refactor: unify DAG construction by moving topological sort into execution_graph.py

Eliminates dag.py and its networkx dependency by moving
topologically_sort_column_configs into execution_graph.py as a
module-level function. Side-effect resolution is now O(1) via a
side_effect_map dict (previously O(n²) linear scan). Kahn's algorithm
is reused in-place rather than leaning on networkx.topological_sort.

Closes #510

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Author: przemekboruta

packages/data-designer-engine/src/data_designer/engine/dataset_builders/utils/config_compiler.py

@@ -11,8 +11,8 @@
     SamplerMultiColumnConfig,
     SeedDatasetMultiColumnConfig,
 )
-from data_designer.engine.dataset_builders.utils.dag import topologically_sort_column_configs
 from data_designer.engine.dataset_builders.utils.errors import ConfigCompilationError
+from data_designer.engine.dataset_builders.utils.execution_graph import topologically_sort_column_configs
 
 
 def compile_dataset_builder_column_configs(config: DataDesignerConfig) -> list[DatasetBuilderColumnConfigT]:

packages/data-designer-engine/src/data_designer/engine/dataset_builders/utils/dag.py

@@ -3,16 +3,22 @@
 
 from __future__ import annotations
 
+import logging
 import math
 from collections import deque
 
 from data_designer.config.column_configs import GenerationStrategy
+from data_designer.config.column_types import ColumnConfigT
+from data_designer.engine.column_generators.utils.generator_classification import column_type_used_in_execution_dag
 from data_designer.engine.dataset_builders.multi_column_configs import (
     DatasetBuilderColumnConfigT,
     MultiColumnConfig,
 )
 from data_designer.engine.dataset_builders.utils.errors import DAGCircularDependencyError
 from data_designer.engine.dataset_builders.utils.task_model import SliceRef
+from data_designer.logging import LOG_INDENT
+
+logger = logging.getLogger(__name__)
 
 
 class ExecutionGraph:
@@ -258,3 +264,55 @@ def to_mermaid(self) -> str:
             for dep in sorted(self._upstream.get(col, set())):
                 lines.append(f"    {dep} --> {col}")
         return "\n".join(lines)
+
+
+def topologically_sort_column_configs(column_configs: list[ColumnConfigT]) -> list[ColumnConfigT]:
+    non_dag_cols = [col for col in column_configs if not column_type_used_in_execution_dag(col.column_type)]
+    dag_col_dict = {col.name: col for col in column_configs if column_type_used_in_execution_dag(col.column_type)}
+
+    if not dag_col_dict:
+        return non_dag_cols
+
+    # side_effect_col_name -> producing column name
+    side_effect_map: dict[str, str] = {}
+    for name, col in dag_col_dict.items():
+        for se_col in col.side_effect_columns:
+            side_effect_map[se_col] = name
+
+    def resolve(col_name: str) -> str | None:
+        if col_name in dag_col_dict:
+            return col_name
+        return side_effect_map.get(col_name)
+
+    upstream: dict[str, set[str]] = {name: set() for name in dag_col_dict}
+    downstream: dict[str, set[str]] = {name: set() for name in dag_col_dict}
+
+    logger.info("⛓️ Sorting column configs into a Directed Acyclic Graph")
+    for name, col in dag_col_dict.items():
+        for req in col.required_columns:
+            resolved = resolve(req)
+            if resolved is None or resolved == name:
+                continue
+            logger.debug(f"{LOG_INDENT}🔗 `{name}` depends on `{resolved}`")
+            upstream[name].add(resolved)
+            downstream[resolved].add(name)
+
+    in_degree = {name: len(ups) for name, ups in upstream.items()}
+    queue: deque[str] = deque(name for name, deg in in_degree.items() if deg == 0)
+    order: list[str] = []
+    while queue:
+        name = queue.popleft()
+        order.append(name)
+        for child in downstream.get(name, set()):
+            in_degree[child] -= 1
+            if in_degree[child] == 0:
+                queue.append(child)
+
+    if len(order) != len(dag_col_dict):
+        raise DAGCircularDependencyError(
+            "🛑 The Data Designer column configurations contain cyclic dependencies. Please "
+            "inspect the column configurations and ensure they can be sorted without "
+            "circular references."
+        )
+
+    return non_dag_cols + [dag_col_dict[n] for n in order]

packages/data-designer-engine/src/data_designer/engine/dataset_builders/utils/execution_graph.py

@@ -17,8 +17,8 @@
 from data_designer.config.utils.code_lang import CodeLang
 from data_designer.config.validator_params import CodeValidatorParams
 from data_designer.engine.dataset_builders.multi_column_configs import SamplerMultiColumnConfig
-from data_designer.engine.dataset_builders.utils.dag import topologically_sort_column_configs
 from data_designer.engine.dataset_builders.utils.errors import DAGCircularDependencyError
+from data_designer.engine.dataset_builders.utils.execution_graph import topologically_sort_column_configs
 
 MODEL_ALIAS = "stub-model-alias"