diff --git a/app/services/recommendation_service.py b/app/services/recommendation_service.py
index 0c8ff2b..20e023f 100644
--- a/app/services/recommendation_service.py
+++ b/app/services/recommendation_service.py
@@ -3,6 +3,7 @@ from __future__ import annotations
 import json
 import logging
 import math
+from types import SimpleNamespace
 from typing import Any
 
 from sqlalchemy import select
@@ -12,6 +13,7 @@ from app.models.settings import SystemSetting
 from app.models.sr_level import SRLevel
 from app.models.ticker import Ticker
 from app.models.trade_setup import TradeSetup
+from app.services.sr_service import cluster_sr_zones
 
 logger = logging.getLogger(__name__)
 
@@ -38,11 +40,58 @@ _TARGET_HORIZON_DAYS = 30.0
 _CONSERVATIVE_MAX_ATR = 2.9
 _MODERATE_MAX_ATR = 4.6
 
+# Merge S/R levels within this fraction into one zone before generating targets —
+# the same tolerance the chart and alerts use, so S/R is one model app-wide.
+_SR_ZONE_TOLERANCE = 0.02
+
 
 def _clamp(value: float, low: float, high: float) -> float:
     return max(low, min(high, value))
 
 
+def _zone_representative_levels(sr_levels: list[SRLevel], entry_price: float) -> list[Any]:
+    """Collapse near-duplicate S/R levels into one representative per zone.
+
+    Targets are generated from these representatives, so a clustered wall (e.g.
+    183 + 185) becomes a single target carrying the zone's COMBINED strength
+    (capped at 100) instead of two near-identical targets, each undervaluing the
+    wall. Same clusterer as the chart and alerts → one S/R model everywhere.
+
+    The representative price is the zone's near edge (the reachable side of the
+    wall) and it keeps the strongest constituent's id for reference. Singleton
+    levels pass through unchanged.
+    """
+    if not sr_levels or entry_price <= 0:
+        return list(sr_levels)
+
+    level_dicts = [
+        {"price_level": float(lv.price_level), "strength": int(lv.strength), "type": lv.type}
+        for lv in sr_levels
+    ]
+    zones = cluster_sr_zones(level_dicts, entry_price, tolerance=_SR_ZONE_TOLERANCE)
+
+    reps: list[Any] = []
+    for zone in zones:
+        constituents = [
+            lv for lv in sr_levels if zone["low"] <= float(lv.price_level) <= zone["high"]
+        ]
+        if not constituents:
+            continue
+        strongest = max(constituents, key=lambda lv: lv.strength)
+        # Near edge: bottom of a resistance wall (above entry), top of a support
+        # wall (below entry) — the first price the move reaches.
+        near_edge = zone["low"] if zone["type"] == "resistance" else zone["high"]
+        reps.append(
+            SimpleNamespace(
+                id=int(strongest.id),
+                price_level=float(near_edge),
+                type=zone["type"],
+                strength=int(zone["strength"]),
+            )
+        )
+    return reps
+
+
 def _norm_cdf(x: float) -> float:
     """Standard normal CDF via erf (no SciPy dependency)."""
     return 0.5 * (1.0 + math.erf(x / math.sqrt(2.0)))
@@ -522,11 +571,15 @@ async def enhance_trade_setup(
     direction = setup.direction.lower()
     confidence = long_confidence if direction == "long" else short_confidence
 
+    # Merge near-duplicate levels into zone representatives first, so a clustered
+    # wall yields one strength-combined target instead of several near-identical
+    # ones — consistent with the chart and alerts.
+    zone_levels = _zone_representative_levels(sr_levels, setup.entry_price)
     targets = target_generator.generate_targets(
         direction=direction,
         entry_price=setup.entry_price,
         stop_loss=setup.stop_loss,
-        sr_levels=sr_levels,
+        sr_levels=zone_levels,
         atr_value=atr_value,
     )
 
diff --git a/tests/unit/test_recommendation_service.py b/tests/unit/test_recommendation_service.py
index b7a27c9..a503194 100644
--- a/tests/unit/test_recommendation_service.py
+++ b/tests/unit/test_recommendation_service.py
@@ -226,3 +226,38 @@ def test_classify_by_probability_thresholds():
     assert _classify_by_probability(75) == "Conservative"
     assert _classify_by_probability(50) == "Moderate"
     assert _classify_by_probability(20) == "Aggressive"
+
+
+def test_zone_representative_levels_merges_wall():
+    """Near-duplicate resistances collapse to one zone with combined strength."""
+    from types import SimpleNamespace
+    from app.services.recommendation_service import _zone_representative_levels
+
+    levels = [
+        SimpleNamespace(id=1, price_level=183.0, type="resistance", strength=60),
+        SimpleNamespace(id=2, price_level=185.0, type="resistance", strength=60),
+        SimpleNamespace(id=3, price_level=200.0, type="resistance", strength=50),
+    ]
+    reps = _zone_representative_levels(levels, entry_price=180.0)
+
+    # 183/185 merge into one zone; 200 stays separate → 2 representatives
+    assert len(reps) == 2
+    wall = min(reps, key=lambda r: r.price_level)
+    assert wall.price_level == 183.0          # near edge of the wall
+    assert wall.strength == 100               # 60 + 60, capped at 100
+    far = max(reps, key=lambda r: r.price_level)
+    assert far.price_level == 200.0
+    assert far.strength == 50
+
+
+def test_zone_representative_levels_singletons_unchanged():
+    from types import SimpleNamespace
+    from app.services.recommendation_service import _zone_representative_levels
+
+    levels = [
+        SimpleNamespace(id=1, price_level=120.0, type="resistance", strength=70),
+        SimpleNamespace(id=2, price_level=150.0, type="resistance", strength=40),
+    ]
+    reps = _zone_representative_levels(levels, entry_price=100.0)
+    assert len(reps) == 2
+    assert {round(r.price_level) for r in reps} == {120, 150}