eezd/AlphaPulse
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add three-stage cross-domain news research and reading briefings

Browse Source 
Group original news into tagged fact packages, review each package with evidence and read-only research, and build complete 72-hour reading lists with independent model selections.

Add paused RSS/Atom subscriptions, news-scoped Skills, versioned analysis records, and locked deployment support for SearXNG. Preserve original news and keep live migration and legacy AI cleanup separately authorized.

Validate with 604 backend tests, 49 frontend tests, 19 CI control tests, lint, type checks, production build, and disposable PostgreSQL migration and three-stage smoke checks.
This commit is contained in:
eezd committed 2026-10-31 22:08:59 +08:00
1 parent ae35d3d608
commit 80d266dba7
44 files changed
+2682 -574
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

backend/tests/test_news_risk.py
+146 -122
View File
@@ -1,6 +1,5 @@
"""Risk evidence, identity and model boundaries use synthetic inputs only."""
import asyncio
import json
from datetime import UTC, datetime
import pytest
@@ -47,44 +46,65 @@ def test_evidence_retains_quotes_present_in_source(risk):
assert item.evidence == '“安全事件”'
@pytest.mark.parametrize('valid', [True, False])
def test_enable_validates_evidence_before_saving_settings(risk, monkeypatch, valid):
def mock_enable(risk, monkeypatch, valid=True, verification='reported', direction='neutral'):
from types import SimpleNamespace
from unittest.mock import AsyncMock
from alphapulse.news_risk import pipeline, briefing
from alphapulse.api import risk as api
provider = SimpleNamespace(model='news-only', max_tokens=1000, context_window=200000)
session = SimpleNamespace(get=AsyncMock(return_value=None), merge=AsyncMock(), commit=AsyncMock())
monkeypatch.setattr(pipeline, 'configuration', AsyncMock(return_value=(provider, 'rules', {}, 'fingerprint')))
async def complete(provider, system, payload, schema):
if schema is pipeline.Grouping:
return pipeline.Grouping( reason='财经维护通知', events=[pipeline.Match(event_id=None,
group_key='maintenance', title='维护', category='company', entities=['示例公司'], fact='维护',
evidence=payload['article']['summary'] if valid else '捏造损失', urgent=False, tags=['维护'], content_kind='statement')]), {}
if schema is risk.Outlook:
return risk.Outlook(windows=[risk.Scenario(hours=h, direction='unknown', summary='不足', conditions='不足',
counter_factors='不足', uncertainty='不足', event_ids=[]) for h in (24, 48, 168)]), {}
article = payload['articles'][0]
result = pipeline.EventResult(**{**label(risk).model_dump(exclude={'event_id', 'same_event_as', 'evidence', 'stars'}), 'verification': verification,
'direction': direction}, facts='维护', timeline='维护',
asset_impacts='未知', risk_stars=0, importance_stars=3, opinions='待观察', counter_evidence='不足', watchpoints='恢复', claims=[pipeline.Claim(statement='维护', verdict='insufficient', evidence_refs=[])], related_packages=[], excluded_article_ids=[],
evidence_refs=[pipeline.Evidence(article_id=1, quote=article['summary'])])
return result, {}
async def high(provider, system, payload, schema):
if schema is briefing.Ranked:
return briefing.Ranked(reading=[briefing.Reading(id=p['id'], revision=p['revision'], priority=50, reason='重要') for p in payload['packages']], notes='虚构测试'), {}
trend = briefing.Trend(summary='未知', conditions='不足', counter_evidence='不足', watchpoints='后续')
return briefing.Synthesis(summary='不足', market='未知', short_term=trend, medium_term=trend, references=[]), {}
monkeypatch.setattr(briefing, 'complete', high)
monkeypatch.setattr(api, 'complete', complete)
monkeypatch.setattr(pipeline, 'complete', complete)
return session
def enable_response(session):
from fastapi import FastAPI
import httpx
from alphapulse.api import risk as api
session = SimpleNamespace(merge=AsyncMock(), commit=AsyncMock())
provider = SimpleNamespace(model='news-only')
monkeypatch.setattr(api, 'provider_for', AsyncMock(return_value=provider))
async def complete(actual_provider, system, payload, schema):
assert actual_provider is provider
news = payload['news'][0]
assert news['content'] and news['summary']
evidence = '“'+news['summary']+'”' if valid else '虚构的资产损失6%'
return risk.Labels(items=[label(risk).model_copy(update={'evidence': evidence})]), {}
monkeypatch.setattr(api, 'complete', complete)
app = FastAPI()
app.include_router(api.router)
app.dependency_overrides[api.require_admin] = lambda: None
