuid pos_id = pos.get("id") or f"POS-{uuid.uuid4().hex[:8].upper()}" legs = pos.get("legs", []) num_contracts = sum(abs(leg.get("quantity", 1)) for leg in legs) ib_fees = compute_ib_fees(num_contracts) conn = get_conn() conn.execute("""INSERT INTO portfolio ( id, title, underlying, strategy, asset_class, entry_date, expiry_date, expiry_days, legs, capital_invested, entry_underlying_price, geo_trigger, rationale, status, notes, ib_fees_entry ) VALUES (?,?,?,?,?,?,?,?,?,?,?,?,?,'open',?,?)""", ( pos_id, pos.get("title", pos.get("underlying", "")), pos.get("underlying", ""), pos.get("strategy", ""), pos.get("asset_class", ""), pos.get("entry_date", datetime.utcnow().isoformat()[:10]), pos.get("expiry_date", ""), pos.get("expiry_days", 90), json.dumps(legs), pos.get("capital_invested", 1000.0), pos.get("entry_underlying_price"), pos.get("geo_trigger", ""), pos.get("rationale", ""), pos.get("notes", ""), ib_fees, )) conn.commit() conn.close() return pos_id def get_positions(status: str = "open") -> List[Dict[str, Any]]: conn = get_conn() rows = conn.execute( "SELECT * FROM portfolio WHERE status=? ORDER BY created_at DESC", (status,) ).fetchall() conn.close() result = [] for r in rows: d = dict(r) d["legs"] = json.loads(d.get("legs", "[]")) result.append(d) return result def close_position(pos_id: str, close_value: float) -> Dict[str, Any]: conn = get_conn() pos = conn.execute("SELECT * FROM portfolio WHERE id=?", (pos_id,)).fetchone() if not pos: conn.close() return {"error": "Position non trouvée"} legs = json.loads(pos["legs"]) num_contracts = sum(abs(leg.get("quantity", 1)) for leg in legs) ib_exit = compute_ib_fees(num_contracts) conn.execute("""UPDATE portfolio SET status='closed', close_date=?, close_value=?, ib_fees_exit=? WHERE id=?""", (datetime.utcnow().isoformat()[:10], close_value, ib_exit, pos_id)) conn.commit() pnl = close_value - pos["capital_invested"] - pos["ib_fees_entry"] - ib_exit conn.close() return {"id": pos_id, "close_value": close_value, "ib_fees_exit": ib_exit, "pnl": pnl} def update_position_notes(pos_id: str, notes: str): conn = get_conn() conn.execute("UPDATE portfolio SET notes=? WHERE id=?", (notes, pos_id)) conn.commit() conn.close() # ── Custom Patterns ──────────────────────────────────────────────────────────── def seed_builtin_patterns(builtin_patterns: List[Dict[str, Any]]): """Seed built-in patterns into DB (idempotent — skips existing IDs).""" conn = get_conn() existing = {r[0] for r in conn.execute("SELECT id FROM custom_patterns").fetchall()} for p in builtin_patterns: if p["id"] not in existing: conn.execute("""INSERT INTO custom_patterns ( id, name, description, triggers, keywords, historical_instances, suggested_trades, asset_class, expected_move_pct, probability, horizon_days, source, is_active, updated_at ) VALUES (?,?,?,?,?,?,?,?,?,?,?,'builtin',1,datetime('now'))""", ( p["id"], p.get("name", ""), p.get("description", ""), json.dumps(p.get("triggers", [])), json.dumps(p.get("keywords", [])), json.dumps(p.get("historical_instances", [])), json.dumps(p.get("suggested_trades", [])), p.get("asset_class", "indices"), p.get("expected_move_pct", 0), p.get("probability", 0.5), p.get("horizon_days", 30), )) conn.commit() conn.close() def save_custom_pattern(pattern: Dict[str, Any]) -> str: import uuid pat_id = pattern.get("id") or f"P_USER_{uuid.uuid4().hex[:6].upper()}" source = pattern.get("source", "custom") conn = get_conn() conn.execute("""INSERT OR REPLACE INTO custom_patterns ( id, name, description, triggers, keywords, historical_instances, suggested_trades, asset_class, expected_move_pct, probability, horizon_days, ai_quality_score, ai_evaluation, source, counter_thesis, invalidation_trigger, invalidation_probability, is_active, updated_at ) VALUES (?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,?,1,datetime('now'))""", ( pat_id, pattern.get("name", ""), pattern.get("description", ""), json.dumps(pattern.get("triggers", [])), json.dumps(pattern.get("keywords", [])), json.dumps(pattern.get("historical_instances", [])), json.dumps(pattern.get("suggested_trades", [])), pattern.get("asset_class", "indices"), pattern.get("expected_move_pct", 0), pattern.get("probability", 0.5), pattern.get("horizon_days", 30), pattern.get("ai_quality_score"), json.dumps(pattern.get("ai_evaluation", {})), source, pattern.get("counter_thesis"), pattern.get("invalidation_trigger"), pattern.get("invalidation_probability"), )) conn.commit() conn.close() return pat_id def get_custom_patterns() -> List[Dict[str, Any]]: conn = get_conn() rows = conn.execute( "SELECT * FROM custom_patterns WHERE is_active=1 ORDER BY source DESC, created_at DESC" ).fetchall() conn.close() result = [] for r in rows: d = dict(r) for f in ["triggers", "keywords", "historical_instances", "suggested_trades", "ai_evaluation"]: d[f] = json.loads(d.get(f) or "[]") result.append(d) return result def toggle_pattern_active(pat_id: str) -> bool: """Toggle is_active for a pattern. Returns the new state.""" conn = get_conn() row = conn.execute("SELECT is_active FROM custom_patterns WHERE id=?", (pat_id,)).fetchone() if not row: conn.close() return False new_state = 0 if row["is_active"] else 1 conn.execute("UPDATE custom_patterns SET is_active=? WHERE id=?", (new_state, pat_id)) conn.commit() conn.close() return bool(new_state) def delete_custom_pattern(pat_id: str): conn = get_conn() conn.execute("UPDATE custom_patterns SET is_active=0 WHERE id=?", (pat_id,)) conn.commit() conn.close() # ── Risk Profiles ───────────────────────────────────────────────────────────── def get_risk_profiles(enabled_only: bool = False) -> List[Dict[str, Any]]: conn = get_conn() q = "SELECT * FROM risk_profiles" if enabled_only: q += " WHERE enabled=1" q += " ORDER BY sort_order ASC, id ASC" rows = conn.execute(q).fetchall() conn.close() return [dict(r) for r in rows] def upsert_risk_profile(profile: Dict[str, Any]) -> int: conn = get_conn() pid = profile.get("id") if pid: conn.execute("""UPDATE risk_profiles SET name=?, min_score=?, min_gain_pct=?, color=?, enabled=?, sort_order=? WHERE id=?""", ( profile["name"], int(profile["min_score"]), float(profile["min_gain_pct"]), profile.get("color", "#3b82f6"), 1 if profile.get("enabled", True) else 0, int(profile.get("sort_order", 0)), pid, )) else: cur = conn.execute("""INSERT INTO risk_profiles (name, min_score, min_gain_pct, color, enabled, sort_order) VALUES (?,?,?,?,?,?)""", ( profile["name"], int(profile["min_score"]), float(profile["min_gain_pct"]), profile.get("color", "#3b82f6"), 1 if profile.get("enabled", True) else 0, int(profile.get("sort_order", 0)), )) pid = cur.lastrowid conn.commit() conn.close() return pid def delete_risk_profile(profile_id: int): conn = get_conn() conn.execute("DELETE FROM risk_profiles WHERE id=?", (profile_id,)) conn.commit() conn.close() def _compute_trade_score(score: int, gain_pct: float) -> tuple[float, float, float]: """ Returns (ev_gross, ev_net, trade_score) for a (score, gain_pct) pair. - ev_gross = p × G (raw expected multiple) - ev_net = p × G - (1-p) (net EV assuming total loss if wrong) - trade_score = p×G / (p×G + (1-p)) × 100 (normalized 0-100) """ p = max(0.0, min(1.0, score / 100)) G = abs(gain_pct) / 100 ev_gross = round(p * G, 4) ev_net = round(p * G - (1 - p), 4) denom = p * G + (1 - p) trade_score = round((p * G / denom * 100) if denom > 0 else 0.0, 1) return ev_gross, ev_net, trade_score def _matches_profile(score: int, gain_pct: float, profiles: List[Dict[str, Any]]) -> Optional[str]: """Return the name of the first enabled profile this trade satisfies, or None.""" for prof in profiles: if not prof.get("enabled", True): continue if score >= prof["min_score"] and gain_pct >= prof["min_gain_pct"]: return prof["name"] return None # ── Journal de Bord ──────────────────────────────────────────────────────────── def log_macro_regime(dominant: str, scores: Dict[str, Any], reasons: Dict[str, Any], gauges_summary: Dict[str, Any]): """Append a macro regime snapshot. Keeps last 90 days.""" conn = get_conn() conn.execute("""INSERT INTO macro_regime_history (timestamp, dominant, scores_json, reasons_json, gauges_summary_json) VALUES (datetime('now'), ?, ?, ?, ?)""", (dominant, json.dumps(scores), json.dumps(reasons), json.dumps(gauges_summary))) conn.execute("""DELETE FROM macro_regime_history WHERE timestamp < datetime('now', '-90 days')""") conn.commit() conn.close() def get_macro_regime_history(days: int = 15) -> List[Dict[str, Any]]: conn = get_conn() rows = conn.execute( "SELECT * FROM macro_regime_history WHERE timestamp >= datetime('now', ?) ORDER BY timestamp DESC", (f"-{days} days",) ).fetchall() conn.close() result = [] for r in rows: d = dict(r) d["scores"] = json.loads(d.pop("scores_json", "{}")) d["reasons"] = json.loads(d.pop("reasons_json", "{}")) d["gauges_summary"] = json.loads(d.pop("gauges_summary_json", "{}")) result.append(d) return result def log_geo_alert(geo_score: int, top_patterns: List[Dict[str, Any]], news_count: int, run_id: str): """Append a geo alert snapshot tied to a scoring run.""" conn = get_conn() conn.execute("""INSERT INTO geo_alert_history (timestamp, run_id, geo_score, top_patterns_json, news_count) VALUES (datetime('now'), ?, ?, ?, ?)""", (run_id, geo_score, json.dumps(top_patterns[:10]), news_count)) conn.execute("DELETE FROM geo_alert_history WHERE timestamp < datetime('now', '-90 days')") conn.commit() conn.close() def get_geo_alert_history(days: int = 30) -> List[Dict[str, Any]]: conn = get_conn() rows = conn.execute( "SELECT * FROM geo_alert_history WHERE timestamp >= datetime('now', ?) ORDER BY timestamp DESC", (f"-{days} days",) ).fetchall() conn.close() result = [] for r in rows: d = dict(r) d["top_patterns"] = json.loads(d.pop("top_patterns_json", "[]")) result.append(d) return result def _normalize_yf_ticker(ticker: str) -> str: """Normalize ticker for yfinance. - USD/KRW → USDKRW=X (slash-format forex pairs from GPT-4o) - USDKRW → USDKRW=X (bare 6-char alphabetic forex pairs) - CL=F, SPY, etc. → unchanged """ t = ticker.upper().strip() if '/' in t: parts = t.split('/') if len(parts) == 2 and all(p.isalpha() and len(p) >= 2 for p in parts): return parts[0] + parts[1] + '=X' return t if len(t) == 6 and t.isalpha(): return t + "=X" return t def log_trade_entries(run_id: str, scored_patterns: List[Dict[str, Any]], quotes: Dict[str, Any]): """ For each scored pattern's trade_rankings, record entry price if the trade passes at least one enabled risk profile (min_score + min_gain_pct pair). Deduplicates: one row per (pattern_id, underlying, strategy). Falls back to yfinance for tickers not found in the quotes snapshot. """ import logging as _logging _log = _logging.getLogger(__name__) profiles = get_risk_profiles(enabled_only=True) _log.info(f"[TradeLog] run_id={run_id} scored_patterns={len(scored_patterns)} profiles={len(profiles)}") # Load original patterns as fallback for expected_move_pct # (GPT-4o scored output doesn't include this field) _orig_patterns = {p.get("id", ""): p for p in get_custom_patterns()} # Build price map from pre-fetched quotes price_map: Dict[str, float] = {} for asset_class, items in quotes.items(): if isinstance(items, list): for item in items: if item.get("ticker") and item.get("price") is not None: price_map[item["ticker"].upper()] = float(item["price"]) elif isinstance(items, dict): for ticker, item in items.items(): if isinstance(item, dict) and item.get("price") is not None: price_map[ticker.upper()] = float(item["price"]) # Collect tickers NOT already in price_map for yfinance fallback tickers_to_fetch: set = set() for sp in scored_patterns: for trade in sp.get("trade_rankings") or sp.get("suggested_trades", []): t = (trade.get("underlying") or trade.get("ticker", "")).upper() if t and t not in price_map: tickers_to_fetch.add(t) if tickers_to_fetch: _log.info(f"[TradeLog] yfinance fallback for {len(tickers_to_fetch)} tickers: {sorted(tickers_to_fetch)}") try: import yfinance as yf import pandas as pd from concurrent.futures import ThreadPoolExecutor, as_completed def _fetch(ticker: str): normalized = _normalize_ticker(ticker) # handles WHEAT→ZW=F, EUR/USD→EURUSD=X, etc. try: # Use yf.download() — fresh HTTP request, no in-process Ticker cache for kwargs in [ {"period": "1d", "interval": "5m"}, {"period": "5d", "interval": "1d"}, ]: df = yf.download(normalized, progress=False, auto_adjust=True, **kwargs) if df.empty: continue if isinstance(df.columns, pd.MultiIndex): df.columns = df.columns.get_level_values(0) if "Close" not in df.columns: continue close = df["Close"].dropna() if close.empty: continue price = float(close.iloc[-1]) if price > 0: _log.debug(f"[TradeLog] {ticker} → {normalized} = {price}") return ticker, price except Exception as e: _log.warning(f"[TradeLog] Failed to fetch '{ticker}' (normalized='{normalized}'): {e}") return ticker, None with ThreadPoolExecutor(max_workers=min(len(tickers_to_fetch), 10)) as ex: for fut in as_completed({ex.submit(_fetch, t): t for t in tickers_to_fetch}, timeout=20): try: tk, price = fut.result() if price is not None: price_map[tk] = price except Exception: pass except Exception as e: _log.error(f"[TradeLog] yfinance fallback failed: {e}") conn = get_conn() today = datetime.utcnow().isoformat()[:10] now_ts = datetime.utcnow().isoformat() inserted_count = 0 updated_count = 0 skipped_no_profile = 0 for sp in scored_patterns: pid = sp.get("pattern_id", "") pattern_name = sp.get("geo_trigger") or sp.get("pattern_name") or pid base_score = int(sp.get("score") or 0) _orig = _orig_patterns.get(pid, {}) for trade in sp.get("trade_rankings") or sp.get("suggested_trades", []): underlying = trade.get("underlying") or trade.get("ticker", "") if not underlying: continue strategy = trade.get("strategy") or trade.get("trade_type", "") delta = int(trade.get("score_delta") or 0) eff_score = max(0, min(100, base_score + delta)) # Fallback chain: trade field → scored sp field → auto_cycle enrichment → original DB pattern exp_move = abs(float( trade.get("expected_move_pct") or sp.get("expected_move_pct") or _orig.get("expected_move_pct") or 0 )) if exp_move == 0: _log.warning(f"[TradeLog] Pattern '{pattern_name}' trade {underlying} has expected_move_pct=0 — all profiles with min_gain_pct>0 will fail") # Check if this trade passes any enabled risk profile matched = _matches_profile(eff_score, exp_move, profiles) if matched is None: skipped_no_profile += 1 _log.debug(f"[TradeLog] SKIP {underlying} score={eff_score} gain={exp_move:.0f}% — no profile match") _trade_ac = trade.get("asset_class") or sp.get("asset_class") or _orig.get("asset_class") or "" try: log_skipped_trade( run_id=run_id, pattern_id=pid, pattern_name=pattern_name, underlying=underlying, strategy=strategy, score=eff_score, expected_move_pct=exp_move, skip_detail=f"profiles checked: {len(profiles)}, best: score>={eff_score} gain>={exp_move:.0f}%", asset_class=_trade_ac, ) except Exception: pass continue ev_gross, ev_net, trade_score = _compute_trade_score(eff_score, exp_move) ticker_key = _normalize_ticker(underlying.upper()) entry_price = price_map.get(ticker_key) horizon = int( trade.get("horizon_days") or sp.get("horizon_days") or sp.get("recommended_trade", {}).get("expiry_days") or _orig.get("horizon_days") or 90 ) strike_guidance = ( trade.get("strike_guidance") or sp.get("recommended_trade", {}).get("strike_guidance") or None ) expiry_days_entry = int( trade.get("expiry_days") or sp.get("recommended_trade", {}).get("expiry_days") or horizon ) existing_row = conn.execute( "SELECT id FROM trade_entry_prices WHERE pattern_id=? AND underlying=? AND strategy=?", (pid, ticker_key, strategy) ).fetchone() if existing_row: conn.execute( "UPDATE trade_entry_prices SET latest_score=?, trade_score=?, last_seen_at=? WHERE id=?", (eff_score, trade_score, now_ts, existing_row["id"]) ) updated_count += 1 else: _trade_asset_class = ( trade.get("asset_class") or sp.get("asset_class") or _orig.get("asset_class") or "" ) conn.execute("""INSERT INTO trade_entry_prices (run_id, pattern_id, pattern_name, underlying, strategy, entry_price, entry_date, score_at_entry, latest_score, expected_move_pct, horizon_days, ev_at_entry, ev_net, trade_score, matched_profile, last_seen_at, strike_guidance, expiry_days_at_entry, asset_class) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)""", ( run_id, pid, pattern_name, ticker_key, strategy, entry_price, today, eff_score, eff_score, exp_move, horizon, ev_gross, ev_net, trade_score, matched, now_ts, strike_guidance, expiry_days_entry, _trade_asset_class, )) inserted_count += 1 _log.info(f"[TradeLog] NEW trade: pattern='{pattern_name}' {underlying} {strategy} score={eff_score} gain={exp_move:.0f}% profile='{matched}' price={entry_price}") _log.info(f"[TradeLog] Done — inserted={inserted_count} updated={updated_count} skipped_no_profile={skipped_no_profile}") _retention = int(get_config("journal_retention_days") or "90") conn.execute(f"DELETE FROM trade_entry_prices WHERE entry_date < date('now', '-{_retention} days')") conn.commit() conn.close() def reset_journal_history(): """Truncate all journal history tables for a clean slate.""" conn = get_conn() conn.execute("DELETE FROM trade_entry_prices") conn.execute("DELETE FROM macro_regime_history") conn.execute("DELETE FROM geo_alert_history") conn.execute("DELETE FROM cycle_runs") conn.commit() conn.close() def get_last_completed_cycle_ts() -> Optional[str]: """Return ISO timestamp of the last successfully completed cycle, or None.""" conn = get_conn() row = conn.execute( "SELECT completed_at FROM cycle_runs WHERE status='completed' ORDER BY completed_at DESC LIMIT 1" ).fetchone() conn.close() return row["completed_at"] if row else None def add_cycle_run(run_id: str, trigger: str = "auto") -> None: conn = get_conn() conn.execute( "INSERT OR IGNORE INTO cycle_runs (run_id, started_at, trigger, status) VALUES (?, datetime('now'), ?, 'running')", (run_id, trigger) ) conn.commit() conn.close() def cleanup_stale_running_cycles() -> int: """Mark any cycle_runs still in 'running' state as 'error' (stale from a crashed process).""" conn = get_conn() cur = conn.execute( "UPDATE cycle_runs SET status='error', completed_at=datetime('now') WHERE status='running'" ) conn.commit() conn.close() return cur.rowcount def update_cycle_run(run_id: str, **fields) -> None: if not fields: return allowed = {"completed_at", "patterns_suggested", "patterns_added", "patterns_scored", "geo_score", "dominant_regime", "commentary", "status"} sets = ", ".join(f"{k}=?" for k in fields if k in allowed) vals = [v for k, v in fields.items() if k in allowed] if not sets: return conn = get_conn() conn.execute(f"UPDATE cycle_runs SET {sets} WHERE run_id=?", vals + [run_id]) conn.commit() conn.close() def get_cycle_runs(limit: int = 30) -> List[Dict[str, Any]]: conn = get_conn() rows = conn.execute( "SELECT * FROM cycle_runs ORDER BY started_at DESC LIMIT ?", (limit,) ).fetchall() conn.close() return [dict(r) for r in rows] def get_cycle_run(run_id: str) -> Optional[Dict[str, Any]]: conn = get_conn() row = conn.execute("SELECT * FROM cycle_runs WHERE run_id=?", (run_id,)).fetchone() conn.close() return dict(row) if row else None def _trade_maturity(days_held: int, horizon_days: int) -> Dict[str, Any]: """ Classify a trade's maturity based on elapsed time vs planned horizon. Thresholds read from config (maturity_threshold_pct, default 35%). """ h = max(horizon_days or 90, 1) d = max(days_held or 0, 0) ratio = d / h pct = round(ratio * 100, 1) mature_threshold = float(get_config("maturity_threshold_pct") or "35") / 100.0 if ratio < 0.10: return { "status": "trop_tot", "label": "Trop tôt", "emoji": "🕐", "weight": 0.0, "color": "slate", "ratio_pct": pct, "readable": f"{d}j / {h}j ({pct}% écoulé — bruit statistique)", } elif ratio < mature_threshold: return { "status": "debut", "label": "Début", "emoji": "📊", "weight": 0.25, "color": "yellow", "ratio_pct": pct, "readable": f"{d}j / {h}j ({pct}% écoulé — signal précoce)", } elif ratio < 