From 3d85b073a41431827f3d2cbb13c8c83087a24689 Mon Sep 17 00:00:00 2001
From: yuxuanhui <ud.k2007@gmail.com>
Date: Wed, 9 Sep 2026 19:34:08 +0800
Subject: [PATCH] fix: extend polling budget for slow WorldQuant PnL

---
 backend/app/config.py            |  1 +
 backend/app/worldquant.py        | 16 ++++++++---
 backend/tests/test_worldquant.py | 46 ++++++++++++++++++++++++++++++++
 3 files changed, 59 insertions(+), 4 deletions(-)

diff --git a/backend/app/config.py b/backend/app/config.py
index 4b381b7..76959bc 100644
--- a/backend/app/config.py
+++ b/backend/app/config.py
@@ -24,6 +24,7 @@ class Settings(BaseSettings):
     wq_base_url: str = "https://api.worldquantbrain.com"
     request_timeout: float = 30
     retry_attempts: int = Field(default=4, ge=1, le=8)
+    pnl_poll_attempts: int = Field(default=120, ge=1, le=1000)
     enable_runner: bool = True
     mcp_enabled: bool = False
     ai_request_limit: int = Field(default=12, ge=1, le=30)
diff --git a/backend/app/worldquant.py b/backend/app/worldquant.py
index 9a997bc..d1475e3 100644
--- a/backend/app/worldquant.py
+++ b/backend/app/worldquant.py
@@ -268,14 +268,15 @@ class WqClient:
     async def get(self, path: str, params=None, headers=None):
         return await self._read_json("GET", path, params=params, headers=headers)
 
-    async def _read_json(self, method: str, path: str, *, allow_list=False, **kwargs):
+    async def _read_json(self, method: str, path: str, *, allow_list=False, poll_attempts=None, **kwargs):
         """Authenticated read with shared refresh/retry handling; callers use GET or OPTIONS."""
         if not self.credentials:
             raise WqError("请先连接 WorldQuant", "disconnected")
         if not self.authenticated:
             await self.authenticate(*self.credentials)
         refreshed = False
-        for attempt in range(self.settings.retry_attempts):
+        attempts = self.settings.retry_attempts if poll_attempts is None else poll_attempts
+        for attempt in range(attempts):
             generation = self.auth_generation
             response = await self._request(method, path, **kwargs)
             if response.status_code == 401 and not refreshed:
@@ -293,7 +294,7 @@ class WqClient:
                 response.headers.get("Retry-After")
                 and self.retry_delay(response.headers["Retry-After"], 0) > 0
             ):
-                if attempt + 1 == self.settings.retry_attempts:
+                if attempt + 1 == attempts:
                     raise WqError("平台数据仍在准备，请稍后重试", "pending")
                 delay = self.retry_delay(response.headers["Retry-After"], attempt)
                 if self.on_retry:
@@ -390,7 +391,14 @@ class WqClient:
         return await self.get(f"/alphas/{alpha_id}")
 
     async def pnl(self, alpha_id):
-        return await self.get(f"/alphas/{alpha_id}/recordsets/pnl")
+        """Wait for slow PnL generation separately from transport-error retries.
+
+        Each pending response uses the platform's Retry-After delay. Exhausting
+        the bounded polling budget raises WqError with code 'pending'.
+        """
+        return await self._read_json(
+            "GET", f"/alphas/{alpha_id}/recordsets/pnl", poll_attempts=self.settings.pnl_poll_attempts
+        )
 
     async def catalog_page(self, scope, dataset_id, offset):
         """Read a single scoped page. IDs are query parameters, never upstream paths."""
diff --git a/backend/tests/test_worldquant.py b/backend/tests/test_worldquant.py
index 04bfb83..77bc838 100644
--- a/backend/tests/test_worldquant.py
+++ b/backend/tests/test_worldquant.py
@@ -265,3 +265,49 @@ async def test_concurrent_expiry_authenticates_once(settings):
     assert await asyncio.gather(client.profile(), client.profile()) == [{"id": "user"}, {"id": "user"}]
     assert auth_count == 2  # Initial connection plus one shared reauthentication.
     await client.close()
+
+
+async def test_slow_pnl_waits_beyond_network_retry_budget(settings):
+    calls, delays = 0, []
+
+    async def sleep(delay):
+        delays.append(delay)
+
+    def handler(request):
+        nonlocal calls
+        calls += 1
+        assert request.url.path == '/alphas/LL977PqL/recordsets/pnl'
+        if calls <= 6:
+            return httpx.Response(200, headers={'Retry-After': '1.0'})
+        return httpx.Response(200, json={'records': []})
+
+    client = WqClient(settings, transport=httpx.MockTransport(handler), sleep=sleep)
+    client.credentials, client.authenticated = ('test@example.com', 'secret'), True
+    try:
+        assert await client.pnl('LL977PqL') == {'records': []}
+        assert calls == 7
+        assert delays == [1.0] * 6
+    finally:
+        await client.close()
+
+
+async def test_pnl_polling_remains_bounded(settings):
+    settings.pnl_poll_attempts = 5
+    delays = []
+
+    async def sleep(delay):
+        delays.append(delay)
+
+    client = WqClient(
+        settings,
+        transport=httpx.MockTransport(lambda r: httpx.Response(200, headers={'Retry-After': '1.0'})),
+        sleep=sleep,
+    )
+    client.credentials, client.authenticated = ('test@example.com', 'secret'), True
+    try:
+        with pytest.raises(WqError) as error:
+            await client.pnl('LL977PqL')
+        assert error.value.code == 'pending'
+        assert delays == [1.0] * 4
+    finally:
+        await client.close()