mirror of
https://github.com/ThearchyHelios/AgentLab.git
synced 2026-11-22 09:41:57 +00:00
固化成口径草稿:口径卡用传入的名字、报告指令不写死代表那一轮的日期、指标名取目录中文名、已固化去重
验收报告里 certify.freeze 的四处:
- 口径卡的 caliber 用的是代表问题的原文,没用传入的 name。改成 name(去首尾空白)优先,没传才用代表问题。
- 报告的 instructions 写死成「回答:<代表问题>」,问题里带着那一轮的日期(「上周(10月5日到11日)」「九月第一周」),
参数化之后这句就错了。有入口参数时改写运行时渲染的参数(「这次的参数:p1 = {{ input.p1 }},…;时间范围、筛选的
取值以参数为准」),不写问题原文;没有参数时取数的字面量都是口径的常量,照旧写问题原文。
- 指标名直接用列名。现在能从数据目录取到中文名的用中文名:先看查询快照冻结的目录(schema_artifact,和口径比对用的
同一份,ledger.match._frozen),老快照没冻结的看数据源现在的目录;只认列名本身就是目录里的一列(SELECT amount、
SUM(amount) AS amount),gmv 这类算出来起的别名取不到,照旧用列名。
- 认证队列里 cluster 项的 frozen_into 把同一个工作流列了好几次:固化时同组的几次运行都记进 origin.sources,一项里
的几次运行就各指一遍同一个工作流。shape 项同样会重。加 _frozen_of 按工作流去重(保持先后),三种项都用它。
测试(test_ledger_certify):原来的固化用例改成断言指令里没有代表问题和日期、有 {{ input.p1 }} {{ input.p2 }},
没传名字时口径卡照旧用代表问题,shape 和 cluster 两项的 frozen_into 都只有一个工作流;新增一条:传了名字的口径卡
用名字,目录里有中文名的列(amount → 金额)用中文名、取不到的照旧(n),没有参数时指令照旧写问题原文。去掉修复
回跑两条都挂。
This commit is contained in:
@@ -180,7 +180,11 @@ async def test_freezing_makes_a_fixed_sql_draft_that_passes_the_governed_gate(cl
|
||||
"required": ["m1"]}
|
||||
assert {k: nodes["write"]["data"]["config"].get(k) for k in ("numbers", "on_violation", "claims")} == {
|
||||
"numbers": "strict", "on_violation": "fail", "claims": "require_citation"}
|
||||
assert nodes["write"]["data"]["config"]["instructions"] == f"回答:{QUESTION}"
|
||||
# 有入口参数:不写代表那一轮的问题原文(「九月第一周」参数化之后就不对了),写运行时渲染的参数
|
||||
instructions = nodes["write"]["data"]["config"]["instructions"]
|
||||
assert QUESTION not in instructions and "2026-09" not in instructions, instructions
|
||||
assert "{{ input.p1 }}" in instructions and "{{ input.p2 }}" in instructions
|
||||
assert nodes["card"]["data"]["config"]["caliber"] == QUESTION, "没传名字:口径卡照旧用代表问题"
|
||||
spec = GraphSpec.model_validate(wf.graph)
|
||||
assert not [i for i in validate_graph(spec).issues if i.level == "error"]
|
||||
assert not [i for i in publish_issues(spec, level="governed") if i.level == "error"], \
|
||||
@@ -189,9 +193,12 @@ async def test_freezing_makes_a_fixed_sql_draft_that_passes_the_governed_gate(cl
|
||||
assert all(s["question"] == QUESTION for s in wf.origin["sources"])
|
||||
assert wf.origin["run_id"] == rep_run.id and wf.origin["freeze"] is True
|
||||
|
||||
# 队列上标着已经固化过
|
||||
[again] = shape_items((await client.get("/api/ledger/certify-queue")).json())
|
||||
assert {w["workflow_id"] for w in again["frozen_into"]} == {wf.id}
|
||||
# 队列上标着已经固化过:同一个工作流只列一次(三个来源运行都指着它)
|
||||
body = (await client.get("/api/ledger/certify-queue")).json()
|
||||
[again] = shape_items(body)
|
||||
assert [w["workflow_id"] for w in again["frozen_into"]] == [wf.id]
|
||||
[cluster] = [i for i in body["items"] if i["kind"] == "cluster" and i["question"] == QUESTION]
|
||||
assert [w["workflow_id"] for w in cluster["frozen_into"]] == [wf.id], cluster["frozen_into"]
|
||||
|
||||
