feat: Phase 2 + context log — FRED releases, cycle context snapshot, onglet Contexte IA

Phase 2 — Données macro FRED :
- fred_fetcher.py (nouveau) : 7 séries FRED (CPI, NFP, UNRATE, FEDFUNDS, GDP, ICSA,
  spread 10Y-2Y) avec détection direction bullish/bearish et block prompt formaté
- ai_analyzer.py : param fred_block dans suggest + score, injecté dans les deux prompts
- auto_cycle.py : fetch FRED non-bloquant avant la suggestion

Context log — Snapshot du contexte complet :
- database.py : table cycle_context_snapshots + save/get/list fonctions
- auto_cycle.py : sauvegarde le snapshot (meta, news partitionnées, FRED, tech, IV, quotes)
- cycle.py : GET /api/cycle/contexts + GET /api/cycle/contexts/{run_id}
- useApi.ts : hooks useCycleContextSnapshots + useCycleContextSnapshot
- SystemLogs.tsx : onglet "Contexte IA" avec liste de cycles et visualiseur JSON
  par section (cycle_meta, macro, news, FRED, tech) avec accordéon

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

backend/services/database.py

@@ -379,6 +379,12 @@ def init_db():
         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,
@@ -2090,6 +2096,40 @@ def clear_system_logs(older_than_days: int = 30) -> int:
     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: