mirror of
https://github.com/ThearchyHelios/AgentLab.git
synced 2026-11-15 03:51:58 +00:00
ThearchyHelios
b3dcddb52e
- W4R-01：召回只查新版图里会不会写外部系统（apps/backfill 抽出 graph_external_write，graph_side_effect 复用它）。召回图只有两版
的取数和口径卡，图里别处的人工节点、按流程使用的问题碰不到它；口径卡上游的人工节点 derive 本来就认作数据部分不能复用。
「按新版重新出具」走完整的正式运行，仍按 graph_side_effect 全套拒绝。原来带审批的口径升版后一组都不召回，L6 对它们失效。
- W4R-09：收尾时召回卡读不出、或缺了某个比较的旧值 / 新值，照实记重算失败（读不出召回卡），原答案一个不动。原来两边都是空，
按渲染比被当成「没变」，给每个原答案永久盖上「已核对，不影响」，收过尾之后再也不核对。
- W4R-12：这一版已经不是当前发布版（之后又发布了更新的版本）时不再发起召回、不给接着算，批次里写 continue_reason，接着算的
接口 409 带同一句。同启动时接着做只认当前发布版：新版本的召回覆盖更早的所有版本，再按旧版开「口径升到 vN」的待办只是添乱。
- W4R-13：开登录时一组答案几个主人就几条待办，全局渠道却按这一批（recall.batch_of_key：同一次召回、同一个来由）只在最早开的
那条上推一次，答案、待办按这一批汇总，几条的链到待办箱；别的几条连 task.opened 也不再推全局渠道。个人渠道照旧每人一条。
- W4R-11：目录审阅之后的核对按数据源排队、批量审阅的几张表合成一遍（catalog_pass，同一数据源一把锁）；查询快照按数据源在库里
筛、按运行结束时间分页、每张表凑够 BASIS_MAX_RUNS 次运行就停；冻结的表结构快照这一遍里按工件 id 只读一次。原来批量审阅
几十张表就同时起几十个后台任务，每个都全表扫查询快照、反复读同一份几 MB 的表结构快照。
- W4R-03（本包那一半）：GET /api/runs/{id}/ledger 加 recall：checked（已按 vN 核对，不影响）、basis（依据有变：哪一种、几项、
新出现几条错误级问题）、tasks（看的这个人手上说的是这个答案、还没处理的 recall 待办）。不放数、不放表名。几种状态都带。
- W4R-10（本包那一半）：新事件 ledger.feedback（对账运行上的封存后事件），POST /api/ledger/answers/{run}/reconcile/{rid}/feedback
{verdict: useful | unclear} 记反馈，同一个人改主意只算最后一次（app/ledger/feedback.py）；账本接口的 reconciled 每一项带
feedback {mine, useful, unclear}；统计 E2 的 feedback 数到它，去掉「第 4 波接上」的占位说法。离线核对页、封存后事件摘要
都认得这个事件。
测试：test_ledger_recall 新增七个用例、改了人工节点那一个（召回照算、重新出具照实拒绝）；新增 test_ledger_feedback；
test_ledger_api 的 E2 断言跟上。每个修复都先写失败的测试、去掉修复回跑确认抓得住。后端全量 14237 通过。
194 lines
10 KiB
Python
194 lines
10 KiB
Python
"""口径账本交给界面的样子（docs/design/next-round/02-口径账本.md 做法 3）：GET /api/runs/{run_id}/ledger、证据片段接口的
|
||
ledger 键、报告导出的片段面板，三处读同一份比对工件、按同一套遮罩给。
|
||
|
||
遮罩按读的那一刻重滤（同证据面板，api/evidence._Masks）：绑定的值是这次运行查到过的遮罩值时不给值（也就不能拿它代填出具），
|
||
差异条目里的 SQL 片段走 _Shown 同一套换法。工作流名按现在的取（工件里不存名字）。
|
||
|
||
界面层不放逻辑：标签、整题判断、能做的动作都由这里给。actions（第 3 波）：整题等价时按那份口径正式出具（能不能、能不能
|
||
自动、不能的原因，ledger/issue.plan_issue，按看的这个人的权限判）；有相关口径的查询看差多少（口径对账，ledger/reconcile）。
|
||
issued 是这次运行按口径出具过的正式运行，reconciled 是对过的账（各自的运行、状态，第 4 波起带上结果上的「说明有用 /
|
||
看不懂」：看的这个人给过的、各几个，ledger/feedback）。
|
||
|
||
recall（第 4 波，ledger/recall.answer_marks）：这个答案身上的召回标记——「已按 vN 核对，不影响」（checked）、依据有变
|
||
（basis）、看的这个人手上说的是它的 recall 待办（tasks）。几种状态都带：没比对过、不比对的答案照样可能被标依据有变。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
from typing import Any
|
||
|
||
from sqlalchemy import select
|
||
|
||
from app.db.base import SessionLocal
|
||
from app.db.models import Run, Workflow
|
||
from app.ledger import labels as ledger_labels
|
||
from app.ledger import match as ledger_match
|
||
from app.ledger import store
|
||
|
||
#: state：matched 比对过；pending 已排队按需比对；ineligible 这次运行不比对（reason 写为什么）；unreadable 比对记录读不出
|
||
STATES = ("matched", "pending", "ineligible", "unreadable")
|
||
|
||
|
||
class _Hide:
|
||
"""按这次运行查到过的遮罩值遮：hide(值) 这个值给不给，shown(文字) 文字里的遮罩值换成「已遮罩」。"""
|
||
|
||
def __init__(self, secrets: Any) -> None:
|
||
from app.api.evidence import _Shown
|
||
|
||
self._secrets = secrets
|
||
self._shown = _Shown(secrets)
|
||
|
||
def hide(self, value: Any) -> bool:
|
||
if self._secrets is None or value is None or isinstance(value, bool):
|
||
return False
|
||
return bool(self._secrets.hit(value) or self._secrets.weak_hit(str(value)))
|
||
|
||
def shown(self, value: Any) -> Any:
|
||
return self._shown.text(value)
|
||
|
||
|
||
async def _hider(sealed: Any) -> _Hide:
|
||
from app.api.evidence import _Masks
|
||
|
||
return _Hide(await _Masks(sealed).run_secrets())
|
||
|
||
|
||
async def _names(ids: set[str]) -> dict[str, str]:
|
||
if not ids:
|
||
return {}
|
||
async with SessionLocal() as session:
|
||
rows = await session.execute(select(Workflow.id, Workflow.name).where(Workflow.id.in_(sorted(ids))))
|
||
return {wid: name for wid, name in rows.all()}
|
||
|
||
|
||
def _workflow_ids(content: dict[str, Any]) -> set[str]:
|
||
return {str(c.get("workflow_id")) for c in content.get("calibers") or [] if c.get("workflow_id")}
|
||
|
||
|
||
def _whole_view(whole: dict[str, Any], hider: _Hide, names: dict[str, str]) -> dict[str, Any]:
|
||
out = {k: v for k, v in whole.items() if k != "binding"}
|
||
if whole.get("equivalent"):
|
||
out["binding"] = ledger_labels.binding_view(whole.get("binding"), hider.hide)
|
||
out["workflow_name"] = names.get(str(whole.get("workflow_id") or ""))
|
||
out["level_text"] = ledger_labels.LEVEL_TEXT.get(str(whole.get("level") or ""), "")
|
||
return out
|
||
|
||
|
||
def _query_view(query: dict[str, Any], hider: _Hide, names: dict[str, str]) -> dict[str, Any]:
|
||
out = {k: query[k] for k in ("artifact", "node_id", "source", "tables", "status", "reason", "note") if k in query}
|
||
cands = []
|
||
for cand in query.get("candidates") or []:
|
||
item = ledger_labels.related_view(cand, hide=hider.hide, shown=hider.shown, names=names)
|
||
item["status"] = cand.get("status")
|
||
if cand.get("how"):
|
||
item["how"] = cand["how"]
|
||
if cand.get("columns") is not None:
|
||
item["columns"] = cand["columns"]
|
||
cands.append(item)
|
||
out["candidates"] = cands
|
||
return out
|
||
|
||
|
||
def _labels_view(content: dict[str, Any], hider: _Hide, names: dict[str, str]) -> dict[str, Any]:
|
||
