fix: 避免空 Description 模板触发误报冲突

backend/app/submission.py

@@ -72,8 +72,25 @@ def source(raw):
     }
 
 
+def comparable_description(text):
+    """Canonicalize empty platform placeholders only; preserve all substantive text.
+
+    This comparison key must never replace the reviewed text sent to the platform.
+    Unknown or partially filled templates remain exact to protect concurrent edits.
+    """
+    empty_template = r"\s*" + r"\s*".join(re.escape(heading.strip()) for heading in HEADINGS) + r"\s*"
+    return "" if not text.strip() or re.fullmatch(empty_template, text) else text
+
+
 def fingerprint(value):
-    return hashlib.sha256(json.dumps(value, sort_keys=True, ensure_ascii=False).encode()).hexdigest()
+    comparable = {
+        **value,
+        "sections": {
+            key: {**item, "description": comparable_description(item["description"])}
+            for key, item in value["sections"].items()
+        },
+    }
+    return hashlib.sha256(json.dumps(comparable, sort_keys=True, ensure_ascii=False).encode()).hexdigest()
 
 
 def parse_description(text):
@@ -300,7 +317,10 @@ async def run_check(runner, job_id, payload):
     patch = {}
     for section, item in current["sections"].items():
         before, target = expected["sections"][section], payload["descriptions"][section]
-        if item["code"] != before["code"] or item["description"] not in (before["description"], target):
+        if item["code"] != before["code"] or comparable_description(item["description"]) not in (
+            comparable_description(before["description"]),
+            comparable_description(target),
+        ):
             raise WqError("平台表达式或 Description 已变化，未覆盖；请刷新后重新核对", "conflict")
         if item["description"] != target:
             patch[section] = {"description": target}

backend/tests/test_submission.py

@@ -10,7 +10,7 @@ from pydantic_ai.models.function import FunctionModel
 from app.alphas import upsert_alpha
 from app.models import Account, AISettings, Alpha, Job, Research, SelfCorrelation
 from app.security import cipher
-from app.submission import HEADINGS, Description
+from app.submission import HEADINGS, Description, comparable_description, fingerprint, source
 from app.worldquant import WqClient
 from tests.conftest import alpha
 
@@ -28,6 +28,26 @@ ACCRUAL_FIELDS = {
 CHECKS = [{"name": "PROD_CORRELATION", "result": "FAIL", "value": 0.8, "limit": 0.7}]
 
 
+@pytest.mark.parametrize(
+    "text",
+    [
+        "plain text",
+        "Idea: actual idea\nRationale for data used:\nRationale for operators used:",
+        "Idea:\nRationale for data used: actual data\nRationale for operators used:",
+        "Idea:\nRationale for data used:\nRationale for operators used: actual operator",
+        "Idea:\nRationale for data used:",
+        "Rationale for data used:\nIdea:\nRationale for operators used:",
+    ],
+)
+def test_substantive_or_unknown_descriptions_remain_exact(text):
+    assert comparable_description(text) == text
+    original = source(alpha(regular={"code": "rank(close)", "description": text}))
+    changed = copy.deepcopy(original)
+    changed["sections"]["regular"]["description"] = text + " "
+    assert fingerprint(original) != fingerprint(changed)
+    assert original["sections"]["regular"]["description"] == text
+
+
 class Platform:
     def __init__(self, raw):
         self.raw = copy.deepcopy(raw)
@@ -141,6 +161,40 @@ async def test_local_correlation_blocks_upstream(app, logged_in, status, stale):
     assert platform.calls == []
 
 
+@pytest.mark.parametrize("kind", ["REGULAR", "SUPER"])
+@pytest.mark.parametrize("refresh", [False, True])
+@pytest.mark.parametrize(
+    "before,after",
+    [
+        ("", "Idea: \nRationale for data used: \nRationale for operators used:"),
+        ("Idea:\r\n Rationale for data used:\t Rationale for operators used: ", ""),
+        (None, " \r\n\t\u00a0"),
+    ],
+)
+async def test_empty_description_representations_allow_check(app, logged_in, kind, refresh, before, after):
+    sections = ["regular"] if kind == "REGULAR" else ["selection", "combo"]
+    raw = alpha(type=kind, **{key: {"code": "rank(close)", "description": before} for key in sections})
+    platform = await setup(app, raw)
+    state = (await logged_in.get("/api/v1/alphas/alpha1/submission")).json()
+    for key in sections:
+        platform.raw[key]["description"] = after
+    if refresh:
+        async with app.state.sessions.begin() as db:
+            await upsert_alpha(db, platform.raw)
+    target = Description(**FIELDS).text()
+    response = await logged_in.post(
+        "/api/v1/alphas/alpha1/submission-check",
+        json={"snapshot": state["snapshot"], "descriptions": dict.fromkeys(sections, target)},
+    )
+    assert response.status_code == 202, response.text
+    await app.state.runner.execute(response.json()["id"])
+    async with app.state.sessions() as db:
+        job = await db.get(Job, response.json()["id"])
+        assert job.status == "completed", job.error
+    assert platform.patches == [{key: {"description": target} for key in sections}]
+    assert ("GET", "/alphas/alpha1/check") in platform.calls
+
+
 @pytest.mark.parametrize("change", ["description", "code", "settings", "status"])
 async def test_remote_conflict_never_overwrites(app, logged_in, change):
     platform = await setup(app)