diff --git a/backend/routers/activity.py b/backend/routers/activity.py
index b718134..a7a2e64 100644
--- a/backend/routers/activity.py
+++ b/backend/routers/activity.py
@@ -16,7 +16,15 @@ from auth import require_auth, check_feature_access, increment_feature_usage
 from models import ActivityEntry
 from routers.profiles import get_pid
 from feature_logger import log_feature_usage
-from evaluation_helper import evaluate_and_save_activity
+
+# Evaluation import with error handling (Phase 1.2)
+try:
+    from evaluation_helper import evaluate_and_save_activity
+    EVALUATION_AVAILABLE = True
+except Exception as e:
+    logger.warning(f"[AUTO-EVAL] Evaluation system not available: {e}")
+    EVALUATION_AVAILABLE = False
+    evaluate_and_save_activity = None
 
 router = APIRouter(prefix="/api/activity", tags=["activity"])
 logger = logging.getLogger(__name__)
@@ -66,24 +74,25 @@ def create_activity(e: ActivityEntry, x_profile_id: Optional[str]=Header(default
              d['rpe'],d['source'],d['notes']))
 
         # Phase 1.2: Auto-evaluation after INSERT
-        # Load the activity data to evaluate
-        cur.execute("""
-            SELECT id, profile_id, date, training_type_id, duration_min,
-                   hr_avg, hr_max, distance_km, kcal_active, kcal_resting,
-                   rpe, pace_min_per_km, cadence, elevation_gain
-            FROM activity_log
-            WHERE id = %s
-        """, (eid,))
-        activity_row = cur.fetchone()
-        if activity_row:
-            activity_dict = dict(activity_row)
-            training_type_id = activity_dict.get("training_type_id")
-            if training_type_id:
-                try:
-                    evaluate_and_save_activity(cur, eid, activity_dict, training_type_id, pid)
-                    logger.info(f"[AUTO-EVAL] Evaluated activity {eid} on INSERT")
-                except Exception as eval_error:
-                    logger.error(f"[AUTO-EVAL] Failed to evaluate activity {eid}: {eval_error}")
+        if EVALUATION_AVAILABLE:
+            # Load the activity data to evaluate
+            cur.execute("""
+                SELECT id, profile_id, date, training_type_id, duration_min,
+                       hr_avg, hr_max, distance_km, kcal_active, kcal_resting,
+                       rpe, pace_min_per_km, cadence, elevation_gain
+                FROM activity_log
+                WHERE id = %s
+            """, (eid,))
+            activity_row = cur.fetchone()
+            if activity_row:
+                activity_dict = dict(activity_row)
+                training_type_id = activity_dict.get("training_type_id")
+                if training_type_id:
+                    try:
+                        evaluate_and_save_activity(cur, eid, activity_dict, training_type_id, pid)
+                        logger.info(f"[AUTO-EVAL] Evaluated activity {eid} on INSERT")
+                    except Exception as eval_error:
+                        logger.error(f"[AUTO-EVAL] Failed to evaluate activity {eid}: {eval_error}")
 
     # Phase 2: Increment usage counter (always for new entries)
     increment_feature_usage(pid, 'activity_entries')
@@ -102,24 +111,25 @@ def update_activity(eid: str, e: ActivityEntry, x_profile_id: Optional[str]=Head
                      list(d.values())+[eid,pid])
 
         # Phase 1.2: Auto-evaluation after UPDATE
-        # Load the updated activity data to evaluate
-        cur.execute("""
-            SELECT id, profile_id, date, training_type_id, duration_min,
-                   hr_avg, hr_max, distance_km, kcal_active, kcal_resting,
-                   rpe, pace_min_per_km, cadence, elevation_gain
-            FROM activity_log
-            WHERE id = %s
-        """, (eid,))
-        activity_row = cur.fetchone()
-        if activity_row:
-            activity_dict = dict(activity_row)
-            training_type_id = activity_dict.get("training_type_id")
-            if training_type_id:
-                try:
-                    evaluate_and_save_activity(cur, eid, activity_dict, training_type_id, pid)
-                    logger.info(f"[AUTO-EVAL] Re-evaluated activity {eid} on UPDATE")
-                except Exception as eval_error:
-                    logger.error(f"[AUTO-EVAL] Failed to re-evaluate activity {eid}: {eval_error}")
+        if EVALUATION_AVAILABLE:
+            # Load the updated activity data to evaluate
+            cur.execute("""
+                SELECT id, profile_id, date, training_type_id, duration_min,
+                       hr_avg, hr_max, distance_km, kcal_active, kcal_resting,
+                       rpe, pace_min_per_km, cadence, elevation_gain
+                FROM activity_log
+                WHERE id = %s
+            """, (eid,))
+            activity_row = cur.fetchone()
+            if activity_row:
+                activity_dict = dict(activity_row)
+                training_type_id = activity_dict.get("training_type_id")
+                if training_type_id:
+                    try:
+                        evaluate_and_save_activity(cur, eid, activity_dict, training_type_id, pid)
+                        logger.info(f"[AUTO-EVAL] Re-evaluated activity {eid} on UPDATE")
+                    except Exception as eval_error:
+                        logger.error(f"[AUTO-EVAL] Failed to re-evaluate activity {eid}: {eval_error}")
 
