mirror of
https://github.com/ThearchyHelios/AgentLab.git
synced 2026-11-22 07:42:00 +00:00
E4 的版本用量只算有口径卡的工作流
验收:E4 的用量把没有口径卡的普通发布工作流也当成口径计数。_e4 按(工作流, 版本)数所有 run_class=formal 的运行, 不看那一版是不是口径。 改法:数完之后按 WorkflowVersion 的图过一遍,只留图上有源头口径卡的版本(recall.source_cards:metrics 节点、不是 转抄别处口径的 caliber_from,和召回认口径卡的同一个判断)。比对里等价已证明的运行数(proven_runs)本来就只来自口径, 不动。写进了模块说明。 测试:test_ledger_api 新增一条:一个有口径卡、一个没有的已发布工作流各跑两次正式运行,E4 用量里只有前者、formal_runs 为 2。去掉修复回跑挂。
This commit is contained in:
@@ -17,7 +17,8 @@
|
||||
段对话的算重复的形状,给出这样的形状几个、有重复形状的运行占几成;问题聚类(app/chat/questions:全站唯一的聚类,只取问题
|
||||
原文、不含 history、排除系统派生的运行)里 ≥ REPEAT_RUNS 个问题的类占几成。认证队列的转化(第 3 波,ledger/certify):固化成
|
||||
口径草稿几份(origin.freeze 的工作流)、其中发布了几份、点了「不是口径」几项。
|
||||
- E4 召回:每个口径版本被用了多少次(比对里等价已证明的运行数、这一版的正式运行数);每次发布(口径升到某一版)召回了几组、
|
||||
- E4 召回:每个口径版本被用了多少次(比对里等价已证明的运行数、这一版的正式运行数——只算图上有源头口径卡的版本,没有口径卡
|
||||
的普通发布工作流的正式运行不算);每次发布(口径升到某一版)召回了几组、
|
||||
收过尾的几组、其中数变了的几组和比例、重算失败的几组(ledger/recall:召回运行和它收尾时记的 ledger.recalled,第 4 波)。
|
||||
按召回运行的发起时间筛窗口;表结构变了之后的口径试算不算召回。
|
||||
"""
|
||||
@@ -289,8 +290,10 @@ async def _e4(session: Any, contents: list[dict[str, Any]], **scope: Any) -> dic
|
||||
stmt = stmt.where(Run.created_at >= scope["since"])
|
||||
if scope.get("until") is not None:
|
||||
stmt = stmt.where(Run.created_at < scope["until"])
|
||||
formal = {ledger_labels.caliber_key(w, v): int(n)
|
||||
for w, v, n in (await session.execute(stmt.group_by(Run.workflow_id, Run.version))).all()}
|
||||
counted = {(w, v): int(n) for w, v, n in (await session.execute(stmt.group_by(Run.workflow_id, Run.version))).all()}
|
||||
# 只算有口径卡的那几版:没有口径卡的普通发布工作流的正式运行不是「这个口径版本被用了」
|
||||
calibers = await _caliber_versions(session, counted)
|
||||
formal = {ledger_labels.caliber_key(w, v): n for (w, v), n in counted.items() if (w, v) in calibers}
|
||||
recalls = int(await session.scalar(select(func.count()).select_from(Run).where(Run.origin_kind == "recall")) or 0)
|
||||
usage = [{"caliber": key, "workflow_id": key.rsplit("@", 1)[0], "version": int(key.rsplit("@", 1)[1]),
|
||||
"proven_runs": proven.get(key, 0), "formal_runs": formal.get(key, 0)}
|
||||
@@ -298,6 +301,24 @@ async def _e4(session: Any, contents: list[dict[str, Any]], **scope: Any) -> dic
|
||||
return {"usage": usage, "recall_runs": recalls, "per_publish": await _per_publish(session, **scope)}
|
||||
|
||||
|
||||
async def _caliber_versions(session: Any, keys: Collection[tuple[str, int]]) -> set[tuple[str, int]]:
|
||||
"""这几个(工作流, 版本)里图上有源头口径卡的那些(recall.source_cards:metrics 节点、不是转抄别处的 caliber_from)。"""
|
||||
from sqlalchemy import or_
|
||||
|
||||
from app.db.models import WorkflowVersion
|
||||
from app.ledger.recall import source_cards
|
||||
|
||||
keys = list(keys)
