feat: integrate chatbox research with datasets and backtests

backend/app/backtests/contracts.py

@@ -50,6 +50,7 @@ class Source(Contract):
     template_input_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):

backend/app/backtests/routes.py

@@ -3,6 +3,8 @@
 from fastapi import APIRouter, Depends, Query, Request
 
 from ..business import Business
+from ..research.contracts import ResearchPreviewInput
+from ..research.service import ResearchBuilder
 from ..security import require_auth
 from .contracts import (
     ControlInput,
@@ -75,6 +77,13 @@ async def preview(body: PreviewInput, request: Request):
         return await Business(db).backtests.preview(body)
 
 
+@router.post("/research-previews", status_code=201, response_model=PreviewOutput)
+async def research_preview(body: ResearchPreviewInput, request: Request):
+    """Prepare typed field bindings for any research producer; never start a simulation."""
+    async with request.app.state.sessions.begin() as db:
+        return await ResearchBuilder(db, Business(db).backtests).prepare(body)
+
+
 @router.get("/previews/{preview_id}", response_model=PreviewOutput)
 async def get_preview(
     preview_id: str, request: Request, limit: int = Query(25, ge=1, le=100), offset: int = Query(0, ge=0)
@@ -97,9 +106,17 @@ async def runs(
     limit: int = Query(25, ge=1, le=100),
     offset: int = Query(0, ge=0),
     source: str | None = Query(None, max_length=100),
+    reference: str | None = Query(None, max_length=200),
+    research_id: str | None = Query(None, max_length=200),
 ):
     async with request.app.state.sessions() as db:
-        return await Business(db).backtests.runs(limit, offset, source)
+        return await Business(db).backtests.runs(limit, offset, source, reference, research_id)
+
+
+@router.get("/sources", response_model=list[str])
+async def sources(request: Request):
+    async with request.app.state.sessions() as db:
+        return await Business(db).backtests.sources()
 
 
 @router.get("/runs/{run_id}", response_model=RunOutput)

backend/app/backtests/service.py

@@ -161,9 +161,22 @@ class Backtests:
             {k: getattr(row, k) for k in ("id", "version", "name", "source", "candidates", "updated_at")}
         )
 
-    async def preview(self, body):
+    async def preview(self, body, *, preserve_source=False):
+        """Fix inputs; new chatbox candidates inherit trusted generating-run provenance.
+
+        Existing draft references and server-side subsets/reruns retain their
+        producer. ai_context separately identifies whoever starts the execution.
+        """
         if body.inline:
             data = body.inline.model_dump(mode="json")
+            if self.ai_context and not preserve_source:
+                data["source"] = {
+                    **data["source"],
+                    "kind": "chatbox",
+                    "reference": self.ai_context["conversation_id"],
+                    "research_id": self.ai_context["ai_run_id"],
+                    "parent_run_id": None,
+                }
         else:
             draft = await self.db.scalar(
                 select(BacktestDraft).where(BacktestDraft.id == body.draft_id).with_for_update()
@@ -316,10 +329,11 @@ class Backtests:
         await self.db.flush()
         return await self.run(run.id)
 
-    async def runs(self, limit=25, offset=0, source=None):
+    async def runs(self, limit=25, offset=0, source=None, reference=None, research_id=None):
         query = select(BacktestRun)
-        if source:
-            query = query.where(BacktestRun.source["kind"].as_string() == source)
+        for key, value in (("kind", source), ("reference", reference), ("research_id", research_id)):
+            if value:
+                query = query.where(BacktestRun.source[key].as_string() == value)
         total = await self.db.scalar(select(func.count()).select_from(query.subquery()))
         rows = (
             await self.db.scalars(
@@ -333,6 +347,10 @@ class Backtests:
             "offset": offset,
         }
 
+    async def sources(self):
+        kinds = await self.db.scalars(select(BacktestRun.source["kind"].as_string()).distinct())
+        return sorted({kind for kind in kinds if kind} | {"chatbox", "manual"})
+
     async def run(self, run_id):
         row = await self.db.get(BacktestRun, run_id)
         if not row:
@@ -562,7 +580,8 @@ class Backtests:
                         for r in selected
                     ],
                 )
-            )
+            ),
+            preserve_source=True,
         )
 
     async def attach_reference(self, attempt_id, body):
@@ -603,5 +622,6 @@ class Backtests:
         if not candidates:
             raise HTTPException(422, "至少保留一条候选")
         return await self.preview(
-            PreviewInput(inline=DraftInput(name=parent.name, source=parent.source, candidates=candidates))
+            PreviewInput(inline=DraftInput(name=parent.name, source=parent.source, candidates=candidates)),
+            preserve_source=True,
         )