diff --git a/backend/data_layer/activity_session_metrics.py b/backend/data_layer/activity_session_metrics.py
index 6894559..2681b68 100644
--- a/backend/data_layer/activity_session_metrics.py
+++ b/backend/data_layer/activity_session_metrics.py
@@ -13,9 +13,31 @@ from data_layer.activity_data_canon import (
     ACTIVITY_LOG_LEGACY_COLUMN_FOR_EAV_PRIMARY_PARAM,
     ACTIVITY_MODULE_REGISTRY_FIELD_KEYS,
 )
+from data_layer.prompt_output_compact import normalize_prompt_number
 
 logger = logging.getLogger(__name__)
 
+
+def _normalize_metric_value_for_read(data_type: str, val: Any) -> Any:
+    """Lesepfad (Layer 1): keine unnötig langen Float-Strings für KI/UI (Issue 53 / Platzhalter)."""
+    if val is None:
+        return None
+    dt = (data_type or "").strip().lower()
+    if dt == "string":
+        return val
+    if dt == "boolean":
+        return bool(val)
+    if dt == "integer":
+        try:
+            if isinstance(val, bool):
+                return int(val)
+            return int(val)
+        except (TypeError, ValueError):
+            return normalize_prompt_number(val)
+    if dt == "float":
+        return normalize_prompt_number(val)
+    return normalize_prompt_number(val)
+
 # Diese Spalten nicht aus CSV-Parameter-Zuordnung überschreiben (kommen aus Typ-Mapping / System).
 ACTIVITY_LOG_PATCH_FORBIDDEN = frozenset(
     {
@@ -430,6 +452,8 @@ def merge_column_backed_and_eav_metrics(
             keys_handled.add(k)
 
     merged.sort(key=lambda x: x["key"])
+    for m in merged:
+        m["value"] = _normalize_metric_value_for_read(m.get("data_type") or "", m.get("value"))
     return merged
 
 
diff --git a/backend/data_layer/prompt_output_compact.py b/backend/data_layer/prompt_output_compact.py
index d74994a..7949c6d 100644
--- a/backend/data_layer/prompt_output_compact.py
+++ b/backend/data_layer/prompt_output_compact.py
@@ -70,6 +70,31 @@ def compact_json_payload_for_prompts(obj: Any) -> Any:
     return normalize_prompt_number(obj)
 
 
+def format_scalar_for_prompt_text(x: Any) -> str:
+    """
+    Kurzdarstellung für Text-Platzhalter (activity_detail, Tabellen, …).
+    Nutzt dieselbe Komprimierung wie JSON (normalize_prompt_number).
+    """
+    if x is None:
+        return "—"
+    if isinstance(x, bool):
+        return "ja" if x else "nein"
+    if isinstance(x, str):
+        return x
+    n = normalize_prompt_number(x)
+    if isinstance(n, bool):
+        return "ja" if n else "nein"
+    if isinstance(n, int) and not isinstance(n, bool):
+        return str(n)
+    if isinstance(n, float):
+        if not math.isfinite(n):
+            return str(n)
+        if abs(n - round(n)) < 1e-9:
+            return str(int(round(n)))
+        return str(n)
+    return str(n)
+
+
 def session_metrics_list_to_key_value_compact(metrics: list[Any] | None) -> dict[str, Any]:
     """
     Session-Metriken für KI-JSON: nur key → Wert (keine wiederholten Namen/Beschreibungen).
diff --git a/backend/placeholder_resolver.py b/backend/placeholder_resolver.py
index bdb248f..8f8973d 100644
--- a/backend/placeholder_resolver.py
+++ b/backend/placeholder_resolver.py
@@ -28,6 +28,8 @@ from data_layer.nutrition_metrics import (
     get_nutrition_days_data,
     get_protein_targets_data
 )
+from data_layer.prompt_output_compact import format_scalar_for_prompt_text
+
 from data_layer.activity_metrics import (
     get_activity_summary_data,
     get_activity_detail_data,
@@ -350,7 +352,11 @@ def get_activity_summary(profile_id: str, days: int = 14) -> str:
     if data['confidence'] == 'insufficient':
         return f"Keine Aktivitäten in den letzten {days} Tagen"
 
