Add three-stage cross-domain news research and reading briefings
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
1 parent
ae35d3d608
commit
80d266dba7
44 files changed
+2682
-574
No files matched your search
@@ -0,0 +1,211 @@
|
||||
"""Research and briefing acceptance uses synthetic I/O only."""
|
||||
import asyncio
|
||||
from types import SimpleNamespace
|
||||
from unittest.mock import AsyncMock
|
||||
import pytest
|
||||
|
||||
|
||||
def test_private_and_mixed_dns_are_rejected(trading, monkeypatch):
|
||||
from alphapulse.news_risk.research import public_address
|
||||
async def check():
|
||||
loop = asyncio.get_running_loop()
|
||||
monkeypatch.setattr(loop, 'getaddrinfo', AsyncMock(return_value=[(None, None, None, None, ('127.0.0.1', 80))]))
|
||||
with pytest.raises(ValueError, match='非公开'): await public_address('https://example.invalid/test')
|
||||
monkeypatch.setattr(loop, 'getaddrinfo', AsyncMock(return_value=[(None, None, None, None, ('8.8.8.8', 80)), (None, None, None, None, ('10.0.0.1', 80))]))
|
||||
with pytest.raises(ValueError, match='非公开'): await public_address('https://example.invalid/test')
|
||||
for url in ('file:///etc/passwd', 'http://user:[email protected]', 'http://example.invalid:8000'):
|
||||
with pytest.raises(ValueError): await public_address(url)
|
||||
asyncio.run(check())
|
||||
|
||||
|
||||
def test_read_web_requires_discovered_url_and_budget(trading):
|
||||
from alphapulse.news_risk.research import Research
|
||||
research = Research()
|
||||
with pytest.raises(ValueError, match='本轮搜索'):
|
||||
asyncio.run(research.tool('read_web', {'url': 'https://example.invalid'}))
|
||||
research.counts['read_web'] = 4
|
||||
with pytest.raises(ValueError, match='预算'):
|
||||
asyncio.run(research.tool('read_web', {'url': 'https://example.invalid'}))
|
||||
|
||||
|
||||
def test_briefing_covers_all_packages_across_batches(trading, monkeypatch):
|
||||
from alphapulse.news_risk import briefing
|
||||
provider = SimpleNamespace(max_tokens=100, context_window=7000)
|
||||
inputs = [{'id': i, 'revision': 2, 'importance_stars': 3, 'result': {'summary': 'x'*1600}} for i in range(15)]
|
||||
batches = []
|
||||
async def complete(provider, system, payload, schema):
|
||||
assert briefing.fits_context(provider, system, payload, schema)
|
||||
if schema is briefing.Ranked:
|
||||
batches.append(payload['packages'])
|
||||
return briefing.Ranked(reading=[briefing.Reading(id=p['id'], revision=2, priority=p['id'], reason='Read') for p in payload['packages']], notes='Notes'), {}
|
||||
trend = briefing.Trend(summary='Unknown', conditions='Unknown', counter_evidence='Unknown', watchpoints='Unknown')
|
||||
return briefing.Synthesis(summary='Unknown', market='Unknown', short_term=trend, medium_term=trend, references=[]), {}
|
||||
monkeypatch.setattr(briefing, 'complete', complete)
|
||||
result = asyncio.run(briefing.generate(provider, 'rules', inputs))
|
||||
assert len(batches) > 1
|
||||
assert [p['id'] for p in result['reading']] == list(reversed(range(15)))
|
||||
|
||||
|
||||
@pytest.mark.parametrize('ids', [[], [1, 1], [2]])
|
||||
def test_briefing_rejects_missing_duplicate_and_unknown_ids(trading, monkeypatch, ids):
|
||||
from alphapulse.news_risk import briefing
|
||||
async def complete(*args):
|
||||
return briefing.Ranked(reading=[briefing.Reading(id=i, revision=1, priority=50, reason='Read') for i in ids], notes='Notes'), {}
|
||||
