mirror of
https://github.com/ThearchyHelios/AgentLab.git
synced 2026-11-17 20:11:59 +00:00
8d9a712eae
- 新增标准业务实体(CanonicalEntity)模型、确定性跨源编码翻译、后台候选实体扫描与文档驱动实体智能助手 - 新增指标本体图谱(factor / reconciles_with / upstream_driver)、DAG 防环校验以及 ontology_neighbors / source_health 内置工具 - 新增跨源对账(analysis_reconcile)与滞后共变(analysis_cochange)分析算子,打通 [[h:H1]] 数据源健康证据链、报告导出与本体消融评测 - 数据目录新增「标准业务实体」视图与候选审阅工作台,口径页集成指标本体拓扑面板与端到端浏览器检查
370 lines
16 KiB
Python
370 lines
16 KiB
Python
"""Wave 1-b 单元测试:数据源健康度检查 check_source_health、跨源对账算子 reconcile、伴随异动算子 cochange 及 Agent 工具接入。"""
|
||
from __future__ import annotations
|
||
|
||
import asyncio
|
||
from datetime import date
|
||
|
||
import pytest
|
||
from langchain_core.messages import AIMessage, ToolMessage
|
||
from sqlalchemy import delete, select
|
||
|
||
import app.analysis as analysis_ops
|
||
from app.analysis import contract
|
||
from app.analysis.contract import CallError
|
||
from app.core import artifact_store
|
||
from app.data import source_changes as sc
|
||
from app.data import source_health as sh
|
||
from app.db.base import SessionLocal
|
||
from app.db.models import DataSource, Run, RunEvent
|
||
from app.db.models_ontology import CanonicalEntity
|
||
from app.engine.runner import run_manager
|
||
from app.tools.analysis import input_snapshot
|
||
from tests.fixtures.acceptance import multi_source_ontology as mso
|
||
|
||
|
||
@pytest.fixture(autouse=True)
|
||
async def _engine_lifecycle():
|
||
await run_manager.setup()
|
||
yield
|
||
await run_manager.shutdown()
|
||
async with SessionLocal() as session:
|
||
await session.execute(delete(CanonicalEntity))
|
||
await session.commit()
|
||
|
||
|
||
def _snap(ref: str, columns: list[str], rows: list[list], *, masked: list[str] | None = None,
|
||
truncated: bool = False, source: str = "ops_shift", artifact: str | None = None) -> dict:
|
||
return input_snapshot(
|
||
{
|
||
"columns": columns,
|
||
"rows": rows,
|
||
"sql": f"SELECT {', '.join(columns)} FROM t",
|
||
"source": source,
|
||
"truncated": truncated,
|
||
},
|
||
ref=ref,
|
||
artifact=artifact or (ref.lower().ljust(64, "0")[:64]),
|
||
node_id="bot",
|
||
masked=masked or [],
|
||
)
|
||
|
||
|
||
async def test_source_health_verdicts_masking_and_caliber_reverse_lineage(tmp_path, scratch_source, monkeypatch):
|
||
seeded = await mso.seed_ontology_fixture(tmp_path, scratch_source, today=date(2026, 10, 22))
|
||
yesterday = "2026-10-21"
|
||
|
||
async with SessionLocal() as session:
|
||
# 1) ops_shift 数据最新覆盖到昨天 -> healthy,且探查绝不触碰遮罩列 operator_phone
|
||
healthy = await sh.check_source_health(
|
||
session,
|
||
source_name=mso.SOURCE_OPS,
|
||
tables=["shift_output"],
|
||
start="2026-10-15",
|
||
end=yesterday,
|
||
)
|
||
assert healthy["verdict"] == sh.HEALTHY
|
||
assert "operator_phone" not in str(healthy)
|
||
assert "138-0010" not in str(healthy)
|
||
|
||
# 2) quality_scrap 在昨天断更(SourceChange date_stalled + 现查最大日期 2026-10-19 < 2026-10-21)-> anomalous
|
||
anomalous = await sh.check_source_health(
|
||
session,
|
||
source_name=mso.SOURCE_QUALITY,
|
||
tables=["scrap_ledger"],
|
||
start=yesterday,
|
||
end=yesterday,
|
||
)
|
||
assert anomalous["verdict"] == sh.ANOMALOUS
|
||
assert any(i["kind"] == sc.DATE_STALLED for i in anomalous["issues"])
|
||
assert "inspector_id" not in str(anomalous)
|
||
assert "INSP-900" not in str(anomalous)
|
||
|
||
# 3) restricted=True 受限视角隐去物理表名、物理列名与底层数据源标识
|
||
restricted_res = await sh.check_source_health(
|
||
session,
|
||
source_name=mso.SOURCE_QUALITY,
|
||
tables=["scrap_ledger"],
|
||
start=yesterday,
|
||
end=yesterday,
|
||
restricted=True,
|
||
)
|
||
assert restricted_res["verdict"] == sh.ANOMALOUS
|
||
assert "scrap_ledger" not in str(restricted_res)
|
||
assert "inspect_date" not in str(restricted_res)
|
||
|
||
# 4) 按口径卡反向血缘自动解析底层数据源与物理表
|
||
via_caliber = await sh.check_source_health(
|
||
session,
|
||
workflow_id=seeded["workflow_ids"]["quality"],
|
||
card_id="m_quality",
|
||
metric_id="ledger_scrap_units",
|
||
start=yesterday,
|
||
end=yesterday,
|
||
)
|
||
assert via_caliber["verdict"] == sh.ANOMALOUS
|
||
assert via_caliber["caliber_ref"]["workflow_id"] == seeded["workflow_ids"]["quality"]
|
||
|
||
# 5) codes_new 新码值提醒 -> degraded
|
||
equip_src = await session.get(DataSource, seeded["source_ids"][mso.SOURCE_EQUIP])
|
||
await sc.record(
|
||
session,
|
||
equip_src,
|
||
sc.NewChange(kind=sc.CODES_NEW, table="downtime_events", column="fault_category", severity="warning", key="new_code"),
|
||
sc.Detected(job_kind="profile", trigger="manual", actor="tester"),
|
||
)
|
||
await session.commit()
|
||
degraded = await sh.check_source_health(
|
||
session,
|
||
source_name=mso.SOURCE_EQUIP,
|
||
tables=["downtime_events"],
|
||
start="2026-10-15",
|
||
end=yesterday,
|
||
)
|
||
assert degraded["verdict"] == sh.DEGRADED
|
||
|
||
# 6) 工件存储与台账条目形状校验
|
||
art_id = await sh.store_source_health(anomalous, run_id=None, node_id="bot")
|
||
loaded = artifact_store.load(art_id)
|
||
assert sh.is_health_result(loaded)
|
||
entry = sh.ledger_entry(anomalous, node_id="bot", exec_no=1, artifact=art_id, call_id="c1")
|
||
assert entry["kind"] == "source_health" and entry["verdict"] == sh.ANOMALOUS
|
||
|
||
# 7) 实时探查异常降级为 unverified 而不抛未捕获异常
|
||
async def _boom(*_a, **_kw):
|
||
raise TimeoutError("simulated timeout")
|
||
|
||
monkeypatch.setattr(sh, "run_query", _boom)
|
||
fallback = await sh.check_source_health(session, source_name=mso.SOURCE_OPS, tables=["shift_output"])
|
||
assert fallback["verdict"] == sh.UNVERIFIED
|
||
|
||
|
||
async def _run_op(req: dict, resolve, *, refuse_data_errors: bool = False) -> dict:
|
||
return await analysis_ops.run(
|
||
req,
|
||
resolve,
|
||
settings=contract.DEFAULTS,
|
||
context={},
|
||
refuse_data_errors=refuse_data_errors,
|
||
)
|
||
|
||
|
||
async def test_reconcile_operator_verdicts_errors_and_byte_identical_recompute():
|
||
q_left = _snap("Q1", ["line_code", "scrap_qty", "operator_phone"], [["L1", 20, "***"], ["L2", 50, "***"]], masked=["operator_phone"])
|
||
q_right_ok = _snap("Q2", ["wc_line", "scrap_units"], [["L1", 20], ["L2", 50]], source="quality_scrap")
