模型不在价格目录里时运行金额写「金额无法估算」,不写 $0:真实运行里 token 记到了上百万,金额却是 $0,看着像没花钱。llm.end 发出时,用了 token、模型却不在价格目录里的标 unpriced(目录里标 0 价的本地模型不算);运行用量按 llm.end 数出 unpriced_calls,成功的运行也补上(状态里的用量分不出 0 是免费还是没价)。运行详情、画布运行面板、航迹的金额:一分都没估出来写「金额无法估算」,估出一部分写「≥ $x」,悬停说几次调用不在价格目录中。check-trace 补断言;流式用量测试和注释里的真实调用次数换成概括说法

This commit is contained in:
ThearchyHelios
2026-10-04 12:27:38 +08:00
parent 720f842b82
commit 46330dfd96
11 changed files with 151 additions and 20 deletions
+42 -9
View File
@@ -171,9 +171,8 @@ async def engine_up():
await run_manager.shutdown()
async def test_run_usage_counts_streamed_tokens(server, engine_up):
"""整条链:兼容接入 → llm 节点流式调用 → llm.end → 运行的用量。修之前这里是 0 token、0 美元。"""
server()
async def _run_once(model: str) -> tuple[Run, list[RunEvent]]:
"""兼容接入上用 model 跑一个 llm 节点,返回运行行和 llm.end 事件。"""
provider = _provider()
async with SessionLocal() as session:
session.add(provider)
@@ -185,7 +184,7 @@ async def test_run_usage_counts_streamed_tokens(server, engine_up):
"nodes": [
{"id": "in", "type": "input", "data": {"config": {}}},
{"id": "ask", "type": "llm", "data": {"label": "问答", "config": {
"prompt": "上周到店多少人", "provider": provider.name, "model": PRICED}}},
"prompt": "上周到店多少人", "provider": provider.name, "model": model}}},
{"id": "out", "type": "output", "data": {"config": {
"fields": [{"name": "回答", "value": "{{ nodes.ask.text }}"}]}}},
],
@@ -202,12 +201,46 @@ async def test_run_usage_counts_streamed_tokens(server, engine_up):
async with SessionLocal() as session:
ends = list((await session.execute(select(RunEvent).where(
RunEvent.run_id == started.id, RunEvent.type == "llm.end"))).scalars())
assert [(e.data["input_tokens"], e.data["output_tokens"]) for e in ends] == [(1200, 300)]
assert row.usage["input_tokens"] == 1200 and row.usage["output_tokens"] == 300
assert row.usage["total_tokens"] == 1500
expected = round(catalog.estimate_cost(PRICED, 1200, 300), 6)
assert expected > 0 and row.usage["cost_usd"] == pytest.approx(expected)
return row, ends
finally:
async with SessionLocal() as session:
await session.execute(delete(Provider).where(Provider.id == provider.id))
await session.commit()
async def test_run_usage_counts_streamed_tokens(server, engine_up):
"""整条链:兼容接入 → llm 节点流式调用 → llm.end → 运行的用量。修之前这里是 0 token、0 美元。"""
server()
row, ends = await _run_once(PRICED)
assert [(e.data["input_tokens"], e.data["output_tokens"]) for e in ends] == [(1200, 300)]
assert row.usage["input_tokens"] == 1200 and row.usage["output_tokens"] == 300
assert row.usage["total_tokens"] == 1500
expected = round(catalog.estimate_cost(PRICED, 1200, 300), 6)
assert expected > 0 and row.usage["cost_usd"] == pytest.approx(expected)
assert "unpriced" not in ends[0].data and "unpriced_calls" not in row.usage
async def test_a_model_missing_from_the_price_catalog_is_marked_unpriced(server, engine_up):
"""token 记到了,模型却不在价格目录里:金额估不出来,不能让运行页写 $0 像是没花钱。
llm.end 标 unpriced(运行中的实时统计据此数),运行用量记 unpriced_calls(界面据此写「无法估算」)。"""
server()
row, ends = await _run_once("vendor-unlisted-model")
assert [(e.data["input_tokens"], e.data["output_tokens"]) for e in ends] == [(1200, 300)]
assert ends[0].data["unpriced"] is True and ends[0].data["cost_usd"] == 0
assert row.usage["total_tokens"] == 1500 and row.usage["cost_usd"] == 0
assert row.usage["unpriced_calls"] == 1
@pytest.mark.parametrize(("data", "unpriced"), [
({"model": "vendor-unlisted-model", "input_tokens": 10, "output_tokens": 2, "cost_usd": 0}, True),
({"model": PRICED, "input_tokens": 10, "output_tokens": 2, "cost_usd": 0.0001}, False),
# 目录里标 0 价的本地模型是真不花钱,不是估不出来
({"model": "qwen3:8b", "input_tokens": 10, "output_tokens": 2, "cost_usd": 0}, False),
# 没用 token 的调用(失败、被取消)谈不上金额
({"model": "vendor-unlisted-model", "input_tokens": 0, "output_tokens": 0}, False),
# 老事件没有 unpriced 键:按模型名补判;事件自己标了的以它为准
({"model": PRICED, "input_tokens": 10, "unpriced": True}, True),
(None, False),
])
def test_unpriced_call(data, unpriced):
assert catalog.unpriced_call(data) is unpriced