mirror of
https://github.com/ThearchyHelios/AgentLab.git
synced 2026-11-15 14:31:58 +00:00
ThearchyHelios
a17c822d57
复核提出的问题和改法：
- 第 2 轮为了不误遮阈值，把范围边界、字符串的范围边界和选出列、函数参数里的数从正文和格子的按值遮里一并免掉；而按词认用法时，
简单 CASE 的 WHEN、IN (VALUES …)、行值、= ANY(ARRAY[…])、IS NOT DISTINCT FROM、套了括号的值这几种在找某一个值的写法被当成「别处」，
两头相同的范围（BETWEEN v AND v、>= v AND <= v）被当成阈值，遮罩值就留在封存的 SQL、回答正文和质询工件里，最后一道关也放行：
- 字面量改按语法树认用在哪：越过括号、负号、CAST、行值、VALUES、ARRAY、ANY / ALL 这些外壳再看上一层，上面几种都认作在找某一个值，
被比较的是哪一列也认得出（短的数照旧只在和遮罩列比较时换）
- 同一列上同一个值两边都被隔开的范围按在找这个值换：BETWEEN v AND v、>= v AND <= v、> v OR < v、整数的 >= v AND < v + 1，一头是几个数
算出来的（13900000002 - 1）也算；只从一边隔开的（>= v，或按 v 分成两段）照旧是阈值
- 数字照原样留着的只剩没夹住某一个值的范围边界和 LIMIT / OFFSET 的行数，而且同一个数在这条 SQL 别的字面量里没被换掉；选出列、函数参数、
算式里够长的遮罩值照第 1 轮换；字符串的范围边界照第 1 轮按值换。名字、注释里写着阈值不牵连阈值本身（AS 超过30000的笔数）
- SQL 里照原样留着的数只在回答正文里不遮，格子、列名、SQL 里照旧按值遮；同一个数在别的查询里被换掉了，正文里也遮。组装后的最后一道关
只放过正文里的这些数，渲染进单元格引用里的照旧拦下
- SQL 解析不了时认不准哪个数是阈值，一律不免，只按词认简单的等值比较
- 质询工件里两处免遮接线没有测试守住：报告指标、运行输入的值那一处，单笔目标那条端到端测试补上取质询工件，核对别的列里正好是这个数的
格子在回答、工件里都照常显示；SQL 里阈值那一处随上面的改法拿掉了（格子不再免阈值），补上「格子正好等于阈值」的端到端测试，核对回答和
工件里这一格一样遮住、两边对得上；阈值那条端到端测试补上取等值查询的质询工件，核对 SQL 和事件里一字不差
- 上面每种写法都补了单元测试和端到端测试（手机号存成整数、文字两种），另补开头带换行的 SQL 位置对得上、名字里的阈值不牵连阈值的测试。
查询清单的 SQL 现在要解析，改在线程里换（同 _plan）。每处改动都在副本上做过去掉实现、测试变红的验证
1969 lines
109 KiB
Python
1969 lines
109 KiB
Python
"""审批质询：审批人针对待审报告里的一句话提问，一个只读 agent 当场查库作答，问答写进这次运行。
|
||
|
||
审批卡上只有报告正文和核对概况。审批人对某句话有疑问（「排除测试账号会怎样」「这个数含不含退款」），以前只能驳回重跑，
|
||
或者自己去查库。质询让一个只读 agent（engine/verify_agent.py）当场作答，报告本身一个字不改：
|
||
|
||
1. 开放条件（_open）：运行停在审批上、问的是那张待处理的审批卡——问答落在以后的封存范围里，随运行结束一起封存；或者
|
||
运行已经结束封存、核对一致、是探索运行——问答追加在封存之后（post_seal），是批注不是证据。正式运行封存之后不再追加
|
||
（同按需裁判）；设置里关了「审批质询 · 启用」一律不答。同一次运行同时只答一条：进程内登记（_ANSWERING），登记期间
|
||
这次运行的审批回复、继续运行也不受理（api/runs.py），免得运行往下走了、问答还在路上
|
||
2. 回答（_answer）：交给 agent 被问的那句原文、它挂的证据摘录（照 judge.prepare 的办法取，数据源遮罩的列照旧不给，原报告
|
||
的编号标明「原报告」）、审批人选中的原文和问题；工具是这次运行用过的查询工具对应的数据源（同名重建的、没固定过版本的
|
||
上传表格不算，见 _usable_sources）；上限按设置（每次的查询次数、时长，全局每日金额）。回答先给结论，数字只能引用 agent
|
||
自己查询的格子，或者报告里已有的指标、运行输入；回答文档由 compose_doc 组装，裸数字被标出来（提问人自己写的数除外）。
|
||
封存之后的追问查的是数据源现在的数据，任务里给报告生成的时间，回答末尾注明；触顶、查询失败、引用解析不了也在末尾注明
|
||
3. 遮罩（_plan）：哪些列要遮照证据面板的规则（查询当时记下的，加上数据源现在设的），另按 SQL 认出改了名字的遮罩列
|
||
（起别名、套函数、经子查询转一道、和 * 写在同一支里，_derived_hidden；认不出落在哪一列的，整份快照遮掉）；快照按列
|
||
遮，再按值遮（别的列里写着遮罩值的格子，_masked_view）。回答正文、查询清单里的遮罩值换成「已遮罩」（_Secrets、
|
||
_scrub_sql）：按值认有门槛；SQL 里的字面量按语法树认用在哪（_literal_uses），数字照原样留着的只有范围比较的边界
|
||
（没把某一个值夹住的）和 LIMIT 的行数，封存的是实际执行的语句；在找某一个值的（等值、IN、简单 CASE……）和别处
|
||
够长的遮罩值都换。已经摆在读者眼前的值不换：问题和选中原文里的、报告列出的指标和运行输入的值；SQL 里照原样留着
|
||
的阈值只在回答正文里不换，格子照旧换。组装之后还认得出遮罩值的，这份回答不交出去
|
||
4. 写入（_record）：一条 approval.inquiry 事件，node_id 为空，用量写在数据的 usage 里（计进运行用量，见 runner 的
|
||
_usage_of_events）。质询的查询快照只放在 inquiry_artifacts / queries 里，绝不放在 query_artifact 下：证据接口按那个键
|
||
收集封存的查询，会把质询的查询当成报告的证据。回答期间运行状态变了（被批准、被放弃、继续运行之后重新封存），
|
||
append_events 不写，回答照样交回给提问的人，说明没有写进运行记录（这样的回答在进程里留一阵，_HELD）。触顶、失败
|
||
照样记一条
|
||
5. 读取：列表读 approval.inquiry 事件（封存前后的都算，按先后）；质询工件只认质询引用过的（查询快照、回答文档、回答里
|
||
引用的报告口径卡），遮罩照回答时的办法
|
||
|
||
不发 tool.start、llm.start 这类事件（run_verify_agent 不传 emit）：界面从接口的返回取回答；runner 的 _stale_replay
|
||
只看 tool.start，质询不影响恢复后的重放。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import asyncio
|
||
import contextlib
|
||
import json
|
||
import logging
|
||
import re
|
||
import time
|
||
from collections import OrderedDict
|
||
from collections.abc import Callable, Iterable, Iterator
|
||
from dataclasses import dataclass, field
|
||
from datetime import datetime, timezone
|
||
from decimal import Decimal
|
||
from typing import Any
|
||
|
||
from sqlalchemy import func, select
|
||
|
||
from app.core import artifact_store
|
||
from app.core.errors import describe_exception
|
||
from app.core.events import EventType
|
||
from app.data.catalog import QUERY_SNAPSHOT_KIND
|
||
from app.data.provenance_types import DOC_PROVENANCE
|
||
from app.db.base import SessionLocal
|
||
from app.db.models import Approval, Artifact, DataSource, Run, RunEvent
|
||
from app.engine import judge as judging
|
||
from app.engine.evidence import MARKER_RE, RenderError, compose_doc, iter_segments, iter_units, render_cell
|
||
from app.engine.expressions import numeric_text
|
||
from app.engine.issuance import extract_numbers
|
||
from app.engine.merge_query import MERGE_SOURCE
|
||
from app.engine.nodes.challenge import mark_original, with_note
|
||
from app.engine.run_append import append_events
|
||
from app.engine.toolcalls import QUERY_PREFIX
|
||
from app.engine.verify_agent import RATIONALE, VerifyOutcome, run_verify_agent
|
||
|
||
logger = logging.getLogger(__name__)
|
||
|
||
#: 不受理时的机读码（前后端约定）。审批回复、继续运行在质询期间回的也是 INQUIRY_BUSY（api/runs.py）
|
||
INQUIRY_NOT_OPEN = "inquiry_not_open"
|
||
INQUIRY_BUSY = "inquiry_busy"
|
||
INQUIRY_DISABLED = "inquiry_disabled"
|
||
RUN_NOT_FOUND = "run_not_found"
|
||
ARTIFACT_NOT_FOUND = "inquiry_artifact_not_found"
|
||
ARTIFACT_TAMPERED = "snapshot_tampered"
|
||
#: 问题、选中的原文最长多少字
|
||
QUESTION_MAX = 1000
|
||
QUOTE_MAX = 500
|
||
#: 回答期间运行状态变了、问答没写进运行记录时给提问的人的说明
|
||
NOT_RECORDED = "运行状态已经变化，这次质询的问答没有写入运行记录"
|
||
BUSY = "这次运行另有一条质询正在回答，回答完再提问"
|
||
#: 质询正在回答时，这次运行的审批回复（批准 / 驳回）、继续运行回的话（api/runs.py）
|
||
BUSY_DECIDE = "正在回答质询，回答完再批准或驳回"
|
||
BUSY_CONTINUE = "正在回答质询，回答完再继续运行"
|
||
#: 触顶原因：前后端约定的四种。verify_agent 另有 max_steps（模型想了太多轮）：走到那一步时查询次数一定还没用完，
|
||
#: 不能说成查询次数到顶，记为 null，回答末尾注明（NOTE_ROUNDS）
|
||
LIMITS = ("max_queries", "timeout_s", "max_cost_usd", "daily_max_usd")
|
||
#: 事件、接口里的用量只给这几项（runner 计进运行用量的也是这几项，_INQUIRY_KEYS）
|
||
USAGE_KEYS = ("input_tokens", "output_tokens", "cost_usd", "calls", "unpriced_calls")
|
||
#: 查询清单每条给的几项：没有行，查询结果只在快照里（取的时候按遮罩遮好）
|
||
QUERY_KEYS = ("alias", "artifact", "sql", "row_count", "truncated", "source")
|
||
#: 回答文档存成工件时的种类；工件引用的 meta 里记下问题的前这么多字，运行的工件列表据此认得出是哪个问题的回答
|
||
ANSWER_KIND = "inquiry_answer"
|
||
QUESTION_BRIEF = 40
|
||
#: 没指明句子时交给 agent 的报告正文最多多少字
|
||
REPORT_CHARS = 4000
|
||
#: 列给 agent 的报告指标、运行输入最多几条
|
||
REFS_MAX = 40
|
||
#: 被问的是表格里的一格时，交给 agent 的表格最多几行（不含表头）
|
||
TABLE_ROWS = 20
|
||
#: 按值认遮罩值的门槛：文字至少这么多字（一个字的「是」「男」换掉，会把不相干的词也换得面目全非）；纯数字至少这么多位
|
||
#: （年龄、等级、小额金额这类短的数和阈值、天数、日期、LIMIT 里的数太容易撞上，按值换会把实际执行的 SQL、提问人自己
|
||
#: 的条件改得面目全非。它们只在 SQL 里和遮罩列做等值一类比较时才换，见 _scrub_sql；引用到的格子照旧按列遮）
|
||
SECRET_MIN = 2
|
||
SECRET_DIGITS = 5
|
||
#: 遮罩列的值最多收这么多种写法（一份快照最多上千行）：再多就按已经收到的换
|
||
SECRETS_MAX = 20_000
|
||
#: 没写进运行记录的回答在进程里留多久、最多留几条：这段时间里质询工件接口照样认它引用的工件
|
||
HELD_TTL_S = 3600
|
||
HELD_MAX = 200
|
||
#: 运行的终态。封存之后的追问只在这几种状态上
|
||
_TERMINAL = ("succeeded", "failed", "cancelled")
|
||
#: 按词边界认值的字符：值的头尾是这样的字时，前后不能紧挨着同类的字（13900000001 不换掉 139000000012 的一截）
|
||
_WORD = re.compile(r"[0-9A-Za-z_]")
|
||
|
||
INQUIRY_SYSTEM = (
|
||
"你在帮人核对一份报告：提问人针对报告里的一句话提了问题，你查库作答。你不写报告，也不改报告。\n"
|
||
"- 问题是「如果……会怎样」（排除测试账号、换个时间范围、只看某个区域）时，写只读查询把它算出来，不要凭印象推测\n"
|
||
"- 回答直截了当：第一句直接给结论（是还是不是、是多少、差多少），再用一两句说依据；不要复述问题，不要客套\n"
|
||
"- 回答里的每个数字都写成引用：你自己查询结果里的一格写 [[v:Qn.rX.列名]]，报告里已有的指标、运行输入照任务里列出的"
|
||
"写法引用；不要直接写数字，没有出处的数字会被标出来\n"
|
||
"- 数据源设了遮罩的列（手机号、姓名这类）：查询里不要选出原值，也不要给它们起别名；要数人数、笔数用 COUNT，回答里需要"
|
||
"指明时说「该客户」「这一笔」，不要写出原值\n"
|
||
"- 查不到、数据里没有判断所需的信息，就照实说查不到，不要编造"
|
||
)
|
||
INQUIRY_TASK_PROMPT = (
|
||
"报告「{report}」{where}\n\n"
|
||
"{evidence}"
|
||
"{refs}"
|
||
"可以查询的数据源：{sources}\n\n"
|
||
"{since}"
|
||
"{masked}"
|
||
"提问人的问题：\n{question}\n\n"
|
||
"按上面的做法作答，回答写在 rationale 里。"
|
||
)
|
||
#: 交给核查 agent 的结果结构：只有回答一项（verify_agent 的理由字段，沿用这里写的说明）
|
||
INQUIRY_SCHEMA: dict[str, Any] = {
|
||
"type": "object",
|
||
"properties": {RATIONALE: {
|
||
"type": "string",
|
||
"description": "回答：第一句直接给结论，再用一两句说依据；数字一律写成引用（[[v:Qn.rX.列名]]，"
|
||
"或任务里列出的报告指标、运行输入）",
|
||
}},
|
||
"required": [RATIONALE],
|
||
"additionalProperties": False,
|
||
}
|
||
|
||
# 不受理的说法
|
||
DISABLED_WORDS = "审批质询已关闭（设置中的「{label}」），如需质询，请在设置的「核查」一节开启"
|
||
STILL_RUNNING = "运行仍在执行。停在人工审批时，或运行结束并封存后，才能质询"
|
||
STILL_RUNNING_FORMAL = "运行仍在执行，停在人工审批时才能质询"
|
||
CARD_MOVED = "这张审批卡已处理，运行正在继续执行，请刷新页面查看最新状态"
|
||
NO_CARD = "运行没有停在人工审批上（可能是服务重启时中断的），没有可以质询的审批"
|
||
CARD_GONE = "这张审批卡已处理，或不是这次运行正在等待的审批，请刷新页面查看最新状态"
|
||
CARD_DONE = "这张审批卡已处理，运行已经结束，请刷新页面查看最新状态"
|
||
FORMAL_SEALED = "正式运行已结束并封存，问答不能再追加进运行记录；封存之后只有探索运行可以继续质询"
|
||
UNSEALED = "运行已结束，但还没有封存，暂时不能质询"
|
||
BROKEN_SEAL = "封存核对未通过：封存后有事件被修改、删除或插入，报告和证据已不可信，不能再质询"
|
||
NEED_CARD = "运行停在人工审批上，需要指明质询的是哪张审批卡"
|
||
BAD_BODY = ("请求格式有误：需要一个对象，写明报告（report，报告撰写节点的 ID）和问题（question），"
|
||
"可选句子编号（unit）、选中的原文（quote）、审批卡（approval_id）")
|
||
DOC_TAMPERED = "报告文档与哈希不一致，疑似被修改，不能据此质询"
|
||
DOC_MISSING = "无法读取报告文档"
|
||
# 没能给出回答的说法：说发生了什么、下一步。核查 agent 的原话（「交结果」「按结构」、裸写的字段名）只进日志
|
||
NO_ANSWER = "模型没有给出回答内容，请重新提问"
|
||
LEAKED = "回答中含有设了遮罩的值，无法遮住，已不予展示，请换个问法重新提问"
|
||
ERR_DAILY = "今日核查花费已达上限（{cap}），未能给出回答，可在设置的「核查」一节调高上限"
|
||
ERR_COST = "这次回答的花费已达上限，未能给出回答，可缩小问题范围后重新提问"
|
||
ERR_TIMEOUT = "回答超过时长上限{seconds}，未能给出回答，可缩小问题范围后重新提问"
|
||
ERR_SHAPE = "模型未能按要求给出回答，请重新提问；如反复出现，请在设置的「核查」一节更换核查模型"
|
||
ERR_SILENT = "模型没有给出回复，未能给出回答，请重新提问"
|
||
# 回答末尾的系统说明（with_note：另起一段，不挂出处、不查裸数字）
|
||
NOTE_LOST = "注：这次运行还用到了数据源{names}，已不存在、已停用或已被重建，未能查询，以上回答不含其中的数据。"
|
||
NOTE_ROUNDS = "注：调用模型的轮数已用完，以上回答只依据已经查到的结果，可能不完整。"
|
||
NOTE_FAILED = "注：有 {n} 次查询执行失败（查询清单只列成功的查询），以上回答可能缺少依据。"
|
||
NOTE_UNRESOLVED = "注：回答中有 {n} 处引用无法解析，相关的数没有出处。"
|
||
NOTE_LIVE = "注：以上回答依据的是数据源当前的数据，晚于报告生成的时间；与报告不一致时，可能是报告生成之后数据有更新。"
|
||
|
||
|
||
class InquiryRefused(Exception):
|
||
"""质询不受理：status 是 HTTP 状态码，message 是给人看的话；409 带机读码 code，422 带出错的那一项 field。"""
|
||
|
||
def __init__(self, status: int, message: str, *, code: str | None = None, field: str | None = None) -> None:
|
||
super().__init__(message)
|
||
self.status, self.message, self.code, self.field = status, message, code, field
|
||
|
||
|
||
def _invalid(message: str, name: str | None) -> InquiryRefused:
|
||
return InquiryRefused(422, message, field=name)
|
||
|
||
|
||
def _not_open(message: str) -> InquiryRefused:
|
||
return InquiryRefused(409, message, code=INQUIRY_NOT_OPEN)
|
||
|
||
|
||
# --------------------------------------------------------------------------
|
||
# 同一次运行同时只答一条
|
||
# --------------------------------------------------------------------------
|
||
|
||
|
||
class _Answering:
|
||
"""正在回答质询的运行（进程内登记）。
|
||
|
||
只在本进程里有效：另一个进程里的批准拦不住，那时追加按条件更新核对（append_events），写不进就照实说没写进。"""
|
||
|
||
def __init__(self) -> None:
|
||
self._runs: set[str] = set()
|
||
|
||
def busy(self, run_id: str) -> bool:
|
||
return run_id in self._runs
|
||
|
||
@contextlib.contextmanager
|
||
def hold(self, run_id: str) -> Iterator[None]:
|
||
# 查和登记之间没有 await：同一个事件循环里的两条质询不会都看到「没人在答」
|
||
if run_id in self._runs:
|
||
raise InquiryRefused(409, BUSY, code=INQUIRY_BUSY)
|
||
self._runs.add(run_id)
|
||
try:
|
||
yield
|
||
finally:
|
||
self._runs.discard(run_id)
|
||
|
||
|
||
_ANSWERING = _Answering()
|
||
|
||
|
||
def inquiry_busy(run_id: str) -> bool:
|
||
"""这次运行是不是正在回答质询（api/runs.py 据此让审批回复、继续运行回 409）。"""
|
||
return _ANSWERING.busy(run_id)
|
||
|
||
|
||
class _Held:
|
||
"""没写进运行记录的回答（回答期间运行状态变了）：进程内留 HELD_TTL_S 秒、最多 HELD_MAX 条，先进先出。
|
||
|
||
提问人手里那份回答里的数要点得开，质询工件接口在这段时间里照样认它引用的工件（遮罩照旧）。过了时间、或者服务
|
||
重启过，接口照常回 404：回答本身已经交回去了，只是数字不能再下钻。"""
|
||
|
||
def __init__(self) -> None:
|
||
self._items: OrderedDict[int, tuple[str, float, dict[str, Any]]] = OrderedDict()
|
||
self._next = 0
|
||
|
||
def keep(self, run_id: str, data: dict[str, Any]) -> None:
|
||
self._next += 1
|
||
self._items[self._next] = (run_id, time.monotonic() + HELD_TTL_S, data)
|
||
while len(self._items) > HELD_MAX:
|
||
self._items.popitem(last=False)
|
||
|
||
def of(self, run_id: str) -> list[dict[str, Any]]:
|
||
now = time.monotonic()
|
||
for key in [k for k, (_, until, _) in self._items.items() if until <= now]:
|
||
del self._items[key]
|
||
return [data for owner, _, data in self._items.values() if owner == run_id]
|
||
|
||
|
||
_HELD = _Held()
|
||
|
||
|
||
# --------------------------------------------------------------------------
|
||
# 请求
|
||
# --------------------------------------------------------------------------
|
||
|
||
|
||
@dataclass(frozen=True)
|
||
class Ask:
|
||
"""一条质询：哪份报告（报告撰写节点的 id）的哪一句（句子单元 id，可以不指明）、选中的原文、问题、问的是哪张审批卡。"""
|
||
|
||
report: str
|
||
unit: str | None
|
||
quote: str | None
|
||
question: str
|
||
approval_id: str | None
|
||
|
||
|
||
def parse_ask(body: Any) -> Ask:
|
||
"""请求体 → Ask。不合法时抛 422，field 指明是哪一项。"""
|
||
if not isinstance(body, dict):
|
||
raise _invalid(BAD_BODY, None)
|
||
report = body.get("report")
|
||
if not isinstance(report, str) or not report.strip():
|
||
raise _invalid("请指明质询的是哪份报告（报告撰写节点的 ID）", "report")
|
||
unit = _blank_as_none(body.get("unit"))
|
||
if unit is not None and not isinstance(unit, str):
|
||
raise _invalid("句子编号需要是文字，例如「u12」；不指明句子时留空", "unit")
|
||
quote = body.get("quote")
|
||
if quote is not None and not isinstance(quote, str):
|
||
raise _invalid("选中的原文需要是文字", "quote")
|
||
quote = (quote or "").strip() or None
|
||
if quote is not None and len(quote) > QUOTE_MAX:
|
||
raise _invalid(f"选中的原文最长 {QUOTE_MAX} 字，当前为 {len(quote)} 字，请缩短选区", "quote")
|
||
question = body.get("question")
|
||
if not isinstance(question, str) or not question.strip():
|
||
raise _invalid("请填写要质询的问题", "question")
|
||
question = question.strip()
|
||
if len(question) > QUESTION_MAX:
|
||
raise _invalid(f"问题最长 {QUESTION_MAX} 字，当前为 {len(question)} 字", "question")
|
||
approval_id = _blank_as_none(body.get("approval_id"))
|
||
if approval_id is not None and not isinstance(approval_id, str):
|
||
raise _invalid("审批卡的 ID 需要是文字；不是在审批卡上提问时留空", "approval_id")
|
||
return Ask(report=report.strip(), unit=unit.strip() if unit else None, quote=quote, question=question,
|
||
approval_id=approval_id.strip() if approval_id else None)
|
||
|
||
|
||
def _blank_as_none(value: Any) -> Any:
|
||
"""不指明句子、不是在审批卡上问的：写 null 和写空串是一个意思。别的类型原样交回，由调用方报格式不对。"""
|
||
return None if isinstance(value, str) and not value.strip() else value
|
||
|
||
|
||
# --------------------------------------------------------------------------
|
||
# 开放条件
|
||
# --------------------------------------------------------------------------
|
||
|
||
Events = list[tuple[int, str, str | None, Any]]
|
||
|
||
|
||
@dataclass
|
||
class _Opening:
|
||
"""开放了的这一次质询：往哪种运行里写（mode）、写的时候要核对什么（approval_id / seal），以及被问的报告文档。
|
||
|
||
loader 是取证据的函数：封存之后只认封存范围内的工件（同按需裁判，api/evidence._sealed_loader），停在审批时和
|
||
报告节点里的裁判一样直接读工件库。events 是这次运行的事件（封存之后只取封存范围内的）。finished 是运行结束的时间
|
||
（UTC，封存之后的追问才有）：报告是那时生成的，之后数据可能有更新。"""
|
||
|
||
run_id: str
|
||
mode: str
|
||
title: str
|
||
versions: Any
|
||
events: Events
|
||
doc: dict[str, Any]
|
||
loader: Callable[[str], Any]
|
||
approval_id: str | None = None
|
||
seal: tuple[int | None, str | None] | None = None
|
||
finished: str | None = None
|
||
|
||
|
||
async def _open(run_id: str, ask: Ask) -> _Opening:
|
||
"""这条质询开不开放：开放就交回往哪写、问的是哪份文档；不开放抛 409（输入不对的抛 422、运行不在的抛 404）。"""
|
||
cards: list[str] = []
|
||
rows: Events = []
|
||
async with SessionLocal() as session:
|
||
run = await session.get(Run, run_id)
|
||
if run is None:
|
||
raise InquiryRefused(404, "运行记录不存在", code=RUN_NOT_FOUND)
|
||
status, run_class, graph, versions = run.status, run.run_class, run.graph or {}, run.data_versions
|
||
finished = _utc(run.finished_at)
|
||
if status == "interrupted":
|
||
cards = [str(a) for a in (await session.execute(
|
||
select(Approval.id).where(Approval.run_id == run_id, Approval.status == "pending"))).scalars()]
|
||
rows = [tuple(r) for r in await session.execute(
|
||
select(RunEvent.seq, RunEvent.type, RunEvent.node_id, RunEvent.data)
|
||
.where(RunEvent.run_id == run_id).order_by(RunEvent.seq))]
|
||
title = _node_title(graph, ask.report)
|
||
if status == "interrupted":
|
||
if not cards:
|
||
raise _not_open(NO_CARD)
|
||
if ask.approval_id is None:
|
||
raise _invalid(NEED_CARD, "approval_id")
|
||
if ask.approval_id not in cards:
|
||
raise _not_open(CARD_GONE)
|
||
doc = _waiting_doc(rows, run_id, ask.report, title)
|
||
return _Opening(run_id=run_id, mode="interrupted", title=title, versions=versions, events=rows, doc=doc,
|
||
loader=artifact_store.load, approval_id=ask.approval_id)
|
||
if status not in _TERMINAL:
|
||
# 带着审批卡来的，多半是卡刚被别人批了、运行往下走了：叫人刷新。没带的按运行类别说什么时候能问
|
||
raise _not_open(CARD_MOVED if ask.approval_id is not None
|
||
else STILL_RUNNING_FORMAL if run_class == "formal" else STILL_RUNNING)
|
||
if ask.approval_id is not None:
|
||
raise _not_open(CARD_DONE)
|
||
if run_class == "formal":
|
||
raise _not_open(FORMAL_SEALED)
|
||
from app.api.evidence import _reports, _sealed, _sealed_loader # api.evidence 导入了 engine 里的模块
|
||
|
||
sealed = await _sealed(run_id)
|
||
if sealed.status not in _TERMINAL:
|
||
# 上面读完状态之后运行被继续了：记录上的封存是上一次结束时的，追加会被下一次封存收进去
|
||
raise _not_open(STILL_RUNNING)
|
||
if not sealed.sealed:
|
||
raise _not_open(UNSEALED)
|
||
if not sealed.trusted:
|
||
raise _not_open(BROKEN_SEAL)
|
||
report = next((r for r in _reports(sealed) if r.node_id == ask.report), None)
|
||
if report is None:
|
||
raise _invalid(_no_report(title), "report")
|
||
if report.hash_ok is False:
|
||
raise _invalid(DOC_TAMPERED, "report")
|
||
if report.doc is None:
|
||
raise _invalid(DOC_MISSING, "report")
|
||
# 带期 4 标记的文档才让摘录取得到哈希链上的清单，和按需裁判同一个口径
|
||
loader = _sealed_loader(sealed, chain=report.doc.get("provenance") == DOC_PROVENANCE)
|
||
return _Opening(run_id=run_id, mode="sealed", title=title, versions=versions, events=list(sealed.events),
|
||
doc=report.doc, loader=loader, seal=(sealed.run_manifest_seq, sealed.manifest_hash),
|
||
finished=finished)
|
||
|
||
|
||
def _utc(ts: datetime | None) -> str | None:
|
||
"""运行记录上的时间 → UTC 的「2026-10-06T08:12:33」。带时区的换成 UTC，不带的本来就是 UTC。"""
|
||
if ts is None:
|
||
return None
|
||
if ts.tzinfo is not None:
|
||
ts = ts.astimezone(timezone.utc).replace(tzinfo=None)
|
||
return ts.isoformat(timespec="seconds")
|
||
|
||
|
||
def _node_title(graph: dict[str, Any], node_id: str) -> str:
|
||
for n in graph.get("nodes") or []:
|
||
if isinstance(n, dict) and n.get("id") == node_id:
|
||
return str((n.get("data") or {}).get("label") or node_id)
|
||
return node_id
|
||
|
||
|
||
def _no_report(title: str) -> str:
|
||
return f"这次运行里没有报告「{title}」的报告文档，请刷新页面后重新选择"
|
||
|
||
|
||
def _waiting_doc(events: Events, run_id: str, report: str, title: str) -> dict[str, Any]:
|
||
"""停在审批时被问的报告文档：这个报告节点最后一次 report.checked 里的那份（同证据接口的 _reports）。文档要真是
|
||
这次运行里这个节点写的——内容寻址只保证没被改，不保证没被张冠李戴。"""
|
||
artifact = None
|
||
for _, etype, node_id, data in events:
|
||
if etype == EventType.REPORT_CHECKED and node_id == report and isinstance(data, dict) and data.get("doc_artifact"):
|
||
artifact = str(data["doc_artifact"])
|
||
if artifact is None:
|
||
raise _invalid(_no_report(title), "report")
|
||
try:
|
||
doc = artifact_store.load(artifact)
|
||
except ValueError as e:
|
||
raise _invalid(DOC_TAMPERED, "report") from e
|
||
if not isinstance(doc, dict):
|
||
raise _invalid(DOC_MISSING, "report")
|
||
if doc.get("node_id") != report or doc.get("run_id") != run_id:
|
||
raise _invalid(DOC_TAMPERED, "report")
|
||
return doc
|
||
|
||
|
||
# --------------------------------------------------------------------------
|
||
# 被问的那句
|
||
# --------------------------------------------------------------------------
|
||
|
||
|
||
@dataclass
|
||
class _Target:
|
||
"""被问的那句：按裁判的候选句建（judge._candidate，带它挂的依据），表格里的一格另带整张表。"""
|
||
|
||
cand: judging.Candidate
|
||
table: str | None = None
|
||
|
||
|
||
def _target(doc: dict[str, Any], unit: str) -> _Target:
|
||
"""文档里的这一句。按 judge.candidates 的走法记小节和先后；不是结论句的（表格里的一格、标题）也照样建，
|
||
审批人问的不一定是结论句。没有这一句抛 422。"""
|
||
markdown = str(doc.get("markdown") or "")
|
||
section = ""
|
||
for order, (block, item) in enumerate(iter_units(doc)):
|
||
text = judging._unit_text(item, markdown)
|
||
if block.get("type") == "heading":
|
||
section = text
|
||
if item.get("id") != unit:
|
||
continue
|
||
priority = judging.claim_priority(item, block, markdown) or 3
|
||
cand = judging._candidate(item, priority, order, text, section)
|
||
return _Target(cand, _table_text(block, markdown) if block.get("type") == "table" else None)
|
||
raise _invalid(f"报告里没有这句（{unit}），请刷新页面后重新选择", "unit")
|
||
|
||
|
||
def _table_text(block: dict[str, Any], markdown: str) -> str:
|
||
"""表格整张压成几行（表头在前），一格的值离了行列说不清是什么。"""
|
||
rows: dict[int, dict[int, str]] = {}
|
||
for unit in block.get("units") or []:
|
||
loc = unit.get("loc") if isinstance(unit, dict) else None
|
||
if isinstance(loc, dict) and isinstance(loc.get("row"), int) and isinstance(loc.get("col"), int):
|
||
rows.setdefault(loc["row"], {})[loc["col"]] = judging._unit_text(unit, markdown)
|
||
lines = [" | ".join(cells[c] for c in sorted(cells)) for _, cells in sorted(rows.items())]
|
||
kept = lines[:TABLE_ROWS + 1]
|
||
return "\n".join(kept) + ("\n…（后面的行省略了）" if len(lines) > len(kept) else "")
|
||
|
||
|
||
def _excerpts(doc: dict[str, Any], catalog: dict[str, Any], cand: judging.Candidate, loader: Callable[[str], Any],
|
||
masked: dict[str, Any]) -> list[str]:
|
||
"""这句挂的每件证据的摘录：和 judge.prepare 一样逐件摘（数据源遮罩的列不给，带期 4 标记的文档多来历行），
|
||
指向原报告编号的写法标上「原报告」——agent 自己的查询也编 Q1、Q2…，不分开的话会把它们混成一回事。"""
|
||
fetch = judging._Fetch(loader)
|
||
provenance_on = doc.get("provenance") == DOC_PROVENANCE
|
||
queries = {a for a, e in catalog.items() if isinstance(e, dict) and e.get("kind") == "query"}
|
||
out: list[str] = []
|
||
for alias in cand.aliases:
|
||
entry = catalog.get(alias)
|
||
if isinstance(entry, dict) and (text := judging._excerpt(alias, entry, [cand], fetch, masked, catalog,
|
||
provenance_on=provenance_on)):
|
||
out.append(mark_original(text, alias, queries))
|
||
return out
|
||
|
||
|
||
def _report_refs(catalog: dict[str, Any]) -> dict[str, dict[str, Any]]:
|
||
"""报告目录里回答可以直接引用的出处：有值的口径卡指标（m:）和运行输入（i:）。它们的编号和 agent 自己的 Q1… 不会
|
||
撞；报告的查询格子不行——agent 的查询也编 Q1，引用 Q1 说不清是哪一份。没有值的引用了也解析不了，不列。"""
|
||
return {a: e for a, e in catalog.items()
|
||
if isinstance(e, dict) and e.get("kind") in ("metric", "input") and e.get("value") not in (None, "")}
|
||
|
||
|
||
def _ref_values(refs: dict[str, dict[str, Any]]) -> list[str]:
|
||
"""报告里列出的指标、运行输入的值（原样和渲染出来的写法）：报告里就看得到，碰巧和遮罩列里的某个值一样，回答引用
|
||
它也不算露出遮罩值（_Secrets.protect）。不免的话，引用「单笔目标」这样的指标整份回答都交不出去，换个问法也一样。"""
|
||
out: list[str] = []
|
||
for entry in refs.values():
|
||
out += _forms(entry.get("value"))
|
||
if isinstance(entry.get("rendered"), str):
|
||
out.append(entry["rendered"])
|
||
return out
|
||
|
||
|
||
def _run_sources(events: Events) -> list[str]:
|
||
"""这次运行用过的查询工具对应的数据源，按第一次用到的先后。"""
|
||
out: list[str] = []
|
||
for _, etype, _, data in events:
|
||
if etype not in (EventType.TOOL_START, EventType.TOOL_END) or not isinstance(data, dict):
|
||
continue
|
||
tool = str(data.get("tool") or "")
|
||
name = tool[len(QUERY_PREFIX):] if tool.startswith(QUERY_PREFIX) else ""
|
||
if name and name not in out:
|
||
out.append(name)
|
||
return out
|
||
|
||
|
||
async def _usable_sources(run_id: str, names: Iterable[str], versions: Any) -> dict[str, list[str]]:
|
||
"""这次运行用过、现在还能查的数据源 → 它现在设了遮罩的列。
|
||
|
||
工具按名字建（核查建工具时只认存在、没有停用的源），名字背后的源却可能换过：运行用过的源被删了、又用同一个名字
|
||
新建一个，查到的已经不是这次运行的数据。所以按名字找到现在的源之后，再核对是不是运行用过的那一个——运行里的查询
|
||
快照在工件引用的 meta 里记着源 id（质询自己的查询不算，它们的 node_id 为空），上传表格还记在运行固定的版本里
|
||
（data_versions）。没固定过版本的上传表格也不交给 agent：建工具时会把当前版本补固定进运行记录（tools/datasource
|
||
的 _pin_late），质询不发事件，已经封存的运行就被悄悄改了。升级前发起的运行（data_versions 为 None）照旧按当前版本。"""
|
||
from app.data.engine import masked_columns
|
||
|
||
wanted = list(dict.fromkeys(names))
|
||
if not wanted:
|
||
return {}
|
||
pins = versions if isinstance(versions, dict) else None
|
||
async with SessionLocal() as session:
|
||
rows = (await session.execute(
|
||
select(DataSource.id, DataSource.name, DataSource.origin, DataSource.options)
|
||
.where(DataSource.name.in_(wanted), DataSource.enabled.is_(True)))).all()
|
||
metas = (await session.execute(
|
||
select(Artifact.meta).where(Artifact.run_id == run_id, Artifact.kind == QUERY_SNAPSHOT_KIND,
|
||
func.coalesce(Artifact.node_id, "") != ""))).scalars().all()
|
||
used: dict[str, set[str]] = {}
|
||
for meta in metas:
|
||
if isinstance(meta, dict) and meta.get("source") in wanted and meta.get("source_id"):
|
||
used.setdefault(str(meta["source"]), set()).add(str(meta["source_id"]))
|
||
for source_id, entry in (pins or {}).items():
|
||
if isinstance(entry, dict) and entry.get("name") in wanted:
|
||
used.setdefault(str(entry["name"]), set()).add(str(source_id))
|
||
out: dict[str, list[str]] = {}
|
||
for source_id, name, origin, options in rows:
|
||
known = used.get(str(name))
|
||
if known and str(source_id) not in known:
|
||
continue
|
||
if (origin or "manual") == "upload" and pins is not None and source_id not in pins:
|
||
continue
|
||
out[str(name)] = masked_columns(options)
|
||
return out
|
||
|
||
|
||
def _quoted(names: Iterable[str]) -> str:
|
||
return "、".join(f"「{n}」" for n in names)
|
||
|
||
|
||
def _task(op: _Opening, ask: Ask, target: _Target | None, excerpts: list[str], refs: dict[str, dict[str, Any]],
|
||
live: dict[str, list[str]], lost: list[str]) -> str:
|
||
if target is not None:
|
||
cand = target.cand
|
||
where = f"中的这句话{f'（所在小节「{cand.section}」）' if cand.section else ''}：\n「{cand.text}」"
|
||
if target.table:
|
||
where += f"\n\n这句话在一张表格里，表格是（每行一条，单元格用 | 隔开）：\n{target.table}"
|
||
else:
|
||
where = "，提问人没有指明是哪一句"
|
||
if ask.quote:
|
||
where += f"\n\n提问人选中的原文：\n「{ask.quote}」"
|
||
if target is None:
|
||
markdown = str(op.doc.get("markdown") or "")
|
||
cut = markdown[:REPORT_CHARS] + ("\n…（后面的省略了）" if len(markdown) > REPORT_CHARS else "")
|
||
where += f"\n\n报告正文：\n{cut}"
|
||
evidence = ""
|
||
if target is not None:
|
||
evidence = ("这句话挂的证据摘录（编号属于原报告；你的查询另起编号，回答里只能引用你自己的查询）：\n"
|
||
+ "\n\n".join(excerpts) + "\n\n") if excerpts else "这句话没有挂依据。\n\n"
|
||
lines = [f"[[{alias}]] {entry.get('label') or alias}" for alias, entry in list(refs.items())[:REFS_MAX]]
|
||
more = f"\n…另有 {len(refs) - REFS_MAX} 项" if len(refs) > REFS_MAX else ""
|
||
refs_text = ("报告里已有的指标和运行输入（回答里可以照这个写法直接引用）：\n" + "\n".join(lines) + more + "\n\n"
|
||
if lines else "")
|
||
sources = "、".join(live) if live else "（没有可以查询的数据源，只能依据上面的报告内容作答）"
|
||
if lost:
|
||
sources += f"（这次运行还用到了{_quoted(lost)}，已不存在、已停用或已被重建，无法查询）"
|
||
# 封存之后的追问：报告是运行结束时生成的，现在查到的数据可能已经变了
|
||
since = (f"报告生成于 {op.finished}（UTC），之后数据可能有更新：查询结果和报告对不上时，先说明这一点。\n\n"
|
||
if op.mode == "sealed" and op.finished else "")
|
||
hidden = [f"「{name}」的 {'、'.join(cols)}" for name, cols in live.items() if cols]
|
||
masked = (f"设了遮罩的列（查询里不要选出原值、不要起别名，回答里不要写出这些列的值）：{'；'.join(hidden)}\n\n"
|
||
if hidden else "")
|
||
return INQUIRY_TASK_PROMPT.format(report=op.title, where=where, evidence=evidence, refs=refs_text,
|
||
sources=sources, since=since, masked=masked, question=ask.question)
|
||
|
||
|
||
# --------------------------------------------------------------------------
|
||
# 遮罩：哪些列
|
||
# --------------------------------------------------------------------------
|
||
|
||
|
||
def _query_shaped(content: Any) -> bool:
|
||
return isinstance(content, dict) and isinstance(content.get("rows"), list)
|
||
|
||
|
||
async def _hidden_columns(snapshot: dict[str, Any], masks: Any) -> tuple[set[str], list[str]]:
|
||
"""一份查询快照要遮的列（小写）和已经不在的数据源，照证据面板的规则（api/evidence.py 的 _query_step）：查询当时
|
||
记下的，加上数据源现在设的；合并查询按它合并的那几个数据源算。"""
|
||
from app.api.evidence import _merge_masks, _recorded_masks
|
||
|
||
if snapshot.get("source") == MERGE_SOURCE:
|
||
return await _merge_masks(snapshot, masks)
|
||
cols, found = await masks.of(snapshot.get("source"))
|
||
return cols | _recorded_masks(snapshot), ([] if found or not snapshot.get("source") else [str(snapshot["source"])])
|
||
|
||
|
||
def _masked_word() -> str:
|
||
from app.api.evidence import MASKED
|
||
|
||
return MASKED
|
||
|
||
|
||
def _value_columns(node: Any) -> set[str]:
|
||
"""一个选出列的值取自哪些列（列名小写）。COUNT 里的只数个数，窗口的分区键、排序键只决定次序，都带不出值，不算；
|
||
套在里面的子查询只看它选出来的列（它的条件、连接里写的列带不出值）。"""
|
||
from sqlglot import exp
|
||
|
||
out: set[str] = set()
|
||
stack = [node]
|
||
while stack:
|
||
item = stack.pop()
|
||
if isinstance(item, exp.Column):
|
||
if not isinstance(item.this, exp.Star) and item.name:
|
||
out.add(item.name.lower())
|
||
elif isinstance(item, exp.Count):
|
||
continue
|
||
elif isinstance(item, exp.Window):
|
||
stack.append(item.this)
|
||
elif isinstance(item, exp.Select):
|
||
stack.extend(item.expressions)
|
||
else:
|
||
stack.extend(item.iter_expressions())
|
||
return out
|
||
|
||
|
||
def _is_star(item: Any) -> bool:
|
||
from sqlglot import exp
|
||
|
||
return isinstance(item, exp.Star) or (isinstance(item, exp.Column) and isinstance(item.this, exp.Star))
|
||
|
||
|
||
def _branches(root: Any) -> list[list[Any]]:
|
||
"""一块查询选出的列：一条 SELECT 一支，UNION 这类的每一支各一支（结果的第 i 列来自每一支的第 i 项）。"""
|
||
from sqlglot import exp
|
||
|
||
out: list[list[Any]] = []
|
||
stack = [root]
|
||
while stack:
|
||
node = stack.pop()
|
||
if isinstance(node, exp.Subquery):
|
||
stack.append(node.this)
|
||
elif isinstance(node, exp.SetOperation):
|
||
stack.extend((node.expression, node.this))
|
||
elif isinstance(node, exp.Select):
|
||
out.append(list(node.expressions))
|
||
return out
|
||
|
||
|
||
def _output_name(item: Any) -> str | None:
|
||
"""一个选出项在结果里的列名（小写）：起了别名的是别名，直接选一列的是列名。别的表达式（函数、运算、CAST、括号、
|
||
子查询）的列名各数据库起法不同（SQLite 照写法原样记「SUBSTR(buyer_phone, 4)」，Postgres 记函数名或 ?column?），
|
||
认不准，返回 None。"""
|
||
from sqlglot import exp
|
||
|
||
if isinstance(item, exp.Alias):
|
||
return item.alias.lower() or None
|
||
if isinstance(item, exp.Column) and not isinstance(item.this, exp.Star):
|
||
return item.name.lower() or None
|
||
return None
|
||
|
||
|
||
def _places(branch: list[Any], width: int | None) -> list[int | None]:
|
||
"""一支里每一项落在结果的第几列。没有 * 的一一对上；有 * 的，第一个 * 前面的从头数，最后一个 * 后面的从结果末尾
|
||
倒着数（width 是结果的列数，不知道就数不了）；两个 * 之间的、* 本身认不出位置（None）。"""
|
||
stars = [i for i, item in enumerate(branch) if _is_star(item)]
|
||
if not stars:
|
||
return list(range(len(branch)))
|
||
first, last = stars[0], stars[-1]
|
||
tail = len(branch) - 1 - last
|
||
# * 至少展开成 0 列：倒着数要是数到了 * 前面那几项的位置上，列数对不上，后面的一项都不认
|
||
countable = width is not None and width - tail >= first
|
||
return [i if i < first else width - (len(branch) - i) if i > last and countable else None
|
||
for i in range(len(branch))]
|
||
|
||
|
||
def _blocks(root: Any) -> list[tuple[Any, str, list[str] | None]]:
|
||
"""SQL 里的每一块查询（一条 SELECT，或者 UNION 这类连起来的一串）和它的结果流到哪：
|
||
- "result"：最外层，结果就是快照的列；
|
||
- "source"：当成一张表用的——WITH 里的一段、FROM / JOIN 里的子查询、LATERAL，外层按列名取它的列，* 会把它的列
|
||
全带出去。写了列名表的（t(p)）带上列名表；
|
||
- "other"：标量子查询、IN / EXISTS 里的，值经外层的表达式带出（_value_columns 已经算上），列名无关紧要。
|
||
套在外面的括号（可能好几层）不改变结果流到哪：先越过它们再看。UNION 里的一支不另算，整串按一块。"""
|
||
from sqlglot import exp
|
||
|
||
out: list[tuple[Any, str, list[str] | None]] = []
|
||
for node in root.find_all(exp.Select, exp.SetOperation):
|
||
wrappers: list[Any] = []
|
||
outer = node
|
||
while isinstance(outer.parent, exp.Subquery):
|
||
outer = outer.parent
|
||
wrappers.append(outer)
|
||
parent = outer.parent
|
||
if isinstance(parent, exp.SetOperation):
|
||
continue
|
||
if parent is None:
|
||
out.append((node, "result", None))
|
||
elif isinstance(parent, (exp.CTE, exp.Lateral)) or (wrappers and isinstance(parent, (exp.From, exp.Join))):
|
||
# 别名（和列名表）记在 WITH 的那一段、LATERAL 上，FROM 里的子查询记在带别名的那层括号上
|
||
alias = next((h.args["alias"] for h in [parent, *reversed(wrappers)] if h.args.get("alias")), None)
|
||
listed = [c.name.lower() for c in alias.columns] if alias is not None and alias.columns else None
|
||
out.append((node, "source", listed))
|
||
else:
|
||
out.append((node, "other", None))
|
||
return out
|
||
|
||
|
||
def _source_names(top: Any, listed: list[str] | None, names: set[str]) -> tuple[set[str], bool]:
|
||
"""派生来源的结果里值取自遮罩列的那几列的名字，以及有没有认不出名字的（没起别名的表达式、两个 * 之间的项）。
|
||
写了列名表的按位置对上列名表；没写的，单独一条 SELECT 取各项自己的列名，UNION 这类按位置对上第一支的列名。"""
|
||
branches = _branches(top)
|
||
found: set[str] = set()
|
||
unknown = False
|
||
|
||
def take(name: str | None) -> None:
|
||
nonlocal unknown
|
||
if name is None:
|
||
unknown = True
|
||
else:
|
||
found.add(name)
|
||
|
||
if listed is not None:
|
||
for branch in branches:
|
||
for item, place in zip(branch, _places(branch, len(listed))):
|
||
if names & _value_columns(item):
|
||
take(listed[place] if place is not None and place < len(listed) else None)
|
||
return found, unknown
|
||
first = branches[0] if branches else []
|
||
for item in first:
|
||
if names & _value_columns(item):
|
||
take(_output_name(item))
|
||
if len(branches) > 1:
|
||
# 每一支一样宽：拿一支没有 * 的定宽度，* 后面的项才数得出位置
|
||
width = next((len(b) for b in branches if not any(_is_star(i) for i in b)), None)
|
||
heads = {place: _output_name(item) for item, place in zip(first, _places(first, width)) if place is not None}
|
||
for branch in branches[1:]:
|
||
for item, place in zip(branch, _places(branch, width)):
|
||
if names & _value_columns(item):
|
||
take(heads.get(place) if place is not None else None)
|
||
return found, unknown
|
||
|
||
|
||
def _tainted(sql: str, kind: str | None, masked: set[str], width: int) -> tuple[set[str], set[int]] | None:
|
||
"""SQL 里指代遮罩列的名字（小写），和结果（width 列）里值取自遮罩列的那几列的位置。解析不了返回 None。
|
||
|
||
名字从遮罩列本身起，一层层传下去：选出列的值取自这些名字的（buyer_phone AS 手机号、UPPER(buyer_phone) AS x），它的
|
||
名字也算；派生来源（子查询、WITH 里的一段）按位置对上列名表、UNION 第一支的列名，也算，直到不再多出名字。同名
|
||
不同层的也一并算上（宁可多遮）。
|
||
位置是给没起别名的表达式用的（UPPER(buyer_phone) 的结果列名对不上任何名字）：和 * 写在同一支里的，* 前面的从头数、
|
||
后面的从末尾倒着数。认不出的——两个 * 之间的项、派生来源里没起别名的表达式（外层的 * 会把它原样带出来，列名
|
||
又认不准）——整份快照的列都算（同解析不了）。"""
|
||
from sqlglot import exp
|
||
|
||
from app.data.sql_semantics import _parse, _read
|
||
|
||
try:
|
||
root, _ = _parse(sql, _read(kind))
|
||
except Exception: # noqa: BLE001 - 解析器的意外按解析不了处理
|
||
root = None
|
||
if root is None:
|
||
return None
|
||
try:
|
||
names = set(masked)
|
||
selects = list(root.find_all(exp.Select))
|
||
blocks = _blocks(root)
|
||
sources = [(top, listed) for top, role, listed in blocks if role == "source"]
|
||
for _ in range(len(selects) + len(sources) + 1):
|
||
before = len(names)
|
||
for select_ in selects:
|
||
for item in select_.expressions:
|
||
name = item.alias_or_name.lower()
|
||
if name and name not in names and names & _value_columns(item):
|
||
names.add(name)
|
||
for top, listed in sources:
|
||
names |= _source_names(top, listed, names)[0]
|
||
if len(names) == before:
|
||
break
|
||
everything = any(_source_names(top, listed, names)[1] for top, listed in sources)
|
||
positions: set[int] = set()
|
||
for top, role, _listed in blocks:
|
||
if role != "result":
|
||
continue
|
||
for branch in _branches(top):
|
||
for item, place in zip(branch, _places(branch, width)):
|
||
if names & _value_columns(item):
|
||
if place is None or place >= width:
|
||
everything = True
|
||
else:
|
||
positions.add(place)
|
||
return names, set(range(width)) if everything else positions
|
||
except Exception: # noqa: BLE001 - 分析本身的缺陷不能让回答出错：按解析不了处理（宁可多遮）
|
||
logger.warning("质询的 SQL 遮罩分析失败", exc_info=True)
|
||
return None
|
||
|
||
|
||
def _mentions(sql: str, names: Iterable[str]) -> bool:
|
||
return any(re.search(rf"(?<![0-9A-Za-z_]){re.escape(n)}(?![0-9A-Za-z_])", sql, re.I) for n in names if n)
|
||
|
||
|
||
def _derived_hidden(snapshot: dict[str, Any], hidden: set[str], kind: str | None) -> tuple[set[str], set[str]]:
|
||
"""(这份快照要遮的列, SQL 里指代遮罩列的名字)，都是小写。
|
||
|
||
证据面板只按列名遮（hidden）；agent 的查询起了别名、套了函数，结果列名就对不上。本仓库的查询惯例是起中文别名
|
||
（region AS 区域），所以按 SQL 认出改了名字的遮罩列（_tainted）。SQL 解析不了、里面又写着遮罩列的，整份快照的
|
||
列都遮掉；合并查询的快照不看 SQL，它记着自己的来历（_hidden_columns 已按 _merge_masks 遮好）。"""
|
||
base = set(hidden)
|
||
sql = snapshot.get("sql")
|
||
if not base or not isinstance(sql, str) or not sql.strip() or snapshot.get("source") == MERGE_SOURCE:
|
||
return base, base
|
||
columns = [str(c) for c in snapshot.get("columns") or []]
|
||
found = _tainted(sql, kind, base, len(columns))
|
||
if found is None:
|
||
return (base | {c.lower() for c in columns}, base) if _mentions(sql, base) else (base, base)
|
||
names, positions = found
|
||
return names | {columns[i].lower() for i in positions if i < len(columns)}, names
|
||
|
||
|
||
# --------------------------------------------------------------------------
|
||
# 遮罩：哪些值
|
||
# --------------------------------------------------------------------------
|
||
|
||
#: 一个数的写法：可带正负号、千分位、小数、百分号
|
||
_NUMERIC = re.compile(r"[-+]?(?:\d{1,3}(?:,\d{3})+|\d+)(?:\.\d+)?%?")
|
||
#: 正文里一个个「词」：字母数字下划线连成的一串。头尾都是这种字的遮罩值，只能整个对上这样一串
|
||
_WORDS = re.compile(r"[0-9A-Za-z_]+")
|
||
#: 正文里的一串数（可带千分位、小数）：带千分位的遮罩值按去掉逗号的样子比
|
||
_DIGITS = re.compile(r"\d[\d,]*(?:\.\d+)?")
|
||
#: 中文这类遮罩值按开头几个字分桶找（_Secrets._partition）
|
||
_PREFIX = 8
|
||
|
||
|
||
def _plain_text(value: Any) -> str:
|
||
text = json.dumps(value, ensure_ascii=False, default=str) if isinstance(value, (dict, list)) else str(value)
|
||
return re.sub(r"\s+", " ", text).strip()
|
||
|
||
|
||
def _numeric(value: Any) -> bool:
|
||
if isinstance(value, bool):
|
||
return False
|
||
return isinstance(value, (int, float)) or (isinstance(value, str) and numeric_text(value) is not None)
|
||
|
||
|
||
def _forms(value: Any) -> set[str]:
|
||
"""一格的值在正文里可能的写法：原样（压成一行），是数的再加上千分位的写法（13,900,000,001）。"""
|
||
text = _plain_text(value)
|
||
forms = {text} if text else set()
|
||
if _numeric(value):
|
||
with contextlib.suppress(RenderError, ValueError, ArithmeticError):
|
||
forms.add(render_cell(value))
|
||
return forms
|
||
|
||
|
||
def _strong(form: str) -> bool:
|
||
"""按值认得出的写法（见 SECRET_MIN、SECRET_DIGITS）。"""
|
||
if _NUMERIC.fullmatch(form):
|
||
return sum(c.isdigit() for c in form) >= SECRET_DIGITS
|
||
return len(form) >= SECRET_MIN
|
||
|
||
|
||
def _digits_of(form: str) -> str:
|
||
return form.replace(",", "").lstrip("+-").rstrip("%")
|
||
|
||
|
||
def _pattern(value: str) -> str:
|
||
"""一个值的正则：头尾是字母数字的按词边界认；数字还不能是更长的数、日期、时间的一截（12.5 里的 2.5、2026-01-25 里的
|
||
25、12:30 里的 30），也不能是千分位写法里的一组（1,390 里的 390）。逗号隔开的一串长号码（13900000001,13900000002）
|
||
各自照认：千分位一组只有三位。"""
|
||
head = tail = ""
|
||
if _WORD.match(value[0]):
|
||
head = r"(?<![0-9A-Za-z_])"
|
||
if value[0].isdigit():
|
||
head += r"(?<!\d[.:/-])" + (r"(?<!\d,)" if len(re.match(r"\d*", value).group()) == 3 else "")
|
||
if _WORD.match(value[-1]):
|
||
tail = r"(?![0-9A-Za-z_])"
|
||
if value[-1].isdigit():
|
||
tail += r"(?![.:/-]\d)(?!,\d{3}(?!\d))"
|
||
return head + re.escape(value) + tail
|
||
|
||
|
||
@dataclass
|
||
class _Secrets:
|
||
"""遮罩列里出现过的值。模型看得到原始的查询结果（工具交回的是原样），回答里照着复述、或者把值写进查询条件，
|
||
都会把它带进回答正文和查询清单；按值找出来换成「已遮罩」。这只减少暴露，不是安全边界（同证据面板的遮罩）。
|
||
|
||
strong 是按值认得出的写法（够长的数、两个字以上的文字），正文、SQL 里的字面量、名字和注释、别的列里的格子、列名都按
|
||
它换；weak 是遮罩列里的全部写法（含短的数），只用在 SQL 里和遮罩列做等值比较的字面量上；shown 是 SQL 里照原样
|
||
留着的阈值、行数（去掉千分位、正负号的数字），只在回答正文里不换（scrub 的 prose）。换的时候先按词、按开头两个
|
||
字筛出正文里真有的那几个值，再拿它们现编正则：遮罩值上万个时，现编一个上万分支的正则要一秒上下，每次都卡住整个进程。"""
|
||
|
||
strong: set[str] = field(default_factory=set)
|
||
weak: set[str] = field(default_factory=set)
|
||
shown: set[str] = field(default_factory=set)
|
||
_index: Any = field(default=None, repr=False, compare=False)
|
||
_compiled: dict[frozenset[str], re.Pattern[str]] = field(default_factory=dict, repr=False, compare=False)
|
||
|
||
def add(self, snapshot: Any, hidden: set[str]) -> None:
|
||
if not _query_shaped(snapshot) or not hidden:
|
||
return
|
||
columns = [str(c) for c in snapshot.get("columns") or []]
|
||
index = [i for i, c in enumerate(columns) if c.lower() in hidden]
|
||
for row in snapshot["rows"]:
|
||
if len(self.weak) >= SECRETS_MAX:
|
||
break
|
||
if isinstance(row, list):
|
||
cells = [row[i] for i in index if i < len(row)]
|
||
elif isinstance(row, dict):
|
||
cells = [v for k, v in row.items() if str(k).lower() in hidden]
|
||
else:
|
||
continue
|
||
for value in cells:
|
||
if value is None or isinstance(value, bool):
|
||
continue
|
||
for form in _forms(value):
|
||
self.weak.add(form)
|
||
if _strong(form):
|
||
self.strong.add(form)
|
||
self._index = None
|
||
|
||
def protect(self, texts: Iterable[str | None]) -> None:
|
||
"""已经摆在读者眼前的值不换：提问人自己写进问题、选中原文里的（「13900000001 这位客户」「排除 300 以下的」），
|
||
报告里列出的指标、运行输入的值——换了只会让回答、查询对不上问题和报告。正文、格子、SQL 里都不换。"""
|
||
given = " ".join(t for t in texts if t)
|
||
if not given:
|
||
return
|
||
numbers = {_digits_of(n) for n in _DIGITS.findall(given)}
|
||
|
||
def asked(form: str) -> bool:
|
||
return _digits_of(form) in numbers if _NUMERIC.fullmatch(form) else form in given
|
||
|
||
self.strong = {f for f in self.strong if not asked(f)}
|
||
self.weak = {f for f in self.weak if not asked(f)}
|
||
self._index, self._compiled = None, {}
|
||
|
||
def show(self, numbers: Iterable[str]) -> None:
|
||
"""SQL 里照原样留着的阈值、行数（_shown_literals）：回答正文里复述它们不换（「金额不低于 30000 元」），换了只会
|
||
让回答和 SQL 对不上。只免正文：格子、列名、SQL 里照旧按值换——格子里的值正好是这个数，可能就是那个人
|
||
（col >= v 再按 col 排序取第一行，查出来的就是 v）。"""
|
||
self.shown = set(numbers)
|
||
|
||
def is_shown(self, form: str) -> bool:
|
||
return bool(_NUMERIC.fullmatch(form)) and _digits_of(form) in self.shown
|
||
|
||
def hit(self, value: Any) -> bool:
|
||
"""一格（或 SQL 里一个字面量）的值是不是按值认得出的遮罩值。短的数不算（见 SECRET_DIGITS）。"""
|
||
if value is None or isinstance(value, bool) or not self.strong:
|
||
return False
|
||
text = _plain_text(value)
|
||
if text in self.strong:
|
||
return True
|
||
if _numeric(value) and sum(c.isdigit() for c in text) >= SECRET_DIGITS:
|
||
with contextlib.suppress(RenderError, ValueError, ArithmeticError):
|
||
return render_cell(value) in self.strong
|
||
return False
|
||
|
||
def weak_hit(self, text: str) -> bool:
|
||
"""SQL 里一个字面量是不是遮罩列里出现过的值（短的数也算）。"""
|
||
return _plain_text(text) in self.weak
|
||
|
||
def scrub(self, text: str, *, prose: bool = False) -> str:
|
||
"""text 里的遮罩值换成「已遮罩」。prose：这是回答正文，SQL 里照原样留着的阈值、行数不换（show）。"""
|
||
if not text or not self.strong:
|
||
return text
|
||
pattern = self.pattern(text, prose=prose)
|
||
return pattern.sub(_masked_word(), text) if pattern is not None else text
|
||
|
||
def pattern(self, text: str, *, prose: bool = False) -> re.Pattern[str] | None:
|
||
"""认 text 里出现的遮罩值的正则；一个都没有时为 None。prose 同 scrub。"""
|
||
found = self._found(text) if text and self.strong else set()
|
||
if prose and self.shown:
|
||
found = {v for v in found if not self.is_shown(v)}
|
||
if not found:
|
||
return None
|
||
key = frozenset(found)
|
||
if key not in self._compiled:
|
||
if len(self._compiled) > 64:
|
||
self._compiled = {}
|
||
# 长的在前：13900000001 先于它的一截被认出来
|
||
self._compiled[key] = re.compile("|".join(_pattern(v) for v in sorted(found, key=lambda v: (-len(v), v))))
|
||
return self._compiled[key]
|
||
|
||
def _found(self, text: str) -> set[str]:
|
||
words, numbers, others = self._partition()
|
||
found = {w for w in _WORDS.findall(text) if w in words}
|
||
if numbers:
|
||
for run in _DIGITS.findall(text):
|
||
found |= numbers.get(_digits_of(run), set())
|
||
for i in range(len(text) - 1) if others else ():
|
||
for size, buckets in others.items():
|
||
for length, values in buckets.get(text[i:i + size], {}).items():
|
||
if (piece := text[i:i + length]) in values:
|
||
found.add(piece)
|
||
return found
|
||
|
||
def prepare(self) -> None:
|
||
"""先把索引建好（收完值、去掉提问人写的之后）：上万个值建一次要几十毫秒，放在线程里建，别等到事件循环里第一次换。"""
|
||
self._partition()
|
||
|
||
def _partition(self) -> tuple[set[str], dict[str, set[str]], dict[int, dict[str, dict[int, set[str]]]]]:
|
||
"""strong 分成三类：只有字母数字的（按词比）、带千分位小数的数（按去掉逗号的数比）、其余的（中文、日期、
|
||
邮箱）。其余的按开头至多 _PREFIX 个字分桶、桶里再按长短分：同一个市区的上万个地址开头七八个字都一样，只按开头
|
||
分的话，正文里每碰到一次那几个字都要逐个比；再按长短分，碰到一次只是按几种长短各查一下。三类各自只在正文里
|
||
真出现时才进正则。"""
|
||
if self._index is None:
|
||
words: set[str] = set()
|
||
numbers: dict[str, set[str]] = {}
|
||
others: dict[int, dict[str, dict[int, set[str]]]] = {}
|
||
for value in self.strong:
|
||
if _WORDS.fullmatch(value):
|
||
words.add(value)
|
||
elif _NUMERIC.fullmatch(value):
|
||
numbers.setdefault(_digits_of(value), set()).add(value)
|
||
else:
|
||
size = min(len(value), _PREFIX)
|
||
others.setdefault(size, {}).setdefault(value[:size], {}).setdefault(len(value), set()).add(value)
|
||
self._index = (words, numbers, others)
|
||
return self._index
|
||
|
||
|
||
#: 单元格引用的前一截（Q1.r0.）：后面才是列名
|
||
_CELL_HEAD = re.compile(r"^\s*[QK]\d+\.r\d+\.")