monkeypatch.setattr(briefing, 'complete', complete)
|
||||
with pytest.raises(ValueError, match='遗漏、重复'):
|
||||
asyncio.run(briefing.generate(SimpleNamespace(max_tokens=100, context_window=10000), 'rules', [{'id': 1, 'revision': 1, 'importance_stars': 5}]))
|
||||
|
||||
|
||||
def test_high_importance_positive_package_is_valid(trading):
|
||||
from alphapulse.news_risk import pipeline
|
||||
from test_news_pipeline import event_result
|
||||
result = event_result(pipeline, [pipeline.Evidence(article_id=1, quote='突破')])
|
||||
result.risk_stars = 0; result.importance_stars = 5
|
||||
pipeline.validate_event(result, {1: {'title': '科技突破'}})
|
||||
assert result.importance_stars == 5 and result.risk_stars == 0
|
||||
|
||||
|
||||
def test_public_fetch_pins_address_and_rechecks_redirect(trading, monkeypatch):
|
||||
import httpx
|
||||
from alphapulse.news_risk import research
|
||||
calls = []
|
||||
original = httpx.AsyncClient
|
||||
async def resolve(url):
|
||||
from urllib.parse import urlsplit
|
||||
if 'private.invalid' in url: raise ValueError('非公开地址')
|
||||
return urlsplit(url), '8.8.8.8'
|
||||
async def handle(request):
|
||||
calls.append(request)
|
||||
assert request.url.host == '8.8.8.8' and request.headers['host'] == 'public.invalid'
|
||||
assert request.extensions['sni_hostname'] == 'public.invalid'
|
||||
return httpx.Response(302, headers={'location': 'http://private.invalid'})
|
||||
monkeypatch.setattr(research, 'public_address', resolve)
|
||||
monkeypatch.setattr(httpx, 'AsyncClient', lambda **kwargs: original(transport=httpx.MockTransport(handle)))
|
||||
with pytest.raises(ValueError, match='非公开'):
|
||||
asyncio.run(research.fetch_public('https://public.invalid'))
|
||||
assert len(calls) == 1
|
||||
|
||||
|
||||
def test_failed_review_can_reuse_saved_evidence_without_new_io(trading):
|
||||
from alphapulse.news_risk.research import Research
|
||||
research = Research()
|
||||
record = {'tool': 'read_web', 'arguments': {'url': 'https://example.invalid'}, 'result': {'article_id': -1, 'content': 'Original'}}
|
||||
research.restore([record])
|
||||
assert asyncio.run(research.tool('read_web', record['arguments']))['content'] == 'Original'
|
||||
assert not research.records and research.counts['read_web'] == 0
|
||||
|
||||
|
||||
def test_research_stops_after_eight_tool_rounds_and_retains_failures(trading, monkeypatch):
|
||||
from alphapulse.news_risk import research
|
||||
from pydantic import BaseModel
|
||||
class Result(BaseModel):
|
||||
summary: str
|
||||
rounds = []
|
||||
async def stream(provider, system, messages, tools, effort):
|
||||
rounds.append(tools)
|
||||
if len(rounds) == 9:
|
||||
assert [tool.name for tool in tools] == ['submit']
|
||||
yield research.llm.Completion(tool_calls=[{'id': 'submit', 'name': 'submit', 'arguments': {'summary': '证据不足'}}])
|
||||
else:
|
||||
yield research.llm.Completion(tool_calls=[{'id': str(len(rounds)), 'name': 'unknown_tool', 'arguments': {}}])
|
||||
monkeypatch.setattr(research.llm, 'stream', stream)
|
||||
review = research.Research()
|
||||
result, _ = asyncio.run(review.run(SimpleNamespace(max_tokens=1000, context_window=200000, reasoning_effort=None), 'rules', {}, Result))
|
||||
assert result.summary == '证据不足'
|
||||
assert len(rounds) == 9 and len(review.records) == 8
|
||||
assert all('error' in record['result'] for record in review.records)
|
||||
|
||||
|
||||
