feat: expose local self-correlation tools through MCP

backend/app/research_access/contracts.py

@@ -11,6 +11,7 @@ from ..schemas import Contract
 
 Identifier = Annotated[str, Field(min_length=1, max_length=100)]
 RunId = Annotated[str, Field(min_length=1, max_length=36)]
+AlphaId = Annotated[str, Field(min_length=1, max_length=100, pattern=r"^[A-Za-z0-9_-]+$")]
 
 
 class Empty(Contract):
@@ -124,6 +125,14 @@ class JobReference(Page):
     job_id: RunId
 
 
+class SelfCorrelationCheck(Contract):
+    alpha_ids: list[AlphaId] = Field(min_length=1, max_length=100)
+
+
+class SelfCorrelationReference(Contract):
+    alpha_id: AlphaId
+
+
 class History(Page):
     source: str | None = Field(default=None, max_length=100)
     reference: str | None = Field(default=None, max_length=200)

backend/app/research_access/service.py

@@ -16,6 +16,7 @@ from ..catalog.contracts import CatalogJobInput
 from ..catalog.platform import platform_options, validate_platform_scope
 from ..catalog.research_metadata import ResearchMetadata, availability_key
 from ..catalog.service import Catalog
+from ..correlation import MIN_SAMPLES, THRESHOLD, WINDOW_YEARS
 from ..models import Account, Alpha, BacktestItem, Job, JobItem, ResearchRequest, SimulationAttempt, now
 from ..research.serialization import encode_snapshot
 from ..research.workspace_contracts import FieldAvailabilityInput
@@ -48,7 +49,15 @@ class ResearchAccess:
                 "settings_schema": DirectCandidate.model_json_schema(),
                 "confirmation": "调用者须已获本批执行授权；直接提交后返回稳定运行 ID",
                 "duplicate_policies": ["reject", "rerun"], "permissions": sorted(self.principal.scopes),
-                "metadata_only": True, "actual_platform_allowance": None}
+                "metadata_only": True, "actual_platform_allowance": None,
+                "self_correlation": {
+                    "check_with": "check_self_correlation", "read_with": "get_self_correlation",
+                    "job_with": "get_refresh_job", "max_targets": 100, "source": "local",
+                    "reference_scope": "本地已同步的同地区已提交 Alpha，排除自身",
+                    "method": "累计 PnL 日变化的 Pearson 相关系数，取带符号最大值",
+                    "threshold": THRESHOLD, "min_samples": MIN_SAMPLES, "window_years": WINDOW_YEARS,
+                    "platform_check": False,
+                }}
 
     async def catalog(self, args):
         data = await Catalog(self.db).search(args.filters, args.dataset_id)
@@ -101,7 +110,7 @@ class ResearchAccess:
 
     async def refresh_job(self, args):
         job = await self.db.get(Job, args.job_id)
-        if not job or job.kind not in {"catalog_sync", "field_sync", "pnl_refresh"}:
+        if not job or job.kind not in {"catalog_sync", "field_sync", "pnl_refresh", "self_correlation"}:
             raise ResearchError("NOT_FOUND", "研究刷新任务不存在")
         result = await self.business.get_job_status(args.job_id)
         query = select(JobItem).where(JobItem.job_id == job.id, JobItem.error.is_not(None))
@@ -111,6 +120,27 @@ class ResearchAccess:
         return {**result, "job_id": job.id, "artifact_reference": job.payload,
                 "errors": page([{"alpha_id": e.alpha_id, "error": e.error} for e in errors], total, args.limit, args.offset)}
 
+    async def check_self_correlation(self, args):
+        """Queue local checks for synced IDs; caller commits before waking the runner.
+
+        The shared job service deduplicates active batches. Missing PnL is fetched
+        by the durable runner, so slow upstream reads do not hold the MCP call.
+        """
+        ids = sorted(set(args.alpha_ids))
+        existing = set(await self.db.scalars(select(Alpha.id).where(Alpha.id.in_(ids))))
+        if existing != set(ids):
+            raise ResearchError("NOT_FOUND", "部分 Alpha 尚未同步，请先导入", affected_items=sorted(set(ids)-existing))
+        job = await self.business.create_sync_job(JobInput(kind="self_correlation", alpha_ids=ids))
+        self.wake = "jobs"
+        return {"job_id": job["id"], "status": job["status"], "alpha_ids": ids,
+                "source": "local", "job_with": "get_refresh_job", "read_with": "get_self_correlation"}
+
+    async def self_correlation(self, args):
+        """Read the latest local result without fetching PnL or starting a check."""
+        data = await self.business.get_self_correlation(args.alpha_id)
+        status = "not_cached" if not data["cached"] else "stale" if data["result"]["stale"] else "available"
+        return {"alpha_id": args.alpha_id, "source": "local", "status": status, **data}
+
     async def history(self, args):
         return await self.evidence.history(args)