feat: Phase 4+5 — price discovery status + replay historique

Phase 4 — Price Discovery Status (la pièce maîtresse) :
- price_discovery.py (nouveau) : capture_price_snapshots() sauve les prix des tickers
  liés à chaque news scorée (energy→BZ=F/NG=F, metals→GC=F/HG=F, indices→^GSPC/IWM)
- compute_absorptions() mesure combien du mouvement attendu s'est déjà produit
  (status: not_yet_priced <30% / partially_priced 30-80% / fully_priced >80%)
- build_price_discovery_block() → bloc prompt avec opportunités classées
- database.py : table news_price_snapshots + save/get/purge fonctions
- auto_cycle.py : capture après ai_score_news_batch, compute avant suggestions,
  block injecté dans suggestion + scoring prompts + context snapshot
- ai_analyzer.py : param price_discovery_block dans suggest + score

Phase 5 — Replay historique :
- cycle.py : POST /api/cycle/contexts/{run_id}/replay — recharge le snapshot historique
  et relance suggest_patterns_from_market_context avec le contexte original
- useApi.ts : hook useReplayCycle
- SystemLogs.tsx : bouton "Rejouer ce cycle" dans onglet Contexte IA avec champ
  notes, résultats inline (liste des patterns générés), section price_discovery
  ouverte par défaut en rouge

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

backend/services/database.py

@@ -385,6 +385,19 @@ def init_db():
         context_json TEXT NOT NULL
     )""")
 
+    c.execute("""CREATE TABLE IF NOT EXISTS news_price_snapshots (
+        id INTEGER PRIMARY KEY AUTOINCREMENT,
+        article_hash TEXT NOT NULL,
+        article_title TEXT,
+        ticker TEXT NOT NULL,
+        expected_direction TEXT,
+        expected_impact_score REAL,
+        price_at_capture REAL,
+        captured_at TEXT NOT NULL DEFAULT (datetime('now')),
+        capture_cycle_id TEXT,
+        UNIQUE(article_hash, ticker)
+    )""")
+
     c.execute("""CREATE TABLE IF NOT EXISTS skipped_trades (
         id INTEGER PRIMARY KEY AUTOINCREMENT,
         run_id TEXT,
@@ -2130,6 +2143,57 @@ def list_cycle_context_snapshots(limit: int = 30) -> list:
     return [{"run_id": r["run_id"], "ts": r["ts"]} for r in rows]
 
 
+# ── News Price Snapshots (Phase 4 — Price Discovery) ─────────────────────────
+
+def save_news_price_snapshot(
+    article_hash: str,
+    article_title: str,
+    ticker: str,
+    expected_direction: str,
+    expected_impact_score: float,
+    price_at_capture: float,
+    cycle_id: str,
+) -> None:
+    conn = get_conn()
+    conn.execute(
+        """INSERT OR IGNORE INTO news_price_snapshots
+           (article_hash, article_title, ticker, expected_direction,
+            expected_impact_score, price_at_capture, capture_cycle_id)
+           VALUES (?, ?, ?, ?, ?, ?, ?)""",
+        (article_hash, article_title, ticker, expected_direction,
+         expected_impact_score, price_at_capture, cycle_id),
+    )
+    conn.commit()
+    conn.close()
+
+
+def get_news_price_snapshots(max_age_days: int = 7, min_age_minutes: float = 30.0) -> list:
+    conn = get_conn()
+    rows = conn.execute(
+        """SELECT article_hash, article_title, ticker, expected_direction,
+                  expected_impact_score, price_at_capture, captured_at, capture_cycle_id
+           FROM news_price_snapshots
+           WHERE captured_at >= datetime('now', ? || ' days')
+             AND captured_at <= datetime('now', ? || ' minutes')
+           ORDER BY captured_at DESC""",
+        (f"-{max_age_days}", f"-{int(min_age_minutes)}"),
+    ).fetchall()
+    conn.close()
+    return [dict(r) for r in rows]
+
+
+def purge_old_price_snapshots(older_than_days: int = 14) -> int:
+    conn = get_conn()
+    conn.execute(
+        "DELETE FROM news_price_snapshots WHERE captured_at < datetime('now', ? || ' days')",
+        (f"-{older_than_days}",),
+    )
+    deleted = conn.total_changes
+    conn.commit()
+    conn.close()
+    return deleted
+
+
 # ── Knowledge Base Decay ──────────────────────────────────────────────────────
 
 def decay_kb_confidence() -> int: