mirror of
https://github.com/ThearchyHelios/AgentLab.git
synced 2026-11-15 03:31:58 +00:00
核查设置：设置里加 verify 一组，双盲复算、反方审稿、审批质询共用。核查模型（接入、模型）空着沿用证据裁判模型的取值链；双盲复算 {启用, 允许的相对误差默认 1e-6, 查询次数, 时长}、反方审稿 {启用, 每份报告最多审几句, 每句查询次数, 时长}、审批质询 {启用, 每次查询次数, 时长}，另有核查每日金额上限，上限存 null 表示不限。写法照裁判一组：PUT 先查后写，有一项不对整个请求回 422、说明写设置页上的叫法；库里存坏的项读出来按默认，三项各自那一组逐项补。verify_settings(session) 给节点和质询接口读，verify_model_spec(session, node_config) 按节点 → 设置 → judge_model_spec 取模型，整组取一级、不跨级拼。核查的每日计数不从设置接口进出，另加只读的 GET /api/settings/verify/spend 给设置页看今天花了多少
This commit is contained in:
ThearchyHelios
+172
-7
@@ -1,5 +1,6 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import math
|
||||
import os
|
||||
from typing import Any
|
||||
|
||||
@@ -14,9 +15,11 @@ from app.core.config import settings as app_settings
|
||||
from app.core.crypto import encrypt, mask
|
||||
from app.db.base import get_session
|
||||
from app.db.models import Provider, Setting
|
||||
from app.engine.judge import JUDGE_DEFAULTS, SETTING_GROUP as JUDGE_GROUP, SPEND_KEY as JUDGE_SPEND
|
||||
from app.engine.judge import daily_spend, judge_settings
|
||||
from app.engine.judge import JUDGE_DEFAULTS, MAX_TOKENS as JUDGE_MAX_TOKENS
|
||||
from app.engine.judge import SETTING_GROUP as JUDGE_GROUP, SPEND_KEY as JUDGE_SPEND
|
||||
from app.engine.judge import daily_spend, judge_model_spec, judge_settings
|
||||
from app.engine.judge import sanitize_settings as judge_values, settings_problem as judge_problem
|
||||
from app.engine.spend import SPEND_KEY as VERIFY_SPEND, daily_spend as verify_daily_spend
|
||||
from app.providers import catalog
|
||||
from app.providers.factory import ModelSpec, ProviderNotConfigured, _resolve_key, build_chat_model
|
||||
|
||||
@@ -412,6 +415,153 @@ async def probe_provider_models(
|
||||
return {"ok": True, "models": models, "url": url}
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------
|
||||
# 核查：双盲复算、反方审稿、审批质询共用的一组设置
|
||||
# --------------------------------------------------------------------------
|
||||
|
||||
#: 设置里 verify 这一组。三项都是让一个只读 agent 查库核对（engine/verify_agent.py），共用核查模型和每日金额上限；
|
||||
#: 各自的开关和上限分开放。上限写 null 表示不限（和裁判一组的约定一样）
|
||||
VERIFY_GROUP = "verify"
|
||||
VERIFY_DEFAULTS: dict[str, Any] = {
|
||||
"provider": None, # 核查模型：空着沿用证据裁判模型的取值链（verify_model_spec）
|
||||
"model": None,
|
||||
# 双盲复算：tolerance 是允许的相对误差，两边的值差在这个比例以内算一致
|
||||
"dual_check": {"enabled": True, "tolerance": 1e-6, "max_queries": 6, "timeout_s": 120},
|
||||
# 反方审稿：max_claims 是每份报告最多挑几句关键结论来审，查询次数、时长按每句算
|
||||
"challenge": {"enabled": True, "max_claims": 5, "max_queries": 4, "timeout_s": 90},
|
||||
# 审批质询：查询次数、时长按每次提问算
|
||||
"inquiry": {"enabled": True, "max_queries": 6, "timeout_s": 120},
|
||||
"daily_max_usd": 2.0, # 全局每日核查金额上限（按本地日期），和裁判的每日上限分开记账（engine/spend.py）
|
||||
}
|
||||
#: 三项各自那一组的键
|
||||
_VERIFY_PARTS = ("dual_check", "challenge", "inquiry")
|
||||
_VERIFY_COUNTS = frozenset({"max_queries", "max_claims"})
|
||||
|
||||
#: 设置页「核查」一节各项的叫法：报错时写它，不写键名。嵌套的项写成「组.项」
|
||||
VERIFY_SETTING_LABEL = {
|
||||
"provider": "核查模型 · 接入", "model": "核查模型 · 模型",
|
||||