|
||
|
||
|
||
def _scrubbed_source(text: str, secrets: _Secrets) -> str:
|
||
"""回答原文里的遮罩值换成「已遮罩」：标记之外按正文的办法换（SQL 里照原样留着的阈值不换）；标记里的按段换（| 隔开
|
||
的几段各自换），单元格引用只换列名那一截——编号、行号换不出东西，整段换的话「r0.」会让列名开头的长号码看着像小数
|
||
的一截，反而认不出来。列名照快照、SQL 里的名字那样换（阈值也换），换得一样才对得上。
|
||
标记里写着遮罩值的引用换完多半解析不了（列名里写着遮罩值的除外：快照的列名也换过了，正好对上），宁可弄坏一个
|
||
引用，也不让值留在存下的原文、片段里，或者从解析不了的占位里露出来。"""
|
||
if not text or not secrets.strong:
|
||
return text
|
||
out: list[str] = []
|
||
last = 0
|
||
for m in MARKER_RE.finditer(text):
|
||
out.append(secrets.scrub(text[last:m.start()], prose=True))
|
||
start, end = m.span("body")
|
||
parts = text[start:end].split("|")
|
||
head = _CELL_HEAD.match(parts[0]) if m.group("kind").strip() == "v" else None
|
||
first = parts[0][:head.end()] + secrets.scrub(parts[0][head.end():]) if head \
|
||
else secrets.scrub(parts[0], prose=True)
|
||
parts = [first, *(secrets.scrub(p, prose=True) for p in parts[1:])]
|
||
out.append(text[m.start():start] + "|".join(parts) + text[end:m.end()])
|
||
last = m.end()
|
||
out.append(secrets.scrub(text[last:], prose=True))
|
||
return "".join(out)
|
||
|
||
|
||
def _masked_view(snapshot: dict[str, Any], hidden: set[str], secrets: _Secrets) -> tuple[dict[str, Any], list[str]]:
|
||
"""一份查询快照遮好的样子和遮掉的列：要遮的列（hidden，小写）每一格都换成「已遮罩」、类型记成文本（渲染时不当数）；
|
||
别的列里写着按值认得出的遮罩值的格子也换（另一张表里没设遮罩的同一个手机号、改了名字没认出来的遮罩列）。
|
||
列名里写着遮罩值的（agent 把遮罩值写进了别名，「13900000001 的单」），列名也换（同 SQL 里的名字，_scrub_sql）。
|
||
原快照不动；没有要遮的返回原快照。"""
|
||
columns = [str(c) for c in snapshot.get("columns") or []]
|
||
index = {i for i, c in enumerate(columns) if c.lower() in hidden}
|
||
by_value = bool(secrets.strong)
|
||
if not index and not by_value:
|
||
return snapshot, []
|
||
word = _masked_word()
|
||
touched = set(index)
|
||
position = {c: i for i, c in enumerate(columns)}
|
||
names = [secrets.scrub(c) for c in columns] if by_value else columns
|
||
|
||
def cell(i: int | None, value: Any) -> Any:
|
||
if i in index:
|
||
return word
|
||
if by_value and secrets.hit(value):
|
||
if i is not None:
|
||
touched.add(i)
|
||
return word
|
||
return value
|
||
|
||
def key(k: Any) -> Any:
|
||
i = position.get(str(k))
|
||
return names[i] if i is not None else k
|
||
|
||
rows: list[Any] = []
|
||
for row in snapshot["rows"]:
|
||
if isinstance(row, list):
|
||
rows.append([cell(i, v) for i, v in enumerate(row)])
|
||
elif isinstance(row, dict):
|
||
rows.append({key(k): word if str(k).lower() in hidden else cell(position.get(str(k)), v)
|
||
for k, v in row.items()})
|
||
else:
|
||
rows.append(row)
|
||
renamed = names != columns
|
||
if not touched and not renamed:
|
||
return snapshot, []
|
||
types = {key(k): v for k, v in snapshot["column_types"].items()} \
|
||
if isinstance(snapshot.get("column_types"), dict) else {}
|
||
types.update({names[i]: "text" for i in index})
|
||
view = {**snapshot, "rows": rows, "column_types": types, **({"columns": names} if renamed else {})}
|
||
return view, [names[i] for i in sorted(touched)]
|
||
|
||
|
||
#: 按词认在找某一个值的比较（SQL 解析不了时的退路，见 _context）：col = 'x'、col <> 'x'、col LIKE 'x'、SQLite 的
|
||
#: col IS 'x'（IN 列表另外认）
|
||
_EQUAL_TOKENS = frozenset({"EQ", "NEQ", "NULLSAFE_EQ", "LIKE", "ILIKE", "GLOB", "RLIKE", "IS"})
|
||
#: 范围比较（BETWEEN 另外认）
|
||
_RANGE_TOKENS = frozenset({"GT", "GTE", "LT", "LTE"})
|
||
_NAME_TOKENS = frozenset({"VAR", "IDENTIFIER"})
|
||
#: 字面量前面可能连着的：正负号、MySQL 的字符集前缀（_utf8mb4'x'）
|
||
_LEADS = frozenset({"DASH", "PLUS", "INTRODUCER"})
|
||
#: 能结束一个值的词：减号跟在它们后面是两数相减，不是负号
|
||
_VALUE_ENDS = frozenset({"NUMBER", "VAR", "IDENTIFIER", "R_PAREN", "R_BRACKET", "NULL", "TRUE", "FALSE"})
|
||
#: 数字照原样留在 SQL 里的两种用法（_literal_uses）：范围比较的边界、LIMIT 这类的行数
|
||
_KEPT = frozenset({"range", "limit"})
|
||
#: 字面量写在左边时运算符翻过来：25 < age 就是 age > 25
|
||
_FLIP = {">": "<", ">=": "<=", "<": ">", "<=": ">="}
|
||
#: 一个纯粹的数（可带正负号、小数）：范围边界按数比大小，写成字符串的也一样
|
||
_PLAIN_NUMBER = re.compile(r"[-+]?\d+(?:\.\d+)?")
|
||
|
||
|
||
def _is_literal(kind: str) -> bool:
|
||
"""字符串（含 N'…'、E'…'、$$…$$、U&'…' 这些带前缀的变体）和数字。"""
|
||
return kind == "NUMBER" or kind.endswith("STRING")
|
||
|
||
|
||
def _operand_start(kinds: list[str], k: int) -> int:
|
||
"""第 k 个字面量连同它前面的负号、字符集前缀从哪个词开始（-25、_utf8mb4'x'）。"""
|
||
while k >= 1 and kinds[k - 1] in _LEADS and (
|
||
kinds[k - 1] == "INTRODUCER" or k < 2 or not (kinds[k - 2] in _VALUE_ENDS or _is_literal(kinds[k - 2]))):
|
||
k -= 1
|
||
return k
|
||
|
||
|
||
def _name_at(tokens: list[Any], kinds: list[str], k: int) -> str | None:
|
||
return tokens[k].text.lower() if 0 <= k < len(kinds) and kinds[k] in _NAME_TOKENS else None
|
||
|
||
|
||
def _context(tokens: list[Any], kinds: list[str], i: int) -> tuple[str, str | None]:
|
||
"""按词认第 i 个字面量用在哪，只在 SQL 解析不了时用（_literals），只认得出简单的写法：("equal", 列名) 在找某一个
|
||
值——col = 'x'、col NOT LIKE 'x'、col IS NOT 25、col IN ('x', …)、'x' = col；("range", None) 范围比较的边界——
|
||
col > 25、col BETWEEN a AND b；("other", None) 别的。列名是比较另一边的那个名字（s.buyer_phone 取 buyer_phone，
|
||
小写），另一边不是单独一个名字（函数、算式）时为 None。"""
|
||
j = _operand_start(kinds, i) - 1
|
||
if j >= 1 and kinds[j] == "NOT" and kinds[j - 1] == "IS":
|
||
return "equal", _name_at(tokens, kinds, j - 2)
|
||
if j >= 0 and kinds[j] in _EQUAL_TOKENS:
|
||
return "equal", _name_at(tokens, kinds, j - 2 if j >= 1 and kinds[j - 1] == "NOT" else j - 1)
|
||
if j >= 0 and (kinds[j] in _RANGE_TOKENS or kinds[j] == "BETWEEN"):
|
||
return "range", None
|
||
if j >= 1 and kinds[j] == "AND" and _is_literal(kinds[j - 1]):
|
||
# BETWEEN a AND b 的 b
|
||
lower = _operand_start(kinds, j - 1) - 1
|
||
if lower >= 0 and kinds[lower] == "BETWEEN":
|
||
return "range", None
|
||
# IN 列表：往回越过逗号和别的字面量，找到「IN (」
|
||
k = j
|
||
while k >= 0 and (kinds[k] == "COMMA" or kinds[k] in _LEADS or _is_literal(kinds[k])):
|
||
k -= 1
|
||
if k >= 1 and kinds[k] == "L_PAREN" and kinds[k - 1] == "IN":
|
||
return "equal", _name_at(tokens, kinds, k - 3 if k >= 2 and kinds[k - 2] == "NOT" else k - 2)
|
||
# 字面量在左边：'x' = col、25 < t.col
|
||
after = i + 1
|
||
if after < len(kinds) and kinds[after] in _RANGE_TOKENS:
|
||
return "range", None
|
||
if after < len(kinds) and kinds[after] in _EQUAL_TOKENS:
|
||
last = after + 1
|
||
while last + 2 < len(kinds) and kinds[last + 1] == "DOT" and kinds[last + 2] in _NAME_TOKENS:
|
||
last += 2
|
||
return "equal", _name_at(tokens, kinds, last)
|
||
return "other", None
|
||
|
||
|
||
def _column_of(node: Any, index: int | None) -> str | None:
|
||
"""比较另一边的列名（小写、不带表名）；另一边是行值时取第 index 项。不是单独一列（函数、算式、子查询）时为 None。"""
|
||
from sqlglot import exp
|
||
|
||
if index is not None and isinstance(node, exp.Tuple):
|
||
items = node.expressions
|
||
node = items[index] if index < len(items) else None
|
||
while isinstance(node, exp.Paren):
|
||
node = node.this
|
||
if isinstance(node, exp.Column) and not isinstance(node.this, exp.Star):
|
||
return node.name.lower() or None
|
||
return None
|
||
|
||
|
||
def _use_of(node: Any) -> tuple[str, str | None]:
|
||
"""语法树里一个字面量用在哪：(用法, 列名)，用法见 _literal_uses。
|
||
|
||
先往上越过不改变「找的是哪个值」的外壳：括号、负号、CAST、字符集前缀、COLLATE；行值、VALUES、ARRAY、ANY / ALL
|
||
也越过，记下「在一组值里」（行值另记下是第几项）。再看外壳的上一层：等值一类、IN、简单 CASE 的 WHEN 是在找这个值；
|
||
范围比较、LIMIT 一类只认单独一个值（一组值里的、算式里的都不算）。"""
|
||
from sqlglot import exp
|
||
|
||
child, parent = node, node.parent
|
||
index, grouped = None, False
|
||
while parent is not None:
|
||
if isinstance(parent, exp.Tuple):
|
||
if index is None:
|
||
index = next((k for k, item in enumerate(parent.expressions) if item is child), None)
|
||
grouped = True
|
||
elif isinstance(parent, (exp.Array, exp.Values, exp.Any, exp.All)) or (
|
||
isinstance(parent, exp.Subquery) and isinstance(child, exp.Values)) or (
|
||
isinstance(parent, exp.Anonymous) and str(parent.this).upper() in ("ANY", "ALL", "SOME")):
|
||
# = ANY(ARRAY[…])、= ANY(VALUES …)；Postgres 的 <> ALL(…) 解析成名叫 ALL 的函数
|
||
grouped = True
|
||
elif not _wraps(parent, child):
|
||
break
|
||
child, parent = parent, parent.parent
|
||
if isinstance(parent, (exp.EQ, exp.NEQ, exp.NullSafeEQ, exp.NullSafeNEQ, exp.Is, exp.Like, exp.ILike, exp.Glob,
|
||
exp.RegexpLike, exp.SimilarTo)):
|
||
return "equal", _column_of(parent.expression if child is parent.this else parent.this, index)
|
||
if isinstance(parent, exp.In):
|
||
return "equal", None if child is parent.this else _column_of(parent.this, index)
|
||
if isinstance(parent, exp.If) and child is parent.this and isinstance(parent.parent, exp.Case) \
|
||
and parent.parent.this is not None:
|
||
# 简单 CASE：CASE buyer_phone WHEN 13900000001 THEN …（CASE WHEN col = v 的写法走上面的等值）
|
||
return "equal", _column_of(parent.parent.this, index)
|
||
if grouped:
|
||
return "other", None
|
||
if type(parent) in _range_ops() and (child is parent.this or child is parent.expression):
|
||
return "range", _column_of(parent.expression if child is parent.this else parent.this, None)
|
||
if isinstance(parent, exp.Between) and child is not parent.this:
|
||
return "range", _column_of(parent.this, None)
|
||
if (isinstance(parent, (exp.Limit, exp.Offset)) and child is parent.expression) or (
|
||
isinstance(parent, exp.Fetch) and child is parent.args.get("count")):
|
||
return "limit", None
|
||
return "other", None
|
||
|
||
|
||
def _wraps(parent: Any, child: Any) -> bool:
|
||
"""parent 只是 child 的外壳，不改变它是哪个值：括号、负号、CAST、字符集前缀（_utf8mb4'x'）、COLLATE。"""
|
||
from sqlglot import exp
|
||
|
||
return isinstance(parent, (exp.Paren, exp.Neg, exp.Cast)) or (
|
||
isinstance(parent, exp.Introducer) and child is parent.expression) or (
|
||
isinstance(parent, exp.Collate) and child is parent.this)
|
||
|
||
|
||
def _range_ops() -> dict[Any, str]:
|
||
"""范围比较的语法树节点 → 「列 运算符 值」方向的运算符。"""
|
||
from sqlglot import exp
|
||
|
||
return {exp.GT: ">", exp.GTE: ">=", exp.LT: "<", exp.LTE: "<="}
|
||
|
||
|
||
def _constant(node: Any) -> Any:
|
||
"""写死的值：数按数（几个数加减乘除算出来的也算，13900000002 - 1），字符串按原文（纯粹的数照样按数）；别的为 None。"""
|
||
from sqlglot import exp
|
||
|
||
if isinstance(node, exp.Neg):
|
||
value = _constant(node.this)
|
||
return -value if isinstance(value, Decimal) else None
|
||
if isinstance(node, (exp.Paren, exp.Cast, exp.Collate)):
|
||
return _constant(node.this)
|
||
if isinstance(node, exp.Introducer):
|
||
return _constant(node.expression)
|
||
if isinstance(node, _literal_types()):
|
||
text = str(node.this).strip()
|
||
return Decimal(text) if _PLAIN_NUMBER.fullmatch(text) else text
|
||
if isinstance(node, (exp.Add, exp.Sub, exp.Mul, exp.Div)):
|
||
a, b = _constant(node.this), _constant(node.expression)
|
||
if not (isinstance(a, Decimal) and isinstance(b, Decimal)):
|
||
return None
|
||
if isinstance(node, exp.Div):
|
||
return a / b if b else None
|
||
return a + b if isinstance(node, exp.Add) else a - b if isinstance(node, exp.Sub) else a * b
|
||
return None
|