@pytest.mark.parametrize('mode,created', [('unchanged', False), ('ordinary_wait', False), ('ordinary_due', True), ('urgent_wait', False), ('urgent_due', True), ('expired', True)])
|
||||
def test_reading_updates_only_for_changes_and_respects_aggregation(trading, monkeypatch, mode, created):
|
||||
from datetime import UTC, datetime, timedelta
|
||||
from alphapulse.news_risk import worker
|
||||
now = datetime.now(UTC)
|
||||
event = SimpleNamespace(id=1, published_revision=2, importance_stars=5 if mode.startswith('urgent') else 3,
|
||||
category='politics', tags=['政策'], result={'summary': '当前说明'}, analyzed_at=now)
|
||||
semantic = [{'id': event.id, 'importance_stars': event.importance_stars, 'result': event.result}]
|
||||
fingerprint = worker.briefing.fingerprint(semantic, {}) if mode == 'unchanged' else 'previous'
|
||||
latest = SimpleNamespace(created_at=now-timedelta(seconds=30 if mode == 'urgent_wait' else 120), quotes={'fingerprint': fingerprint})
|
||||
if mode in ('ordinary_due', 'expired'): latest.quotes['dirty_since'] = (now-timedelta(minutes=16)).isoformat()
|
||||
session = AsyncMock()
|
||||
session.__aenter__.return_value = session
|
||||
session.get.return_value = SimpleNamespace(enabled=True)
|
||||
session.scalar.side_effect = [latest, None]
|
||||
session.scalars.return_value = SimpleNamespace(all=lambda: [] if mode == 'expired' else [event])
|
||||
added = []
|
||||
session.add = added.append
|
||||
monkeypatch.setattr(worker, 'SessionLocal', lambda: session)
|
||||
monkeypatch.setattr(worker, 'configuration', AsyncMock(return_value=(SimpleNamespace(model='advanced'), 'rules', {}, 'rules-key')))
|
||||
monkeypatch.setattr(worker.briefing, 'generate', AsyncMock(return_value={'reading': [], 'synthesis': None, 'usage': []}))
|
||||
asyncio.run(worker.outlook())
|
||||
assert bool(added) is created
|
||||
if created: assert added[0].state == 'done'
|
||||
if mode == 'ordinary_wait': assert latest.quotes['dirty_since']
|
||||
|
||||
|
||||
def test_truncated_reading_batches_split_until_all_versions_are_ranked(trading, monkeypatch):
|
||||
from alphapulse.news_risk import briefing
|
||||
from alphapulse.news_risk.service import OutputTruncated
|
||||
inputs = [{'id': i, 'revision': 3, 'importance_stars': 3, 'result': {'summary': 'Short'}} for i in range(1, 41)]
|
||||
calls = []
|
||||
async def complete(provider, system, payload, schema):
|
||||
calls.append(payload)
|
||||
if schema is briefing.Ranked:
|
||||
if len(payload['packages']) > 5: raise OutputTruncated('Synthetic output limit', {'output_tokens': 256})
|
||||
return briefing.Ranked(reading=[briefing.Reading(id=p['id'], revision=3, priority=100-p['id'], reason='Read') for p in payload['packages']], notes='Notes'), {'output_tokens': 100}
|
||||
trend = briefing.Trend(summary='Unknown', conditions='Unknown', counter_evidence='Unknown', watchpoints='Unknown')
|
||||
return briefing.Synthesis(summary='Unknown', market='Unknown', short_term=trend, medium_term=trend, references=[]), {}
|
||||
monkeypatch.setattr(briefing, 'complete', complete)
|
||||
result = asyncio.run(briefing.generate(SimpleNamespace(max_tokens=256, context_window=200000), 'rules', inputs))
|
||||
assert [r['id'] for r in result['reading']] == list(range(1, 41))
|
||||
assert all(r['revision'] == 3 for r in result['reading'])
|
||||
assert len(result['usage']) == len(calls)
|
||||
assert any(u.get('output_tokens') == 256 for u in result['usage'])
|