"daily_max_usd": "核查每日金额上限（美元）",
|
||||
"dual_check": "双盲复算", "dual_check.enabled": "双盲复算 · 启用",
|
||||
"dual_check.tolerance": "双盲复算 · 允许的相对误差", "dual_check.max_queries": "双盲复算 · 每项最多查询次数",
|
||||
"dual_check.timeout_s": "双盲复算 · 每项时长上限（秒）",
|
||||
"challenge": "反方审稿", "challenge.enabled": "反方审稿 · 启用",
|
||||
"challenge.max_claims": "反方审稿 · 每份报告最多审几句", "challenge.max_queries": "反方审稿 · 每句最多查询次数",
|
||||
"challenge.timeout_s": "反方审稿 · 每句时长上限（秒）",
|
||||
"inquiry": "审批质询", "inquiry.enabled": "审批质询 · 启用",
|
||||
"inquiry.max_queries": "审批质询 · 每次最多查询次数", "inquiry.timeout_s": "审批质询 · 每次时长上限（秒）",
|
||||
}
|
||||
|
||||
|
||||
def _positive(value: Any, *, whole: bool) -> bool:
|
||||
"""上限：null（不限），或大于 0 的有限数；whole 时还得是整数（次数、句数）。True / False 不算数。"""
|
||||
if value is None:
|
||||
return True
|
||||
if isinstance(value, bool) or not isinstance(value, (int, float)) or not math.isfinite(value) or value <= 0:
|
||||
return False
|
||||
return not (whole and int(value) != value)
|
||||
|
||||
|
||||
def _tolerance_ok(value: Any) -> bool:
|
||||
"""允许的相对误差：不小于 0 的有限数（0 表示必须完全一致）。不能是 null：没有「不限」的说法。"""
|
||||
return not isinstance(value, bool) and isinstance(value, (int, float)) and math.isfinite(value) and value >= 0
|
||||
|
||||
|
||||
def _verify_item_ok(key: str, value: Any) -> bool:
|
||||
if key == "enabled":
|
||||
return isinstance(value, bool)
|
||||
if key == "tolerance":
|
||||
return _tolerance_ok(value)
|
||||
return _positive(value, whole=key in _VERIFY_COUNTS)
|
||||
|
||||
|
||||
def _verify_item_problem(part: str, key: str, value: Any) -> str | None:
|
||||
label = VERIFY_SETTING_LABEL[f"{part}.{key}"]
|
||||
if _verify_item_ok(key, value):
|
||||
return None
|
||||
if key == "enabled":
|
||||
return f"「{label}」需要选择开启或关闭，当前为「{value}」"
|
||||
if key == "tolerance":
|
||||
return f"「{label}」需要填写不小于 0 的数（例如 0.000001 表示百万分之一），当前为「{value}」"
|
||||
words = "正整数（次数）" if key == "max_queries" else "正整数（句数）" if key == "max_claims" else "大于 0 的秒数"
|
||||
return f"「{label}」需要填写{words}，留空表示不限，当前为「{value}」"
|
||||
|
||||
|
||||
def verify_problem(value: Any) -> str | None:
|
||||
"""设置页写进来的 verify 这一组有什么问题，没问题返回 None。说明写设置页上的叫法。"""
|
||||
if not isinstance(value, dict):
|
||||
return f"「核查」设置格式有误，需要是一个对象，当前为「{value}」"
|
||||
for key, item in value.items():
|
||||
if key not in VERIFY_DEFAULTS:
|
||||
return (f"「核查」设置中不支持「{key}」，可设置的项："
|
||||
+ "、".join(f"「{VERIFY_SETTING_LABEL[k]}」" for k in VERIFY_DEFAULTS))
|
||||
label = VERIFY_SETTING_LABEL[key]
|
||||
if key in ("provider", "model"):
|
||||
if item is not None and not isinstance(item, str):
|
||||
return f"「{label}」需要填写模型接入的名称或模型 ID，留空表示沿用证据裁判模型，当前为「{item}」"
|
||||
elif key == "daily_max_usd":
|
||||
if not _positive(item, whole=False):
|
||||
return f"「{label}」需要填写大于 0 的金额（美元），留空表示不限，当前为「{item}」"
|
||||
elif not isinstance(item, dict):
|
||||
return f"「{label}」设置格式有误，需要是一个对象，当前为「{item}」"
|
||||
else:
|
||||
allowed = VERIFY_DEFAULTS[key]
|
||||
for sub, sub_value in item.items():
|
||||
if sub not in allowed:
|
||||
return (f"「{label}」设置中不支持「{sub}」，可设置的项："
|
||||
