feat: 更新首页信息处理模型，支持内存缓存与过期机制；添加全量目录同步脚本

backend/app/home_information.py

@@ -4,6 +4,7 @@ Only allowlisted platform paths are fetched. HTML is converted to inert text;
 platform content is never an instruction and never supplies model/tool endpoints.
 """
 import asyncio
+import calendar
 import hashlib
 import json
 import math
@@ -131,10 +132,10 @@ def next_offset(data, path, current):
         raise WqError("平台分页信息无法识别", "invalid_response") from None
 
 
-async def all_pages(client, path):
+async def all_pages(client, path, limit=None):
     output, offset = [], 0
     for _ in range(100):
-        data = await client.get(path, params={"offset": offset})
+        data = await client.get(path, params={"offset": offset, **({"limit": limit} if limit else {})})
         output.extend(rows(data))
         offset = next_offset(data, path, offset)
         if offset is None:
@@ -160,14 +161,17 @@ def competition(item, user):
 async def source(client, module, user, offset, cid):
     if module == "messages":
         path = "/users/self/messages"
-        data = await client.get(path, params={"offset": offset})
         items = []
-        for item in rows(data):
+        for item in await all_pages(client, path, limit=100):
+            created = instant(item.get("dateCreated"))
+            if not created or not month_start() <= created <= now():
+                continue
             body, links = plain(item.get("description"))
             items.append(dict(id=text(item.get("id")), title=text(item.get("title")) or "平台消息",
                               type=text(item.get("type")), date=text(item.get("dateCreated")),
                               description=body, links=links, url="https://platform.worldquantbrain.com/messages/" + ("announcements" if item.get("type") == "ANNOUNCEMENT" else "notifications")))
-        return dict(items=items, offset=offset, next_offset=next_offset(data, path, offset), total=number(data.get("count")))
+        items.sort(key=lambda item: instant(item["date"]), reverse=True)
+        return dict(items=items)
     if module == "leaderboard":
         data = await client.get("/consultant/boards/leader", params={"user": user})
         matches = [r for r in rows(data) if r.get("user") == user]
@@ -227,8 +231,74 @@ def config_version(config):
     return digest([config.description_model, config.base_url, config.api_key_encrypted, config.protocol])
 
 
+def month_start():
+    """One calendar month before the Eastern wall time, clamped at month end."""
+    at = now().astimezone(EASTERN)
+    year, month = (at.year, at.month - 1) if at.month > 1 else (at.year - 1, 12)
+    return at.replace(year=year, month=month, day=min(at.day, calendar.monthrange(year, month)[1]))
+
+
+def message_page(request, user, offset):
+    """Return a detached page; neither source text nor AI output enters an ORM session."""
+    cached = request.app.state.home_message_cache.get(user)
+    if cached is None:
+        return None
+    if now() - cached.created_at >= timedelta(minutes=15):
+        del request.app.state.home_message_cache[user]
+        return None
+    content = None
+    if cached.content is not None:
+        # Enforce the rolling boundary even on cached reads and generation commits.
+        filtered = [item for item in cached.content["items"]
+                    if month_start() <= instant(item["date"]) <= now()]
+        if len(filtered) != len(cached.content["items"]):
+            cached.analyses.clear()
+        cached.content = {"items": filtered}
+        items = cached.content["items"]
+        content = dict(items=items[offset:offset + 10], total=len(items), offset=offset,
+                       next_offset=offset + 10 if offset + 10 < len(items) else None)
+    return SimpleNamespace(content=content, version=digest(content), fetched_at=cached.fetched_at,
+                           error=cached.error, analysis=cached.analyses.get(offset))
+
+
+async def read_messages(request, user, offset, refresh):
+    """Keep only a 15-minute in-process cache; restart/expiry discards interpretations too."""
+    async with lock(request, (user, "messages")):
+        cache = request.app.state.home_message_cache
+        for owner, entry in list(cache.items()):
+            if now() - entry.created_at >= timedelta(minutes=15):
+                del cache[owner]
+        cached = cache.get(user)
+        if cached is not None and not refresh:
+            return message_page(request, user, offset)
+        try:
+            content = await source(request.app.state.runner.client, "messages", user, 0, "")
+            error = None
+        except WqError as exc:
+            content, error = None, str(exc)
+        if await identity(request) != user:
+            raise HTTPException(409, "账户已变化，请重新读取信息")
+        if cached is None:
+            cached = SimpleNamespace(content=None, fetched_at=None, created_at=now(), error=None, analyses={})
+            cache[user] = cached
+        cached.error = error
+        if content is not None:
+            if cached.content != content:
+                cached.analyses.clear()
+            cached.content, cached.fetched_at = content, now()
+        return message_page(request, user, offset)
+
+
+async def cached_record(request, db, user, module, offset, key):
+    if module == "messages":
+        return message_page(request, user, offset)
+    return await db.get(HomeInformation, (user, key))
+
+
 async def read_record(request, user, module, offset, cid, refresh=False):
     key = resource_key(module, offset, cid)
+    if module == "messages":
+        return await read_messages(request, user, offset, refresh)
     async with lock(request, (user, key)):
         async with request.app.state.sessions() as db:
             record = await db.get(HomeInformation, (user, key))
@@ -303,12 +373,16 @@ async def output(request, user, module, record):
         config = await db.get(AISettings, 1)
     _, version = await analysis_sources(request, user, module, record)
     analysis = record.analysis
+    if module == "messages" and analysis and analysis["source_version"] != version:
+        request.app.state.home_message_cache[user].analyses.pop(record.content["offset"], None)
+        analysis = None
     if analysis:
         analysis = {**analysis, "outdated": analysis["source_version"] != version or analysis["config_version"] != config_version(config)}
         analysis.pop("config_version", None)
     return dict(content=temporal(record.content, module), fetched_at=record.fetched_at.replace(tzinfo=timezone.utc) if record.fetched_at else None, error=record.error,
                 stale=bool(record.error) or bool(module == "leaderboard" and record.content and record.content["scope"] != "dailyOsmosisRank:" + now().astimezone(EASTERN).date().isoformat()) or bool(record.fetched_at and now() - record.fetched_at.replace(tzinfo=timezone.utc) > timedelta(hours=24)),
                 source_version=record.version, analysis=analysis,
+                ephemeral=module == "messages",
                 can_generate=bool(config.description_model and config.api_key_encrypted and config.base_url and record.content))
 
 
@@ -364,7 +438,7 @@ async def generate(request: Request, module: Module, offset: int = Query(0, ge=0
         raise HTTPException(409, "该模块正在生成解读，请稍候")
     async with generation_lock:
         async with request.app.state.sessions() as db:
-            record = await db.get(HomeInformation, (user, key))
+            record = await cached_record(request, db, user, module, offset, key)
             config = await db.get(AISettings, 1)
             if not config.description_model or not config.api_key_encrypted or not config.base_url:
                 raise HTTPException(409, "请先配置基础信息处理模型及共享连接配置")
@@ -396,13 +470,17 @@ async def generate(request: Request, module: Module, offset: int = Query(0, ge=0
         await ai.authorize(token_hash(request.cookies["wq_session"]))
         if await identity(request) != user:
             raise HTTPException(409, "账户已变化，请重新生成")
-        async with lock(request, (user, key)):
+        async with lock(request, (user, "messages" if module == "messages" else key)):
             async with request.app.state.sessions.begin() as db:
-                record = await db.get(HomeInformation, (user, key))
+                record = await cached_record(request, db, user, module, offset, key)
                 current_config = await db.get(AISettings, 1)
+                if record is None:
+                    raise HTTPException(409, "公告内存缓存已失效，请刷新后重新生成")
                 _, current_version = await analysis_sources(request, user, module, record)
                 if current_version != version or config_version(current_config) != fingerprint:
                     raise HTTPException(409, "生成期间来源或模型配置已变化，已保留上次解读，请重新生成")
                 record.analysis = dict(**interpretation, source_version=version, config_version=fingerprint,
                                        model=connection.model, generated_at=now().isoformat())
+                if module == "messages":
+                    request.app.state.home_message_cache[user].analyses[offset] = record.analysis
         return await output(request, user, module, record)

backend/app/main.py

@@ -138,6 +138,7 @@ def create_app(settings=None, wq_client=None, ai_model_factory=None):
     app.state.settings = settings
     app.state.ai = ai_runtime
     app.state.home_information_locks = {}
+    app.state.home_message_cache = {}
     app.state.research = research_runtime
     app.state.mcp = mcp_runtime
     login_failures = defaultdict(list)

backend/migrations/versions/0017_remove_message_cache.py

@@ -0,0 +1,18 @@
+"""Remove persisted announcement sources and interpretations; use memory only."""
+import sqlalchemy as sa
+from alembic import op
+
+revision = "0017"
+down_revision = "0016"
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    cache = sa.table("home_information", sa.column("resource", sa.String()))
+    op.execute(cache.delete().where(cache.c.resource.like("messages:%")))
+
+
+def downgrade():
+    # Platform cache is reproducible; deleted text and interpretations are not restored.
+    pass