0.75: return { "status": "mature", "label": "Signal fiable", "emoji": "✅", "weight": 1.0, "color": "emerald", "ratio_pct": pct, "readable": f"{d}j / {h}j ({pct}% écoulé — signal fiable)", } else: return { "status": "fin_horizon", "label": "Fin d'horizon", "emoji": "⏰", "weight": 1.0, "color": "orange", "ratio_pct": pct, "readable": f"{d}j / {h}j ({pct}% écoulé — surveiller de près)", } def get_trade_entry_prices(days: int = 30) -> List[Dict[str, Any]]: conn = get_conn() rows = conn.execute( """SELECT * FROM trade_entry_prices WHERE (status IS NULL OR status = 'open') AND entry_date >= date('now', ?) ORDER BY entry_date DESC, score_at_entry DESC""", (f"-{days} days",) ).fetchall() conn.close() return [dict(r) for r in rows] def get_closed_trades(days: int = 180) -> List[Dict[str, Any]]: conn = get_conn() rows = conn.execute( """SELECT * FROM trade_entry_prices WHERE status = 'closed' AND closed_at >= date('now', ?) ORDER BY closed_at DESC""", (f"-{days} days",) ).fetchall() conn.close() return [dict(r) for r in rows] def delete_trade(trade_id: int) -> bool: conn = get_conn() cur = conn.execute("DELETE FROM trade_entry_prices WHERE id = ?", (trade_id,)) conn.commit() conn.close() return cur.rowcount > 0 def get_skipped_trades(days: int = 30) -> List[Dict[str, Any]]: conn = get_conn() rows = conn.execute( """SELECT * FROM skipped_trades WHERE created_at >= date('now', ?) ORDER BY created_at DESC, score DESC""", (f"-{days} days",) ).fetchall() conn.close() return [dict(r) for r in rows] def log_skipped_trade(run_id: str, pattern_id: str, pattern_name: str, underlying: str, strategy: str, score: int, expected_move_pct: float, skip_reason: str = "no_profile", skip_detail: str = "", asset_class: str = "") -> None: conn = get_conn() conn.execute( """INSERT INTO skipped_trades (run_id, pattern_id, pattern_name, underlying, strategy, score, expected_move_pct, skip_reason, skip_detail, asset_class) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)""", (run_id, pattern_id, pattern_name, underlying, strategy, score, expected_move_pct, skip_reason, skip_detail, asset_class) ) conn.commit() conn.close() def close_trade(trade_id: int, close_price: float, pnl_realized: float, close_reason: str, close_note: str = "") -> bool: conn = get_conn() cur = conn.execute( """UPDATE trade_entry_prices SET status='closed', closed_at=datetime('now'), close_price=?, pnl_realized=?, close_reason=?, close_note=? WHERE id=? AND (status IS NULL OR status='open')""", (close_price, pnl_realized, close_reason, close_note, trade_id) ) conn.commit() conn.close() return cur.rowcount > 0 def update_trade_exit_params(trade_id: int, target_pct: float = None, stop_loss_pct: float = None, signal_threshold: float = None) -> bool: updates: List[str] = [] vals: List[Any] = [] if target_pct is not None: updates.append("target_pct=?"); vals.append(target_pct) if stop_loss_pct is not None: updates.append("stop_loss_pct=?"); vals.append(stop_loss_pct) if signal_threshold is not None: updates.append("signal_threshold=?"); vals.append(signal_threshold) if not updates: return False conn = get_conn() cur = conn.execute( f"UPDATE trade_entry_prices SET {', '.join(updates)} WHERE id=?", vals + [trade_id] ) conn.commit() conn.close() return cur.rowcount > 0 def get_trade_entry_by_id(trade_id: int) -> Optional[Dict[str, Any]]: conn = get_conn() row = conn.execute("SELECT * FROM trade_entry_prices WHERE id=?", (trade_id,)).fetchone() conn.close() return dict(row) if row else None # ── AI Reasoning Traces ─────────────────────────────────────────────────────── def save_reasoning_trace( run_id: str, trace_type: str, pattern_id: str = None, input_context: Dict[str, Any] = None, output: Dict[str, Any] = None, reasoning_summary: str = None, geo_score: int = None, macro_dominant: str = None, ) -> int: """Persist one AI reasoning step. Returns the new row id.""" conn = get_conn() cur = conn.execute( """INSERT INTO ai_reasoning_traces (run_id, trace_type, pattern_id, input_context_json, output_json, reasoning_summary, geo_score, macro_dominant) VALUES (?, ?, ?, ?, ?, ?, ?, ?)""", ( run_id, trace_type, pattern_id, json.dumps(input_context or {}, ensure_ascii=False, default=str), json.dumps(output or {}, ensure_ascii=False, default=str), reasoning_summary, geo_score, macro_dominant, ), ) row_id = cur.lastrowid conn.commit() conn.close() return row_id def _parse_trace(row) -> Dict[str, Any]: """Deserialize a reasoning trace row.""" d = dict(row) for field in ("input_context_json", "output_json"): try: d[field.replace("_json", "")] = json.loads(d.get(field) or "{}") except Exception: d[field.replace("_json", "")] = {} return d def get_scoring_trace(run_id: str, pattern_id: str) -> Optional[Dict[str, Any]]: """Return the scoring trace for a given (run_id, pattern_id) pair.""" conn = get_conn() row = conn.execute( "SELECT * FROM ai_reasoning_traces WHERE run_id=? AND pattern_id=? AND trace_type='scoring'", (run_id, pattern_id), ).fetchone() conn.close() return _parse_trace(row) if row else None def get_suggestion_trace(pattern_id: str) -> Optional[Dict[str, Any]]: """Return the original suggestion trace for a pattern (first one ever).""" conn = get_conn() row = conn.execute( """SELECT * FROM ai_reasoning_traces WHERE pattern_id=? AND trace_type='suggestion' ORDER BY created_at ASC LIMIT 1""", (pattern_id,), ).fetchone() conn.close() return _parse_trace(row) if row else None def get_pattern_scoring_history(pattern_id: str, limit: int = 10) -> List[Dict[str, Any]]: """All scoring traces for a pattern across cycles — for trend analysis.""" conn = get_conn() rows = conn.execute( """SELECT * FROM ai_reasoning_traces WHERE pattern_id=? AND trace_type='scoring' ORDER BY created_at DESC LIMIT ?""", (pattern_id, limit), ).fetchall() conn.close() return [_parse_trace(r) for r in rows] _BEARISH_KEYWORDS = {"bear", "put", "short", "sell", "vente", "baissier"} _EXCHANGE_PREFIX_MAP = { "NSE": ".NS", "BSE": ".BO", "TSX": ".TO", "LSE": ".L", "HKG": ".HK", "SHA": ".SS", "SHE": ".SZ", "TYO": ".T", } # Commodity names that GPT-4o sometimes suggests as tickers _COMMODITY_ALIAS: Dict[str, str] = { "WHEAT": "ZW=F", "CORN": "ZC=F", "SOYBEANS": "ZS=F", "SOYBEAN": "ZS=F", "SUGAR": "SB=F", "COFFEE": "KC=F", "COTTON": "CT=F", "OIL": "CL=F", "CRUDE": "CL=F", "CRUDEOIL": "CL=F", "WTI": "CL=F", "BRENT": "BZ=F", "NATGAS": "NG=F", "GAS": "NG=F", "GOLD": "GC=F", "SILVER": "SI=F", "COPPER": "HG=F", "PLATINUM": "PL=F", "PALLADIUM": "PA=F", "NASDAQ": "QQQ", "SP500": "SPY", "DOW": "DIA", "VIX": "^VIX", "DOLLAR": "DX-Y.NYB", "DXY": "DX-Y.NYB", "EURUSD": "EURUSD=X", "GBPUSD": "GBPUSD=X", "USDJPY": "USDJPY=X", "USDCHF": "USDCHF=X", "AUDUSD": "AUDUSD=X", "USDCAD": "USDCAD=X", } def _normalize_ticker(ticker: str) -> str: """Convert various ticker formats (from GPT-4o) to yfinance-compatible tickers.""" t = ticker.strip() if not t: return t # exchange:symbol format (e.g. NSE:RELIANCE → RELIANCE.NS) if ":" in t: exchange, symbol = t.split(":", 1) suffix = _EXCHANGE_PREFIX_MAP.get(exchange.upper(), "") return symbol + suffix if suffix else symbol # slash forex format (e.g. EUR/USD → EURUSD=X) if "/" in t: parts = t.upper().split("/") if len(parts) == 2 and all(p.isalpha() and len(p) >= 2 for p in parts): return parts[0] + parts[1] + "=X" return t u = t.upper() # commodity / index aliases (checked first so EURUSD etc. in table win) if u in _COMMODITY_ALIAS: return _COMMODITY_ALIAS[u] # bare 6-char alphabetic forex pairs not already in alias table (e.g. USDSEK → USDSEK=X) if len(u) == 6 and u.isalpha(): _MAJORS = {"USD", "EUR", "GBP", "JPY", "CHF", "AUD", "CAD", "NZD", "SEK", "NOK"} if u[3:] in _MAJORS or u[:3] in _MAJORS: return u + "=X" return t def _fetch_live_prices(tickers: List[str], timeout: int = 20) -> Dict[str, Optional[float]]: """ Fetch current prices for a list of tickers using yf.download(). Shared by journal MTM and portfolio report so both get consistent live data. """ result: Dict[str, Optional[float]] = {t: None for t in tickers} if not tickers: return result try: import yfinance as yf import pandas as pd from concurrent.futures import ThreadPoolExecutor, as_completed def _one(ticker: str) -> tuple: yf_ticker = _normalize_ticker(ticker) for kwargs in [ {"period": "1d", "interval": "5m"}, {"period": "5d", "interval": "1d"}, ]: try: df = yf.download(yf_ticker, progress=False, auto_adjust=True, **kwargs) if df.empty: continue if isinstance(df.columns, pd.MultiIndex): df.columns = df.columns.get_level_values(0) if "Close" not in df.columns: continue close = df["Close"].dropna() if close.empty: continue price = float(close.iloc[-1]) if price > 0: return ticker, price except Exception: continue return ticker, None with ThreadPoolExecutor(max_workers=min(len(tickers), 10)) as ex: futs = {ex.submit(_one, t): t for t in tickers} from concurrent.futures import as_completed as _ac for fut in _ac(futs, timeout=timeout): try: tk, price = fut.result() result[tk] = price except Exception: pass except Exception: pass return result def get_mtm_trades_with_traces(days: int = 90, limit_movers: int = 5) -> Dict[str, Any]: """ Return all MTM trades with live prices and reasoning traces for the top winners and losers (by pnl_pct). Used by the AI portfolio report. """ from datetime import timedelta cutoff_date = (datetime.utcnow() - timedelta(days=days)).strftime("%Y-%m-%d") conn = get_conn() rows = conn.execute( """SELECT * FROM trade_entry_prices WHERE entry_date >= ? ORDER BY entry_date DESC""", (cutoff_date,), ).fetchall() conn.close() all_trades = [dict(r) for r in rows] # Fetch live prices for all unique tickers tickers = list({(t.get("underlying") or "").upper() for t in all_trades if t.get("underlying")}) live_prices = _fetch_live_prices(tickers, timeout=25) # Enrich trades with live price + pnl_pct def _with_pnl(trade: Dict) -> Dict: ticker = (trade.get("underlying") or "").upper() entry = trade.get("entry_price") current = live_prices.get(ticker) pnl_pct = None if entry and current and entry > 0: raw = (current - entry) / entry * 100 strategy = trade.get("strategy", "").lower() bearish = any(k in strategy for k in _BEARISH_KEYWORDS) pnl_pct = round(-raw if bearish else raw, 2) return {**trade, "current_price": current, "pnl_pct": pnl_pct} enriched = [_with_pnl(t) for t in all_trades] priced = [t for t in enriched if t.get("pnl_pct") is not None] winners = sorted(priced, key=lambda t: t.get("pnl_pct", 0), reverse=True)[:limit_movers] losers = sorted(priced, key=lambda t: t.get("pnl_pct", 0))[:limit_movers] def _with_traces(trade: Dict) -> Dict: pid = trade.get("pattern_id", "") run_id = trade.get("run_id", "") sc = get_scoring_trace(run_id, pid) if run_id and pid else None sg = get_suggestion_trace(pid) if pid else None history = get_pattern_scoring_history(pid, limit=5) if pid else [] return { **trade, "scoring_context": sc, "suggestion_context": sg, "score_history_count": len(history), "score_trend": [h["output"].get("score") for h in reversed(history)] if history else [], } return { "total_trades": len(all_trades), "priced_count": len(priced), "avg_pnl_pct": (sum(t.get("pnl_pct", 0) for t in priced) / len(priced)) if priced else None, "winners": [_with_traces(t) for t in winners], "losers": [_with_traces(t) for t in losers], "all_trades": enriched, } def save_ai_report( days: int, stats: Dict[str, Any], winners: List[Dict], losers: List[Dict], report: Dict[str, Any], report_type: str = "portfolio", ) -> int: conn = get_conn() cur = conn.execute( """INSERT INTO ai_reports (report_type, days, stats_json, winners_json, losers_json, report_json) VALUES (?, ?, ?, ?, ?, ?)""", ( report_type, days, json.dumps(stats, ensure_ascii=False, default=str), json.dumps(winners, ensure_ascii=False, default=str), json.dumps(losers, ensure_ascii=False, default=str), json.dumps(report, ensure_ascii=False, default=str), ), ) row_id = cur.lastrowid conn.commit() conn.close() return row_id def _parse_report(row) -> Dict[str, Any]: d = dict(row) for field in ("stats_json", "winners_json", "losers_json", "report_json"): key = field.replace("_json", "") try: d[key] = json.loads(d.get(field) or "{}") except Exception: d[key] = {} return d def get_latest_portfolio_lessons() -> Optional[Dict[str, Any]]: """ Return the key lessons from the most recent portfolio report. Used by auto_cycle to inject feedback into the next AI cycle's prompts. Returns None if no report exists yet. """ conn = get_conn() row = conn.execute( """SELECT report_json, stats_json, created_at, days FROM ai_reports WHERE report_type='portfolio' ORDER BY created_at DESC LIMIT 1""" ).fetchone() conn.close() if not row: return None try: report = json.loads(row["report_json"] or "{}") stats = json.loads(row["stats_json"] or "{}") except Exception: return None if not report: return None return { "created_at": row["created_at"], "days": row["days"], "stats": stats, "headline": report.get("headline", ""), "winners_analysis": report.get("winners_analysis", ""), "losers_analysis": report.get("losers_analysis", ""), "key_lessons": report.get("key_lessons", []), "blind_spots": report.get("blind_spots", ""), "next_cycle_priorities": report.get("next_cycle_priorities", ""), "risk_watch": report.get("risk_watch", ""), } def list_ai_reports(report_type: str = "portfolio", limit: int = 20) -> List[Dict[str, Any]]: conn = get_conn() rows = conn.execute( """SELECT id, report_type, days, stats_json, report_json, created_at FROM ai_reports WHERE report_type=? ORDER BY created_at DESC LIMIT ?""", (report_type, limit), ).fetchall() conn.close() result = [] for row in rows: d = dict(row) for field in ("stats_json", "report_json"): key = field.replace("_json", "") try: d[key] = json.loads(d.get(field) or "{}") except Exception: d[key] = {} result.append(d) return result def get_ai_report(report_id: int) -> Optional[Dict[str, Any]]: conn = get_conn() row = conn.execute("SELECT * FROM ai_reports WHERE id=?", (report_id,)).fetchone() conn.close() return _parse_report(row) if row else None # ── Knowledge Base ───────────────────────────────────────────────────────────── def save_kb_entry(category: str, title: str, content: str, confidence: int = 50, tags: str = "", existing_id: Optional[int] = None) -> int: conn = get_conn() now = datetime.utcnow().isoformat() if existing_id: conn.execute("""UPDATE knowledge_base SET content=?, confidence=?, tags=?, last_confirmed_at=?, confirmation_count=confirmation_count+1 WHERE id=?""", (content, confidence, tags, now, existing_id)) conn.commit() conn.close() return existing_id cur = conn.execute("""INSERT INTO knowledge_base (category, title, content, confidence, confirmation_count, status, tags, first_seen_at, last_confirmed_at) VALUES (?,?,?,?,1,'active',?,?,?)""", (category, title, content, confidence, tags, now, now)) new_id = cur.lastrowid conn.commit() conn.close() return new_id def get_kb_entries(status: str = "active") -> List[Dict[str, Any]]: conn = get_conn() rows = conn.execute( "SELECT * FROM knowledge_base WHERE status=? ORDER BY confidence DESC, last_confirmed_at DESC", (status,) ).fetchall() conn.close() return [dict(r) for r in rows] def get_all_kb_entries() -> List[Dict[str, Any]]: conn = get_conn() rows = conn.execute( "SELECT * FROM knowledge_base ORDER BY confidence DESC, last_confirmed_at DESC" ).fetchall() conn.close() return [dict(r) for r in rows] def update_kb_entry_status(entry_id: int, status: str): conn = get_conn() conn.execute("UPDATE knowledge_base SET status=? WHERE id=?", (status, entry_id)) conn.commit() conn.close() # ── Reasoning State ──────────────────────────────────────────────────────────── def save_reasoning_state(narrative: str, synthesis: Dict[str, Any], sources_count: int = 0, reports_used: int = 0, trades_analyzed: int = 0) -> int: conn = get_conn() cur_row = conn.execute( "SELECT COALESCE(MAX(version), 0) as v FROM reasoning_state" ).fetchone() next_version = (cur_row["v"] if cur_row else 0) + 1 cur = conn.execute("""INSERT INTO reasoning_state (version, narrative, synthesis_json, sources_count, reports_used, trades_analyzed, created_at) VALUES (?,?,?,?,?,?,datetime('now'))""", (next_version, narrative, json.dumps(synthesis), sources_count, reports_used, trades_analyzed)) new_id = cur.lastrowid conn.commit() conn.close() return new_id def get_latest_reasoning_state() -> Optional[Dict[str, Any]]: conn = get_conn() row = conn.execute( "SELECT * FROM reasoning_state ORDER BY version DESC LIMIT 1" ).fetchone() conn.close() if not row: return None d = dict(row) try: d["synthesis"] = json.loads(d.get("synthesis_json") or "{}") except Exception: d["synthesis"] = {} return d def get_reasoning_history(limit: int = 10) -> List[Dict[str, Any]]: conn = get_conn() rows = conn.execute( "SELECT id, version, sources_count, reports_used, trades_analyzed, created_at FROM reasoning_state ORDER BY version DESC LIMIT ?", (limit,) ).fetchall() conn.close() return [dict(r) for r in rows] def get_reasoning_state_by_id(state_id: int) -> Optional[Dict[str, Any]]: conn = get_conn() row = conn.execute("SELECT * FROM reasoning_state WHERE id=?", (state_id,)).fetchone() conn.close() if not row: return None d = dict(row) try: d["synthesis"] = json.loads(d.get("synthesis_json") or "{}") except Exception: d["synthesis"] = {} return d def delete_ai_report(report_id: int) -> bool: conn = get_conn() cur = conn.execute("DELETE FROM ai_reports WHERE id=?", (report_id,)) conn.commit() conn.close() return cur.rowcount > 0 def delete_reasoning_state(state_id: int) -> bool: conn = get_conn() cur = conn.execute("DELETE FROM reasoning_state WHERE id=?", (state_id,)) conn.commit() conn.close() return cur.rowcount > 0 def delete_kb_entry(entry_id: int) -> bool: conn = get_conn() cur = conn.execute("DELETE FROM knowledge_base WHERE id=?", (entry_id,)) conn.commit() conn.close() return cur.rowcount > 0 # ── IV History ──────────────────────────────────────────────────────────────── def save_iv_snapshot(ticker: str, recorded_date: str, iv_current: float, iv_30d=None, iv_60d=None, iv_90d=None) -> None: conn = get_conn() conn.execute( """INSERT OR REPLACE INTO iv_history (ticker, recorded_date, iv_current, iv_30d, iv_60d, iv_90d) VALUES (?, ?, ?, ?, ?, ?)""", (ticker.upper(), recorded_date, iv_current, iv_30d, iv_60d, iv_90d), ) conn.commit() conn.close() def get_iv_rank_percentile(ticker: str, current_iv: float, days: int = 252) -> Dict[str, Any]: conn = get_conn() rows = conn.execute( """SELECT iv_current FROM iv_history WHERE ticker=? AND iv_current IS NOT NULL AND iv_current > 0 ORDER BY recorded_date DESC LIMIT ?""", (ticker.upper(), days), ).fetchall() conn.close() if not rows: return {"iv_rank": None, "iv_percentile": None, "history_days": 0} hist = [r["iv_current"] for r in rows] iv_min = min(hist) iv_max = max(hist) iv_rank = ( round((current_iv - iv_min) / (iv_max - iv_min) * 100, 1) if iv_max > iv_min else 50.0 ) iv_percentile = round(sum(1 for v in hist if v < current_iv) / len(hist) * 100, 1) return { "iv_rank": iv_rank, "iv_percentile": iv_percentile, "history_days": len(hist), "iv_min_52w": round(iv_min * 100, 1), "iv_max_52w": round(iv_max * 100, 1), } def get_iv_history(ticker: str, days: int = 90) -> List[Dict]: conn = get_conn() rows = conn.execute( """SELECT recorded_date, iv_current, iv_30d, iv_60d, iv_90d FROM iv_history WHERE ticker=? AND iv_current IS NOT NULL ORDER BY recorded_date DESC LIMIT ?""", (ticker.upper(), days), ).fetchall() conn.close() return [dict(r) for r in rows] # ── IV Watchlist ────────────────────────────────────────────────────────────── def get_watchlist_tickers() -> List[str]: conn = get_conn() rows = conn.execute( "SELECT ticker FROM iv_watchlist WHERE is_active=1 ORDER BY added_by='builtin' DESC, added_date ASC" ).fetchall() conn.close() return [r["ticker"] for r in rows] def get_watchlist_entries() -> List[Dict]: conn = get_conn() rows = conn.execute( "SELECT ticker, added_date, added_by, is_active FROM iv_watchlist ORDER BY added_by, ticker" ).fetchall() conn.close() return [dict(r) for r in rows] def