refactor: unify data preparations and research input snapshots

backend/app/research/workspace_contracts.py

@@ -7,6 +7,7 @@ from pydantic import Field, field_validator, model_validator
 
 from ..backtests.contracts import SimulationSettings
 from ..catalog.contracts import Scope
+from ..preparations.contracts import PreparationReference
 from ..schemas import Contract
 from .expressions import IDENTIFIER, PLACEHOLDER, normalize_template
 
@@ -70,7 +71,8 @@ class FeatureStep(Contract):
 class FeatureSpec(Contract):
     name: str = Field(min_length=1, max_length=200)
     hypothesis: str = Field(min_length=1, max_length=10000)
-    input_ids: list[str] = Field(min_length=1, max_length=20)
+    input_ids: list[str] = Field(default_factory=list, max_length=20)
+    preparation_refs: list[PreparationReference] = Field(default_factory=list, max_length=20)
     steps: list[FeatureStep] = Field(default_factory=list, max_length=30)
     template: TemplateSpec | None = None
 
@@ -102,7 +104,8 @@ class Expansion(Contract):
     asset_id: str | None = Field(default=None, max_length=36)
     version: int | None = Field(default=None, ge=1)
     template: TemplateSpec | None = None
-    input_ids: list[str] = Field(min_length=1, max_length=20)
+    input_ids: list[str] = Field(default_factory=list, max_length=20)
+    preparation_refs: list[PreparationReference] = Field(default_factory=list, max_length=20)
     hypothesis: str = Field(min_length=1, max_length=10000)
     settings: SimulationSettings
     mode: Literal["all", "random"] = "all"
@@ -123,7 +126,8 @@ class Expansion(Contract):
 class Generation(Contract):
     name: str = Field(min_length=1, max_length=200)
     hypothesis: str = Field(min_length=1, max_length=10000)
-    input_ids: list[str] = Field(min_length=1, max_length=20)
+    input_ids: list[str] = Field(default_factory=list, max_length=20)
+    preparation_refs: list[PreparationReference] = Field(default_factory=list, max_length=20)
     parent_alpha_ids: list[str] = Field(default_factory=list, max_length=20)
     parent_experiment_ids: list[str] = Field(default_factory=list, max_length=20)
     method: Literal["template", "structure", "feature"] = "template"
@@ -131,7 +135,8 @@ class Generation(Contract):
 
 class SettingVariants(Contract):
     alpha_id: str = Field(min_length=1, max_length=100)
-    input_ids: list[str] = Field(min_length=1, max_length=100)
+    input_ids: list[str] = Field(default_factory=list, max_length=100)
+    preparation_refs: list[PreparationReference] = Field(default_factory=list, max_length=100)
     hypothesis: str = Field(default="保持表达式，比较字段共同支持的市场与设置", max_length=10000)
 
 
@@ -229,7 +234,8 @@ class FlowStart(Contract):
     name: str = Field(min_length=1, max_length=200)
     workflow_id: str | None = None
     workflow_version: int | None = Field(default=None, ge=1)
-    input_ids: list[str] = Field(min_length=1, max_length=20)
+    input_ids: list[str] = Field(default_factory=list, max_length=20)
+    preparation_refs: list[PreparationReference] = Field(default_factory=list, max_length=20)
     hypothesis: str = Field(min_length=1, max_length=10000)
     settings: SimulationSettings
     budget: Budget