||
|
||
|
||
def _bare_literal(node: Any) -> Any:
|
||
"""边界本身就是一个字面量（套了括号、负号、CAST 的也算）时交回那个字面量，否则 None。"""
|
||
from sqlglot import exp
|
||
|
||
while node is not None and not isinstance(node, _literal_types()):
|
||
if isinstance(node, (exp.Paren, exp.Neg, exp.Cast, exp.Collate)):
|
||
node = node.this
|
||
elif isinstance(node, exp.Introducer):
|
||
node = node.expression
|
||
else:
|
||
return None
|
||
return node
|
||
|
||
|
||
def _bounds_of(node: Any) -> list[tuple[Any, str | None, Any, str]]:
|
||
"""一个范围比较里写死的边界：(字面量节点, 列名, 值, 「列 运算符 值」的运算符)。边界是几个数算出来的也算，
|
||
字面量节点记 None：它照样能夹住另一头的值，换的是另一头的字面量。"""
|
||
from sqlglot import exp
|
||
|
||
if isinstance(node, exp.Between):
|
||
sides = [(node.args.get("low"), node.this, ">="), (node.args.get("high"), node.this, "<=")]
|
||
elif (op := _range_ops().get(type(node))) is not None:
|
||
sides = [(node.expression, node.this, op), (node.this, node.expression, _FLIP[op])]
|
||
else:
|
||
return []
|
||
out = []
|
||
for operand, other, op in sides:
|
||
value = _constant(operand) if operand is not None else None
|
||
if value is not None:
|
||
out.append((_bare_literal(operand), _column_of(other, None), value, op))
|
||
return out
|
||
|
||
|
||
def _literal_types() -> tuple[Any, ...]:
|
||
"""语法树里的字面量：数字、字符串，以及字符串带前缀的几种变体（N'…'、$$…$$、U&'…'、E'…'、X'…'、B'…'）。"""
|
||
from sqlglot import exp
|
||
|
||
return (exp.Literal, exp.National, exp.RawString, exp.UnicodeString, exp.ByteString, exp.HexString, exp.BitString)
|
||
|
||
|
||
def _pinned(bounds: list[tuple[Any, str | None, Any, str]]) -> set[int]:
|
||
"""范围比较里把某一个值夹住了的边界字面量（交回 id(字面量节点)）。bounds 见 _bounds_of。
|
||
|
||
一个值 v 被从下面隔开，是说 v 和比它小一点的值结果不同（col >= v、col < v）；被从上面隔开，是和比它大一点的值结果
|
||
不同（col <= v、col > v）。同一列上 v 两边都被隔开，条件就只认 v 这一个值：col >= v AND col <= v、BETWEEN v AND v、
|
||
col > v OR col < v（就是 col <> v）——这是在找 v，和等值比较一样换。整数的 col < v + 1 就是 col <= v、col > v - 1
|
||
就是 col >= v，所以 col >= v AND col < v + 1 也算夹住了 v。只从一边隔开的是阈值：col >= v 和 col < v 各数一遍，
|
||
是按 v 分成两段，照原样。另一边不是单独一列的（SUM(amount) >= 900）和哪一列都算同一列（宁可多换）。"""
|
||
sides: dict[Any, list[tuple[str, str | None, Any]]] = {}
|
||
for literal, column, value, op in bounds:
|
||
whole = isinstance(value, Decimal) and value == value.to_integral_value()
|
||
marks = {">=": [(value, "below")], "<=": [(value, "above")],
|
||
">": [(value, "above"), *([(value + 1, "below")] if whole else [])],
|
||
"<": [(value, "below"), *([(value - 1, "above")] if whole else [])]}[op]
|
||
for point, side in marks:
|
||
sides.setdefault(point, []).append((side, column, literal))
|
||
out: set[int] = set()
|
||
for marks in sides.values():
|
||
for side, column, literal in marks:
|
||
for other, column2, literal2 in marks:
|
||
if side == "below" and other == "above" and (column is None or column2 is None or column == column2):
|
||
out |= {id(n) for n in (literal, literal2) if n is not None}
|
||
return out
|
||
|
||
|
||
def _literal_uses(sql: str, kind: str | None) -> dict[int, tuple[str, str | None]] | None:
|
||
"""SQL 里每个字面量（按它在原文里的起始位置）用在哪，按语法树认（写法怎么变都认得出）：
|
||
- ("equal", 列名)：在找某一个值——等值、不等、IN（含 VALUES、行值）、LIKE 一类、IS [NOT] DISTINCT FROM、简单 CASE 的
|
||
WHEN、= ANY(ARRAY[…])，套了括号、负号、CAST 的照认；把某一个值夹住的范围（_pinned）也算。列名是被比较的那一列
|
||
（小写、不带表名），另一边不是单独一列时为 None；
|
||
- ("range", 列名)：范围比较（> >= < <=、BETWEEN）的边界，是 agent 定的阈值；
|
||
- ("limit", None)：LIMIT / OFFSET / FETCH / TOP 的行数；
|
||
- ("other", None)：别的——选出列、函数参数、算式、THEN 后面的值、子查询里选出的值。
|
||
解析不了返回 None。"""
|
||
from sqlglot import exp
|
||
|
||
from app.data.sql_semantics import _parse, _read
|
||
|
||
try:
|
||
root, _ = _parse(sql, _read(kind))
|
||
except Exception: # noqa: BLE001 - 解析器的意外按解析不了处理
|
||
root = None
|
||
if root is None:
|
||
return None
|
||
# 解析的是去掉头尾空白的 SQL：位置补上开头的空白，才对得上原文里的词
|
||
offset = len(sql) - len(sql.lstrip())
|
||
uses: dict[int, tuple[str, str | None]] = {}
|
||
try:
|
||
literals = {id(n): n for n in root.walk() if isinstance(n, _literal_types())}
|
||
pinned = _pinned([b for n in root.find_all(exp.Between, *_range_ops()) for b in _bounds_of(n)])
|
||
for key, node in literals.items():
|
||
start = (node.meta or {}).get("start")
|
||
if isinstance(start, int):
|
||
use, column = _use_of(node)
|
||
uses[start + offset] = ("equal", column) if key in pinned and use == "range" else (use, column)
|
||
except Exception: # noqa: BLE001 - 分析本身的缺陷不能让回答出错：按解析不了处理（认不准的地方不免）
|
||
logger.warning("质询的 SQL 字面量分析失败", exc_info=True)
|
||
return None
|
||
return uses
|
||
|
||
|
||
def _requote(raw: str, change: Callable[[str], str]) -> str:
|
||
"""一个字面量或名字的原文 → 只换里面的字：引号、N'' E'' U&'' 这类前缀、$tag$ 照留；不带引号的整个交给 change。"""
|
||
if raw.startswith("$") and (end := raw.find("$", 1)) > 0:
|
||
tag = raw[:end + 1]
|
||
if len(raw) >= 2 * len(tag) and raw.endswith(tag):
|
||
return tag + change(raw[len(tag):-len(tag)]) + tag
|
||
for opening, closing in (("'", "'"), ('"', '"'), ("`", "`"), ("[", "]")):
|
||
start = raw.find(opening)
|
||
if start >= 0 and len(raw) - start >= 2 and raw.endswith(closing):
|
||
return raw[:start + 1] + change(raw[start + 1:-1]) + closing
|
||
return change(raw)
|
||
|
||
|
||
def _sql_tokens(sql: str, kind: str | None) -> tuple[list[Any], list[str]] | None:
|
||
from app.data.sql_semantics import _read, _tokens
|
||
|
||
try:
|
||
tokens = _tokens(sql, _read(kind))
|
||
except Exception: # noqa: BLE001 - 分词器认不了的写法（引号没闭合这类）
|
||
return None
|
||
return tokens, [t.token_type.name for t in tokens]
|
||
|
||
|
||
def _literals(sql: str, kind: str | None) -> tuple[list[Any], list[str], dict[int, tuple[str, str | None]]] | None:
|
||
"""分词，加上每个字面量（按词的下标）用在哪（_literal_uses）。语法树里对不上位置的字面量记 "other"；SQL 解析
|
||
不了时只按词认简单的等值比较（_context），别的一律 "other"——认不准的地方不免。分词出错返回 None。
|
||
|
||
照原样留着的数还得在这条 SQL 的字面量里处处都是阈值、行数：同一个数在别的字面量里（等值比较、算式、字符串）也
|
||
出现过，那里会被换掉，这里留着就把它露了（BETWEEN 13900000001 AND 13900000001 + 0），所以这里也改记成在找这个值。
|
||
名字、注释里的不算：那是 agent 给阈值起的说法（AS 超过30000的笔数），照常按值换，留着的阈值不必跟着换。"""
|
||
split = _sql_tokens(sql, kind)
|
||
if split is None:
|
||
return None
|
||
tokens, kinds = split
|
||
uses = _literal_uses(sql, kind)
|
||
found: dict[int, tuple[str, str | None]] = {}
|
||
for i, token in enumerate(tokens):
|
||
if not _is_literal(kinds[i]):
|
||
continue
|
||
if uses is not None:
|
||
found[i] = uses.get(token.start, ("other", None))
|
||
else:
|
||
use, column = _context(tokens, kinds, i)
|
||
found[i] = (use, column) if use == "equal" else ("other", None)
|
||
kept = {i for i, (use, _) in found.items() if kinds[i] == "NUMBER" and use in _KEPT}
|
||
elsewhere = _numbers_in(tokens[i].text for i in found if i not in kept)
|
||
for i in kept:
|
||
if _digits_of(tokens[i].text) in elsewhere:
|
||
found[i] = ("equal", found[i][1])
|
||
return tokens, kinds, found
|
||
|
||
|
||
def _numbers_in(texts: Iterable[str]) -> set[str]:
|
||
"""这几段字里写着的数（去掉千分位、正负号）。"""
|
||
return {_digits_of(n) for text in texts for n in _DIGITS.findall(text)}
|
||
|
||
|
||
def _scrub_sql(sql: str, secrets: _Secrets, compared: set[str], kind: str | None) -> str:
|
||
"""SQL 里遮罩列的值换成「已遮罩」，别的一个字不动：查询清单随运行封存，它得是实际执行的那条，审批人看 what-if 的
|
||
条件（阈值、日期、LIMIT、别的列的条件）看的就是它。字面量按用在哪换（_literals）：
|
||
|
||
- 在找某一个值的（equal）：和遮罩列（或它的别名，compared）比较的，是遮罩列里出现过的值就换，短的数也换
|
||
（age = 25）；和别的列比较的，够长的遮罩值也换（另一张表里没设遮罩的同一个手机号）；
|
||
- 范围比较的边界（age > 31、BETWEEN 10000 AND 50000）、LIMIT / OFFSET 的行数，数字照原样：它们是 agent 自己定的
|
||
阈值，不是在找某一个人，换了封存的就不是实际执行的语句；
|
||
- 别处的数（选出列、函数参数、算式）认不准是不是在找某一个值，够长的遮罩值换；
|
||
- 字符串在哪都按值换（范围边界也一样：写成字符串的长号码做边界，多半是在找那一个人），注释、名字（AS
|
||
"13900000001 的单"、张伟的单数）也按值换（同正文：够长的数、两个字以上的文字）。
|
||
分词出错就整条按正文的办法换；解析不了的认不准哪个数是阈值，范围边界、行数也不免（_literals）。"""
|
||
if not sql or not (secrets.strong or secrets.weak):
|
||
return sql
|
||
split = _literals(sql, kind)
|
||
if split is None:
|
||
return secrets.scrub(sql)
|
||
tokens, kinds, uses = split
|
||
word = _masked_word()
|
||
out: list[str] = []
|
||
last = 0
|
||
for i, token in enumerate(tokens):
|
||
start, end = token.start, token.end + 1
|
||
if start < last or end > len(sql):
|
||
continue
|
||
gap = sql[last:start]
|
||
out.append(secrets.scrub(gap) if gap.strip() else gap)
|
||
raw = sql[start:end]
|
||
if i in uses:
|
||
use, column = uses[i]
|
||
if use == "equal" and ((column in compared and secrets.weak_hit(token.text)) or secrets.hit(token.text)):
|
||
raw = _requote(raw, lambda _: word)
|
||
elif kinds[i] != "NUMBER":
|
||
raw = _requote(raw, secrets.scrub)
|
||
elif use not in _KEPT and secrets.hit(token.text):
|
||
raw = word
|
||
elif kinds[i] in _NAME_TOKENS:
|
||
raw = _requote(raw, secrets.scrub)
|
||
out.append(raw)
|
||
last = end
|
||
rest = sql[last:]
|
||
out.append(secrets.scrub(rest) if rest.strip() else rest)
|
||
return "".join(out)
|
||
|
||
|
||
def _shown_literals(sqls: Iterable[tuple[str, str | None]]) -> set[str]:
|
||
"""几条 SQL（和各自数据源的类型）里照原样留着的数，去掉千分位、正负号：范围比较的边界、LIMIT / OFFSET 的行数
|
||
（_scrub_sql 不换的那两种）。它们随 SQL 摆在读者眼前，回答正文里复述（「金额不低于 30000 元」）再遮也遮不住
|
||
什么，只会让回答和 SQL 对不上（_Secrets.show）。同一个数在别的查询里出现在别的字面量里也不算（等值比较、选出列、
|
||
函数参数、字符串；同一条里的 _literals 已经不留）：那里它会被换掉，正文写出来就把那里换掉的值露了。SQL 解析
|
||
不了的一个都不算，里面写着的数也都不算。"""
|
||
kept: set[str] = set()
|
||
elsewhere: set[str] = set()
|
||
for sql, kind in sqls:
|
||
split = _literals(sql, kind) if sql else None
|
||
if split is None:
|
||
elsewhere |= _numbers_in([sql or ""])
|
||
continue
|
||
tokens, kinds, uses = split
|
||
keep = {i for i, (use, _) in uses.items() if kinds[i] == "NUMBER" and use in _KEPT}
|
||
kept |= {_digits_of(tokens[i].text) for i in keep}
|
||
elsewhere |= _numbers_in(tokens[i].text for i in uses if i not in keep)
|
||
return kept - elsewhere
|
||
|
||
|
||
@dataclass
|
||
class _Plan:
|
||
"""一次回答（或一次取质询工件）的遮罩：agent 每份查询快照遮好的样子（views）和遮掉的列（masked）、SQL 里指代
|
||
遮罩列的名字（tainted）、数据源的类型（kinds，SQL 按它的方言分词）、遮罩列里出现过的值（secrets），以及已经不在的
|
||
数据源（gone，按查询当时记下的遮罩处理）。"""
|
||
|
||
views: dict[str, dict[str, Any]]
|
||
masked: dict[str, list[str]]
|
||
tainted: dict[str, set[str]]
|
||
kinds: dict[str, str | None]
|
||
secrets: _Secrets
|
||
gone: dict[str, list[str]]
|
||
|
||
|
||
async def _source_kinds(names: Iterable[str]) -> dict[str, str | None]:
|
||
wanted = sorted({n for n in names if n})
|
||
if not wanted:
|
||
return {}
|
||
async with SessionLocal() as session:
|
||
rows = (await session.execute(select(DataSource.name, DataSource.kind)
|
||
.where(DataSource.name.in_(wanted)))).all()
|
||
return {str(name): kind for name, kind in rows}
|
||
|
||
|
||
async def _plan(own: dict[str, dict[str, Any]], others: list[dict[str, Any]], given: list[str | None],
|
||
shown: list[tuple[str, str]] | None = None) -> _Plan:
|
||
"""own：agent 自己的查询快照（工件 id → 内容）；others：报告自己的查询快照（被问的那句可能直接写着遮罩列的值，
|
||
agent 会照着复述、写进查询条件）；given：问题、选中的原文、报告里列出的指标和运行输入的值（都已经摆在读者眼前，
|
||
里面的值哪里都不换）；shown：agent 执行的 SQL 和它查的数据源名（照原样留在 SQL 里的阈值、LIMIT，回答正文里