+ "、".join(f"「{VERIFY_SETTING_LABEL[f'{key}.{k}']}」" for k in allowed))
|
||||
if problem := _verify_item_problem(key, sub, sub_value):
|
||||
return problem
|
||||
return None
|
||||
|
||||
|
||||
def verify_values(stored: Any) -> dict[str, Any]:
|
||||
"""库里存的 verify 一组 → 补齐默认的完整设置。存坏了的项（旧版本、手改）按默认，存了 null 的上限就是不限；
|
||||
三项各自那一组逐项补，只存了一项的其余照默认。"""
|
||||
stored = stored if isinstance(stored, dict) else {}
|
||||
out: dict[str, Any] = {k: dict(v) if isinstance(v, dict) else v for k, v in VERIFY_DEFAULTS.items()}
|
||||
for key in ("provider", "model"):
|
||||
value = stored.get(key)
|
||||
out[key] = value.strip() or None if isinstance(value, str) else None
|
||||
if "daily_max_usd" in stored and _positive(stored["daily_max_usd"], whole=False):
|
||||
out["daily_max_usd"] = stored["daily_max_usd"]
|
||||
for part in _VERIFY_PARTS:
|
||||
saved = stored.get(part)
|
||||
if not isinstance(saved, dict):
|
||||
continue
|
||||
for key in VERIFY_DEFAULTS[part]:
|
||||
if key in saved and _verify_item_ok(key, saved[key]):
|
||||
out[part][key] = saved[key]
|
||||
return out
|
||||
|
||||
|
||||
async def verify_settings(session: AsyncSession) -> dict[str, Any]:
|
||||
"""设置里的 verify 一组，没存过的键补默认（读法同 judge_settings）。节点、质询接口都从这里读。"""
|
||||
row = await session.get(Setting, VERIFY_GROUP)
|
||||
return verify_values(row.value if row else None)
|
||||
|
||||
|
||||
def _model_text(value: Any) -> str | None:
|
||||
return value.strip() or None if isinstance(value, str) else None
|
||||
|
||||
|
||||
async def verify_model_spec(session: AsyncSession, node_config: dict[str, Any] | None = None, *,
|
||||
settings: dict[str, Any] | None = None) -> ModelSpec:
|
||||
"""核查用哪个模型：节点配置里的 provider / model > 设置里的核查模型 > 证据裁判模型的取值链（裁判设置 >
|
||||
助手模型 > 默认接入，见 judge.judge_model_spec）。哪一级写了就整组用哪一级，不跨级拼接入和模型。
|
||||
|
||||
和裁判一样关掉 thinking、max_tokens 4096：核查最后要按结构交结果（强制工具调用），和思考模式不兼容。
|
||||
建议和被核查的模型不同，否则等于自己核自己；比较、提醒由调用方做（它知道被核查的是哪个模型）。
|
||||
"""
|
||||
node = node_config if isinstance(node_config, dict) else {}
|
||||
provider, model = _model_text(node.get("provider")), _model_text(node.get("model"))
|
||||
if not (provider or model):
|
||||
chosen = settings if settings is not None else await verify_settings(session)
|
||||
provider, model = _model_text(chosen.get("provider")), _model_text(chosen.get("model"))
|
||||
if not (provider or model):
|
||||
return await judge_model_spec(session, None)
|
||||
return ModelSpec(provider=provider, model=model, max_tokens=JUDGE_MAX_TOKENS, thinking="off")
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------
|
||||
# 用户设置
|
||||
# --------------------------------------------------------------------------
|
||||
@@ -440,6 +590,8 @@ DEFAULT_SETTINGS: dict[str, Any] = {
|
||||
# 结论句裁判（engine/judge.py）：证据裁判模型和各项上限，上限存 null 表示不限。不放进 limits：
|
||||
# 那一组是环境变量定的、只读，这一组是用户自己定的
|
||||
JUDGE_GROUP: dict(JUDGE_DEFAULTS),
|
||||
# 核查（双盲复算、反方审稿、审批质询）：核查模型、三项的开关和上限、每日金额上限。和裁判一组一样由用户定
|
||||
VERIFY_GROUP: verify_values(None),
|
||||
}
|
||||
|
||||
|
||||
@@ -488,11 +640,13 @@ async def get_settings(session: AsyncSession = Depends(get_session)) -> dict[str