|
||
q_right_div = _snap("Q2", ["wc_line", "scrap_units"], [["L1", 20], ["L2", 35]], source="quality_scrap")
|
||
q_right_miss = _snap("Q2", ["wc_line", "scrap_units"], [["L1", 20]], source="quality_scrap")
|
||
|
||
# 1) 完全对齐 -> aligned
|
||
res_aligned = await _run_op(
|
||
{
|
||
"op": "reconcile",
|
||
"mode": None,
|
||
"params": {
|
||
"base_query": "Q1",
|
||
"target_query": "Q2",
|
||
"by": ["line_code"],
|
||
"target_by": ["wc_line"],
|
||
"measure": "scrap_qty",
|
||
"target_measure": "scrap_units",
|
||
"label": "报废件数",
|
||
},
|
||
},
|
||
lambda name: {"Q1": q_left, "Q2": q_right_ok}.get(name),
|
||
)
|
||
assert res_aligned["status"] == "ok" and res_aligned["verdict"]["code"] == "aligned"
|
||
|
||
# 2) 超差 -> diverged,且双盲复算重算逐字节一致(contract.same)
|
||
req_div = {
|
||
"op": "reconcile",
|
||
"mode": None,
|
||
"params": {
|
||
"base_query": "Q1",
|
||
"target_query": "Q2",
|
||
"by": ["line_code"],
|
||
"target_by": ["wc_line"],
|
||
"measure": "scrap_qty",
|
||
"target_measure": "scrap_units",
|
||
"label": "报废件数",
|
||
},
|
||
}
|
||
res_div = await _run_op(req_div, lambda name: {"Q1": q_left, "Q2": q_right_div}.get(name))
|
||
res_div_again = await _run_op(req_div, lambda name: {"Q1": q_left, "Q2": q_right_div}.get(name))
|
||
assert res_div["status"] == "ok" and res_div["verdict"]["code"] == "diverged"
|
||
assert res_div["verdict"]["subjects"] == [["L2"]]
|
||
assert contract.same(res_div, res_div_again)
|
||
|
||
# 3) 对侧缺失 -> missing_counterpart
|
||
res_miss = await _run_op(
|
||
{**req_div},
|
||
lambda name: {"Q1": q_left, "Q2": q_right_miss}.get(name),
|
||
)
|
||
assert res_miss["status"] == "ok" and res_miss["verdict"]["code"] == "missing_counterpart"
|
||
|
||
# 4) 单份查询 + unit_factor 换算(千瓦时 vs 兆瓦时 * 1000)
|
||
q_single = _snap("Q3", ["line_code", "kwh", "mwh"], [["L1", 12000, 12.0], ["L2", 13000, 13.0]])
|
||
res_unit = await _run_op(
|
||
{
|
||
"op": "reconcile",
|
||
"mode": None,
|
||
"params": {"query": "Q3", "by": ["line_code"], "measure": "kwh", "target_measure": "mwh", "unit_factor": 1000},
|
||
},
|
||
lambda name: q_single if name == "Q3" else None,
|
||
)
|
||
assert res_unit["status"] == "ok" and res_unit["verdict"]["code"] == "aligned"
|
||
|
||
# 5) 遮罩列拒收 + 截断数据在 refuse_data_errors=True 时返回 refused
|
||
with pytest.raises(CallError):
|
||
await _run_op(
|
||
{
|
||
"op": "reconcile",
|
||
"mode": None,
|
||
"params": {"base_query": "Q1", "target_query": "Q2", "by": ["operator_phone"], "measure": "scrap_qty"},
|
||
},
|
||
lambda name: {"Q1": q_left, "Q2": q_right_ok}.get(name),
|
||
)
|
||
q_trunc = _snap("QT", ["line_code", "kwh", "mwh"], [["L1", 12000, 10.0]], truncated=True)
|
||
res_trunc = await _run_op(
|
||
{"op": "reconcile", "mode": None, "params": {"query": "QT", "by": ["line_code"], "measure": "kwh", "target_measure": "mwh"}},
|
||
lambda name: q_trunc if name == "QT" else None,
|
||
refuse_data_errors=True,
|
||
)
|
||
assert res_trunc["status"] == "refused"
|
||
|
||
|
||
async def test_cochange_operator_verdicts_lag_non_causal_phrase_and_recompute():
|
||
days = [f"2026-10-{d:02d}" for d in range(1, 16)]
|
||
# 前 14 期对称平稳小幅波动,第 15 期主指标暴跌、驱动指标暴涨
|
||
p_base = [100, 102, 99, 101, 100, 98, 103, 101, 99, 102, 100, 98, 101, 100]
|
||
d_base = [12.0, 12.5, 11.8, 12.2, 12.0, 11.6, 12.4, 12.1, 11.9, 12.3, 12.0, 11.7, 12.2, 12.0]
|
||
p_vals = p_base + [68]
|
||
d_spike = d_base + [85.0]
|
||
d_flat = d_base + [12.1]
|
||
|
||
q_primary = _snap("Q1", ["shift_date", "good_qty"], [[d, v] for d, v in zip(days, p_vals)])
|
||
q_driver_spike = _snap("Q2", ["event_date", "unplanned_min"], [[d, v] for d, v in zip(days, d_spike)], source="equip_master")
|
||
q_driver_flat = _snap("Q2", ["event_date", "unplanned_min"], [[d, v] for d, v in zip(days, d_flat)], source="equip_master")
|
||
|
||
req_co = {
|
||
"op": "cochange",
|
||
"mode": None,
|
||
"params": {
|
||
"base_query": "Q1",
|
||
"target_query": "Q2",
|
||
"period": "shift_date",
|
||
"target_period": "event_date",
|
||
"measure": "good_qty",
|
||
"driver_measure": "unplanned_min",
|
||
"label": "合格产量",
|
||
},
|
||
}
|
||
res_co = await _run_op(req_co, lambda name: {"Q1": q_primary, "Q2": q_driver_spike}.get(name))
|
||
res_co_2 = await _run_op(req_co, lambda name: {"Q1": q_primary, "Q2": q_driver_spike}.get(name))
|
||
assert res_co["status"] == "ok" and res_co["verdict"]["code"] == "co_anomalous"
|
||
assert contract.same(res_co, res_co_2)
|
||
# 决策 D6:系统判定语严禁输出因果词(导致、引起、造成)
|
||
for forbidden in ("导致", "引起", "造成", "归因于"):
|
||
assert forbidden not in res_co["phrase"]
|
||
|
||
# 上游平稳 -> target_normal
|
||
res_norm_target = await _run_op(req_co, lambda name: {"Q1": q_primary, "Q2": q_driver_flat}.get(name))
|
||
assert res_norm_target["status"] == "ok" and res_norm_target["verdict"]["code"] == "target_normal"
|
||
|
||
# 主指标平稳 -> primary_normal
|
||
q_primary_steady = _snap("Q1", ["shift_date", "good_qty"], [[d, v] for d, v in zip(days, p_base + [101])])
|
||
res_norm_primary = await _run_op(
|
||
req_co, lambda name: {"Q1": q_primary_steady, "Q2": q_driver_spike}.get(name)
|
||
)
|
||
assert res_norm_primary["status"] == "ok" and res_norm_primary["verdict"]["code"] == "primary_normal"
|
||
|
||
# lag=1 领先期检验:驱动指标在第 14 期飙升,主指标在第 15 期下跌 -> co_anomalous
|
||
d_lead = d_base[:-1] + [88.0, 12.0]
|
||
q_driver_lead = _snap("Q2", ["event_date", "unplanned_min"], [[d, v] for d, v in zip(days, d_lead)], source="equip_master")
|
||
res_lag = await _run_op(
|
||
{**req_co, "params": {**req_co["params"], "lag": 1}},
|
||
lambda name: {"Q1": q_primary, "Q2": q_driver_lead}.get(name),
|
||
)
|
||
assert res_lag["status"] == "ok" and res_lag["verdict"]["code"] == "co_anomalous"
|
||
|
||
# 历史不足 -> refused (history_short)
|
||
q_short = _snap("QS", ["shift_date", "good_qty", "unplanned_min"], [[days[i], p_vals[i], d_spike[i]] for i in range(5)])
|
||
res_short = await _run_op(
|
||
{
|
||
"op": "cochange",
|
||
"mode": None,
|
||
"params": {"query": "QS", "period": "shift_date", "measure": "good_qty", "driver_measure": "unplanned_min"},
|
||
},
|
||
lambda name: q_short if name == "QS" else None,
|