add_watchlist_ticker(ticker: str, added_by: str = "manual") -> bool: """Add ticker to watchlist. Returns True if newly inserted, False if already existed.""" conn = get_conn() existing = conn.execute("SELECT ticker, is_active FROM iv_watchlist WHERE ticker=?", (ticker.upper(),)).fetchone() if existing: if not existing["is_active"]: conn.execute("UPDATE iv_watchlist SET is_active=1, added_by=? WHERE ticker=?", (added_by, ticker.upper())) conn.commit() conn.close() return True conn.close() return False conn.execute( "INSERT INTO iv_watchlist (ticker, added_date, added_by) VALUES (?, date('now'), ?)", (ticker.upper(), added_by) ) conn.commit() conn.close() return True def remove_watchlist_ticker(ticker: str) -> bool: conn = get_conn() conn.execute("UPDATE iv_watchlist SET is_active=0 WHERE ticker=?", (ticker.upper(),)) changed = conn.total_changes > 0 conn.commit() conn.close() return changed # ── System Logs ─────────────────────────────────────────────────────────────── def log_system_event( level: str, source: str, message: str, cycle_id: Optional[str] = None, ticker: Optional[str] = None, details: Optional[Dict] = None, ) -> None: try: conn = get_conn() conn.execute( """INSERT INTO system_logs (level, source, cycle_id, ticker, message, details) VALUES (?, ?, ?, ?, ?, ?)""", ( level.upper(), source, cycle_id, ticker.upper() if ticker else None, message, json.dumps(details, default=str) if details else None, ), ) conn.commit() conn.close() except Exception: pass # Never raise from logging def get_system_logs( level: Optional[str] = None, source: Optional[str] = None, cycle_id: Optional[str] = None, ticker: Optional[str] = None, date_from: Optional[str] = None, date_to: Optional[str] = None, limit: int = 300, ) -> List[Dict]: conn = get_conn() clauses = [] params: List[Any] = [] if level: clauses.append("level = ?") params.append(level.upper()) if source: clauses.append("source LIKE ?") params.append(f"%{source}%") if cycle_id: clauses.append("cycle_id = ?") params.append(cycle_id) if ticker: clauses.append("ticker = ?") params.append(ticker.upper()) if date_from: clauses.append("ts >= ?") params.append(date_from) if date_to: clauses.append("ts <= ?") params.append(date_to + "T23:59:59") where = ("WHERE " + " AND ".join(clauses)) if clauses else "" rows = conn.execute( f"SELECT id, ts, level, source, cycle_id, ticker, message, details FROM system_logs {where} ORDER BY ts DESC LIMIT ?", params + [limit], ).fetchall() conn.close() return [dict(r) for r in rows] def clear_system_logs(older_than_days: int = 30) -> int: conn = get_conn() conn.execute(f"DELETE FROM system_logs WHERE ts < datetime('now', '-{older_than_days} days')") deleted = conn.total_changes conn.commit() conn.close() return deleted # ── Cycle Context Snapshots ─────────────────────────────────────────────────── def save_cycle_context_snapshot(run_id: str, context: dict) -> None: import json as _json conn = get_conn() conn.execute( "INSERT OR REPLACE INTO cycle_context_snapshots (run_id, context_json) VALUES (?, ?)", (run_id, _json.dumps(context, ensure_ascii=False, default=str)), ) conn.commit() conn.close() def get_cycle_context_snapshot(run_id: str) -> Optional[dict]: import json as _json conn = get_conn() row = conn.execute( "SELECT run_id, ts, context_json FROM cycle_context_snapshots WHERE run_id = ?", (run_id,) ).fetchone() conn.close() if not row: return None return {"run_id": row["run_id"], "ts": row["ts"], "context": _json.loads(row["context_json"])} def list_cycle_context_snapshots(limit: int = 30) -> list: conn = get_conn() rows = conn.execute( "SELECT run_id, ts FROM cycle_context_snapshots ORDER BY ts DESC LIMIT ?", (limit,) ).fetchall() conn.close() return [{"run_id": r["run_id"], "ts": r["ts"]} for r in rows] # ── Knowledge Base Decay ────────────────────────────────────────────────────── def decay_kb_confidence() -> int: """ Decrease confidence on KB entries past their expires_at or older than confidence_decay_days since last_confirmed_at. Archives entries at 0. Returns number of entries updated. """ conn = get_conn() c = conn.cursor() today_str = datetime.utcnow().date().isoformat() # Entries past expires_at → archive c.execute(""" UPDATE knowledge_base SET status = 'archived', confidence = 0 WHERE expires_at IS NOT NULL AND expires_at <= ? AND status = 'active' """, (today_str,)) expired = c.rowcount # Entries where days_since_confirmation > confidence_decay_days # Reduce confidence by 10 per overdue period rows = c.execute(""" SELECT id, confidence, last_confirmed_at, confidence_decay_days FROM knowledge_base WHERE status = 'active' AND last_confirmed_at IS NOT NULL """).fetchall() decayed = 0 for row in rows: r = dict(row) try: from datetime import date as _d last = _d.fromisoformat(r["last_confirmed_at"][:10]) days_since = (_d.today() - last).days decay_period = r["confidence_decay_days"] or 90 if days_since > decay_period: periods_overdue = days_since // decay_period new_conf = max(0, r["confidence"] - periods_overdue * 10) if new_conf != r["confidence"]: c.execute( "UPDATE knowledge_base SET confidence=? WHERE id=?", (new_conf, r["id"]) ) decayed += 1 if new_conf == 0: c.execute( "UPDATE knowledge_base SET status='archived' WHERE id=?", (r["id"],) ) except Exception: pass conn.commit() conn.close() return expired + decayed # ── Pattern Reliability ─────────────────────────────────────────────────────── def get_pattern_reliability(pattern_id: str = None) -> List[Dict]: """ Compute win_rate, avg_pnl, trade_count, reliability_score per pattern. Uses MATURE trades only (days_held >= 35% of horizon_days). If pattern_id is provided, returns single-item list for that pattern. """ import math from datetime import date as _date conn = get_conn() q = "SELECT * FROM trade_entry_prices WHERE pnl_pct IS NOT NULL" args: list = [] if pattern_id: q += " AND pattern_id = ?" args.append(pattern_id) rows = conn.execute(q, args).fetchall() conn.close() today = _date.today() mature_threshold = float(get_config("maturity_threshold_pct") or "35") / 100.0 by_pattern: Dict[str, list] = {} for row in rows: r = dict(row) try: entry = _date.fromisoformat(r["entry_date"]) days_held = (today - entry).days except Exception: days_held = 0 horizon = r.get("horizon_days") or 30 ratio = days_held / horizon if horizon else 0 if ratio < mature_threshold: continue by_pattern.setdefault(r["pattern_id"], []).append(r) result = [] for pid, trades in by_pattern.items(): pnls = [t["pnl_pct"] for t in trades if t.get("pnl_pct") is not None] if not pnls: continue wins = sum(1 for p in pnls if p > 0) win_rate = wins / len(pnls) avg_pnl = sum(pnls) / len(pnls) # Composite score: win_rate × log(n+1) — penalises small samples reliability = round(win_rate * math.log(len(pnls) + 1), 3) result.append({ "pattern_id": pid, "pattern_name": trades[0].get("pattern_name", pid), "trade_count": len(pnls), "win_rate": round(win_rate, 3), "win_rate_pct": round(win_rate * 100, 1), "avg_pnl_pct": round(avg_pnl, 2), "max_pnl_pct": round(max(pnls), 2), "max_loss_pct": round(min(pnls), 2), "reliability_score": reliability, }) result.sort(key=lambda x: -x["reliability_score"]) return result def get_all_pattern_reliability_map() -> Dict[str, Dict]: """Returns {pattern_id: reliability_dict} for fast lookup.""" return {r["pattern_id"]: r for r in get_pattern_reliability()} # ── Calibration ─────────────────────────────────────────────────────────────── def get_calibration_data(days: int = 365) -> Dict: """ Compare predicted probability (stored at score time) vs realized outcome (pnl_pct > 0 at maturity) to compute Brier score and calibration buckets. """ import math from datetime import date as _date conn = get_conn() # Join pattern_scores (has predicted probability) with trade_entry_prices (has realized P&L) rows = conn.execute(""" SELECT psh.pattern_id, psh.score, tep.pnl_pct, tep.entry_date, tep.horizon_days, cp.probability as predicted_prob FROM pattern_score_history psh JOIN trade_entry_prices tep ON tep.pattern_id = psh.pattern_id LEFT JOIN custom_patterns cp ON cp.id = psh.pattern_id WHERE tep.pnl_pct IS NOT NULL AND cp.probability IS NOT NULL AND tep.entry_date >= date('now', ?) """, (f"-{days} days",)).fetchall() conn.close() today = _date.today() pairs = [] for row in rows: r = dict(row) try: entry = _date.fromisoformat(r["entry_date"]) dh = (today - entry).days except Exception: dh = 0 horizon = r.get("horizon_days") or 30 if dh / horizon < 0.35: continue # only mature pred = float(r["predicted_prob"] or 0) realized = 1.0 if (r["pnl_pct"] or 0) > 0 else 0.0 pairs.append({"predicted": pred, "realized": realized}) if not pairs: return {"pairs": [], "brier_score": None, "buckets": [], "sample_size": 0} # Brier score brier = sum((p["predicted"] - p["realized"]) ** 2 for p in pairs) / len(pairs) # Calibration buckets (deciles) buckets = [] for low in [i / 10 for i in range(0, 10)]: high = low + 0.1 bucket_pairs = [p for p in pairs if low <= p["predicted"] < high] if bucket_pairs: actual_rate = sum(p["realized"] for p in bucket_pairs) / len(bucket_pairs) buckets.append({ "predicted_range": f"{int(low*100)}-{int(high*100)}%", "predicted_mid": round((low + high) / 2, 2), "actual_rate": round(actual_rate, 3), "count": len(bucket_pairs), "bias": round(actual_rate - (low + high) / 2, 3), }) return { "pairs": pairs, "brier_score": round(brier, 4), "buckets": buckets, "sample_size": len(pairs), "interpretation": ( "Bien calibré" if brier < 0.15 else "Modérément calibré" if brier < 0.25 else "Surconfiant ou mal calibré" ), } # ╔══════════════════════════════════════════════════════════════════════════════╗ # ║ PHASE 3 — Portfolio Risk Engine ║ # ╚══════════════════════════════════════════════════════════════════════════════╝ # Risk factor → (asset_classes, trigger_keywords) _RISK_FACTOR_MAP = { "géopolitique": { "asset_classes": {"energy", "metals", "agriculture"}, "triggers": {"military", "sanctions", "trade_war", "political_speech"}, }, "inflation": { "asset_classes": {"energy", "metals", "agriculture", "forex"}, "triggers": {"energy", "resource_scarcity", "trade_war"}, }, "récession": { "asset_classes": {"indices", "equities", "rates"}, "triggers": {"financial_crisis", "elections"}, }, "liquidité": { "asset_classes": {"indices", "equities", "rates"}, "triggers": {"financial_crisis", "health_crisis"}, }, "dollar": { "asset_classes": {"forex", "metals"}, "triggers": {"sanctions", "financial_crisis", "trade_war"}, }, } def _classify_risk_factors(asset_class: str, triggers: List[str]) -> List[str]: """Return list of risk factors for a trade given its asset_class and pattern triggers.""" ac = (asset_class or "").lower() trg_set = {t.lower() for t in (triggers or [])} factors = [] for factor, cfg in _RISK_FACTOR_MAP.items(): if ac in cfg["asset_classes"] or trg_set & cfg["triggers"]: factors.append(factor) return factors or ["autre"] # ── Sprint 3.1 — Portfolio Exposure ────────────────────────────────────────── def get_portfolio_exposure() -> Dict: """ Returns exposure by asset class and by risk factor for open positions, plus P&L timeline and concentration alerts. """ conn = get_conn() trades = conn.execute( "SELECT * FROM portfolio WHERE status='open'" ).fetchall() conn.close() by_class: Dict[str, Dict] = {} by_factor: Dict[str, Dict] = {} total_capital = 0.0 for row in trades: t = dict(row) ac = (t.get("asset_class") or "autre").lower() cap = float(t.get("capital_invested") or 0) total_capital += cap if ac not in by_class: by_class[ac] = {"capital": 0.0, "trade_count": 0, "trades": []} by_class[ac]["capital"] += cap by_class[ac]["trade_count"] += 1 by_class[ac]["trades"].append(t.get("id")) # Pattern triggers for risk factor classification triggers: List[str] = [] try: conn2 = get_conn() pat_row = conn2.execute( "SELECT triggers FROM custom_patterns WHERE id=?", (t.get("geo_trigger") or "",) ).fetchone() conn2.close() if pat_row and pat_row["triggers"]: triggers = json.loads(pat_row["triggers"] or "[]") except Exception: pass factors = _classify_risk_factors(ac, triggers) for f in factors: if f not in by_factor: by_factor[f] = {"capital": 0.0, "trade_count": 0, "trades": []} by_factor[f]["capital"] += cap by_factor[f]["trade_count"] += 1 by_factor[f]["trades"].append(t.get("id")) # Compute percentages + concentration alerts alerts = [] for ac, info in by_class.items(): pct = round(info["capital"] / total_capital * 100, 1) if total_capital else 0 info["pct_of_portfolio"] = pct if pct > 40: alerts.append({ "type": "concentration_class", "level": "high" if pct > 60 else "warning", "message": f"Concentration élevée sur {ac.upper()}: {pct}% du capital", "asset_class": ac, "pct": pct, }) for factor, info in by_factor.items(): pct = round(info["capital"] / total_capital * 100, 1) if total_capital else 0 info["pct_of_portfolio"] = pct if pct > 50: alerts.append({ "type": "concentration_factor", "level": "high" if pct > 70 else "warning", "message": f"Risque concentré sur facteur '{factor}': {pct}% du capital", "factor": factor, "pct": pct, }) return { "by_class": by_class, "by_factor": by_factor, "total_capital": total_capital, "open_trade_count": len(trades), "concentration_alerts": alerts, } def get_pnl_timeline(days: int = 90) -> List[Dict]: """ Returns daily aggregated P&L from trade_entry_prices (closed/mature trades). Used for portfolio equity curve. """ conn = get_conn() rows = conn.execute(""" SELECT entry_date, SUM(pnl_pct * capital_invested / 100) as daily_pnl_abs, AVG(pnl_pct) as avg_pnl_pct, COUNT(*) as trade_count FROM trade_entry_prices WHERE pnl_pct IS NOT NULL AND entry_date >= date('now', ?) GROUP BY entry_date ORDER BY entry_date ASC """, (f"-{days} days",)).fetchall() conn.close() cumulative = 0.0 result = [] for row in rows: r = dict(row) cumulative += r.get("daily_pnl_abs") or 0 r["cumulative_pnl_abs"] = round(cumulative, 2) result.append(r) return result # ── Sprint 3.2 — Risk Cluster Engine ──────────────────────────────────────── def get_risk_clusters() -> Dict: """ Classify all open trades by risk factor, compute exposure per factor, detect saturation (>50%), and return cluster data for the scoring prompt. """ exposure = get_portfolio_exposure() by_factor = exposure["by_factor"] total = exposure["total_capital"] clusters = [] saturated_factors = [] for factor, info in by_factor.items(): pct = info.get("pct_of_portfolio", 0) saturated = pct > 50 if saturated: saturated_factors.append(factor) clusters.append({ "factor": factor, "capital": round(info["capital"], 2), "pct_of_portfolio": pct, "trade_count": info["trade_count"], "saturated": saturated, }) clusters.sort(key=lambda x: -x["pct_of_portfolio"]) return { "clusters": clusters, "saturated_factors": saturated_factors, "total_capital": total, "risk_prompt_context": _build_risk_cluster_prompt(clusters, saturated_factors), } def _build_risk_cluster_prompt(clusters: List[Dict], saturated: List[str]) -> str: if not clusters: return "" lines = ["## ⚠ ÉTAT DU PORTEFEUILLE — Concentration des risques"] for c in clusters[:5]: sat_mark = " 🔴 SATURÉ" if c["saturated"] else "" lines.append(f" - Facteur '{c['factor']}': {c['pct_of_portfolio']}% du capital ({c['trade_count']} trades){sat_mark}") if saturated: lines.append( f"\n⚠ CONSIGNE SCORING: Les facteurs [{', '.join(saturated)}] sont SATURÉS. " "Pénaliser de 15 points les patterns dépendants de ces facteurs. " "Favoriser les patterns sur d'autres facteurs pour diversifier." ) return "\n".join(lines) def get_pattern_correlations() -> Dict: """ Compute Pearson correlation of P&L between pattern pairs with ≥3 mature trades each. Returns correlation matrix and sorted pair list. """ import math from datetime import date as _d conn = get_conn() rows = conn.execute(""" SELECT tep.pattern_id, tep.pnl_pct, tep.entry_date, tep.horizon_days, cp.name as pattern_name FROM trade_entry_prices tep LEFT JOIN custom_patterns cp ON cp.id = tep.pattern_id WHERE tep.pnl_pct IS NOT NULL """).fetchall() conn.close() today = _d.today() by_pattern: Dict[str, list] = {} names: Dict[str, str] = {} for row in rows: r = dict(row) pid = r["pattern_id"] try: entry = _d.fromisoformat(r["entry_date"]) days_held = (today - entry).days except Exception: days_held = 0 horizon = r.get("horizon_days") or 30 if days_held / horizon < 0.35: continue # mature only by_pattern.setdefault(pid, []).append(float(r["pnl_pct"])) names[pid] = r.get("pattern_name") or pid # Keep patterns with ≥3 trades patterns = {pid: pnls for pid, pnls in by_pattern.items() if len(pnls) >= 3} def pearson(a: list, b: list) -> Optional[float]: n = min(len(a), len(b)) if n < 2: return None xa, xb = a[:n], b[:n] ma, mb = sum(xa) / n, sum(xb) / n num = sum((xa[i] - ma) * (xb[i] - mb) for i in range(n)) da = math.sqrt(sum((x - ma) ** 2 for x in xa)) db = math.sqrt(sum((x - mb) ** 2 for x in xb)) if da * db == 0: return None return round(num / (da * db), 3) pids = list(patterns.keys()) pairs = [] matrix: Dict[str, Dict[str, Optional[float]]] = {} for i, pa in enumerate(pids): matrix[pa] = {} for pb in pids: if pa == pb: matrix[pa][pb] = 1.0 else: corr = pearson(patterns[pa], patterns[pb]) matrix[pa][pb] = corr for pb in pids[i + 1:]: corr = matrix[pa].get(pb) if corr is not None: pairs.append({ "pattern_a": pa, "name_a": names.get(pa, pa), "pattern_b": pb, "name_b": names.get(pb, pb), "correlation": corr, "interpretation": ( "Très corrélés — risque concentré" if abs(corr) > 0.7 else "Modérément corrélés" if abs(corr) > 0.4 else "Faiblement corrélés" ), }) pairs.sort(key=lambda x: -abs(x["correlation"])) return { "matrix": matrix, "pairs": pairs[:20], "pattern_names": names, "pattern_count": len(pids), } # ── Sprint 3.3 — Kelly Fractional Sizing ──────────────────────────────────── def compute_kelly_sizing( pattern_id: str, capital_available: float = 10000.0, fractional: float = 0.33, ) -> Dict: """ Compute fractional Kelly position sizing for a pattern. f* = (p × G - (1-p)) / G where G = expected gain as multiplier. Fractional Kelly = fractional × f* (default 33% = between 25-50% institutional norm). Adjusted for risk cluster saturation. """ conn = get_conn() pat = conn.execute("SELECT * FROM custom_patterns WHERE id=?", (pattern_id,)).fetchone() conn.close() if not pat: return {"error": "Pattern not found"} p = dict(pat) prob = float(p.get("probability") or 0.5) expected_move = float(p.get("expected_move_pct") or 50) / 100 # as decimal # G = gain multiplier (if trade wins, return expected_move; if loses, -1) G = max(expected_move, 0.01) kelly_full = (prob * G - (1 - prob)) / G kelly_full = max(0.0, kelly_full) # never negative kelly_frac = kelly_full * fractional # Risk cluster adjustment: halve if saturated ac = (p.get("asset_class") or "").lower() triggers_raw = p.get("triggers") or "[]" try: triggers_list = json.loads(triggers_raw) if isinstance(triggers_raw, str) else triggers_raw except Exception: triggers_list = [] factors = _classify_risk_factors(ac, triggers_list) clusters = get_risk_clusters() saturated = set(clusters.get("saturated_factors", [])) cluster_adjusted = kelly_frac cluster_adjustment_reason = None if factors and saturated & set(factors): cluster_adjusted = kelly_frac / 2 cluster_adjustment_reason = f"Facteur {'|'.join(saturated & set(factors))} saturé → sizing ÷ 2" suggested_capital = round(capital_available * cluster_adjusted, 2) suggested_capital_display = min(suggested_capital, capital_available * 0.25) # hard cap 25% # Reliability adjustment (if available) reliability = get_pattern_reliability(pattern_id=pattern_id) reliability_adjustment = None if reliability: rel = reliability[0] if rel["trade_count"] >= 5 and rel["win_rate"] < 0.4: suggested_capital_display *= 0.5 reliability_adjustment = f"Win rate historique faible ({rel['win_rate_pct']}%) → sizing ÷ 2" return { "pattern_id": pattern_id, "pattern_name": p.get("name"), "probability": prob, "expected_move_pct": round(expected_move * 100, 1), "kelly_full": round(kelly_full, 4), "kelly_fractional": round(kelly_frac, 4), "fractional_pct": round(fractional * 