baodan/tests/ppt_task_lifecycle_test.py
wsb1224 b8c4e8b672 主要完成内容:
修复 PPT 异步任务无法生成的问题,包括任务变量引用错误、失败状态回写、心跳缺失任务恢复。
脱敏改为保司/产品后台统一配置,生成端不再让用户选择;任务创建时保存策略快照。
保司支持独立控制 PPT、海报 Logo 显示。
PPT 核验新增吸烟状态、币种及三个条件字段。
利益演示、退保提取调整为警告,不再阻止生成。
PPT 生成完成后可以直接返回数据核验页修改。
建立不同险种、单图/长图共六套海报字段画像。
PPT“生成场景”支持后台新增、启停和删除。
保司、产品、PPT 模板、文案模板均支持安全删除。
内置模板禁止删除,只允许停用;存在关联数据时拒绝危险删除。
补充策略变更及删除审计日志。
更新 API 文档、部署文档及修复计划实施记录。
关键交付文件:
[数据库迁移 migrate_027.py](D:/work/code/python/coding/baodanagent/api/insurance/db/migrate_027.py)
[海报字段画像 field_profiles.py](D:/work/code/python/coding/baodanagent/api/insurance/poster/field_profiles.py)
[动态场景服务 scenarios.py](D:/work/code/python/coding/baodanagent/api/insurance/ppt/scenarios.py)
[新增回归测试](D:/work/code/python/coding/baodanagent/tests/ppt_poster_optimization_test.py)
[优化修复计划书](D:/work/code/python/coding/baodanagent/docs/保险智能客服系统_PPT与海报优化修复计划书_20260731.md)
验证结果:
核心链路测试:37 passed,1 skipped
扩展回归测试:140 passed
PPT 渲染器测试:6 passed
前端生产构建:通过
Python 编译检查:通过
完整测试集:190 passed,1 failed
唯一失败为 tests/test_chat_save.py::test_chat_logs_query 未建立 Flask application context,与本次 PPT/海报链路无关。
2026-07-31 14:10:24 +08:00

323 lines
11 KiB
Python
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

"""PPT 异步任务生命周期回归测试。"""
import asyncio
import sys
import types
from pathlib import Path
import pytest
sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "api"))
from insurance.generation import task_service
from insurance.ppt import extraction as extraction_module
from insurance.ppt import regex_extractor
from insurance.ppt.extraction import ExtractionOrchestrator, ExtractionResult
from insurance.ppt.llm_client import LLMResponse, _parse_json_content, _parse_timeout_ms
from insurance.ppt.prompts import select_key_pages
class _Field:
def in_(self, _values):
return self
class _Query:
def filter_by(self, **_kwargs):
return self
def filter(self, *_args):
return self
def first(self):
return None
class _Session:
def __init__(self):
self.commits = 0
def add(self, _value):
return None
def commit(self):
self.commits += 1
class _GenerationTask:
status = _Field()
query = _Query()
def __init__(self, **kwargs):
self.id = "task-1"
self.status = "queued"
self.error_code = ""
self.error_message = None
self.finished_at = None
for key, value in kwargs.items():
setattr(self, key, value)
def to_dict(self):
return {
"id": self.id,
"status": self.status,
"errorCode": self.error_code,
"errorMessage": self.error_message,
}
def test_dispatch_failure_finishes_task(monkeypatch):
"""消息队列不可用时,不应留下永久 queued 任务。"""
fake_db = types.SimpleNamespace(session=_Session())
compat_module = types.ModuleType("insurance.db.compat")
compat_module.db = fake_db
model_module = types.ModuleType("insurance.models.generation_task")
model_module.GenerationTask = _GenerationTask
monkeypatch.setitem(sys.modules, "insurance.db.compat", compat_module)
monkeypatch.setitem(sys.modules, "insurance.models.generation_task", model_module)
synced = []
monkeypatch.setattr(
task_service,
"_dispatch_to_celery",
lambda _task: (_ for _ in ()).throw(ConnectionError("broker unavailable")),
)
monkeypatch.setattr(
task_service,
"_sync_failed_ppt_session",
lambda task, message: synced.append((task.id, message)),
)
result = task_service.create_task(
user_id="user-1",
artifact_type="ppt",
operation="parse",
workspace_id="session-1",
)
assert result["code"] == 9999
assert result["data"]["status"] == "failed"
assert result["data"]["errorCode"] == "dispatch_failed"
assert synced and synced[0][0] == result["data"]["id"]