backend/tests/test_home_information.py

@@ -35,6 +35,7 @@ async def setup(app, monkeypatch):
     async with app.state.sessions.begin() as db:
         account = await db.get(Account, 1)
         account.connection_status, account.wq_user_id = "connected", "TEST_USER"
+    monkeypatch.setattr(home, "now", lambda: datetime.fromisoformat("2026-09-12T12:00:00+00:00"))
     calls, state = [], {"rank": 25, "fail": set(), "agreement": "Participants must use GLOBAL region. Delay must be 1."}
 
     async def get(path, params=None, headers=None):
@@ -43,7 +44,7 @@ async def setup(app, monkeypatch):
             raise WqError("资源暂不可用")
         if path == "/users/self/messages":
             offset = params["offset"]
-            return page([{"id": f"msg{offset}", "title": "Update", "description": "<p>News</p><script>secret()</script><a href='javascript:alert(1)'>bad</a>", "dateCreated": "2026-09-11T12:00:00-04:00"}],
+            return page([{"id": f"msg{i}", "title": "Update", "description": "<p>News</p><script>secret()</script><a href='javascript:alert(1)'>bad</a>", "dateCreated": "2026-09-11T12:00:00-04:00"} for i in (range(10) if offset == 0 else [10])],
                         "https://api.worldquantbrain.com/users/self/messages?offset=1" if offset == 0 else None)
         if path == "/consultant/boards/leader":
             assert params == {"user": "TEST_USER"}
@@ -64,12 +65,12 @@ async def setup(app, monkeypatch):
 async def test_cache_pagination_failure_and_account_isolation(app, logged_in, monkeypatch):
     calls, state = await setup(app, monkeypatch)
     first = (await logged_in.get(PREFIX + "/messages")).json()
-    assert first["content"]["next_offset"] == 1
+    assert first["content"]["next_offset"] == 10
     assert "secret()" not in str(first) and "javascript:" not in str(first)
     assert first["analysis"] is None and not first["can_generate"]
-    assert (await logged_in.get(PREFIX + "/messages")).json() == first and len(calls) == 1
-    second = (await logged_in.get(PREFIX + "/messages?offset=1")).json()
-    assert second["content"]["items"][0]["id"] == "msg1"
+    assert (await logged_in.get(PREFIX + "/messages")).json() == first and len(calls) == 2
+    second = (await logged_in.get(PREFIX + "/messages?offset=10")).json()
+    assert second["content"]["items"][0]["id"] == "msg10"
     state["fail"].add("/users/self/messages")
     failed = (await logged_in.post(PREFIX + "/messages/refresh")).json()
     assert failed["stale"] and failed["error"]
@@ -193,7 +194,7 @@ async def test_failed_grounding_preserves_prior_analysis(app, logged_in, monkeyp
 async def test_concurrent_first_reads_are_coalesced(app, logged_in, monkeypatch):
     calls, _ = await setup(app, monkeypatch)
     results = await asyncio.gather(*[logged_in.get(PREFIX + "/messages") for _ in range(4)])
-    assert all(r.status_code == 200 for r in results) and len(calls) == 1
+    assert all(r.status_code == 200 for r in results) and len(calls) == 2
 