|
||||
# limits 是服务端配置（环境变量），只读：库里可能存着旧版设置页写进去的一份
|
||||
#（见过 max_agent_steps: 25），它从来不生效，却会盖住真实的上限，界面照着错的数许诺
|
||||
stored.pop("limits", None)
|
||||
# 裁判的每日计数是引擎记的账，不是用户设置：设置页整组回写时带着一份旧的，会把今天的花费清零
|
||||
# 裁判、核查的每日计数是引擎记的账，不是用户设置：设置页整组回写时带着一份旧的，会把今天的花费清零
|
||||
stored.pop(JUDGE_SPEND, None)
|
||||
stored.pop(VERIFY_SPEND, None)
|
||||
merged = {k: {**v, **(stored.get(k) or {})} for k, v in DEFAULT_SETTINGS.items()}
|
||||
# 裁判设置按引擎实际生效的样子给：存坏了的项显示默认，存了 null 的上限显示不限
|
||||
# 裁判、核查设置按引擎实际生效的样子给：存坏了的项显示默认，存了 null 的上限显示不限
|
||||
merged[JUDGE_GROUP] = judge_values(stored.get(JUDGE_GROUP))
|
||||
merged[VERIFY_GROUP] = verify_values(stored.get(VERIFY_GROUP))
|
||||
for key, value in stored.items():
|
||||
merged.setdefault(key, value)
|
||||
return merged
|
||||
@@ -508,14 +662,16 @@ async def put_settings(
|
||||
) -> dict[str, Any]:
|
||||
from app.tools.trust import SETTING_KEY as TRUST_KEY
|
||||
|
||||
# 先查后写：一组里有一项不对就整个请求不落库，免得存下半组
|
||||
if JUDGE_GROUP in payload.values and (problem := judge_problem(payload.values[JUDGE_GROUP])):
|
||||
# 先查后写：一组里有一项不对就整个请求不落库，免得存下半组
|
||||
raise HTTPException(422, problem)
|
||||
if VERIFY_GROUP in payload.values and (problem := verify_problem(payload.values[VERIFY_GROUP])):
|
||||
raise HTTPException(422, problem)
|
||||
for key, value in payload.values.items():
|
||||
if key in (TRUST_KEY, "limits", JUDGE_SPEND):
|
||||
if key in (TRUST_KEY, "limits", JUDGE_SPEND, VERIFY_SPEND):
|
||||
# 信任三档只走 PUT /api/tools/trust：设置页整组回写时带着一份旧的，
|
||||
# 会把刚在工具页改的档位冲掉。limits 是环境变量定的，写进库也不生效。
|
||||
# 裁判的每日计数是引擎记的账，只有裁判自己写
|
||||
# 裁判、核查的每日计数是引擎记的账，只有引擎自己写
|
||||
continue
|
||||
row = await session.get(Setting, key)
|
||||
if row:
|
||||
@@ -536,6 +692,15 @@ async def get_judge_spend(session: AsyncSession = Depends(get_session)) -> dict[
|
||||
return {**await daily_spend(), "daily_max_usd": (await judge_settings(session))["daily_max_usd"]}
|
||||
|
||||
|
||||
@router.get("/settings/verify/spend")
|
||||
async def get_verify_spend(session: AsyncSession = Depends(get_session)) -> dict[str, Any]:
|
||||
"""今天（本地日期）核查（双盲复算、反方审稿、审批质询）花了多少，设置页放在核查的每日上限旁边。只读。
|
||||
|
||||
形状同 /settings/judge/spend：{date, usd, calls, unpriced_calls, daily_max_usd}，daily_max_usd 为 null 表示不限。
|
||||
"""
|
||||
return {**await verify_daily_spend(), "daily_max_usd": (await verify_settings(session))["daily_max_usd"]}
|
||||
|
||||
|
||||
@router.get("/system")
|
||||
async def system_info() -> dict[str, Any]:
|
||||
"""给设置页顶部展示的运行环境概览。"""
|
||||
|
||||
@@ -0,0 +1,205 @@
|
||||
"""核查设置（api/settings.py 的 verify 一组）：双盲复算、反方审稿、审批质询共用。
|
||||
|
||||
- 核查模型（接入、模型）：节点上写了用节点的，没写用设置里的，设置也没写就沿用证据裁判模型的取值链
|
||||
（裁判设置 > 助手模型 > 默认接入），哪一级写了就整组用哪一级，不跨级拼接入和模型
|
||||
- 三项各有开关和上限：双盲复算 {启用, 允许的相对误差, 查询次数, 时长}、反方审稿 {启用, 句数, 查询次数, 时长}、
|
||||
审批质询 {启用, 查询次数, 时长}；另有全局每日金额上限。上限存 null 表示不限，不会被默认值悄悄盖回去
|
||||
- 设置页写进来的值先查后写：有一项不对整个请求回 422，说明写设置页上的叫法，一项都不落库
|
||||
- 核查的每日计数是引擎记的账（engine/spend.py），不从设置接口进出；有一个只读接口给设置页看今天花了多少
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import pytest
|
||||
from httpx import ASGITransport, AsyncClient