# 按受管级别发布:来源运行在后台补比,变成等价已证明、出了队
|
||||
res = await client.post(f"/api/workflows/{wf.id}/publish", json={"level": "governed"})
|
||||
@@ -216,6 +223,47 @@ async def test_freezing_makes_a_fixed_sql_draft_that_passes_the_governed_gate(cl
|
||||
assert stats["frozen"] >= 1 and stats["published"] >= 1
|
||||
|
||||
|
||||
async def test_freezing_uses_the_given_name_and_catalog_labels_and_no_dates_without_parameters(client, monkeypatch):
|
||||
"""传了名字:口径卡用它(下一轮验收:以前用代表问题的原文)。指标名能从数据目录取到中文名的用中文名,取不到照旧用
|
||||
列名。没有入口参数(字面量都没变过)时报告指令照旧写问题原文:那时问题里的日期就是口径的常量。"""
|
||||
from app.data import catalog
|
||||
from app.db.models import DataSource
|
||||
from sqlalchemy import select
|
||||
|
||||
async with SessionLocal() as session:
|
||||
source = (await session.execute(select(DataSource).where(DataSource.name == S.CURRENT["source"]))).scalar_one()
|
||||
await catalog.write_entry(session, source.id, "orders", {"columns": {
|
||||
"amount": {"label": catalog.make_item("金额", "human")}}}, if_version=0, actor="测试员")
|
||||
sql = "SELECT SUM(amount) AS amount, COUNT(*) AS n FROM orders WHERE status = 'paid' AND paid_at >= '2026-09-01'"
|
||||
S.script(monkeypatch, "金额 [[v:Q1.r0.amount]],[[v:Q1.r0.n]] 单。")
|
||||
conv = await conversation()
|
||||
async with SessionLocal() as session:
|
||||
turn = ConversationTurn(conversation_id=conv, question=QUESTION)
|
||||
session.add(turn)
|
||||
await session.commit()
|
||||
turn_id = turn.id
|
||||
run = await run_manager.start(graph=S.explore_graph(sql), input_payload={"question": QUESTION}, origin_kind="chat",
|
||||
origin={"conversation_id": conv, "turn_id": turn_id})
|
||||
row = await S.wait(run.id)
|
||||
assert row.status == "succeeded", row.error
|
||||
async with SessionLocal() as session:
|
||||
(await session.get(ConversationTurn, turn_id)).run_id = row.id
|
||||
await session.commit()
|
||||
await ledger_match.drain()
|
||||
res = await client.post("/api/copilot/from-run", json={"run_id": row.id, "freeze": True, "name": "九月销售额口径"})
|
||||
assert res.status_code == 200, res.text
|
||||
made = res.json()
|
||||
assert made["params"] == [] and made["name"] == "九月销售额口径"
|
||||
async with SessionLocal() as session:
|
||||
wf = await session.get(Workflow, made["workflow_id"])
|
||||
nodes = {n["id"]: n for n in wf.graph["nodes"]}
|
||||
card = nodes["card"]["data"]["config"]
|
||||
assert card["caliber"] == "九月销售额口径"
|
||||
assert [(m["name"], m["expression"]) for m in card["metrics"]] == [
|
||||
("金额", "cell(nodes.fetch, 0, 'amount')"), ("n", "cell(nodes.fetch, 0, 'n')")]
|
||||
assert nodes["write"]["data"]["config"]["instructions"] == f"回答:{QUESTION}"
|
||||
|
||||
|
||||
async def test_freezing_needs_a_matched_successful_run(client, monkeypatch):
|
||||
res = await client.post("/api/copilot/from-run", json={"run_id": "nope", "freeze": True})
|
||||
assert res.status_code == 404
|
||||
|
||||
Reference in New Issue
Block a user