refactor: unify data preparations and research input snapshots

backend/tests/test_research_integration.py

@@ -11,7 +11,7 @@ from app.ai.tools import CAPABILITIES
 from app.alphas import upsert_alpha
 from app.backtests.contracts import PreviewInput, RerunInput, SubsetInput
 from app.business import Business
-from app.models import BacktestPreview, BacktestRun, Research, TemplateInput
+from app.models import BacktestPreview, BacktestRun, Research, ResearchInputSnapshot
 from tests.test_ai import configure, single_tool_factory
 from tests.test_backtests import execute, setup, start
 from tests.test_catalog import SCOPE, prepare, sync
@@ -47,7 +47,7 @@ def construction(input_id):
     return {
         "name": "字段研究",
         "hypothesis": "显式字段排序",
-        "template_input_id": input_id,
+        "input_snapshot_id": input_id,
         "candidates": [
             {
                 "client_item_id": "one",
@@ -66,7 +66,7 @@ async def test_chatbox_catalog_to_results_and_alpha_sources(app, logged_in, fixe
     conversation = (await logged_in.post("/api/v1/ai/conversations")).json()["id"]
     context = {"page": "datasets", "catalog_scope": SCOPE, "dataset_id": "TEST_FIN"}
     if use_saved_input:
-        context["template_input_id"] = fixed_input["id"]
+        context["input_snapshot_id"] = fixed_input["id"]
     run = await ask(logged_in, conversation, "研究此输入" if use_saved_input else "自行选字段研究", context)
     assert run["status"] == "waiting_approval", run
     assert not platform.posts
@@ -75,7 +75,7 @@ async def test_chatbox_catalog_to_results_and_alpha_sources(app, logged_in, fixe
     assert source["kind"] == "chatbox"
     assert source["reference"] == conversation
     assert source["research_id"] == run["id"]
-    assert source["template_input_id"]
+    assert source["input_snapshot_id"]
     assert approval["preview"]["backtest"]["items"][0]["expression"] == "rank(TEST_FIN_001)"
     async with app.state.sessions() as db:
         assert await db.scalar(select(func.count()).select_from(BacktestRun)) == 0
@@ -128,7 +128,7 @@ async def test_invalid_construction_has_no_partial_preview(logged_in, app, fixed
     elif invalid == "unknown_type":
         item["bindings"]["signal"] = {"field_id": "TEST_FIN_122", "field_type": "MATRIX"}
     else:
-        body["template_input_id"] = "missing"
+        body["input_snapshot_id"] = "missing"
     response = await logged_in.post("/api/v1/backtests/research-previews", json=body)
     assert response.status_code == (404 if invalid == "missing_input" else 422), response.text
     async with app.state.sessions() as db:
@@ -144,15 +144,10 @@ async def test_input_pagination_old_types_and_explicit_exclusions(app, logged_in
     assert page["field_count"] == page["total"] == 123 and len(page["items"]) == 23
     assert page["items"][-1]["field_type"] == "FUTURE_TYPE" and not page["has_more"]
     assert page["_meta"]["source"] == "local_database"
-    selected = await tool(
-        "prepare_research_input",
-        {
-            "scope": SCOPE,
-            "dataset_id": "TEST_FIN",
-            "collection_version": fixed_input["collection_version"],
-            "field_ids": ["TEST_FIN_001"],
-        },
-    )
+    subset = (await logged_in.post("/api/v1/data-preparations", json={"name": "one field", "scope": SCOPE,
+        "fields": [{"scope": SCOPE, "dataset_id": "TEST_FIN", "field_id": "TEST_FIN_001", "source": "local",
+                    "collection_version": fixed_input["fields"][0]["collection_version"]}]})).json()
+    selected = await tool("prepare_research_input", {"items": [{"id": subset["id"], "version": subset["version"]}]})
     assert selected["field_count"] == 1
     bad = construction(selected["id"])
     bad["candidates"][0]["bindings"]["signal"]["field_id"] = "TEST_FIN_002"
@@ -166,19 +161,12 @@ async def test_input_pagination_old_types_and_explicit_exclusions(app, logged_in
         "/api/v1/backtests/research-previews", json=construction(fixed_input["id"])
     )
     assert response.status_code == 201, response.text
+    await logged_in.patch(f"/api/v1/data-preparations/{subset['id']}", json={"name": "edited", "version": subset["version"]})
     with pytest.raises(HTTPException) as exc:
-        await tool(
-            "prepare_research_input",
-            {
-                "scope": SCOPE,
-                "dataset_id": "TEST_FIN",
-                "collection_version": fixed_input["collection_version"],
-                "field_ids": ["TEST_FIN_001"],
-            },
-        )
+        await tool("prepare_research_input", {"items": [{"id": subset["id"], "version": subset["version"]}]})
     assert exc.value.status_code == 409
     async with app.state.sessions() as db:
-        assert await db.scalar(select(func.count()).select_from(TemplateInput)) == 2
+        assert await db.scalar(select(func.count()).select_from(ResearchInputSnapshot)) == 2
 
 
 async def test_multiple_origins_preserve_research_and_do_not_duplicate_alphas(app, logged_in):