|
||
不换，见 _Secrets.show；取质询工件不用：快照里的格子照旧按值遮）。
|
||
|
||
查数据源的遮罩要读库，在这里读；解析 SQL、收上万个值、逐格比对是纯计算，放进线程：放在事件循环里会挡住同一进程
|
||
里别的运行（同 tools/datasource 的 _sql_checks）。"""
|
||
from app.api.evidence import _Masks
|
||
|
||
masks = _Masks()
|
||
shown = shown or []
|
||
named = {artifact: await _hidden_columns(snapshot, masks) for artifact, snapshot in own.items()}
|
||
based = [(snapshot, (await _hidden_columns(snapshot, masks))[0]) for snapshot in others]
|
||
kinds = await _source_kinds([*(str(s.get("source") or "") for s in [*own.values(), *others]),
|
||
*(name for _, name in shown)])
|
||
return await asyncio.to_thread(_settle_plan, own, named, based, kinds, given, shown)
|
||
|
||
|
||
def _settle_plan(own: dict[str, dict[str, Any]], named: dict[str, tuple[set[str], list[str]]],
|
||
based: list[tuple[dict[str, Any], set[str]]], kinds: dict[str, str | None],
|
||
given: list[str | None], shown: list[tuple[str, str]]) -> _Plan:
|
||
secrets = _Secrets()
|
||
hidden: dict[str, set[str]] = {}
|
||
tainted: dict[str, set[str]] = {}
|
||
for artifact, snapshot in own.items():
|
||
hidden[artifact], tainted[artifact] = _derived_hidden(snapshot, named[artifact][0],
|
||
kinds.get(str(snapshot.get("source") or "")))
|
||
secrets.add(snapshot, hidden[artifact])
|
||
for snapshot, base in based:
|
||
secrets.add(snapshot, _derived_hidden(snapshot, base, kinds.get(str(snapshot.get("source") or "")))[0])
|
||
secrets.protect(given)
|
||
secrets.show(_shown_literals((sql, kinds.get(name)) for sql, name in shown))
|
||
secrets.prepare()
|
||
views: dict[str, dict[str, Any]] = {}
|
||
masked: dict[str, list[str]] = {}
|
||
for artifact, snapshot in own.items():
|
||
views[artifact], masked[artifact] = _masked_view(snapshot, hidden[artifact], secrets)
|
||
return _Plan(views=views, masked=masked, tainted=tainted, kinds=kinds, secrets=secrets,
|
||
gone={artifact: named[artifact][1] for artifact in own})
|
||
|
||
|
||
def _masking_loader(views: dict[str, dict[str, Any]]) -> Callable[[str], Any]:
|
||
"""组装回答文档用的 loader：agent 自己的查询快照交遮好的那份（引用到遮罩的格子渲染成「已遮罩」）；别的查询快照
|
||
不交（回答的目录里只有 agent 自己的查询）；口径卡这类没有行的原样，哈希照旧复验。"""
|
||
|
||
def load(artifact: str) -> Any:
|
||
if artifact in views:
|
||
return views[artifact]
|
||
content = artifact_store.load(artifact)
|
||
return None if _query_shaped(content) else content
|
||
|
||
return load
|
||
|
||
|
||
# --------------------------------------------------------------------------
|
||
# 回答
|
||
# --------------------------------------------------------------------------
|
||
|
||
|
||
class _Leak(Exception):
|
||
"""组装出来的正文里还认得出遮罩值（渲染出来才露的，比如别的列里一格文字夹着手机号）：这份回答不交出去。"""
|
||
|
||
|
||
def _limit(outcome: VerifyOutcome) -> str | None:
|
||
return outcome.limit if outcome.limit in LIMITS else None
|
||
|
||
|
||
def _error_words(outcome: VerifyOutcome, *, timeout_s: Any, daily_max_usd: Any) -> str | None:
|
||
"""核查 agent 没交成结果的原话 → 提问人看得懂的话（发生了什么、下一步）。原话里有内部的说法（「交结果」「按结构」、
|
||
裸写的字段名），只进日志；模型不可用、调用失败的说明本来就是给人看的，照用。"""
|
||
error = outcome.error
|
||
if not error:
|
||
return None
|
||
if error.startswith("已达") and error.endswith("没能交结果"):
|
||
if "每日" in error:
|
||
cap = f"核查每日金额上限 {judging._usd(daily_max_usd)}" if daily_max_usd is not None else "核查每日金额上限"
|
||
return ERR_DAILY.format(cap=cap)
|
||
if "时长" in error:
|
||
return _timeout_words(timeout_s)
|
||
return ERR_COST
|
||
if error.startswith("收尾时超过时长上限"):
|
||
return _timeout_words(timeout_s)
|
||
if error.startswith("核查模型没有按结构交结果"):
|
||
return ERR_SHAPE
|
||
if error == "核查模型没有给出回复":
|
||
return ERR_SILENT
|
||
if error.startswith("核查出错（"):
|
||
return f"回答时出错{error[len('核查出错'):]}，请重新提问"
|
||
return error
|
||
|
||
|
||
def _timeout_words(timeout_s: Any) -> str:
|
||
seconds = timeout_s if isinstance(timeout_s, (int, float)) and not isinstance(timeout_s, bool) else None
|
||
return ERR_TIMEOUT.format(seconds=f"（{seconds:g} 秒）" if seconds is not None else "")
|
||
|
||
|
||
def _given_numbers(ask: Ask) -> list[str]:
|
||
"""问题、选中的原文里的数：提问人给的阈值、条件（「排除金额低于 500 的」），回答里复述它们不算没有出处的结论。
|
||
查询结果里来的数照旧必须引用。"""
|
||
return [token.raw for text in (ask.question, ask.quote) if text for token in extract_numbers(text)]
|
||
|
||
|
||
async def _answer(op: _Opening, ask: Ask, target: _Target | None, settings: dict[str, Any]) -> dict[str, Any]:
|
||
"""问 agent，组装回答文档，交回事件数据里回答的那几项。模型用不了、触顶、组装出错都落在 ok / limit / error 里：
|
||
钱已经花了，回答没成也照样记一条。"""
|
||
from app.api.settings import verify_model_spec
|
||
|
||
doc = op.doc
|
||
catalog = doc.get("catalog") if isinstance(doc.get("catalog"), dict) else {}
|
||
masked = await judging.source_masks(catalog, loader=op.loader)
|
||
excerpts = _excerpts(doc, catalog, target.cand, op.loader, masked) if target is not None else []
|
||
refs = _report_refs(catalog)
|
||
wanted = _run_sources(op.events)
|
||
usable = await _usable_sources(op.run_id, wanted, op.versions)
|
||
live, lost = {s: usable[s] for s in wanted if s in usable}, [s for s in wanted if s not in usable]
|
||
part = settings.get("inquiry") if isinstance(settings.get("inquiry"), dict) else {}
|
||
async with SessionLocal() as session:
|
||
spec = await verify_model_spec(session, None, settings=settings)
|
||
outcome = await run_verify_agent(
|
||
spec=spec, system=INQUIRY_SYSTEM, task=_task(op, ask, target, excerpts, refs, live, lost), sources=list(live),
|
||
output_schema=INQUIRY_SCHEMA, max_queries=part.get("max_queries"), timeout_s=part.get("timeout_s"),
|
||
daily_max_usd=settings.get("daily_max_usd"), run_id=op.run_id, data_versions=op.versions)
|
||
|
||
# 遮罩：agent 自己的查询快照、报告自己的查询快照（被问的那句可能直接写着遮罩列的值，agent 会照着复述）
|
||
own: dict[str, dict[str, Any]] = {}
|
||
for query in outcome.queries:
|
||
snapshot = _quiet_load(artifact_store.load, query.get("artifact"))
|
||
if _query_shaped(snapshot):
|
||
own[str(query["artifact"])] = snapshot
|
||
others = [snapshot for entry in catalog.values() if isinstance(entry, dict) and entry.get("kind") == "query"
|
||
and _query_shaped(snapshot := _quiet_load(op.loader, entry.get("artifact")))]
|
||
plan = await _plan(own, others, [ask.question, ask.quote, *_ref_values(refs)],
|
||
[(str(q.get("sql") or ""), str(q.get("source") or "")) for q in outcome.queries])
|
||
|
||
text, doc_id, failed = "", None, None
|
||
source = (outcome.rationale or {}).get("source") if outcome.result is not None else None
|
||
if isinstance(source, str) and source.strip():
|
||
try:
|
||
answer = _compose(source, {**refs, **((outcome.rationale or {}).get("catalog") or {})}, run_id=op.run_id,
|
||
views=plan.views, secrets=plan.secrets, allow=_given_numbers(ask))
|
||
except _Leak:
|
||
logger.warning("质询的回答里有遮罩值遮不住，不交出去（运行 %s）", op.run_id)
|
||
failed = LEAKED
|
||
except Exception as e: # noqa: BLE001 - 原文没组装成文档就不交出去：里面的引用没换成值，遮罩也没做
|
||
logger.warning("质询的回答组装失败（运行 %s）", op.run_id, exc_info=True)
|
||
failed = f"整理回答时出错（{describe_exception(e)}），请重新提问"
|
||
else:
|
||
answer = _with_notes(answer, op, outcome, part, lost, own)
|
||
text = str(answer.get("markdown") or "")
|
||
doc_id = await _store(answer, op, ask)
|
||
ok = bool(text.strip())
|
||
error = None
|
||
if not ok:
|
||
error = _error_words(outcome, timeout_s=part.get("timeout_s"), daily_max_usd=settings.get("daily_max_usd"))
|
||
if outcome.error:
|
||
logger.info("质询没能给出回答（运行 %s）：%s", op.run_id, outcome.error)
|
||
queries = await asyncio.to_thread(_sealed_queries, outcome.queries, plan, live)
|
||
return {
|
||
"answer_text": text, "answer_doc": doc_id, "ok": ok, "limit": _limit(outcome),
|
||
"error": None if ok else (error or failed or NO_ANSWER),
|
||
# 结果一模一样的两次查询是同一份快照（工件按内容寻址）：引用列表里只记一次
|
||
"inquiry_artifacts": list(dict.fromkeys(q["artifact"] for q in queries if q.get("artifact"))),
|
||
"queries": queries,
|
||
"model": outcome.model, "usage": {k: outcome.usage.get(k, 0) for k in USAGE_KEYS},
|
||
}
|
||
|
||
|
||
def _sealed_queries(queries: list[dict[str, Any]], plan: _Plan, live: dict[str, list[str]]) -> list[dict[str, Any]]:
|
||
"""随运行封存的查询清单：每条只留约定的几项，SQL 里的遮罩值换掉。_scrub_sql 要解析 SQL，放在线程里（同 _plan）。"""
|
||
out: list[dict[str, Any]] = []
|
||
for q in queries:
|
||
artifact, name = str(q.get("artifact") or ""), str(q.get("source") or "")
|
||
# 快照没取到的（存不下、被删了），SQL 里按这个源设的遮罩列认比较
|
||
compared = plan.tainted.get(artifact) or {c.lower() for c in live.get(name, [])}
|
||
out.append({**{k: q.get(k) for k in QUERY_KEYS},
|
||
"sql": _scrub_sql(str(q.get("sql") or ""), plan.secrets, compared, plan.kinds.get(name))})
|
||
return out
|
||
|
||
|
||
def _quiet_load(loader: Callable[[str], Any], artifact: Any) -> Any:
|
||
"""取一份快照；取不到、哈希不符都当没有（这里只是为了找遮罩列的值，取不到的那份本来也渲染不出来）。"""
|
||
if not artifact:
|
||
return None
|
||
try:
|
||
return loader(str(artifact))
|
||
except Exception: # noqa: BLE001
|
||
return None
|
||
|
||
|
||
def _compose(source: str, catalog: dict[str, Any], *, run_id: str, views: dict[str, dict[str, Any]],
|
||
secrets: _Secrets, allow: list[str]) -> dict[str, Any]:
|
||
"""agent 写的回答原文（带引用标记）→ 回答文档：目录是 agent 自己的查询，加上报告里的指标和运行输入；快照按遮罩
|
||
遮好再渲染。遮罩值在组装之前换掉（_scrubbed_source）；组装出来还认得出遮罩值（渲染出来才露的，比如别的列里一格
|
||
文字夹着手机号），抛 _Leak，不交出去。allow 是提问人自己写的数（_given_numbers），回答里复述它们不标「无出处」。"""
|
||
loader = _masking_loader(views)
|
||
allowed = list(allow) or None
|
||
# 列名里写着遮罩值的查询：目录里的列名照快照换（_masked_view），整表展开、表头核对、存下的目录都按换过的名字
|
||
catalog = {alias: _renamed_entry(entry, secrets) for alias, entry in catalog.items()}
|
||
doc = compose_doc(_scrubbed_source(source, secrets), catalog, run_id=run_id, loader=loader,
|
||
allow_numbers=allowed)
|
||
if _leaked(doc, secrets):
|
||
raise _Leak()
|
||
return doc
|
||
|
||
|
||
def _leaked(doc: dict[str, Any], secrets: _Secrets) -> bool:
|
||
"""组装出来的正文里还认得出遮罩值。SQL 里照原样留着的阈值写在正文里不算（_Secrets.show），渲染进单元格引用里的
|
||
算：格子已经按值遮过，遮完还认得出，就是一格文字里夹着这个数，渲染出来才露。"""
|
||
markdown = str(doc.get("markdown") or "")
|
||
pattern = secrets.pattern(markdown)
|
||
if pattern is None:
|
||
return False
|
||
cells = [seg["span"] for seg in iter_segments(doc) if str(seg.get("ref") or "").startswith("v:")]
|
||
return any(not secrets.is_shown(m.group()) or any(a < m.end() and m.start() < b for a, b in cells)
|
||
for m in pattern.finditer(markdown))
|
||
|
||
|
||
def _renamed_entry(entry: Any, secrets: _Secrets) -> Any:
|
||
if not (isinstance(entry, dict) and entry.get("kind") == "query" and isinstance(entry.get("columns"), list)):
|
||
return entry
|
||
names = [secrets.scrub(str(c)) for c in entry["columns"]]
|
||
return {**entry, "columns": names} if names != [str(c) for c in entry["columns"]] else entry
|
||
|
||
|
||
def _with_notes(answer: dict[str, Any], op: _Opening, outcome: VerifyOutcome, part: dict[str, Any], lost: list[str],
|
||
own: dict[str, dict[str, Any]]) -> dict[str, Any]:
|
||
