feat: options technical agent — IV/skew/term structure validation per trade

- New options_technical_agent.py: rule engine (IVR, skew, term structure, flow)
  + GPT-4o narrative per trade; verdict OK/WARN/ALERT + fit_score
- options_trade_assessments table in DB for Journal badge persistence
- auto_cycle.py step 5.2: assess newly logged trades after log_trade_entries;
  results embedded in cycle report
- suggest_patterns_from_market_context: +iv_context param + explicit IV→strategy
  rules in prompt (IVR<30%→Long, 30-60%→Spread, >60%→no naked long, >80%→short)
- Pre-fetch iv_context at step 1.9 so suggestion step gets strategy rules
- reports.py: /api/reports/assessments/latest + /assessments/{run_id} endpoints
- RapportIA.tsx: "Validation Technique Options" section with per-trade IVBar,
  VerdictBadge, issues list, GPT-4o analysis, optimal strategy suggestion

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

backend/services/auto_cycle.py

@@ -300,6 +300,24 @@ def run_cycle_once(trigger: str = "auto") -> Dict[str, Any]:
         dominant = scenarios.get("dominant", "incertain")
         summary["dominant_regime"] = dominant
 
+        # ── Step 1.9: Pre-fetch IV context for strategy suggestion rules ──────
+        iv_context = ""
+        try:
+            from services.iv_engine import get_iv_context_for_prompt, IV_WATCHLIST
+            from services.database import get_mtm_trades_with_traces
+            _mtm_pre = get_mtm_trades_with_traces(days=90)
+            _trade_tickers_pre = list({
+                (t.get("underlying") or "").upper()
+                for t in _mtm_pre.get("all_trades", [])
+                if t.get("underlying")
+            })
+            _iv_tickers_pre = (_trade_tickers_pre + IV_WATCHLIST[:6])[:10]
+            iv_context = get_iv_context_for_prompt(_iv_tickers_pre)
+            if iv_context:
+                logger.info(f"[Cycle {run_id[:16]}] IV context pre-fetched for {len(_iv_tickers_pre)} tickers (suggestion step)")
+        except Exception as _e:
+            logger.warning(f"[Cycle] IV context pre-fetch failed (non-blocking): {_e}")
+
         # ── Step 2: Suggest new patterns ──────────────────────────────────────
         logger.info(f"[Cycle {run_id[:16]}] Step 2: suggesting patterns")
         _reliability_map = {}
@@ -317,6 +335,7 @@ def run_cycle_once(trigger: str = "auto") -> Dict[str, Any]:
                 news, quotes, calendar, macro_regime=macro_regime, geo_score=geo_score_obj,
                 portfolio_lessons=portfolio_lessons,
                 reliability_map=_reliability_map or None,
+                iv_context=iv_context,
             )
         except Exception as e:
             logger.warning(f"[Cycle] Suggestion step failed: {e}")
@@ -389,8 +408,7 @@ def run_cycle_once(trigger: str = "auto") -> Dict[str, Any]:
         except Exception as _re:
             logger.warning(f"[Cycle] Risk cluster context failed (non-blocking): {_re}")
 
-        # ── Step 3.6: Collect IV context ─────────────────────────────────────
-        iv_context = ""
+        # ── Step 3.6: Refresh IV context (with full trade+watchlist scope) ──────
         try:
             from services.iv_engine import get_iv_context_for_prompt, IV_WATCHLIST
             # Collect underlyings from current trade journal + default watchlist
@@ -521,8 +539,32 @@ def run_cycle_once(trigger: str = "auto") -> Dict[str, Any]:
         log_geo_alert(geo_score=geo_score_val, top_patterns=top_patterns_log,
                       news_count=len(news), run_id=scoring_run_id)
 
+        _options_assessment = None
         log_trade_entries(run_id=scoring_run_id, scored_patterns=scored, quotes=quotes)
 
+        # ── Step 5.2: Options Technical Agent — validate newly logged trades ──
+        try:
+            from services.options_technical_agent import assess_logged_trades, save_assessments_to_db
+            _options_assessment = assess_logged_trades(
+                scoring_run_id=scoring_run_id,
+                scored=scored,
+                ai_key=ai_key,
+            )
+            if _options_assessment and _options_assessment.get("assessments"):
+                save_assessments_to_db(_options_assessment["assessments"], scoring_run_id)
+                summary["options_assessment"] = {
+                    "n_ok": _options_assessment.get("n_ok", 0),
+                    "n_warn": _options_assessment.get("n_warn", 0),
+                    "n_alert": _options_assessment.get("n_alert", 0),
+                    "global_score": _options_assessment.get("global_score"),
+                }
+                logger.info(
+                    f"[OptionsTech] Assessment done — OK={_options_assessment.get('n_ok')} "
+                    f"WARN={_options_assessment.get('n_warn')} ALERT={_options_assessment.get('n_alert')}"
+                )
+        except Exception as _ota:
+            logger.warning(f"[OptionsTech] Agent failed (non-blocking): {_ota}")
+
         # ── Step 5.1: Portfolio monitor — conflict & concentration check ──────
         try:
             from services.portfolio_risk import analyze_simulation_portfolio
@@ -651,6 +693,7 @@ def run_cycle_once(trigger: str = "auto") -> Dict[str, Any]:
                 scoring_run_id=scoring_run_id,
                 portfolio_monitor=summary.get("portfolio_monitor"),
                 commentary=commentary,
+                options_assessment=_options_assessment,
             )
             if _cycle_report:
                 from services.database import save_cycle_report
@@ -780,6 +823,7 @@ def _generate_cycle_report(
     scoring_run_id: str,
     portfolio_monitor: Optional[Dict],
     commentary: Optional[str],
+    options_assessment: Optional[Dict] = None,
 ) -> Optional[Dict]:
     """
     Build the full cycle report dict:
@@ -987,6 +1031,15 @@ Réponds en JSON avec ce schéma EXACT:
              "summary": (s.get("summary") or "")[:120], "key_catalyst": s.get("key_catalyst", "")}
             for s in sorted(scored, key=lambda x: -(x.get("score") or 0))[:5]
         ],
+        # Options Technical Agent assessment
+        "options_technical": {
+            "global_assessment": (options_assessment or {}).get("global_assessment", ""),
+            "global_score": (options_assessment or {}).get("global_score"),
+            "n_ok": (options_assessment or {}).get("n_ok", 0),
+            "n_warn": (options_assessment or {}).get("n_warn", 0),
+            "n_alert": (options_assessment or {}).get("n_alert", 0),
+            "assessments": (options_assessment or {}).get("assessments", []),
+        } if options_assessment is not None else None,
     }
     return report