Add single-command GTL tuning matrix

app/services/recommendation_service.py

@@ -93,6 +93,7 @@ def _zone_representative_levels(
     entry_price: float,
     *,
     strength_mode: str = "sum",
+    tolerance: float = _SR_ZONE_TOLERANCE,
 ) -> list[Any]:
     """Collapse near-duplicate S/R levels into one representative per zone.
 
@@ -124,7 +125,7 @@ def _zone_representative_levels(
     zones = cluster_sr_zones(
         level_dicts,
         entry_price,
-        tolerance=_SR_ZONE_TOLERANCE,
+        tolerance=tolerance,
         strength_mode=strength_mode,
     )
 
@@ -315,9 +316,16 @@ class TargetGenerator:
         stop_loss: float,
         sr_levels: list[SRLevel],
         atr_value: float,
+        *,
+        max_targets: int | None = 5,
+        max_atr_multiple_override: float | None = None,
     ) -> list[dict[str, Any]]:
         if atr_value <= 0:
             return []
+        if max_targets is not None and max_targets < 1:
+            raise ValueError("max_targets must be positive or None")
+        if max_atr_multiple_override is not None and max_atr_multiple_override <= 0:
+            raise ValueError("max_atr_multiple_override must be positive or None")
 
         risk = abs(entry_price - stop_loss)
         if risk <= 0:
@@ -326,11 +334,12 @@ class TargetGenerator:
         candidates: list[dict[str, Any]] = []
         atr_pct = atr_value / entry_price if entry_price > 0 else 0.0
 
-        max_atr_multiple: float | None = None
-        if atr_pct > 0.05:
-            max_atr_multiple = 10.0
-        elif atr_pct < 0.02:
-            max_atr_multiple = 3.0
+        max_atr_multiple: float | None = max_atr_multiple_override
+        if max_atr_multiple is None:
+            if atr_pct > 0.05:
+                max_atr_multiple = 10.0
+            elif atr_pct < 0.02:
+                max_atr_multiple = 3.0
 
         for level in sr_levels:
             is_candidate = False
@@ -383,6 +392,12 @@ class TargetGenerator:
         if not candidates:
             return []
 
+        if max_targets is None:
+            candidates.sort(key=lambda row: row["distance_from_entry"])
+            for target in candidates:
+                target.pop("quality", None)
+            return candidates
+
         # Select up to 5 targets that SPAN the distance range, instead of the
         # top-5 by quality (which biases toward far, high-R:R levels and buries
         # every nearby target). Guarantees the nearest level plus a
@@ -396,6 +411,8 @@ class TargetGenerator:
         selected_ids: set[int] = set()
 
         def _add(candidate: dict[str, Any] | None) -> None:
+            if len(selected) >= max_targets:
+                return
             if candidate is not None and candidate["sr_level_id"] not in selected_ids:
                 selected.append(candidate)
                 selected_ids.add(candidate["sr_level_id"])
@@ -408,7 +425,7 @@ class TargetGenerator:
                 _add(max(bucket, key=lambda c: c["quality"]))
         # Fill remaining slots with the next-best by quality
         for candidate in sorted(candidates, key=lambda c: c["quality"], reverse=True):
-            if len(selected) >= 5:
+            if len(selected) >= max_targets:
                 break
             _add(candidate)