||
)
|
||
assert res_short["status"] == "refused" and res_short["reason_code"] == "history_short"
|
||
|
||
|
||
async def test_agent_executes_analysis_reconcile_and_cochange_and_records_ledger(tmp_path, scratch_source, monkeypatch):
|
||
from app.providers import mock_model
|
||
|
||
await mso.seed_ontology_fixture(tmp_path, scratch_source, today=date(2026, 10, 22))
|
||
calls = [
|
||
("db_query__ops_shift", {"sql": "SELECT line_code, meter_kwh, settled_mwh FROM energy_readings WHERE shift_date = '2026-10-21' ORDER BY line_code"}),
|
||
(
|
||
"analysis_reconcile",
|
||
{"query": "Q1", "by": ["line_code"], "measure": "meter_kwh", "target_measure": "settled_mwh", "unit_factor": 1000, "label": "产线能耗"},
|
||
),
|
||
("db_query__equip_master", {"sql": "SELECT event_date, net_run_ratio, unplanned_min FROM downtime_events WHERE equip_line_id = 'EQ-L2' ORDER BY event_date"}),
|
||
(
|
||
"analysis_cochange",
|
||
{"query": "Q2", "period": "event_date", "measure": "net_run_ratio", "driver_measure": "unplanned_min", "target": "2026-10-21", "label": "有效运转率"},
|
||
),
|
||
]
|
||
|
||
def decide(model, messages):
|
||
done = sum(isinstance(m, ToolMessage) for m in messages)
|
||
if done < len(calls):
|
||
name, args = calls[done]
|
||
return AIMessage(content="", tool_calls=[{"name": name, "args": args, "id": f"call_{done}"}])
|
||
return AIMessage(content="对账与伴随异动核查已完成。")
|
||
|
||
monkeypatch.setattr(mock_model.MockChatModel, "_decide", decide)
|
||
|
||
nodes = [
|
||
{"id": "start", "type": "input", "position": {"x": 0, "y": 0}, "data": {"label": "入口", "config": {}}},
|
||
{
|
||
"id": "bot",
|
||
"type": "agent",
|
||
"position": {"x": 220, "y": 0},
|
||
"data": {
|
||
"label": "诊断助手",
|
||
"config": {
|
||
"prompt": "执行跨源能耗对账与设备停机伴随异动检验",
|
||
"tools": ["db_query__ops_shift", "db_query__equip_master", "analysis_reconcile", "analysis_cochange"],
|
||
"approval": "never",
|
||
},
|
||
},
|
||
},
|
||
{
|
||
"id": "out",
|
||
"type": "output",
|
||
"position": {"x": 460, "y": 0},
|
||
"data": {"label": "出口", "config": {"fields": [{"name": "answer", "value": "{{ nodes.bot.text }}"}]}},
|
||
},
|
||
]
|
||
graph = {"nodes": nodes, "edges": [{"source": "start", "target": "bot"}, {"source": "bot", "target": "out"}]}
|
||
run = await run_manager.start(graph=graph, input_payload={})
|
||
for _ in range(300):
|
||
await asyncio.sleep(0.05)
|
||
async with SessionLocal() as session:
|
||
row = await session.get(Run, run.id)
|
||
if row.status in ("succeeded", "failed") and row.manifest_seq is not None:
|
||
break
|
||
assert row.status == "succeeded", row.error
|
||
|
||
async with SessionLocal() as session:
|
||
ev = (
|
||
await session.execute(
|
||
select(RunEvent).where(RunEvent.run_id == run.id, RunEvent.type == "node.finished", RunEvent.node_id == "bot")
|
||
)
|
||
).scalar_one()
|
||
analysis_entries = [e for e in ev.data["evidence"] if e.get("kind") == "analysis"]
|
||
assert [(e["op"], e["verdict"]) for e in analysis_entries] == [
|
||
("reconcile", "diverged"),
|
||
("cochange", "co_anomalous"),
|
||
]
|