app.dependency_overrides[api.get_session] = lambda: session
async def check():
async with httpx.AsyncClient(transport=httpx.ASGITransport(app), base_url='http://test') as client:
response = await client.post('/api/risk/enable', json={'provider_id': 1, 'model': 'news-only'})
assert response.status_code == (200 if valid else 502), response.text
if valid:
saved = session.merge.call_args.args[0]
assert saved.enabled and saved.model == 'news-only'
session.commit.assert_awaited_once()
else:
assert '模型证据并非输入原文引用' in response.json()['detail']
session.merge.assert_not_awaited()
session.commit.assert_not_awaited()
asyncio.run(check())
return await client.post('/api/risk/enable', json={'provider_id': 1, 'model': 'news-only'})
return asyncio.run(check())
@pytest.mark.parametrize('valid', [True, False])
def test_enable_validates_evidence_before_saving_settings(risk, monkeypatch, valid):
session = mock_enable(risk, monkeypatch, valid)
response = enable_response(session)
assert response.status_code == (200 if valid else 502), response.text
if valid:
saved = session.merge.call_args.args[0]
assert saved.enabled and saved.start_at is not None
session.commit.assert_awaited_once()
else:
assert '原文引用' in response.text
session.merge.assert_not_awaited()
@pytest.mark.parametrize('verification,direction,status', [
@@ -92,40 +112,14 @@ def test_enable_validates_evidence_before_saving_settings(risk, monkeypatch, val
('insufficient', 'bearish', 502), ('insufficient', 'mixed', 502), ('reported', 'neutral', 200),
])
def test_enable_requires_consistent_uncertainty_without_changing_model_output(risk, monkeypatch, verification, direction, status):
from types import SimpleNamespace
from unittest.mock import AsyncMock
from fastapi import FastAPI
import httpx
from alphapulse.api import risk as api
session = SimpleNamespace(merge=AsyncMock(), commit=AsyncMock())
monkeypatch.setattr(api, 'provider_for', AsyncMock(return_value=object()))
item = label(risk).model_copy(update={'verification': verification, 'direction': direction})
async def complete(provider, system, payload, schema):
item.evidence = payload['news'][0]['summary']
return risk.Labels(items=[item]), {}
monkeypatch.setattr(api, 'complete', complete)
app = FastAPI()
app.include_router(api.router)
app.dependency_overrides[api.require_admin] = lambda: None
app.dependency_overrides[api.get_session] = lambda: session
async def check():
async with httpx.AsyncClient(transport=httpx.ASGITransport(app), base_url='http://test') as client:
response = await client.post('/api/risk/enable', json={'provider_id': 1, 'model': 'news-only'})
assert response.status_code == status, response.text
assert item.direction == direction
if status == 200:
session.merge.assert_awaited_once()
session.commit.assert_awaited_once()
else:
assert 'direction 必须为 unknown' in response.json()['detail']
assert direction in response.json()['detail']
session.merge.assert_not_awaited()
session.commit.assert_not_awaited()
asyncio.run(check())
session = mock_enable(risk, monkeypatch, verification=verification, direction=direction)
response = enable_response(session)
assert response.status_code == status, response.text
if status == 200:
session.merge.assert_awaited_once()
else:
assert '无法判断方向' in response.text
session.merge.assert_not_awaited()
def test_uncertainty_contract_reaches_the_model_with_tool_schema(risk, monkeypatch):
@@ -175,10 +169,11 @@ def test_same_batch_grouping_must_not_cycle(risk):
def test_truncated_completion_is_not_a_safe_label(risk, monkeypatch):
from types import SimpleNamespace
async def stream(*args):
yield risk.llm.Completion(truncated=True)
yield risk.llm.Completion(truncated=True, usage={'output_tokens': 100})
monkeypatch.setattr(risk.llm, 'stream', stream)
with pytest.raises(ValueError, match='截断'):
with pytest.raises(risk.OutputTruncated, match='截断') as exc:
asyncio.run(risk.complete(SimpleNamespace(max_tokens=100, context_window=10000, reasoning_effort=None), '', {}, risk.Labels))
assert exc.value.usage == {'output_tokens': 100}
def test_model_override_never_changes_shared_provider(risk):
@@ -192,69 +187,35 @@ def test_model_override_never_changes_shared_provider(risk):
assert session.detached == 'original' and result.model == 'LUNA'
def test_worker_correction_and_late_backfill_keep_current_and_peak_ratings(risk, monkeypatch):
def test_debounce_is_bounded_and_urgent_bypasses_wait(risk):
from datetime import timedelta
