Fix: Clamp score strictly between 0.01 and 0.99 for validator

server/environment.py

@@ -171,7 +171,7 @@ class DbMigrationEnvironment(Environment):
                 target_schema_sql=self._task_config["target_ddl"],
                 last_execution_result="Error: Environment not initialized. Call reset() first.",
                 step_number=self._step_count,
-                migration_progress=0.0,
+                migration_progress=0.01,
                 task_name=self.task_name,
                 metadata={"error": "not_initialized"},
             )
@@ -200,7 +200,7 @@ class DbMigrationEnvironment(Environment):
         current_score, step_reward = self._reconciler.compute_step_reward(self._conn)
 
         # Episode termination: submit_final, max steps (20), OR perfect score
-        done = action.submit_final or self._step_count >= 20 or current_score >= 1.0
+        done = action.submit_final or self._step_count >= 20 or current_score >= 0.99
 
         # Update state
         self._state.step_count = self._step_count

server/grader.py

@@ -157,7 +157,7 @@ class StateReconciler:
         if has_full_name and old_cols_gone and row_count == 0:
             score = min(score, 0.1)
 
-        return min(1.0, score)
+        return max(0.01, min(0.99, score))
 
     # =========================================================================
     # Task 2: Table Normalization
@@ -223,7 +223,7 @@ class StateReconciler:
             if c_count == 0 and o_count == 0:
                 score = min(score, 0.1)
 
-        return min(1.0, score)
+        return max(0.01, min(0.99, score))
 
     # =========================================================================
     # Task 3: Cascade Migration
@@ -343,4 +343,4 @@ class StateReconciler:
         if "employees" in tables and _get_row_count(conn, "employees") == 0:
             score = min(score, 0.1)
 
-        return min(1.0, score)
+        return max(0.01, min(0.99, score))

test_smoke.py

@@ -58,7 +58,7 @@ conn.execute("ALTER TABLE users_new RENAME TO users")
 conn.commit()
 score = reconciler.score(conn)
 print(f"PASS: Score after correct Task 1: {score:.2f}")
-assert score == 1.0, f"Expected 1.0, got {score}"
+assert score == 0.99, f"Expected 0.99, got {score}"
 conn.close()
 
 # Test 6: Full environment
@@ -88,9 +88,9 @@ for i, sql in enumerate(steps):
     print(f"  Step {i+1}: reward={obs.reward:.2f}, progress={obs.migration_progress:.2f}, done={obs.done}")
 
 assert obs.done == True
-assert obs.migration_progress == 1.0, f"Expected 1.0, got {obs.migration_progress}"
+assert obs.migration_progress == 0.99, f"Expected 0.99, got {obs.migration_progress}"
 env.close()
-print("PASS: Full migration episode completed with score 1.0")
+print("PASS: Full migration episode completed with score 0.99")
 
 # Test 7: Task 2 grader
 conn = sqlite3.connect(":memory:")