"""回答末尾的系统说明：用不了的数据源、模型的轮数用完了、有查询执行失败、有引用解析不了、封存之后查的是现在的数据。
|
||
审批人据此知道这份回答哪里不完整，不会看到「回答完成」却满屏 ⟦?…⟧。"""
|
||
notes: list[str] = []
|
||
if lost:
|
||
notes.append(NOTE_LOST.format(names=_quoted(lost)))
|
||
if outcome.limit == "max_steps":
|
||
notes.append(NOTE_ROUNDS)
|
||
cap = part.get("max_queries")
|
||
# 查询次数到顶时次数一定用满了（被拒的、执行失败的也算一次），清单里少的就是失败的那几次
|
||
if outcome.limit == "max_queries" and isinstance(cap, int) and not isinstance(cap, bool) \
|
||
and len(outcome.queries) < cap:
|
||
notes.append(NOTE_FAILED.format(n=cap - len(outcome.queries)))
|
||
unresolved = sum(1 for seg in iter_segments(answer) if seg.get("issue") == "unresolved_ref")
|
||
if unresolved:
|
||
notes.append(NOTE_UNRESOLVED.format(n=unresolved))
|
||
# 上传表格按运行固定的版本查（快照记着 data_version），手工登记的源查的是现在的库
|
||
if op.mode == "sealed" and any(not snapshot.get("data_version") for snapshot in own.values()):
|
||
notes.append(NOTE_LIVE)
|
||
for note in notes:
|
||
answer = with_note(answer, note)
|
||
return answer
|
||
|
||
|
||
async def _store(doc: dict[str, Any], op: _Opening, ask: Ask) -> str | None:
|
||
try:
|
||
return await artifact_store.put_json(doc, kind=ANSWER_KIND, run_id=op.run_id,
|
||
meta={"report": ask.report, "unit": ask.unit,
|
||
"question": ask.question[:QUESTION_BRIEF]})
|
||
except Exception: # noqa: BLE001 - 存不下不影响回答本身：正文照常交回，只是数字点不开
|
||
logger.warning("质询的回答文档保存失败（运行 %s）", op.run_id, exc_info=True)
|
||
return None
|
||
|
||
|
||
# --------------------------------------------------------------------------
|
||
# 写入与读取
|
||
# --------------------------------------------------------------------------
|
||
|
||
|
||
async def _record(op: _Opening, data: dict[str, Any]) -> tuple[Any, str | None]:
|
||
"""记一条 approval.inquiry。返回 (写入的事件, 没写进时的说明)。
|
||
|
||
停在审批时：那张卡仍待审批、运行仍停着才写（批过了，运行可能已经停到下一张卡上）。封存之后：仍是开始回答时
|
||
的那份封存才写。append_events 返回 None 就是运行在回答期间变了。"""
|
||
items = [(EventType.APPROVAL_INQUIRY, None, data)]
|
||
try:
|
||
if op.mode == "interrupted":
|
||
written = await append_events(op.run_id, items, require="interrupted", approval_id=op.approval_id)
|
||
else:
|
||
written = await append_events(op.run_id, items, require="sealed", seal=op.seal)
|
||
except Exception as e: # noqa: BLE001 - 写不进运行记录也要把回答交回给提问的人
|
||
logger.warning("质询的问答写入运行记录失败（运行 %s）", op.run_id, exc_info=True)
|
||
return None, f"这次质询的问答没能写入运行记录（{describe_exception(e)}）"
|
||
return (written[0], None) if written else (None, NOT_RECORDED)
|
||
|
||
|
||
def _iso(ts: Any) -> str | None:
|
||
if isinstance(ts, bool) or not isinstance(ts, (int, float)):
|
||
return None
|
||
return datetime.fromtimestamp(float(ts), timezone.utc).isoformat()
|
||
|
||
|
||
def inquiry_of(data: Any, *, seq: int | None, ts: Any) -> dict[str, Any]:
|
||
"""事件数据 → 接口上的 Inquiry 对象（前后端约定的形状）。POST 的返回和 GET 的列表都经这里，两边一样。"""
|
||
data = data if isinstance(data, dict) else {}
|
||
usage = data.get("usage") if isinstance(data.get("usage"), dict) else {}
|
||
return {
|
||
"seq": seq, "at": _iso(ts), "actor": data.get("actor"), "report": data.get("report"), "unit": data.get("unit"),
|
||
"quote": data.get("quote"), "question": str(data.get("question") or ""),
|
||
"answer": {"text": str(data.get("answer_text") or ""), "doc_artifact": data.get("answer_doc"),
|
||
"ok": data.get("ok") is True, "limit": data.get("limit"), "error": data.get("error")},
|
||
"queries": [{k: q.get(k) for k in QUERY_KEYS} for q in data.get("queries") or [] if isinstance(q, dict)],
|
||
"model": data.get("model"),
|
||
"usage": {k: usage.get(k, 0) for k in USAGE_KEYS},
|
||
"post_seal": bool(data.get("post_seal")), "approval_id": data.get("approval_id"),
|
||
}
|
||
|
||
|
||
async def ask(run_id: str, request: Ask, *, actor: str | None = None) -> dict[str, Any]:
|
||
"""答一条质询：{inquiry, recorded, note}。不受理时抛 InquiryRefused。
|
||
|
||
设置按现在的（不按发起时快照进运行选项的那份）：质询不在图里执行、不参与重放，关掉「审批质询」应当马上生效。"""
|
||
from app.api.settings import VERIFY_SETTING_LABEL, verify_settings
|
||
|
||
async with SessionLocal() as session:
|
||
settings = await verify_settings(session)
|
||
part = settings.get("inquiry") if isinstance(settings.get("inquiry"), dict) else {}
|
||
if not part.get("enabled", True):
|
||
raise InquiryRefused(409, DISABLED_WORDS.format(label=VERIFY_SETTING_LABEL["inquiry.enabled"]),
|
||
code=INQUIRY_DISABLED)
|
||
with _ANSWERING.hold(run_id):
|
||
opening = await _open(run_id, request)
|
||
target = _target(opening.doc, request.unit) if request.unit else None
|
||
data = {"question": request.question, "quote": request.quote, "report": request.report, "unit": request.unit,
|
||
"approval_id": opening.approval_id, "actor": actor,
|
||
**await _answer(opening, request, target, settings)}
|
||
event, note = await _record(opening, data)
|
||
if event is not None:
|
||
return {"inquiry": inquiry_of(event.data, seq=event.seq, ts=event.ts), "recorded": True, "note": None}
|
||
shown = {**data, "post_seal": True} if opening.mode == "sealed" else data
|
||
_HELD.keep(run_id, shown)
|
||
return {"inquiry": inquiry_of(shown, seq=None, ts=time.time()), "recorded": False, "note": note}
|
||
|
||
|
||
async def _inquiry_events(run_id: str) -> list[tuple[int, float, dict[str, Any]]]:
|
||
async with SessionLocal() as session:
|
||
if await session.get(Run, run_id) is None:
|
||
raise InquiryRefused(404, "运行记录不存在", code=RUN_NOT_FOUND)
|
||
rows = await session.execute(
|
||
select(RunEvent.seq, RunEvent.ts, RunEvent.data)
|
||
.where(RunEvent.run_id == run_id, RunEvent.type == EventType.APPROVAL_INQUIRY).order_by(RunEvent.seq))
|
||
return [(seq, ts, data if isinstance(data, dict) else {}) for seq, ts, data in rows]
|
||
|
||
|
||
async def list_inquiries(run_id: str, *, report: str | None = None, unit: str | None = None) -> list[dict[str, Any]]:
|
||
"""这次运行的质询（封存前后的都算），按先后；给了 report / unit 只要问那份报告、那一句的。"""
|
||
return [inquiry_of(data, seq=seq, ts=ts) for seq, ts, data in await _inquiry_events(run_id)
|
||
if (not report or data.get("report") == report) and (not unit or data.get("unit") == unit)]
|
||
|
||
|
||
def _cited_cards(doc_id: Any) -> set[str]:
|
||
"""回答文档里引用的报告口径卡（m: 条目指向的工件）：界面按 doc.catalog[alias].artifact 取，和查询快照走同一个接口。"""
|
||
doc = _quiet_load(artifact_store.load, doc_id)
|
||
catalog = doc.get("catalog") if isinstance(doc, dict) and isinstance(doc.get("catalog"), dict) else {}
|
||
return {str(e["artifact"]) for e in catalog.values()
|
||
if isinstance(e, dict) and e.get("kind") in ("metric", "input") and e.get("artifact")}
|
||
|
||
|
||
async def _report_material(run_id: str, reports: Iterable[Any]) -> tuple[list[dict[str, Any]], list[str]]:
|
||
"""这几份报告（报告节点 id）的文档目录里的查询快照，和列出的指标、运行输入的值：和回答时收遮罩值、免遮的是同一批
|
||
（报告最后一次 report.checked 的文档）。"""
|
||
wanted = sorted({str(r) for r in reports if isinstance(r, str) and r})
|
||
if not wanted:
|
||
return [], []
|
||
async with SessionLocal() as session:
|
||
rows = await session.execute(
|
||
select(RunEvent.node_id, RunEvent.data)
|
||
.where(RunEvent.run_id == run_id, RunEvent.type == EventType.REPORT_CHECKED, RunEvent.node_id.in_(wanted))
|
||
.order_by(RunEvent.seq))
|
||
docs = {node_id: str(data["doc_artifact"]) for node_id, data in rows
|
||
if isinstance(data, dict) and data.get("doc_artifact")}
|
||
snapshots: list[dict[str, Any]] = []
|
||
values: list[str] = []
|
||
for artifact in docs.values():
|
||
doc = _quiet_load(artifact_store.load, artifact)
|
||
catalog = doc.get("catalog") if isinstance(doc, dict) and isinstance(doc.get("catalog"), dict) else {}
|
||
values += _ref_values(_report_refs(catalog))
|
||
for entry in catalog.values():
|
||
if isinstance(entry, dict) and entry.get("kind") == "query":
|
||
snapshot = _quiet_load(artifact_store.load, entry.get("artifact"))
|
||
if _query_shaped(snapshot):
|
||
snapshots.append(snapshot)
|
||
return snapshots, values
|
||
|
||
|
||
async def inquiry_artifact(run_id: str, artifact_id: str) -> dict[str, Any]:
|
||
"""质询引用过的工件：查询快照（遮罩照回答时的办法，SQL 用事件里记下的那条，两处一字不差）、回答文档（组装时就遮好
|
||
了）、回答里引用的报告口径卡。{id, content, masked[, mask_note]}。
|
||
|
||
认的是这次运行的质询事件引用过的，加上没写进运行记录、还留在进程里的回答（_HELD）引用过的；别的一律 404。"""
|
||
from app.api.evidence import SOURCE_GONE
|
||
|
||
datas = [data for _, _, data in await _inquiry_events(run_id)] + _HELD.of(run_id)
|
||
referenced = [d for d in datas
|
||
if artifact_id in (d.get("inquiry_artifacts") or []) or d.get("answer_doc") == artifact_id]
|
||
if not referenced:
|
||
referenced = [d for d in datas if d.get("answer_doc") and artifact_id in _cited_cards(d.get("answer_doc"))]
|
||
if not referenced:
|
||
raise InquiryRefused(404, "这次运行的质询没有引用这件工件", code=ARTIFACT_NOT_FOUND)
|
||
try:
|
||
content = artifact_store.load(artifact_id)
|
||
except ValueError as e:
|
||
raise InquiryRefused(409, "工件与哈希不一致，疑似被修改，不予展示", code=ARTIFACT_TAMPERED) from e
|
||
if content is None:
|
||
raise InquiryRefused(404, "无法读取这件工件，可能已被删除", code=ARTIFACT_NOT_FOUND)
|
||
if not _query_shaped(content):
|
||
return {"id": artifact_id, "content": content, "masked": []}
|
||
# 遮罩值照回答时收：引用它的那几条质询各自查到的全部快照（查询条件里写着的值，不一定在这一份的结果里），加上报告
|
||
# 自己的查询快照；免遮的也照回答时：提问人自己写的、报告里列出的指标和运行输入的值。SQL 里照原样留着的阈值只在
|
||
# 回答正文里不遮，格子照旧按值遮，这里不用
|
||
own: dict[str, dict[str, Any]] = {artifact_id: content}
|
||
for data in referenced:
|
||
for other in dict.fromkeys(str(a) for a in data.get("inquiry_artifacts") or []):
|
||
if other not in own and _query_shaped(snapshot := _quiet_load(artifact_store.load, other)):
|
||
own[other] = snapshot
|
||
others, values = await _report_material(run_id, (d.get("report") for d in referenced))
|
||
asked = [t for d in referenced for t in (d.get("question"), d.get("quote")) if isinstance(t, str)]
|
||
plan = await _plan(own, others, [*asked, *values])
|
||
shown = plan.views[artifact_id]
|
||
recorded = next((q["sql"] for d in referenced for q in d.get("queries") or []
|
||
if isinstance(q, dict) and q.get("artifact") == artifact_id and isinstance(q.get("sql"), str)),
|
||
None)
|
||
if recorded is not None:
|
||
shown = {**shown, "sql": recorded}
|
||
elif isinstance(shown.get("sql"), str):
|
||
name = str(content.get("source") or "")
|
||
shown = {**shown, "sql": _scrub_sql(shown["sql"], plan.secrets, plan.tainted.get(artifact_id, set()),
|
||
plan.kinds.get(name))}
|
||
out: dict[str, Any] = {"id": artifact_id, "content": shown, "masked": plan.masked[artifact_id]}
|
||
if gone := plan.gone.get(artifact_id):
|
||
out["mask_note"] = SOURCE_GONE.format(source="、".join(gone))
|
||
return out
|
||
|
||
|
||
__all__ = [
|
||
"BUSY_CONTINUE", "BUSY_DECIDE", "INQUIRY_BUSY", "INQUIRY_DISABLED", "INQUIRY_NOT_OPEN", "INQUIRY_SCHEMA",
|
||
"INQUIRY_SYSTEM", "NOT_RECORDED", "QUESTION_MAX", "QUOTE_MAX", "Ask", "InquiryRefused", "ask", "inquiry_artifact",
|
||
"inquiry_busy", "inquiry_of", "list_inquiries", "parse_ask",
|
||
]
|