from types import SimpleNamespace
from unittest.mock import AsyncMock
from alphapulse.news_risk import worker
from alphapulse.models import NewsItem
from alphapulse.models.risk import RiskAnalysis, RiskEvent, RiskSettings
from alphapulse.news_risk.worker import schedule
now = datetime.now(UTC)
original = label(risk)
event = RiskEvent(id=7, title=original.title, category='security', entities=['Exchange'], stars=5,
peak_stars=5, result=original.model_dump(), published_at=now-timedelta(minutes=2), updated_at=now-timedelta(minutes=2))
rows = [RiskAnalysis(id=i, news_id=i, content_hash=str(i), state='pending', input={
'title': '安全事件', 'published_at': (now-timedelta(minutes=minutes)).isoformat(),
'progress_at': (now-timedelta(minutes=minutes)).isoformat()}) for i, minutes in [(2, 1), (1, 3)]]
correction = original.model_copy(update={'id': 2, 'event_id': 7, 'stars': 1, 'verification': 'refuted'})
historical = original.model_copy(update={'id': 1, 'event_id': 7})
class Session:
def __init__(self): self.selections = iter([rows, [event]])
async def __aenter__(self): return self
async def __aexit__(self, *args): pass
async def get(self, model, identifier, **kwargs):
if model is RiskSettings: return SimpleNamespace(enabled=True)
if model is NewsItem: return SimpleNamespace(content_hash=str(identifier))
if model is RiskEvent: return event
raise AssertionError(model)
async def scalars(self, query):
values = next(self.selections)
return SimpleNamespace(all=lambda: values)
async def commit(self): pass
monkeypatch.setattr(worker, 'SessionLocal', Session)
monkeypatch.setattr(worker, 'provider_for', AsyncMock(return_value=SimpleNamespace(model='news-only', max_tokens=1000, context_window=200000)))
monkeypatch.setattr(worker, 'find_candidates', AsyncMock(return_value=([event], {1: 7, 2: 7})))
monkeypatch.setattr(worker, 'enqueue', AsyncMock())
monkeypatch.setattr(worker, 'complete', AsyncMock(return_value=(risk.Labels(items=[historical, correction]), {'input_tokens': 10})))
asyncio.run(worker.analyze())
assert event.stars == 1 and event.peak_stars == 5
assert event.result['verification'] == 'refuted'
assert event.published_at == now-timedelta(minutes=3)
assert all(row.state == 'done' and row.event_id == 7 for row in rows)
assert rows[0].usage == {'input_tokens': 10} and rows[1].usage is None
event = SimpleNamespace(revision=1, result={'summary': '原总结'}, dirty_since=now-timedelta(seconds=170))
schedule(event, now, False)
assert event.due_at == now+timedelta(seconds=10)
assert event.revision == 2
schedule(event, now, True)
assert event.due_at == now
def test_batch_packing_keeps_other_articles_queued_and_retains_linked_event(risk):
def test_long_sources_are_split_without_losing_text(risk, monkeypatch):
from types import SimpleNamespace
from alphapulse.news_risk.worker import pack_batch, batch_payload
now = datetime.now(UTC)
event = SimpleNamespace(id=7, title='安全事件', category='security', entities=['Exchange'],
published_at=now, updated_at=now, result={'summary': '安全事件'})
rows = [SimpleNamespace(id=i, news_id=i, input={'title': '安全事件', 'content': 'x'*1000}) for i in range(10)]
base = len((risk.SYSTEM + json.dumps(risk.Labels.model_json_schema(), ensure_ascii=False)).encode())
provider = SimpleNamespace(max_tokens=256, context_window=base+2000)
packed, candidates, payload = pack_batch(provider, rows, [event], {0: 7})
assert 0 < len(packed) < len(rows)
assert candidates == [event] and risk.fits_context(provider, risk.SYSTEM, payload, risk.Labels)
assert all(len(r.input['content']) == 1000 for r in rows)
rows[0].input['content'] = 'x'*10000
packed, candidates, payload = pack_batch(provider, rows, [event], {0: 7})
assert packed == [rows[0]] and candidates == [event]
assert not risk.fits_context(provider, risk.SYSTEM, payload, risk.Labels)
assert len(batch_payload(rows[1:], [])['news']) == 9
from alphapulse.news_risk import pipeline
provider = SimpleNamespace(max_tokens=100, context_window=10000)
article = {'id': 1, 'title': '安全事件', 'summary': '', 'content': '安'*16000}
seen = []
async def complete(provider, system, payload, schema):
if schema is pipeline.Extraction:
seen.append(payload['content'])
return pipeline.Extraction(facts='事实', evidence_refs=[pipeline.Evidence(article_id=1, quote=payload['content'][:1])]), {}
return pipeline.EventResult(**label(risk).model_dump(exclude={'event_id', 'same_event_as', 'evidence', 'stars'}), facts='事实', timeline='时间', asset_impacts='资产',
