feat(eval): VaR breach rate metric (#12) + HMM regime detector (#13) — rq-04 prep

#12 — VaR_breach_rate_99_oos_regime_cond metric:
- internal/eval/var.go: VaRBreachRate() + kupiecPOF() + LinearProbePredict() (stdlib math only)
- internal/eval/var_test.go: 8 golden tests (zero/all breach, perfect calibration, boundary)
- cmd/eval/main.go: -metric var flag (no-leakage probe → VaR → Kupiec P)
- scripts/var_breach.py: Python equivalent with METRIC_KEY constant (13 TDD tests)
- train.py LOCKED VaR EVAL BLOCK: writes VaR_breach_rate_99_oos_regime_cond + kupiec_p to metrics.json
- Fixed bug: train.py used bare 'os' before import; now uses module-level '_os' consistently

#13 — HMM regime detector + JEPA conditioning seam:
- scripts/prepare_regime.py: GaussianHMM (diag, 3-state) on realized_vol; states sorted by mean vol
  (0=calm, 1=stressed, 2=crisis); deterministic (random_state=42); outputs eurusd_regime.parquet
- tests/test_regime.py: 11 TDD tests (dtype, states, determinism, vol sort, daily fallback)
- train.py: JEPA_ENABLE_REGIME toggle + REGIME CONDITIONING SEAM (concat baseline, agent-editable)
- requirements.txt: hmmlearn>=0.3, scikit-learn>=1.4

78 Python + all Go tests green.

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

train.py

@@ -36,6 +36,7 @@ PHASE1_JOINT       = bool(int(_os.environ.get("JEPA_PHASE1_JOINT",     1)))
 PHASE1_JOINT_EPOCHS= int(_os.environ.get("JEPA_PHASE1_JOINT_EPOCHS",  30))
 PHASE1_ENCODER_LR  = float(_os.environ.get("JEPA_PHASE1_ENCODER_LR",  3e-6))
 USE_MULTIPAIR      = bool(int(_os.environ.get("JEPA_USE_MULTIPAIR",    0)))
+JEPA_ENABLE_REGIME = bool(int(_os.environ.get("JEPA_ENABLE_REGIME",    0)))
 SEED          = int(_os.environ.get("JEPA_SEED",          0))
 # ---------------------------
 
@@ -171,6 +172,22 @@ def build():
         df["date"] = pd.to_datetime(df["date"])
         FEAT_COLS = ["ret", "realized_vol"]
         target_col = "realized_vol"
+    # ── REGIME CONDITIONING SEAM — agent may vary this mechanism ─────────────
+    # Baseline: concat regime flag as an additional feature channel (0=calm, 2=crisis).
+    # Agent may swap for FiLM conditioning, learned regime embedding, or gating.
+    _regime_path = "data/processed/eurusd_regime.parquet"
+    if JEPA_ENABLE_REGIME and os.path.exists(_regime_path):
+        _rdf = pd.read_parquet(_regime_path)
+        _ts_col = "datetime" if "datetime" in _rdf.columns else "date"
+        _rdf[_ts_col] = pd.to_datetime(_rdf[_ts_col])
+        df = df.copy()
+        df = df.merge(
+            _rdf.rename(columns={_ts_col: "date"})[["date", "regime"]],
+            on="date", how="left",
+        )
+        df["regime"] = df["regime"].fillna(0).astype(np.float32)
+        FEAT_COLS = list(FEAT_COLS) + ["regime"]
+    # ── END REGIME SEAM ───────────────────────────────────────────────────────
     feats  = df[FEAT_COLS].to_numpy(np.float32)
     target = df[target_col].to_numpy(np.float32)
     tr_idx = df.index[df["date"].dt.year <= 2021].tolist()
@@ -298,9 +315,18 @@ def main():
     phase1_r2 = float(1 - ((yte - pred_h) ** 2).sum() / ss_tot)
     print("phase1_r2   = %.4f  (n_test=%d)" % (phase1_r2, len(yte)))
 
-    _metrics_out = os.environ.get("METRICS_OUT", "metrics.json")
+    # ── VaR EVAL BLOCK — do NOT edit (agent boundary) ───────────────────────
+    import sys as _sys
+    _sys.path.insert(0, _os.path.dirname(_os.path.abspath(__file__)))
+    from scripts.var_breach import var_breach_rate as _var_breach_rate, METRIC_KEY as _VAR_KEY
+    _var_rate, _kupiec_p = _var_breach_rate(pred_np.tolist(), yte.tolist())
+    print("%s=%.4f  Kupiec_p=%.4f" % (_VAR_KEY, _var_rate, _kupiec_p))
+    # ── END VaR EVAL BLOCK ───────────────────────────────────────────────────
+
+    _metrics_out = _os.environ.get("METRICS_OUT", "metrics.json")
     json.dump({
         "val_vol_r2": val_vol_r2, "phase1_r2": phase1_r2, "n_test": len(yte),
+        _VAR_KEY: _var_rate, "kupiec_p": _kupiec_p,
         "knobs": {"WINDOW": WINDOW, "PATCH_LEN": PATCH_LEN,
                   "D_MODEL": D_MODEL, "DEPTH": DEPTH, "ALPHA": ALPHA,
                   "DELTA_T_MAX": DELTA_T_MAX, "EPOCHS": EPOCHS},