refactor: unify data preparations and research input snapshots

backend/app/backtests/contracts.py

@@ -6,6 +6,7 @@ from typing import Literal
 
 from pydantic import Field, field_validator, model_validator
 
+from ..preparations.contracts import PreparationReference
 from ..schemas import Contract
 
 
@@ -48,13 +49,18 @@ class Source(Contract):
     kind: str = Field(default="manual", min_length=1, max_length=100)
     reference: str | None = Field(default=None, max_length=200)
     batch_id: str | None = Field(default=None, max_length=200)
-    template_input_id: str | None = Field(default=None, max_length=200)
+    input_snapshot_ids: list[str] = Field(default_factory=list, max_length=100)
+    input_snapshot_id: str | None = Field(default=None, max_length=200)
     research_id: str | None = Field(default=None, max_length=200)
     parent_run_id: str | None = Field(default=None, max_length=36)
     hypothesis: str | None = Field(default=None, max_length=2000)
 
 
+
+
 class DraftInput(Contract):
+    preparation_refs: list[PreparationReference] = Field(default_factory=list, max_length=20)
+    input_ids: list[str] = Field(default_factory=list, max_length=20)
     name: str = Field(min_length=1, max_length=200)
     source: Source = Field(default_factory=Source)
     candidates: list[Candidate] = Field(min_length=1, max_length=10000)

backend/app/backtests/service.py

@@ -106,8 +106,33 @@ class Backtests:
             "limits": "并发和批大小为本地配置，并非平台可用额度；账户外提交不在预算内",
         }
 
+    async def bind_preparations(self, body):
+        from ..preparations.service import Preparations
+        from ..research.expressions import analyze
+        if not body.preparation_refs and not body.input_ids:
+            return
+        await Preparations(self.db).bind(body)
+        snapshots = [await Preparations(self.db).snapshot(i) for i in body.input_ids]
+        for candidate in body.candidates:
+            scope = dict(instrument_type=candidate.settings.instrumentType, region=candidate.settings.region,
+                         universe=candidate.settings.universe, delay=candidate.settings.delay)
+            if any(s["scope"] != scope for s in snapshots):
+                raise HTTPException(422, "数据准备集合与回测范围不一致")
+            fields = {}
+            for snapshot in snapshots:
+                for field, kind in snapshot["field_types"].items():
+                    if field in fields and fields[field] != kind:
+                        raise HTTPException(422, "输入字段类型冲突")
+                    fields[field] = kind
+            validation = analyze(candidate.expression, fields)
+            if validation["syntax"] or validation["types"]:
+                raise HTTPException(422, "；".join(validation["syntax"] + validation["types"]))
+        body.source.input_snapshot_ids = body.input_ids
+        body.source.input_snapshot_id = body.input_ids[0] if len(body.input_ids) == 1 else None
+
     async def save_draft(self, body, draft_id=None):
-        data = body.model_dump(mode="json", exclude={"version"})
+        await self.bind_preparations(body)
+        data = body.model_dump(mode="json", exclude={"version", "preparation_refs", "input_ids"})
         if draft_id:
             changed = await self.db.execute(
                 update(BacktestDraft)
@@ -168,6 +193,7 @@ class Backtests:
         producer. ai_context separately identifies whoever starts the execution.
         """
         if body.inline:
+            await self.bind_preparations(body.inline)
             data = body.inline.model_dump(mode="json")
             if self.ai_context and not preserve_source:
                 data["source"] = {