risk_stars=5, importance_stars=5, opinions='待观察', counter_evidence='不足', watchpoints='恢复', claims=[pipeline.Claim(statement='事件', verdict='insufficient', evidence_refs=[])], related_packages=[], excluded_article_ids=[], evidence_refs=[pipeline.Evidence(article_id=1, quote='安全事件')]), {}
monkeypatch.setattr(pipeline, 'complete', complete)
result, _ = asyncio.run(pipeline.summarize_articles(provider, 'rules', [article], {'id': 1, 'fact': 'Synthetic event'}))
assert ''.join(seen) == article['title']+'\n\n'+article['content']
assert result.risk_stars == 5
def test_context_budget_includes_unicode_and_tool_schema(risk):
@@ -263,7 +224,7 @@ def test_context_budget_includes_unicode_and_tool_schema(risk):
assert not risk.fits_context(provider, risk.SYSTEM, {'content': '风'*1000}, risk.Labels)
@pytest.mark.parametrize('endpoint', ['overview', 'events'])
@pytest.mark.parametrize('endpoint', ['overview', 'summaries'])
@pytest.mark.parametrize('hours,status', [(None, 200), ('24', 200), ('48', 200), ('168', 200), ('25', 422), ('0', 422), ('abc', 422)])
def test_window_query_parameters_over_http(risk, monkeypatch, endpoint, hours, status):
from types import SimpleNamespace
@@ -288,3 +249,66 @@ def test_window_query_parameters_over_http(risk, monkeypatch, endpoint, hours, s
if status == 200:
assert response.json()['code'] == 0
asyncio.run(check())
def test_fresh_settings_can_be_saved_without_editing_any_fields(risk):
from types import SimpleNamespace
from unittest.mock import AsyncMock
from fastapi import FastAPI
import httpx
from alphapulse.api import risk as api
session = SimpleNamespace(get=AsyncMock(return_value=None), scalar=AsyncMock(return_value=None),
merge=AsyncMock(), commit=AsyncMock())
app = FastAPI()
app.include_router(api.router)
app.dependency_overrides[api.require_admin] = lambda: None
app.dependency_overrides[api.get_session] = lambda: session
async def check():
async with httpx.AsyncClient(transport=httpx.ASGITransport(app), base_url='http://test') as client:
response = await client.get('/api/risk/settings')
assert response.status_code == 200
value = response.json()['data']
assert value['second_model'] == value['third_model'] == ''
response = await client.put('/api/risk/settings', json=value)
assert response.status_code == 200, response.text
asyncio.run(check())
saved = session.merge.call_args.args[0]
assert saved.enabled is False and saved.third_model == ''
session.commit.assert_awaited_once()
@pytest.mark.parametrize('state,published,reason', [('done', 3, '成功结果'), ('pending', 2, '排队'), ('processing', 2, '正在处理')])
def test_old_failed_analysis_cannot_requeue_a_completed_or_running_revision(risk, state, published, reason):
from types import SimpleNamespace
from unittest.mock import AsyncMock
from fastapi import HTTPException
from alphapulse.api import risk as api
event = SimpleNamespace(revision=3, published_revision=published, state=state)
row = SimpleNamespace(state='failed', summary_id=1, revision=3)
session = SimpleNamespace(get=AsyncMock(side_effect=[row, event]), commit=AsyncMock())
with pytest.raises(HTTPException) as exc:
asyncio.run(api.retry(7, session, stage='analysis'))
assert exc.value.status_code == 409 and reason in exc.value.detail
assert event.state == state
session.commit.assert_not_awaited()
def test_completed_version_recovers_a_previously_stuck_pending_package(risk, monkeypatch):
from types import SimpleNamespace
from unittest.mock import AsyncMock
from alphapulse.news_risk import worker
event = SimpleNamespace(id=1, revision=3, published_revision=3, state='pending', error='Old failure',
dirty_since=datetime.now(UTC), title='Statement', fact='Statement', category='politics', tags=['Statement'], content_kind='statement')
session = AsyncMock()
session.__aenter__.return_value = session
session.get.return_value = SimpleNamespace(enabled=True)
session.scalar.side_effect = [event, SimpleNamespace(state='done')]
session.scalars.return_value = SimpleNamespace(all=lambda: [SimpleNamespace(id=1, input={'title': 'Statement'})])
monkeypatch.setattr(worker, 'SessionLocal', lambda: session)
monkeypatch.setattr(worker, 'configuration', AsyncMock(return_value=(SimpleNamespace(model='medium'), 'rules', {}, 'key')))
analyze = AsyncMock()
monkeypatch.setattr(worker, 'summarize_articles', analyze)
asyncio.run(worker.summarize())
assert event.state == 'done' and event.error is None and event.dirty_since is None
session.commit.assert_awaited_once()
analyze.assert_not_awaited()