feat: integrate chatbox research with datasets and backtests

2026-09-08 12:43:00 +08:00
parent 43336ad960
commit aef8e1d310
37 changed files with 1421 additions and 42 deletions
@@ -0,0 +1,70 @@
+"""Read provenance from saved results, retaining every experiment for an Alpha."""
+
+from collections import defaultdict
+
+from fastapi import HTTPException
+from fastapi.encoders import jsonable_encoder
+from sqlalchemy import func, select
+
+from ..models import Alpha, BacktestItem, BacktestResult, BacktestRun
+
+
+def saved_sources():
+    """Only persisted results establish provenance; pending platform IDs do not."""
+    return (
+        select(BacktestResult, BacktestItem, BacktestRun)
+        .select_from(BacktestResult)
+        .join(BacktestItem, BacktestResult.item_id == BacktestItem.id)
+        .join(BacktestRun, BacktestItem.run_id == BacktestRun.id)
+    )
+
+
+def source_alpha_ids(source=None, source_reference=None, research_id=None, backtest_run_id=None):
+    """An IN subquery keeps list counts and exports independent of source multiplicity."""
+    query = saved_sources().with_only_columns(BacktestResult.alpha_id)
+    for key, value in (("kind", source), ("reference", source_reference), ("research_id", research_id)):
+        if value:
+            query = query.where(BacktestRun.source[key].as_string() == value)
+    if backtest_run_id:
+        query = query.where(BacktestRun.id == backtest_run_id)
+    return query
+
+
+async def source_kinds(db, alpha_ids=None):
+    query = saved_sources().with_only_columns(BacktestResult.alpha_id, BacktestRun.source["kind"].as_string())
+    if alpha_ids is not None:
+        query = query.where(BacktestResult.alpha_id.in_(alpha_ids))
+    values = defaultdict(list)
+    for alpha_id, kind in await db.execute(query.distinct()):
+        if kind:
+            values[alpha_id].append(kind)
+    return {alpha_id: sorted(kinds) for alpha_id, kinds in values.items()}
+
+
+async def alpha_sources(db, alpha_id, limit=25, offset=0):
+    if not await db.get(Alpha, alpha_id):
+        raise HTTPException(404, "Alpha 尚未同步")
+    query = saved_sources().where(BacktestResult.alpha_id == alpha_id)
+    total = await db.scalar(select(func.count()).select_from(query.subquery()))
+    rows = await db.execute(
+        query.order_by(BacktestResult.observed_at.desc(), BacktestResult.item_id).limit(limit).offset(offset)
+    )
+    return jsonable_encoder(
+        {
+            "alpha_id": alpha_id,
+            "total": total,
+            "limit": limit,
+            "offset": offset,
+            "items": [
+                {
+                    "backtest_run_id": run.id,
+                    "name": run.name,
+                    "source": run.source,
+                    "item_id": item.id,
+                    "client_item_id": item.client_item_id,
+                    "observed_at": result.observed_at,
+                }
+                for result, item, run in rows
+            ],
+        }
+    )