def test_cached_extraction_reports_completion(tmp_path, monkeypatch):
"""重复解析应命中缓存,并向调用方报告完成阶段。"""
pdf_path = tmp_path / "plan.pdf"
pdf_path.write_bytes(b"%PDF-1.4")
cached = ExtractionResult(
pdf_path=str(pdf_path),
product_name="测试产品",
plan_type="savings",
status="success",
data={"product_name": "测试产品"},
)
orchestrator = ExtractionOrchestrator()
monkeypatch.setattr(orchestrator, "_load_from_cache", lambda _path: cached)
updates = []
result = asyncio.run(orchestrator.extract_plan(
str(pdf_path),
progress_callback=lambda progress, message: updates.append((progress, message)),
))
assert result is cached
assert updates == [(100, "已使用历史解析结果")]
def test_default_llm_timeout_is_bounded():
assert _parse_timeout_ms(None) == 180_000
assert _parse_timeout_ms("30000") == 30_000
def test_llm_json_parser_accepts_explanation_and_trailing_comma():
content = '结果如下:\n```json\n{"product_name": "测试产品",}\n```\n请核对。'
assert _parse_json_content(content) == {"product_name": "测试产品"}
def test_pdf_pages_keep_page_numbers_and_select_late_benefit_page():
text = extraction_module._format_pdf_pages([
"Product Name: Example IUL",
"general terms",
"Policy Year Account Value Cash Surrender Value Death Benefit 1 1000 900 500000",
])
assert "[PAGE 1]" in text
assert "[PAGE 3]" in text
selected = select_key_pages(text, max_pages=2, max_chars=2000)
assert "Product Name: Example IUL" in selected
assert "Cash Surrender Value" in selected
def test_corrupted_pdf_text_detection_accepts_normal_text_and_rejects_font_garbage():
normal = "保险计划书 被保人年龄 48 岁\nPolicy Year 1 Cash Value 100000\n" * 3
corrupted = "\uffff\uffff\x81\x82ĤøùÿxĀ’@BQā" * 20
assert extraction_module._looks_corrupted(normal) is False
assert extraction_module._looks_corrupted(corrupted) is True
def test_iul_filename_hint_corrects_ocr_product_name():
data = {
"product_name": "SAR Feel",
"policy": {"product_name": "SAR Feel"},
}
corrected = extraction_module._apply_filename_hints(
data,
"/tmp/MLS_SIUL3_F-48-N-CN-USD-S3m.pdf",
"iul",
)
assert corrected["product_name"] == "Manulife SIUL 3"
assert corrected["policy"]["product_name"] == "Manulife SIUL 3"
def test_savings_milestone_rows_are_warnings_not_blocking_errors():
from insurance.ppt.validator import validate_formal_savings_plan
plan = {
"productName": "测试储蓄计划",
"insured": {"age": 41, "smoker": "no"},
"policy": {"currency": "USD", "annualPremium": 5250, "payYears": 5},
"benefitRows": [
{"policyYear": year, "sourcePage": 3}
for year in [1, 2, 3, 4, 5, 10, 15, 20, 25, 30, 65, 70, 75, 80, 85, 90, 95, 100]
],
"withdrawalRows": [],
"source": {"pdfHash": "abc"},
}
issues = validate_formal_savings_plan(plan)
assert not [issue for issue in issues if issue.level == "error"]
assert any(issue.code == "BENEFIT_ROWS_MILESTONE_ONLY" for issue in issues)
assert any(issue.code == "BENEFIT_ROWS_DISCONTINUOUS" for issue in issues)
def test_savings_rows_without_key_years_are_non_blocking_warnings():
from insurance.ppt.validator import validate_formal_savings_plan
plan = {
"productName": "测试储蓄计划",
"insured": {"age": 41, "smoker": "no"},
"policy": {"currency": "USD", "annualPremium": 5250, "payYears": 5},
"benefitRows": [
{"policyYear": year, "sourcePage": 3}
for year in [1, 2, 3, 4, 5]
],
"withdrawalRows": [],
"source": {"pdfHash": "abc"},
}
issues = validate_formal_savings_plan(plan)
assert any(
issue.code == "BENEFIT_ROWS_INCOMPLETE" and issue.level == "warn"
for issue in issues
)
assert not [issue for issue in issues if issue.level == "error"]