     return {"id":eid}
 
@@ -257,28 +267,29 @@ def bulk_categorize_activities(
         updated_count = cur.rowcount
 
         # Phase 1.2: Auto-evaluation after bulk categorization
-        # Load all activities that were just updated and evaluate them
-        cur.execute("""
-            SELECT id, profile_id, date, training_type_id, duration_min,
-                   hr_avg, hr_max, distance_km, kcal_active, kcal_resting,
-                   rpe, pace_min_per_km, cadence, elevation_gain
-            FROM activity_log
-            WHERE profile_id = %s
-              AND activity_type = %s
-              AND training_type_id = %s
-        """, (pid, activity_type, training_type_id))
+        if EVALUATION_AVAILABLE:
+            # Load all activities that were just updated and evaluate them
+            cur.execute("""
+                SELECT id, profile_id, date, training_type_id, duration_min,
+                       hr_avg, hr_max, distance_km, kcal_active, kcal_resting,
+                       rpe, pace_min_per_km, cadence, elevation_gain
+                FROM activity_log
+                WHERE profile_id = %s
+                  AND activity_type = %s
+                  AND training_type_id = %s
+            """, (pid, activity_type, training_type_id))
 
-        activities_to_evaluate = cur.fetchall()
-        evaluated_count = 0
-        for activity_row in activities_to_evaluate:
-            activity_dict = dict(activity_row)
-            try:
-                evaluate_and_save_activity(cur, activity_dict["id"], activity_dict, training_type_id, pid)
-                evaluated_count += 1
-            except Exception as eval_error:
-                logger.warning(f"[AUTO-EVAL] Failed to evaluate bulk-categorized activity {activity_dict['id']}: {eval_error}")
+            activities_to_evaluate = cur.fetchall()
+            evaluated_count = 0
+            for activity_row in activities_to_evaluate:
+                activity_dict = dict(activity_row)
+                try:
+                    evaluate_and_save_activity(cur, activity_dict["id"], activity_dict, training_type_id, pid)
+                    evaluated_count += 1
+                except Exception as eval_error:
+                    logger.warning(f"[AUTO-EVAL] Failed to evaluate bulk-categorized activity {activity_dict['id']}: {eval_error}")
 
-        logger.info(f"[AUTO-EVAL] Evaluated {evaluated_count}/{updated_count} bulk-categorized activities")
+            logger.info(f"[AUTO-EVAL] Evaluated {evaluated_count}/{updated_count} bulk-categorized activities")
 
         # Save mapping for future imports (upsert)
         cur.execute("""
@@ -369,7 +380,7 @@ async def import_activity_csv(file: UploadFile=File(...), x_profile_id: Optional
                     skipped += 1  # Count as skipped (not newly inserted)
 
                     # Phase 1.2: Auto-evaluation after CSV import UPDATE
-                    if training_type_id:
+                    if EVALUATION_AVAILABLE and training_type_id:
                         try:
                             # Build activity dict for evaluation
                             activity_dict = {
@@ -408,7 +419,7 @@ async def import_activity_csv(file: UploadFile=File(...), x_profile_id: Optional
                     inserted+=1
 
                     # Phase 1.2: Auto-evaluation after CSV import INSERT
-                    if training_type_id:
+                    if EVALUATION_AVAILABLE and training_type_id:
                         try:
                             # Build activity dict for evaluation
                             activity_dict = {