feat: integrate chatbox research with datasets and backtests

backend/app/ai/tools.py

@@ -6,6 +6,13 @@ from typing import Literal
 from pydantic import Field
 
 from ..backtests.contracts import ControlInput, PreviewInput, RerunInput, StartInput
+from ..catalog.contracts import UNIVERSES, CatalogFilters, Scope
+from ..research.contracts import (
+    ChatboxResearchInput,
+    InputPageArgs,
+    ResearchInputSelection,
+    ResearchPreviewInput,
+)
 from ..schemas import AlphaFilters, BulkInput, BulkUpdate, Contract, JobInput, ResearchInput, ResearchUpdate
 
 
@@ -52,6 +59,30 @@ class BacktestListArgs(Contract):
     limit: int = Field(default=20, ge=1, le=100)
     offset: int = Field(default=0, ge=0)
     source: str | None = Field(default=None, max_length=100)
+    reference: str | None = Field(default=None, max_length=200)
+    research_id: str | None = Field(default=None, max_length=200)
+
+
+class CatalogSearchArgs(Contract):
+    filters: CatalogFilters
+    dataset_id: str | None = Field(default=None, min_length=1, max_length=200)
+
+
+class CatalogDetailArgs(Contract):
+    scope: Scope
+    dataset_id: str = Field(min_length=1, max_length=200)
+    field_id: str = Field(default="", max_length=200)
+
+
+class BacktestDraftArgs(Contract):
+    draft_id: str = Field(min_length=1, max_length=36)
+    limit: int = Field(default=25, ge=1, le=100)
+    offset: int = Field(default=0, ge=0)
+
+
+class AlphaSourcesArgs(AlphaArgs):
+    limit: int = Field(default=25, ge=1, le=100)
+    offset: int = Field(default=0, ge=0)
 
 
 class BacktestResultsArgs(BacktestRunArgs):
@@ -74,6 +105,32 @@ class BacktestRerunArgs(BacktestRunArgs):
 
 
 CATALOG = {
+    "get_catalog_scopes": (EmptyArgs, "读取本版支持的研究范围组合，不表示账户已获平台权限。"),
+    "search_catalog": (
+        CatalogSearchArgs,
+        "分页查询本地目录。省略 dataset_id 查询数据集；提供 dataset_id 查询其字段、类型和完整集合版本。无缓存时说明需在数据集页同步，不编造字段。",
+    ),
+    "get_catalog_detail": (CatalogDetailArgs, "读取指定范围的数据集或字段详情；field_id 为空表示数据集。"),
+    "prepare_research_input": (
+        ResearchInputSelection,
+        "把明确选出的 1–100 个字段固定为研究输入快照；必须提供已读取的集合版本。只保存本地输入，不启动同步或回测。已有输入引用时直接读取，不重建。",
+    ),
+    "get_research_input": (
+        InputPageArgs,
+        "分页读取不可变研究输入及原版本字段说明。q 仅搜索字段 ID，类型筛选不改变输入。field_count 是输入总数，total 是筛选匹配数。",
+    ),
+    "prepare_research_backtest": (
+        ChatboxResearchInput,
+        "从研究输入快照构建固定回测预览：提供假设、候选模板（如 rank({price})）、具名字段绑定及真实类型、明确模拟参数。服务端校验归属/类型/范围并替换占位符；不验证算子语义、不自动聚合 VECTOR。来源由服务端标记为当前 chatbox 研究。",
+    ),
+    "get_backtest_draft": (
+        BacktestDraftArgs,
+        "分页读取已有候选草稿、版本和来源，随后按 draft_id/draft_version 准备预览。",
+    ),
+    "get_alpha_sources": (
+        AlphaSourcesArgs,
+        "分页读取 Alpha 的全部已保存研究来源、关联回测、聊天会话和输入快照。没有记录不推断来源。",
+    ),
     "get_backtest_capabilities": (
         EmptyArgs,
         "读取回测输入 schema、支持类型和本地调度配置，不代表平台剩余额度。",
@@ -146,7 +203,36 @@ def bounded(value):
 async def read_tool(business, name, args):
     from datetime import timezone
 
-    if name == "get_backtest_capabilities":
+    if name == "get_catalog_scopes":
+        data = {"universes": UNIVERSES, "instrument_type": "EQUITY", "delays": [0, 1]}
+    elif name == "search_catalog":
+        data = await business.catalog.search(args.filters, args.dataset_id)
+        data.update(
+            scope=args.filters.model_dump(include=set(Scope.model_fields)), dataset_id=args.dataset_id
+        )
+    elif name == "get_catalog_detail":
+        data = await business.catalog.detail(args.scope, args.dataset_id, args.field_id)
+        # Saved notes are not required for selection; unsaved drafts never cross this interface.
+        data.pop("research", None)
+    elif name == "prepare_research_input":
+        data = await business.research_builder.select_input(args)
+    elif name == "get_research_input":
+        data = await business.research_builder.input_page(**args.model_dump())
+    elif name == "prepare_research_backtest":
+        data = await business.research_builder.prepare(ResearchPreviewInput(**args.model_dump()))
+    elif name == "get_backtest_draft":
+        data = await business.backtests.draft(args.draft_id)
+        candidates = data.pop("candidates")
+        data.update(
+            items=candidates[args.offset : args.offset + args.limit],
+            total=len(candidates),
+            limit=args.limit,
+            offset=args.offset,
+            has_more=args.offset + args.limit < len(candidates),
+        )
+    elif name == "get_alpha_sources":
+        data = await business.get_alpha_sources(**args.model_dump())
+    elif name == "get_backtest_capabilities":
         data = await business.backtests.capabilities()
     elif name == "prepare_backtest":
         data = await business.backtests.preview(args)