|
||||
from sqlalchemy import delete
|
||||
|
||||
from app.api.settings import (
|
||||
VERIFY_DEFAULTS,
|
||||
VERIFY_GROUP,
|
||||
VERIFY_SETTING_LABEL,
|
||||
verify_model_spec,
|
||||
verify_settings,
|
||||
)
|
||||
from app.db.base import SessionLocal
|
||||
from app.db.models import Setting
|
||||
from app.engine import spend
|
||||
from app.engine.judge import JUDGE_DEFAULTS, MAX_TOKENS
|
||||
from app.main import app
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
async def clean():
|
||||
async with SessionLocal() as session:
|
||||
await session.execute(delete(Setting).where(Setting.key.in_(
|
||||
[VERIFY_GROUP, spend.SPEND_KEY, "judge", "copilot"])))
|
||||
await session.commit()
|
||||
yield
|
||||
|
||||
|
||||
def client() -> AsyncClient:
|
||||
return AsyncClient(transport=ASGITransport(app=app), base_url="http://test")
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------
|
||||
# 默认值与读写
|
||||
# --------------------------------------------------------------------------
|
||||
|
||||
|
||||
def test_the_defaults_are_the_agreed_ones():
|
||||
assert VERIFY_GROUP == "verify"
|
||||
assert VERIFY_DEFAULTS == {
|
||||
"provider": None, "model": None,
|
||||
"dual_check": {"enabled": True, "tolerance": 1e-6, "max_queries": 6, "timeout_s": 120},
|
||||
"challenge": {"enabled": True, "max_claims": 5, "max_queries": 4, "timeout_s": 90},
|
||||
"inquiry": {"enabled": True, "max_queries": 6, "timeout_s": 120},
|
||||
"daily_max_usd": 2.0,
|
||||
}
|
||||
|
||||
|
||||
async def test_settings_expose_the_verify_group_with_defaults():
|
||||
async with client() as c:
|
||||
got = (await c.get("/api/settings")).json()
|
||||
assert got["verify"] == VERIFY_DEFAULTS
|
||||
assert got["judge"] == JUDGE_DEFAULTS, "裁判一组不受影响"
|
||||
assert spend.SPEND_KEY not in got
|
||||
|
||||
|
||||
async def test_a_full_group_round_trips_and_null_stays_unlimited():
|
||||
value = {
|
||||
"provider": "house", "model": "verify-model",
|
||||
"dual_check": {"enabled": False, "tolerance": 0, "max_queries": None, "timeout_s": None},
|
||||
"challenge": {"enabled": True, "max_claims": None, "max_queries": 2, "timeout_s": 30.5},
|
||||
"inquiry": {"enabled": False, "max_queries": 1, "timeout_s": None},
|
||||
"daily_max_usd": None,
|
||||
}
|
||||
async with client() as c:
|
||||
r = await c.put("/api/settings", json={"values": {"verify": value}})
|
||||
assert r.status_code == 200, r.text
|
||||
assert r.json()["verify"] == value
|
||||
assert (await c.get("/api/settings")).json()["verify"] == value
|
||||
async with SessionLocal() as session:
|
||||
assert await verify_settings(session) == value
|
||||
|
||||
|
||||
async def test_a_partial_group_keeps_the_other_defaults_down_to_each_item():
|
||||
async with client() as c:
|
||||
r = await c.put("/api/settings", json={"values": {"verify": {"dual_check": {"enabled": False},
|
||||
"daily_max_usd": 5}}})
|
||||
assert r.status_code == 200, r.text
|
||||
got = (await c.get("/api/settings")).json()["verify"]
|
||||
assert got == {**VERIFY_DEFAULTS, "daily_max_usd": 5,
|
||||