||||
|
||||
|
||||
def test_single_package_truncation_is_bounded_and_does_not_retry_other_errors(trading, monkeypatch):
|
||||
from alphapulse.news_risk import briefing
|
||||
from alphapulse.news_risk.service import OutputTruncated
|
||||
complete = AsyncMock(side_effect=OutputTruncated('Synthetic output limit'))
|
||||
monkeypatch.setattr(briefing, 'complete', complete)
|
||||
with pytest.raises(OutputTruncated, match='单包排序'):
|
||||
asyncio.run(briefing.generate(SimpleNamespace(max_tokens=256, context_window=200000), 'rules', [{'id': 1, 'revision': 1, 'importance_stars': 3}]))
|
||||
assert complete.await_count == 1
|
||||
complete = AsyncMock(side_effect=ValueError('Malformed ranking'))
|
||||
monkeypatch.setattr(briefing, 'complete', complete)
|
||||
with pytest.raises(ValueError, match='Malformed'):
|
||||
asyncio.run(briefing.generate(SimpleNamespace(max_tokens=256, context_window=200000), 'rules', [{'id': 1}, {'id': 2}]))
|
||||
assert complete.await_count == 1
|
||||
|
||||
|
||||
@pytest.mark.parametrize('change,expected', [('links', False), ('verdict', True), ('risk', True), ('fact', True)])
|
||||
def test_reposts_do_not_trigger_advanced_calls_but_review_changes_do(trading, monkeypatch, change, expected):
|
||||
from copy import deepcopy
|
||||
from datetime import UTC, datetime, timedelta
|
||||
from alphapulse.news_risk import worker, briefing
|
||||
now = datetime.now(UTC)
|
||||
inputs = [{'id': 1, 'revision': 1, 'importance_stars': 5, 'result': {'facts': '公开说明', 'risk_stars': 1,
|
||||
'evidence_refs': [{'article_id': 1, 'quote': '公开说明'}],
|
||||
'claims': [{'statement': '公开说明', 'verdict': 'partial', 'evidence_refs': [{'article_id': 1, 'quote': '公开说明'}]}]}}]
|
||||
semantic = briefing.semantic_packages(inputs)
|
||||
latest = SimpleNamespace(created_at=now-timedelta(minutes=2), quotes={'fingerprint': briefing.fingerprint(semantic, {}),
|
||||
'important': {'1': briefing.fingerprint(semantic[0], {})}})
|
||||
updated = deepcopy(inputs)
|
||||
updated[0]['revision'] = 2
|
||||
updated[0]['result']['evidence_refs'].append({'article_id': 2, 'quote': '公开说明'})
|
||||
updated[0]['result']['claims'][0]['evidence_refs'].append({'article_id': 2, 'quote': '公开说明'})
|
||||
if change == 'verdict': updated[0]['result']['claims'][0]['verdict'] = 'supported'
|
||||
if change == 'risk': updated[0]['result']['risk_stars'] = 5
|
||||
if change == 'fact': updated[0]['result']['facts'] = '官方修订说明'
|
||||
assert (briefing.semantic_packages(updated) != semantic) is expected
|
||||
session = AsyncMock(); session.__aenter__.return_value = session
|
||||
session.get.return_value = SimpleNamespace(enabled=True); session.scalar.side_effect = [latest, None]
|
||||
session.scalars.return_value = SimpleNamespace(all=lambda: [SimpleNamespace(id=1, published_revision=2,
|
||||
importance_stars=5, category='politics', tags=[], result=updated[0]['result'], analyzed_at=now)])
|
||||
session.add = lambda value: None
|
||||
generated = AsyncMock(return_value={'reading': [], 'synthesis': None, 'usage': []})
|
||||
monkeypatch.setattr(worker, 'SessionLocal', lambda: session)
|
||||
monkeypatch.setattr(worker, 'configuration', AsyncMock(return_value=(SimpleNamespace(model='advanced'), 'rules', {}, 'key')))
|
||||
monkeypatch.setattr(briefing, 'generate', generated)
|
||||
asyncio.run(worker.outlook())
|
||||
assert bool(generated.await_count) is expected
|
||||
Reference in new issue
Block a user