100), "cluster_adjusted_kelly": round(cluster_adjusted, 4), "risk_factors": factors, "saturated_factors": list(saturated & set(factors)), "cluster_adjustment_reason": cluster_adjustment_reason, "reliability_adjustment": reliability_adjustment, "suggested_capital_pct": round(cluster_adjusted * 100, 1), "suggested_capital_eur": round(suggested_capital_display, 0), "capital_available": capital_available, "explanation": ( f"Kelly complet = {kelly_full*100:.1f}% → Kelly fractionnel ({fractional*100:.0f}%) " f"= {kelly_frac*100:.1f}%" + (f" → Ajusté cluster = {cluster_adjusted*100:.1f}%" if cluster_adjustment_reason else "") ), } # ── Sprint 3.4 — Risk Dashboard ────────────────────────────────────────────── def get_risk_dashboard() -> Dict: """ Full portfolio risk snapshot: concentration, diversification score, expected drawdown estimate, and auto-recommendation. """ import math exposure = get_portfolio_exposure() clusters = get_risk_clusters() corr_data = get_pattern_correlations() by_class = exposure["by_class"] by_factor = exposure["by_factor"] total = exposure["total_capital"] alerts = exposure["concentration_alerts"] # Herfindahl-Hirschman Index (HHI) as concentration measure # HHI = sum of (share_i)^2. HHI=1 fully concentrated, HHI=1/N fully diversified shares = [info["pct_of_portfolio"] / 100 for info in by_class.values() if info.get("pct_of_portfolio")] hhi = sum(s ** 2 for s in shares) if shares else 0 n_classes = len(shares) hhi_min = 1 / n_classes if n_classes > 0 else 1 # Effective N = 1/HHI (Herfindahl diversity = N effective independent positions) effective_n = round(1 / hhi, 2) if hhi > 0 else n_classes max_possible_n = n_classes if n_classes > 0 else 1 diversification_score = round(min(effective_n / max(max_possible_n, 1), 1.0) * 100, 1) # Expected drawdown estimate: weighted by concentration # Simple model: if one factor is at X% and has 40% historical loss → max drawdown = X% × 40% FACTOR_DRAWDOWN = { "géopolitique": 0.40, # high volatility "inflation": 0.30, "récession": 0.45, "liquidité": 0.35, "dollar": 0.25, "autre": 0.30, } expected_drawdown_pct = 0.0 for factor, info in by_factor.items(): w = info.get("pct_of_portfolio", 0) / 100 dd = FACTOR_DRAWDOWN.get(factor, 0.30) expected_drawdown_pct += w * dd * 100 # High-correlation pairs count high_corr_pairs = [p for p in corr_data.get("pairs", []) if abs(p["correlation"]) > 0.7] # Auto-recommendation recommendation = _build_risk_recommendation( clusters.get("saturated_factors", []), diversification_score, round(expected_drawdown_pct, 1), alerts, high_corr_pairs, ) return { "exposure_by_class": {k: {**v, "pct_of_portfolio": v.get("pct_of_portfolio", 0)} for k, v in by_class.items()}, "exposure_by_factor": {k: {**v, "pct_of_portfolio": v.get("pct_of_portfolio", 0)} for k, v in by_factor.items()}, "total_capital": total, "open_trades": exposure["open_trade_count"], "hhi": round(hhi, 4), "diversification_score": diversification_score, "effective_n_positions": effective_n, "expected_drawdown_pct": round(expected_drawdown_pct, 1), "concentration_alerts": alerts, "high_correlation_pairs": high_corr_pairs[:5], "saturated_factors": clusters.get("saturated_factors", []), "risk_clusters": clusters.get("clusters", []), "recommendation": recommendation, } # ╔══════════════════════════════════════════════════════════════════════════════╗ # ║ PHASE 4 — Moteur Probabiliste & Apprentissage Automatique ║ # ╚══════════════════════════════════════════════════════════════════════════════╝ # ── Sprint 4.1 — Bayesian Updating ─────────────────────────────────────────── def update_bayesian_posteriors() -> int: """ Met à jour les posteriors Beta(α,β) de chaque pattern selon ses trades matures. Prior faible : α₀=1, β₀=1 (Laplace smoothing). Posterior : α = 1 + wins, β = 1 + losses → win_rate bayésien = α/(α+β) Retourne le nombre de patterns mis à jour. """ import math as _math from datetime import date as _date conn = get_conn() rows = conn.execute( "SELECT pattern_id, pnl_pct, entry_date, horizon_days FROM trade_entry_prices WHERE pnl_pct IS NOT NULL" ).fetchall() conn.close() today = _date.today() by_pattern: Dict[str, list] = {} for row in rows: r = dict(row) try: entry = _date.fromisoformat(r["entry_date"]) days_held = (today - entry).days except Exception: continue horizon = r.get("horizon_days") or 30 if days_held / max(horizon, 1) < 0.35: continue # trades immatures exclus by_pattern.setdefault(r["pattern_id"], []).append(float(r["pnl_pct"] or 0)) if not by_pattern: return 0 conn = get_conn() c = conn.cursor() updated = 0 now_iso = datetime.utcnow().isoformat() for pid, pnls in by_pattern.items(): n = len(pnls) wins = sum(1 for p in pnls if p > 0) losses = n - wins alpha = 1.0 + wins # posterior alpha beta = 1.0 + losses # posterior beta bayes_wr = alpha / (alpha + beta) c.execute(""" UPDATE custom_patterns SET bayesian_alpha=?, bayesian_beta=?, bayesian_win_rate=?, bayesian_updated_at=?, bayesian_sample_size=? WHERE id=? """, (round(alpha, 1), round(beta, 1), round(bayes_wr, 4), now_iso, n, pid)) if c.rowcount: updated += 1 conn.commit() conn.close() return updated def get_bayesian_posteriors() -> List[Dict]: """ Retourne tous les patterns avec leurs posteriors bayésiens + intervalle de crédibilité 95%. CI 95% via approximation normale : ±1.96 × σ = ±1.96 × sqrt(αβ / (α+β)²(α+β+1)) """ import math as _math conn = get_conn() rows = conn.execute(""" SELECT id, name, probability, bayesian_alpha, bayesian_beta, bayesian_win_rate, bayesian_sample_size, bayesian_updated_at, asset_class, is_active FROM custom_patterns WHERE is_active=1 ORDER BY bayesian_sample_size DESC, name """).fetchall() conn.close() result = [] for row in rows: r = dict(row) alpha = r.get("bayesian_alpha") or 1.0 beta = r.get("bayesian_beta") or 1.0 n = alpha + beta # 95% credible interval (Beta distribution approximation) variance = (alpha * beta) / (n * n * (n + 1)) std = _math.sqrt(max(variance, 0)) bayes_wr = r.get("bayesian_win_rate") or alpha / n lower = max(0.0, bayes_wr - 1.96 * std) upper = min(1.0, bayes_wr + 1.96 * std) sample_size = r.get("bayesian_sample_size") or 0 # Écart entre prior GPT et posterior bayésien prior = r.get("probability") or 0.5 drift = round(bayes_wr - prior, 3) result.append({ "pattern_id": r["id"], "pattern_name": r["name"], "asset_class": r.get("asset_class"), "prior_probability": round(prior, 3), "bayesian_win_rate": round(bayes_wr, 3), "bayesian_win_rate_pct": round(bayes_wr * 100, 1), "lower_ci_95": round(lower, 3), "upper_ci_95": round(upper, 3), "ci_width": round(upper - lower, 3), "sample_size": sample_size, "alpha": alpha, "beta": beta, "prior_vs_posterior_drift": drift, "updated_at": r.get("bayesian_updated_at"), "confidence_level": ( "haute" if sample_size >= 10 else "moyenne" if sample_size >= 5 else "faible" ), }) return result # ── Sprint 4.2 — Détection automatique de régimes ──────────────────────────── _GAUGE_FEATURES = [ "vix", "slope_10y3m", "dxy", "brent", "gold", "copper", "spx_vs_200d" ] _CLUSTER_LABELS = { 0: "Stress Géopolitique", 1: "Expansion Tranquille", 2: "Récession / Risk-Off", 3: "Stagflation / Inflation", 4: "Transition / Incertain", } def _kmeans_numpy(X, n_clusters: int = 4, max_iter: int = 100, seed: int = 42): """K-Means minimal en numpy pur (pas de sklearn nécessaire).""" import numpy as np rng = np.random.default_rng(seed) idx = rng.choice(len(X), size=n_clusters, replace=False) centroids = X[idx].copy() for _ in range(max_iter): dists = np.linalg.norm(X[:, None, :] - centroids[None, :, :], axis=2) labels = np.argmin(dists, axis=1) new_centroids = np.array([ X[labels == k].mean(axis=0) if (labels == k).any() else centroids[k] for k in range(n_clusters) ]) if np.allclose(centroids, new_centroids, atol=1e-6): break centroids = new_centroids return labels, centroids def detect_and_save_regime_clusters(n_clusters: int = 4, days: int = 180) -> Dict: """ Applique K-Means sur l'historique des gauges macro (VIX, pente, DXY…). Sauvegarde l'assignation courante dans regime_clusters. Retourne le cluster actuel + les centroïdes labellisés. """ import numpy as np import json as _json conn = get_conn() rows = conn.execute(""" SELECT timestamp, dominant, gauges_summary_json FROM macro_regime_history WHERE timestamp >= datetime('now', ?) ORDER BY timestamp ASC """, (f"-{days} days",)).fetchall() conn.close() if len(rows) < max(n_clusters * 2, 8): return {"error": "Données insuffisantes", "min_required": max(n_clusters * 2, 8)} snapshots = [] timestamps = [] dominants = [] for row in rows: r = dict(row) try: gauges = _json.loads(r.get("gauges_summary_json") or "{}") except Exception: continue vec = [] for feat in _GAUGE_FEATURES: g = gauges.get(feat, {}) val = g.get("value") if isinstance(g, dict) else g vec.append(float(val) if val is not None else 0.0) snapshots.append(vec) timestamps.append(r["timestamp"]) dominants.append(r.get("dominant", "incertain")) if not snapshots: return {"error": "Aucune donnée de gauges exploitable"} X = np.array(snapshots, dtype=float) # Normalisation z-score par feature mean = X.mean(axis=0) std = X.std(axis=0) std[std == 0] = 1.0 X_norm = (X - mean) / std # Anomaly detection : points > 3σ du vecteur global global_dist = np.linalg.norm(X_norm, axis=1) anomaly_threshold = global_dist.mean() + 3 * global_dist.std() labels, centroids = _kmeans_numpy(X_norm, n_clusters=n_clusters) # Labelliser les clusters selon le dominant le plus fréquent cluster_regimes: Dict[int, str] = {} for k in range(n_clusters): idxs = [i for i, l in enumerate(labels) if l == k] if idxs: dom_counts: Dict[str, int] = {} for i in idxs: d = dominants[i] dom_counts[d] = dom_counts.get(d, 0) + 1 cluster_regimes[k] = max(dom_counts, key=dom_counts.get) # Sauvegarder le snapshot le plus récent last_idx = len(labels) - 1 current_cluster = int(labels[last_idx]) current_anomaly = bool(global_dist[last_idx] > anomaly_threshold) conn = get_conn() conn.execute(""" INSERT INTO regime_clusters (timestamp, cluster_id, cluster_label, dominant_regime, gauges_json, anomaly_flag) VALUES (?, ?, ?, ?, ?, ?) """, ( timestamps[last_idx], current_cluster, _CLUSTER_LABELS.get(current_cluster, f"Cluster {current_cluster}"), cluster_regimes.get(current_cluster, dominants[last_idx]), _json.dumps({f: round(float(snapshots[last_idx][i]), 3) for i, f in enumerate(_GAUGE_FEATURES)}), int(current_anomaly), )) conn.commit() conn.close() # Statistiques par cluster cluster_stats = {} for k in range(n_clusters): k_idxs = [i for i, l in enumerate(labels) if l == k] cluster_stats[k] = { "cluster_id": k, "label": _CLUSTER_LABELS.get(k, f"Cluster {k}"), "dominant_regime": cluster_regimes.get(k, "incertain"), "count": len(k_idxs), "pct": round(len(k_idxs) / len(labels) * 100, 1), "centroid": {f: round(float(centroids[k][i]), 3) for i, f in enumerate(_GAUGE_FEATURES)}, } return { "current_cluster": current_cluster, "current_label": _CLUSTER_LABELS.get(current_cluster, f"Cluster {current_cluster}"), "current_anomaly": current_anomaly, "cluster_stats": list(cluster_stats.values()), "n_snapshots": len(labels), "features": _GAUGE_FEATURES, } def get_regime_cluster_history(days: int = 90) -> List[Dict]: """Retourne l'historique des assignations de clusters.""" conn = get_conn() rows = conn.execute(""" SELECT timestamp, cluster_id, cluster_label, dominant_regime, anomaly_flag, created_at FROM regime_clusters WHERE timestamp >= datetime('now', ?) ORDER BY timestamp DESC LIMIT 200 """, (f"-{days} days",)).fetchall() conn.close() return [dict(r) for r in rows] def get_regime_transition_matrix(days: int = 180) -> Dict: """ Calcule la matrice de transition entre clusters : P(cluster_j | cluster_i) = nb transitions i→j / nb fois où on était en i. """ rows = get_regime_cluster_history(days=days) if len(rows) < 4: return {"matrix": {}, "labels": {}, "n_transitions": 0} # rows trié DESC → inverser pour avoir l'ordre chronologique seq = list(reversed(rows)) cluster_ids = sorted({r["cluster_id"] for r in seq}) counts: Dict[int, Dict[int, int]] = {c: {d: 0 for d in cluster_ids} for c in cluster_ids} totals: Dict[int, int] = {c: 0 for c in cluster_ids} for i in range(len(seq) - 1): src = seq[i]["cluster_id"] dst = seq[i + 1]["cluster_id"] counts[src][dst] = counts[src].get(dst, 0) + 1 totals[src] = totals.get(src, 0) + 1 matrix = {} for src in cluster_ids: matrix[src] = {} total = totals.get(src, 0) for dst in cluster_ids: matrix[src][dst] = round(counts[src].get(dst, 0) / total, 3) if total else 0.0 labels = {k: _CLUSTER_LABELS.get(k, f"Cluster {k}") for k in cluster_ids} n_trans = sum(totals.values()) return {"matrix": matrix, "labels": labels, "cluster_ids": cluster_ids, "n_transitions": n_trans} # ── Sprint 4.3 — Embeddings sémantiques ────────────────────────────────────── def _cosine_similarity(a: List[float], b: List[float]) -> float: """Similarité cosinus entre deux vecteurs.""" import math as _math dot = sum(x * y for x, y in zip(a, b)) na = _math.sqrt(sum(x * x for x in a)) nb = _math.sqrt(sum(y * y for y in b)) if na == 0 or nb == 0: return 0.0 return dot / (na * nb) def get_or_create_pattern_embedding(pattern_id: str, text: str, api_key: str) -> Optional[List[float]]: """ Retourne l'embedding stocké pour ce pattern, ou le crée via OpenAI text-embedding-3-small. Le vecteur est stocké en JSON dans pattern_embeddings. """ import json as _json conn = get_conn() row = conn.execute( "SELECT embedding_json FROM pattern_embeddings WHERE pattern_id=?", (pattern_id,) ).fetchone() conn.close() if row: try: return _json.loads(row["embedding_json"]) except Exception: pass # Créer via OpenAI try: import urllib.request as _req import urllib.error as _uerr payload = _json.dumps({ "input": text[:8000], "model": "text-embedding-3-small", }).encode("utf-8") request = _req.Request( "https://api.openai.com/v1/embeddings", data=payload, headers={"Content-Type": "application/json", "Authorization": f"Bearer {api_key}"}, method="POST", ) with _req.urlopen(request, timeout=15) as resp: data = _json.loads(resp.read()) vec = data["data"][0]["embedding"] except Exception: return None # Persister vec_json = _json.dumps(vec) conn = get_conn() conn.execute(""" INSERT OR REPLACE INTO pattern_embeddings (pattern_id, embedding_json, model_version, updated_at) VALUES (?, ?, 'text-embedding-3-small', ?) """, (pattern_id, vec_json, datetime.utcnow().isoformat())) conn.commit() conn.close() return vec def max_cosine_similarity_vs_existing( candidate_text: str, existing_patterns: List[Dict], api_key: str, candidate_id: Optional[str] = None, ) -> float: """ Calcule la similarité cosinus maximale entre le candidat et les patterns existants. Retourne 0.0 si les embeddings ne sont pas disponibles (fallback Jaccard dans l'appelant). """ import json as _json if not api_key or not existing_patterns: return 0.0 # Obtenir l'embedding du candidat _tmp_id = candidate_id or f"_tmp_{hash(candidate_text) & 0xFFFFFF}" cand_vec = get_or_create_pattern_embedding(_tmp_id, candidate_text, api_key) if not cand_vec: return 0.0 max_sim = 0.0 conn = get_conn() for p in existing_patterns: pid = p.get("id") if not pid: continue row = conn.execute( "SELECT embedding_json FROM pattern_embeddings WHERE pattern_id=?", (pid,) ).fetchone() if row: try: vec = _json.loads(row["embedding_json"]) sim = _cosine_similarity(cand_vec, vec) if sim > max_sim: max_sim = sim except Exception: pass conn.close() return max_sim def get_all_pattern_embeddings_summary() -> List[Dict]: """Liste des patterns avec embedding disponible (pour l'Analytics Dashboard).""" conn = get_conn() rows = conn.execute(""" SELECT pe.pattern_id, pe.model_version, pe.updated_at, cp.name, cp.asset_class FROM pattern_embeddings pe LEFT JOIN custom_patterns cp ON cp.id = pe.pattern_id ORDER BY pe.updated_at DESC """).fetchall() conn.close() return [dict(r) for r in rows] def _build_risk_recommendation( saturated: List[str], div_score: float, exp_dd: float, alerts: List[Dict], high_corr: List[Dict], ) -> Dict: messages = [] level = "ok" if saturated: level = "danger" messages.append( f"Portefeuille sur-concentré sur les facteurs {', '.join(saturated)}. " "Les 2 prochains trades devraient cibler d'autres facteurs de risque." ) if div_score < 40: level = max(level, "warning") if level == "ok" else level messages.append( f"Score de diversification faible ({div_score}%). " "Envisager des positions sur des classes d'actifs non corrélées." ) if exp_dd > 25: level = "danger" messages.append( f"Drawdown attendu estimé à {exp_dd}%. " "Réduire l'exposition aux facteurs à haute volatilité." ) if high_corr: pair = high_corr[0] level = max(level, "warning") if level == "ok" else level messages.append( f"Attention : '{pair['name_a']}' et '{pair['name_b']}' sont fortement corrélés " f"({pair['correlation']:+.2f}) — ils ne représentent pas deux opportunités indépendantes." ) if not messages: messages.append( "Portefeuille bien diversifié. " "Continuer à varier les facteurs de risque à chaque nouveau trade." ) return { "level": level, "messages": messages, "summary": messages[0] if messages else "", } # ── Cycle reports ───────────────────────────────────────────────────────────── def save_cycle_report(run_id: str, report: Dict[str, Any]) -> None: import json as _json conn = get_conn() conn.execute( """INSERT OR REPLACE INTO cycle_reports (run_id, generated_at, macro_dominant, geo_score, patterns_added, trades_logged, trades_closed, pnl_snapshot_id, var_snapshot_id, full_report_json) VALUES (?, datetime('now'), ?, ?, ?, ?, ?, ?, ?, ?)""", ( run_id, report.get("macro_dominant"), report.get("geo_score"), report.get("patterns_added", 0), report.get("trades_logged", 0), report.get("trades_closed", 0), report.get("pnl_snapshot_id"), report.get("var_snapshot_id"), _json.dumps(report, ensure_ascii=False), ), ) conn.commit() conn.close() def get_cycle_reports(limit: int = 20) -> List[Dict[str, Any]]: conn = get_conn() rows = conn.execute( """SELECT run_id, generated_at, macro_dominant, geo_score, patterns_added, trades_logged, trades_closed FROM cycle_reports ORDER BY generated_at DESC LIMIT ?""", (limit,), ).fetchall() conn.close() return [dict(r) for r in rows] def get_cycle_report(run_id: str) -> Optional[Dict[str, Any]]: import json as _json conn = get_conn() row = conn.execute( "SELECT full_report_json, generated_at FROM cycle_reports WHERE run_id=?", (run_id,), ).fetchone() conn.close() if not row or not row["full_report_json"]: return None try: report = _json.loads(row["full_report_json"]) report["generated_at"] = row["generated_at"] return report except Exception: return None def get_latest_cycle_report() -> Optional[Dict[str, Any]]: import json as _json conn = get_conn() row = conn.execute( "SELECT full_report_json, generated_at FROM cycle_reports ORDER BY generated_at DESC LIMIT 1" ).fetchone() conn.close() if not row or not row["full_report_json"]: return None try: report = _json.loads(row["full_report_json"]) report["generated_at"] = row["generated_at"] return report except Exception: return None def get_trade_assessments(run_id: str) -> List[Dict[str, Any]]: import json as _json conn = get_conn() rows = conn.execute( "SELECT * FROM options_trade_assessments WHERE run_id=? ORDER BY id", (run_id,), ).fetchall() conn.close() result = [] for r in rows: d = dict(r) try: d["issues"] = _json.loads(d.get("issues_json") or "[]") except Exception: d["issues"] = [] result.append(d) return result def get_latest_trade_assessments(limit: int = 20) -> List[Dict[str, Any]]: """Return most recent assessments (one per trade_id) — for Journal badges.""" import json as _json conn = get_conn() rows = conn.execute( """SELECT a.* FROM options_trade_assessments a INNER JOIN (SELECT trade_id, MAX(id) as max_id FROM options_trade_assessments WHERE trade_id IS NOT NULL GROUP BY trade_id) m ON a.id = m.max_id ORDER BY a.id DESC LIMIT ?""", (limit,), ).fetchall() conn.close() result = [] for r in rows: d = dict(r) try: d["issues"] = _json.loads(d.get("issues_json") or "[]") except Exception: d["issues"] = [] result.append(d) return result