"dual_check": {**VERIFY_DEFAULTS["dual_check"], "enabled": False}}
|
||||
|
||||
|
||||
@pytest.mark.parametrize("key,value,label", [
|
||||
("daily_max_usd", -1, "daily_max_usd"),
|
||||
("daily_max_usd", "2", "daily_max_usd"),
|
||||
("model", 3, "model"),
|
||||
("dual_check", "on", "dual_check"),
|
||||
("dual_check", {"enabled": "yes"}, "dual_check.enabled"),
|
||||
("dual_check", {"tolerance": -0.1}, "dual_check.tolerance"),
|
||||
("dual_check", {"tolerance": "0.01"}, "dual_check.tolerance"),
|
||||
("dual_check", {"tolerance": None}, "dual_check.tolerance"),
|
||||
("dual_check", {"max_queries": 2.5}, "dual_check.max_queries"),
|
||||
("dual_check", {"max_queries": 0}, "dual_check.max_queries"),
|
||||
("challenge", {"max_claims": True}, "challenge.max_claims"),
|
||||
("challenge", {"timeout_s": -3}, "challenge.timeout_s"),
|
||||
("inquiry", {"timeout_s": 0}, "inquiry.timeout_s"),
|
||||
("inquiry", {"max_claims": 3}, "inquiry.max_claims"),
|
||||
("unknown_key", 1, "unknown_key"),
|
||||
])
|
||||
async def test_bad_values_are_refused_with_the_settings_page_wording(key, value, label):
|
||||
async with client() as c:
|
||||
r = await c.put("/api/settings", json={"values": {"verify": {key: value}, "ui": {"theme": "dark"}}})
|
||||
assert r.status_code == 422, r.text
|
||||
detail = r.json()["detail"]
|
||||
# 报错写设置页上的叫法（「双盲复算 · 允许的相对误差」），不写键名；认不出的键原样点名
|
||||
assert VERIFY_SETTING_LABEL.get(label, label.rpartition(".")[2]) in detail, detail
|
||||
got = (await c.get("/api/settings")).json()
|
||||
assert got["verify"] == VERIFY_DEFAULTS and got["ui"]["theme"] != "dark", "整个请求都没写进去"
|
||||
|
||||
|
||||
@pytest.mark.parametrize("raw", ["NaN", "Infinity"])
|
||||
async def test_non_finite_numbers_are_refused(raw):
|
||||
async with client() as c:
|
||||
r = await c.put("/api/settings", content='{"values": {"verify": {"dual_check": {"tolerance": %s}}}}' % raw,
|
||||
headers={"content-type": "application/json"})
|
||||
assert r.status_code == 422, r.text
|
||||
assert VERIFY_SETTING_LABEL["dual_check.tolerance"] in r.json()["detail"]
|
||||
|
||||
|
||||
async def test_bad_rows_already_in_the_database_fall_back_to_defaults():
|
||||
"""库里存坏了的值（旧版本、手改）读出来按默认，不让核查拿着负数上限、文字开关去查库。"""
|
||||
async with SessionLocal() as session:
|
||||
session.add(Setting(key=VERIFY_GROUP, value={
|
||||
"model": " ", "daily_max_usd": -3,
|
||||
"dual_check": {"enabled": "yes", "tolerance": -1, "max_queries": None},
|
||||
"challenge": "broken", "inquiry": {"timeout_s": 15, "extra": 1}}))
|
||||
await session.commit()
|
||||
got = await verify_settings(session)
|
||||
assert got["model"] is None and got["daily_max_usd"] == VERIFY_DEFAULTS["daily_max_usd"]
|
||||
assert got["dual_check"] == {**VERIFY_DEFAULTS["dual_check"], "max_queries": None}
|
||||
assert got["challenge"] == VERIFY_DEFAULTS["challenge"]
|
||||
assert got["inquiry"] == {**VERIFY_DEFAULTS["inquiry"], "timeout_s": 15}
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------
|
||||
# 每日计数
|
||||
# --------------------------------------------------------------------------
|
||||
|
||||
|
||||
async def test_the_daily_counter_does_not_travel_through_the_settings_api():
|
||||
async with SessionLocal() as session:
|
||||
session.add(Setting(key=spend.SPEND_KEY, value={"date": spend._today(), "usd": 1.5, "calls": 3}))
|
||||
await session.commit()
|
||||
async with client() as c:
|
||||
assert spend.SPEND_KEY not in (await c.get("/api/settings")).json()
|
||||
await c.put("/api/settings", json={"values": {spend.SPEND_KEY: {"date": spend._today(), "usd": 0}}})
|
||||
async with SessionLocal() as session:
|
||||
row = await session.get(Setting, spend.SPEND_KEY)
|
||||
assert row.value["usd"] == 1.5, "设置页整组回写不能把今天的核查花费清零"
|
||||
|
||||
|
||||
async def test_todays_spend_is_readable_next_to_the_daily_cap(monkeypatch):
|
||||
monkeypatch.setattr(spend, "_today", lambda: "2026-10-02")
|
||||
async with SessionLocal() as session:
|
||||
session.add(Setting(key=spend.SPEND_KEY, value={"date": "2026-10-02", "usd": 0.42, "calls": 3,
|
||||
"unpriced_calls": 1}))
|
||||
await session.commit()
|
||||
async with client() as c:
|
||||
got = (await c.get("/api/settings/verify/spend")).json()
|
||||
assert got == {"date": "2026-10-02", "usd": 0.42, "calls": 3, "unpriced_calls": 1, "daily_max_usd": 2.0}
|
||||
await c.put("/api/settings", json={"values": {"verify": {"daily_max_usd": None}}})
|
||||
assert (await c.get("/api/settings/verify/spend")).json()["daily_max_usd"] is None
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------
|
||||
# 核查模型的取值链
|
||||
# --------------------------------------------------------------------------
|
||||
|
||||
|
||||
async def test_the_verify_model_falls_back_along_the_judge_chain():
|
||||
async with SessionLocal() as session:
|
||||
spec = await verify_model_spec(session)
|
||||
assert (spec.provider, spec.model) == (None, None), "什么都没配：默认接入"
|
||||
assert spec.thinking == "off" and spec.max_tokens == MAX_TOKENS
|
||||
|
||||
session.add(Setting(key="copilot", value={"provider": "", "model": "copilot-model"}))
|
||||
await session.commit()
|
||||
assert (await verify_model_spec(session)).model == "copilot-model", "沿用裁判的取值链：助手模型"
|
||||
|
||||
session.add(Setting(key="judge", value={"provider": "house", "model": "judge-model"}))
|
||||
await session.commit()
|
||||
spec = await verify_model_spec(session)
|
||||
assert (spec.provider, spec.model) == ("house", "judge-model"), "沿用裁判的取值链：证据裁判模型"
|
||||
|
||||
session.add(Setting(key=VERIFY_GROUP, value={"model": "verify-model"}))
|
||||
await session.commit()
|
||||
spec = await verify_model_spec(session)
|
||||
assert (spec.provider, spec.model) == (None, "verify-model"), "核查设置写了模型就整组用它，不和裁判的接入拼"
|
||||
assert spec.thinking == "off" and spec.max_tokens == MAX_TOKENS
|
||||
|
||||
spec = await verify_model_spec(session, {"provider": "other", "model": "node-model", "tolerance": 0.1})
|
||||
assert (spec.provider, spec.model) == ("other", "node-model"), "节点上写了就按节点"
|
||||
spec = await verify_model_spec(session, {"provider": " ", "model": None})
|
||||
assert spec.model == "verify-model", "节点上留空等于没写"
|
||||
Reference in New Issue
Block a user