|
||||
out: set[tuple[str, int]] = set()
|
||||
for i in range(0, len(keys), 200):
|
||||
chunk = keys[i:i + 200]
|
||||
rows = (await session.execute(select(WorkflowVersion.workflow_id, WorkflowVersion.version, WorkflowVersion.graph)
|
||||
.where(or_(*[(WorkflowVersion.workflow_id == w) & (WorkflowVersion.version == v)
|
||||
for w, v in chunk])))).all()
|
||||
out |= {(w, v) for w, v, graph in rows if source_cards(graph)}
|
||||
return out
|
||||
|
||||
|
||||
async def _per_publish(session: Any, **scope: Any) -> dict[str, Any]:
|
||||
"""每次发布召回了几组、其中数变了的比例(E4 下半):按(工作流、新版本)分,读召回运行收尾时记的结论。"""
|
||||
from app.core.events import EventType
|
||||
|
||||
@@ -295,6 +295,35 @@ async def test_stats_count_what_the_fixtures_did(client, monkeypatch):
|
||||
assert body["e4"]["per_publish"]["available"] is True and body["e4"]["per_publish"]["groups"] == 0
|
||||
|
||||
|
||||
async def test_e4_usage_counts_formal_runs_only_of_workflows_with_a_caliber_card(client):
|
||||
"""E4 的版本用量只算有口径卡的工作流(下一轮验收:没有口径卡的普通发布工作流的正式运行也被当成口径计数)。卡是转抄别处
|
||||
口径(caliber_from)的不算源头口径,同 recall.source_cards。"""
|
||||
from datetime import datetime, timezone
|
||||
|
||||
from app.db.models import Run, Workflow, WorkflowVersion
|
||||
|
||||
since = datetime.now(timezone.utc)
|
||||
card = {"id": "card", "type": "metrics", "position": {"x": 0, "y": 0},
|
||||
"data": {"label": "口径卡", "config": {"caliber": "周销售", "caliber_version": "v1", "metrics": []}}}
|
||||
plain = {"id": "out", "type": "output", "position": {"x": 0, "y": 0}, "data": {"label": "出口", "config": {}}}
|
||||
async with SessionLocal() as session:
|
||||
made = {}
|
||||
for name, nodes in (("有口径卡", [card, plain]), ("普通工作流", [plain])):
|
||||
wf = Workflow(name=name, graph={"nodes": nodes, "edges": []}, status="published", published_version=1)
|
||||
session.add(wf)
|
||||
await session.flush()
|
||||
session.add(WorkflowVersion(workflow_id=wf.id, version=1, graph={"nodes": nodes, "edges": []}))
|
||||
for _ in range(2):
|
||||
session.add(Run(workflow_id=wf.id, version=1, run_class="formal", status="succeeded",
|
||||
graph={"nodes": nodes, "edges": []}, input={}))
|
||||
made[name] = wf.id
|
||||
await session.commit()
|
||||
body = (await client.get("/api/ledger/stats", params={"since": since.isoformat()})).json()
|
||||
usage = {u["caliber"]: u for u in body["e4"]["usage"]}
|
||||
assert usage[f"{made['有口径卡']}@1"]["formal_runs"] == 2
|
||||
assert f"{made['普通工作流']}@1" not in usage, usage
|
||||
|
||||
|
||||
async def test_stats_take_the_run_ids_the_caller_names(monkeypatch):
|
||||
"""评测(第 3 波)直接调 compute_stats,点名自己的运行:只算这几次。"""
|
||||
from app.ledger.stats import compute_stats
|
||||
|
||||
Reference in New Issue
Block a user