-    return f"{data['activity_count']} Einheiten in {days} Tagen (Ø {data['avg_duration_min']} min/Einheit, {data['total_kcal']} kcal gesamt)"
+    return (
+        f"{data['activity_count']} Einheiten in {days} Tagen (Ø "
+        f"{format_scalar_for_prompt_text(data['avg_duration_min'])} min/Einheit, "
+        f"{format_scalar_for_prompt_text(data['total_kcal'])} kcal gesamt)"
+    )
 
 
 def calculate_age(dob) -> str:
@@ -423,18 +429,23 @@ def get_activity_detail(profile_id: str, days: int = 14) -> str:
     # Format as readable list (max 20 entries to avoid token bloat)
     lines = []
     for activity in data["activities"][:20]:
-        hr_str = f", HF={activity['hr_avg']}" if activity.get("hr_avg") else ""
+        hr_str = (
+            f", HF={format_scalar_for_prompt_text(activity['hr_avg'])}"
+            if activity.get("hr_avg") is not None
+            else ""
+        )
         eav_parts = []
         for m in activity.get("session_metrics") or []:
             k, v = m.get("key"), m.get("value")
             if k is None or v is None:
                 continue
             label = m.get("name_de") or m.get("name_en") or k
-            eav_parts.append(f"{label} ({k})={v}")
+            eav_parts.append(f"{label} ({k})={format_scalar_for_prompt_text(v)}")
         eav_str = f" | EAV: {'; '.join(eav_parts)}" if eav_parts else ""
         lines.append(
             f"{activity['date']}: {activity['activity_type']} "
-            f"({activity['duration_min']}min, {activity['kcal_active']}kcal{hr_str}{eav_str})"
+            f"({format_scalar_for_prompt_text(activity['duration_min'])}min, "
+            f"{format_scalar_for_prompt_text(activity['kcal_active'])}kcal{hr_str}{eav_str})"
         )
 
     return "\n".join(lines)
diff --git a/backend/tests/test_activity_session_metrics.py b/backend/tests/test_activity_session_metrics.py
index a2bc11a..0de2bdf 100644
--- a/backend/tests/test_activity_session_metrics.py
+++ b/backend/tests/test_activity_session_metrics.py
@@ -121,6 +121,38 @@ def test_merge_parameter_schema_includes_descriptions():
     assert merged[0]["description_en"] == "5 min average power"
 
 
+def test_merge_eav_float_value_normalized_no_long_tail():
+    """Layer 1: lange Floats (z. B. kcal_per_km) für Lesepfad kompakt."""
+    schema = [
+        {
+            "training_parameter_id": 1,
+            "key": "kcal_per_km",
+            "data_type": "float",
+            "unit": "kcal/km",
+            "validation_rules": {},
+            "source_field": None,
+            "name_de": "Kcal/km",
+            "name_en": "kcal/km",
+            "description_de": None,
+            "description_en": None,
+            "param_category": "performance",
+        }
+    ]
+    eav = [
+        {
+            "training_parameter_id": 1,
+            "key": "kcal_per_km",
+            "data_type": "float",
+            "unit": "kcal/km",
+            "value": 51.5818181818181818,
+        }
+    ]
+    out = merge_column_backed_and_eav_metrics({}, schema, eav)
+    assert len(out) == 1
+    v = out[0]["value"]
+    assert "581818" not in repr(v)
+
+
 def test_merge_column_backed_includes_human_labels_from_schema():
     schema = [
         {
diff --git a/backend/tests/test_prompt_output_compact.py b/backend/tests/test_prompt_output_compact.py
index cefae36..f00b627 100644
--- a/backend/tests/test_prompt_output_compact.py
+++ b/backend/tests/test_prompt_output_compact.py
@@ -5,6 +5,7 @@ import pytest
 from data_layer.prompt_output_compact import (
     compact_float_for_prompt,
     compact_json_payload_for_prompts,
+    format_scalar_for_prompt_text,
     normalize_prompt_number,
     session_metrics_list_to_key_value_compact,
 )
@@ -38,6 +39,12 @@ def test_compact_json_nested():
     assert out["d"][0] == 1.11
 
 
+def test_format_scalar_no_long_float_tail():
+    s = format_scalar_for_prompt_text(51.5818181818181818)
+    assert "181818" not in s
+    assert len(s) <= 8
+
+
 def test_session_metrics_key_value_only():
     sm = [
         {