 
 async def test_event_sources_include_competitions_and_current_day(app, logged_in, monkeypatch):
@@ -298,3 +299,93 @@ async def test_shared_connection_change_invalidates_ai(app, logged_in, monkeypat
         setattr(await db.get(AISettings, 1), field, value)
     assert (await logged_in.get(PREFIX + '/competition' + QUERY)).json()['analysis']['outdated']
     assert calls == ['basic-model']
+
+
+@pytest.mark.parametrize('at,expected', [
+    ('2026-03-31T12:00:00-04:00', '2026-02-28T12:00:00-05:00'),
+    ('2024-03-31T12:00:00-04:00', '2024-02-29T12:00:00-05:00'),
+    ('2026-01-31T12:00:00-05:00', '2025-12-31T12:00:00-05:00'),
+])
+def test_recent_month_uses_eastern_calendar_month(monkeypatch, at, expected):
+    monkeypatch.setattr(home, 'now', lambda: datetime.fromisoformat(at))
+    assert home.month_start().isoformat() == expected
+
+
+async def test_recent_messages_scan_pages_filter_unknown_future_and_boundary(monkeypatch):
+    monkeypatch.setattr(home, 'now', lambda: datetime.fromisoformat('2026-03-31T12:00:00-04:00'))
+    calls = []
+    class Client:
+        async def get(self, path, params):
+            calls.append(params)
+            if params['offset'] == 0:
+                return page([{'id': 'old', 'dateCreated': '2026-02-28T11:59:59-05:00'},
+                             {'id': 'unknown'}, {'id': 'future', 'dateCreated': '2026-04-01T00:00:00Z'}],
+                            'https://api.worldquantbrain.com/users/self/messages?offset=3&limit=100')
+            return page([{'id': 'boundary', 'dateCreated': '2026-02-28T12:00:00-05:00'},
+                         {'id': 'today', 'dateCreated': '2026-03-31T12:00:00-04:00'}])
+    data = await home.source(Client(), 'messages', 'TEST_USER', 0, '')
+    assert [item['id'] for item in data['items']] == ['today', 'boundary']
+    assert calls == [{'offset': 0, 'limit': 100}, {'offset': 3, 'limit': 100}]
+
+
+async def test_messages_and_ai_never_persist_and_expire_without_auto_generation(app, logged_in, monkeypatch):
+    platform_calls, _ = await setup(app, monkeypatch)
+    await model_setup(app)
+    model_calls = []
+    def respond(messages, info):
+        return ModelResponse(parts=[ToolCallPart(info.output_tools[0].name, {'items': [], 'suggestions': []})])
+    @asynccontextmanager
+    async def factory(config, settings):
+        model_calls.append(config.model)
+        yield FunctionModel(respond)
+    app.state.ai.model_factory = factory
+    # Legacy rows must never be used; migration will remove them on deployment.
+    async with app.state.sessions.begin() as db:
+        db.add(HomeInformation(user_id='TEST_USER', resource='messages:0', content={'items': [{'title': 'legacy'}]}))
+    first = (await logged_in.get(PREFIX + '/messages')).json()
+    assert first['ephemeral'] and first['content']['total'] == 11
+    generated = await logged_in.post(PREFIX + '/messages/generate')
+    assert generated.status_code == 200, generated.text
+    assert generated.json()['analysis']['model'] == 'basic-model'
+    await logged_in.get(PREFIX + '/messages')
+    await logged_in.get(PREFIX + '/messages?offset=10')
+    assert len(platform_calls) == 2 and model_calls == ['basic-model']
+    async with app.state.sessions() as db:
+        saved = (await db.scalars(sa.select(HomeInformation))).all()
+        assert len(saved) == 1 and saved[0].content == {'items': [{'title': 'legacy'}]}
+        assert saved[0].analysis is None
+    monkeypatch.setattr(home, 'now', lambda: datetime.fromisoformat('2026-09-12T12:15:00+00:00'))
+    assert (await logged_in.post(PREFIX + '/messages/generate')).status_code == 409
+    reloaded = (await logged_in.get(PREFIX + '/messages')).json()
+    assert reloaded['analysis'] is None and len(platform_calls) == 4
+    assert model_calls == ['basic-model']
+
+
+async def test_message_window_rechecks_memory_and_removes_expired_interpretation(app, logged_in, monkeypatch):
+    await setup(app, monkeypatch)
+    monkeypatch.setattr(home, 'now', lambda: datetime.fromisoformat('2026-09-12T12:00:00+00:00'))
+    async def upstream(path, params=None):
+        return page([{'id': 'boundary', 'dateCreated': '2026-08-12T08:00:00-04:00'}])
+    monkeypatch.setattr(app.state.runner.client, 'get', upstream)
+    assert (await logged_in.get(PREFIX + '/messages')).json()['content']['total'] == 1
+    app.state.home_message_cache['TEST_USER'].analyses[0] = {'old': 'interpretation'}
+    monkeypatch.setattr(home, 'now', lambda: datetime.fromisoformat('2026-09-12T12:00:01+00:00'))
+    result = (await logged_in.get(PREFIX + '/messages')).json()
+    assert result['content']['total'] == 0 and result['analysis'] is None
+
+
+def test_message_cleanup_migration_only_removes_message_cache(tmp_path):
+    path = Path(__file__).parents[1] / 'migrations/versions/0017_remove_message_cache.py'
+    spec = importlib.util.spec_from_file_location('message_cleanup', path)
+    migration = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(migration)
+    engine = sa.create_engine(f'sqlite:///{tmp_path}/cleanup.db')
+    with engine.begin() as conn:
+        conn.exec_driver_sql('CREATE TABLE home_information (user_id TEXT, resource TEXT, content TEXT, analysis TEXT)')
+        for user, resource in [('A', 'messages:0'), ('B', 'messages:10'), ('A', 'events:'), ('A', 'competition:ARC2026')]:
+            conn.exec_driver_sql('INSERT INTO home_information VALUES (?, ?, ?, ?)', (user, resource, 'source', 'ai'))
+        with Operations.context(MigrationContext.configure(conn)):
+            migration.upgrade()
+            migration.upgrade()
+        assert conn.exec_driver_sql('SELECT resource FROM home_information ORDER BY resource').scalars().all() == ['competition:ARC2026', 'events:']
+    engine.dispose()