def test_split_extraction_merges_identity_and_benefit_result(tmp_path, monkeypatch):
pdf_path = tmp_path / "iul.pdf"
pdf_path.write_bytes(b"%PDF-1.4")
monkeypatch.setattr(
extraction_module,
"_extract_pdf_text",
lambda _path: ("有效计划书文本" * 100, []),
)
monkeypatch.setattr(regex_extractor, "extract_insurance_regex", lambda _text: {})
monkeypatch.setattr(regex_extractor, "count_benefit_rows", lambda _data: 0)
complete = {
"product_name": "测试 IUL",
"product_type": "iul",
"insured": {"age": 35},
"policy": {"sum_insured": 500000, "index_account_rate": 0.05},
"index_accounts": [{"name": "S&P 500"}],
"benefit_illustration": [{"policy_year": 1, "account_value": 1000}],
}
async def fake_structured_output(**kwargs):
prompt = kwargs.get("prompt", "")
if "身份和保单字段" in prompt:
data = {key: value for key, value in complete.items() if key != "benefit_illustration"}
elif "利益演示表" in prompt:
data = {"benefit_illustration": complete["benefit_illustration"]}
elif "提领/提款演示表" in prompt:
data = {"withdrawal_illustration": []}
else:
data = {}
return data, LLMResponse(content="{}", provider="test")
from insurance.ppt.llm_client import llm_client
monkeypatch.setattr(llm_client, "structured_output", fake_structured_output)
result = asyncio.run(
ExtractionOrchestrator(use_cache=False).extract_plan(str(pdf_path), "iul")
)
assert result.status == "success"
assert result.product_name == "测试 IUL"
assert result.data["benefit_illustration"]
def test_generate_ppt_task_marks_failure_and_syncs_workspace(monkeypatch):
"""生成入口自身异常也必须结束任务,不能永久停在 running。"""
celery_module = types.ModuleType("celery")
def shared_task(*_args, **_kwargs):
return lambda func: func
celery_module.shared_task = shared_task
monkeypatch.setitem(sys.modules, "celery", celery_module)
sys.modules.pop("insurance.generation.celery_tasks", None)
from insurance.generation import celery_tasks
task = types.SimpleNamespace(id="task-1", workspace_id="session-1")
session = types.SimpleNamespace(workflow_step="ready")
class TaskQuery:
@staticmethod
def get(_task_id):
return task
class SessionQuery:
@staticmethod
def get(_session_id):
return session
generation_model = types.ModuleType("insurance.models.generation_task")
generation_model.GenerationTask = types.SimpleNamespace(query=TaskQuery())
session_model = types.ModuleType("insurance.models.ppt_session")
session_model.PptSession = types.SimpleNamespace(query=SessionQuery())
fake_db = types.SimpleNamespace(session=_Session())
compat_module = types.ModuleType("insurance.db.compat")
compat_module.db = fake_db
monkeypatch.setitem(sys.modules, "insurance.models.generation_task", generation_model)
monkeypatch.setitem(sys.modules, "insurance.models.ppt_session", session_model)
monkeypatch.setitem(sys.modules, "insurance.db.compat", compat_module)
monkeypatch.setattr(celery_tasks, "_claim_task", lambda _task_id: True)
updates = []
monkeypatch.setattr(
celery_tasks,
"_update_task_status",
lambda _task_id, **kwargs: updates.append(kwargs),
)
monkeypatch.setattr(
celery_tasks,
"_execute_ppt_generate",
lambda _task_id: (_ for _ in ()).throw(RuntimeError("render failed")),
)
synced = []
monkeypatch.setattr(task_service, "sync_workspace_status", lambda value: synced.append(value))
with pytest.raises(RuntimeError, match="render failed"):
celery_tasks.generate_ppt_task(None, "task-1")
assert session.workflow_step == "generating"
assert any(update.get("status") == "failed" for update in updates)
assert synced == [task]