return {node: {"labels": {sid: ledger_labels.view_label(label, hide=hider.hide, shown=hider.shown, names=names)
|
||
for sid, label in (report.get("labels") or {}).items()}}
|
||
for node, report in (content.get("reports") or {}).items()}
|
||
|
||
|
||
def _stamp(recorded: store.Recorded) -> dict[str, Any]:
|
||
"""比对的来历：哪份工件、哪一版算法、谁触发的、什么时候追加的；事后补比的写明按现在的口径回看。"""
|
||
from datetime import datetime, timezone
|
||
|
||
at = datetime.fromtimestamp(recorded.ts, timezone.utc).isoformat(timespec="seconds") \
|
||
if isinstance(recorded.ts, (int, float)) else None
|
||
return {"artifact": recorded.artifact, "algo": recorded.algo, "trigger": recorded.trigger, "retro": recorded.retro,
|
||
"matched_at": at, "post_seal": True, "note": ledger_labels.POST_SEAL_NOTE,
|
||
**({"retro_note": ledger_labels.CERTIFIED_NOTE if recorded.trigger == "certified"
|
||
else ledger_labels.RETRO_NOTE} if recorded.retro else {})}
|
||
|
||
|
||
async def run_view(run_id: str) -> dict[str, Any]:
|
||
"""GET /api/runs/{run_id}/ledger 的答复：标签、整题判断、每条查询的比对、能做的动作。没比对过、能比的运行这时排上按需比对
|
||
（trigger=on_demand），答复 state=pending；不比的照实说为什么。"""
|
||
from app.api.coded import CodedHTTPException
|
||
from app.api.evidence import RUN_NOT_FOUND, _sealed
|
||
|
||
from app.api.deps import current_principal
|
||
from app.ledger.recall import answer_marks
|
||
|
||
async with SessionLocal() as session:
|
||
run = await session.get(Run, run_id)
|
||
if run is None:
|
||
raise CodedHTTPException(404, "运行记录不存在", RUN_NOT_FOUND)
|
||
principal = current_principal()
|
||
marks = await answer_marks(session, run_id, principal)
|
||
base: dict[str, Any] = {"run_id": run_id, "note": ledger_labels.POST_SEAL_NOTE, "recall": marks}
|
||
recorded = await store.latest(run_id)
|
||
if recorded is None:
|
||
why = ledger_match.ineligible(run)
|
||
sealed = await _sealed(run_id) if why is None else None
|
||
if sealed is not None and not sealed.queries:
|
||
why = ledger_match.NO_QUERIES
|
||
if why is not None:
|
||
return {**base, "state": "ineligible", "reason": why}
|
||
ledger_match.schedule(run_id, trigger="on_demand")
|
||
return {**base, "state": "pending"}
|
||
if recorded.content is None:
|
||
return {**base, "state": "unreadable", "reason": recorded.problem, **_stamp(recorded)}
|
||
from app.ledger import feedback as ledger_feedback
|
||
from app.ledger import issue as ledger_issue
|
||
from app.ledger import reconcile as ledger_reconcile
|
||
|
||
content = recorded.content
|
||
sealed = await _sealed(run_id)
|
||
hider = await _hider(sealed)
|
||
names = await _names(_workflow_ids(content))
|
||
plans = await ledger_issue.plans_for(run_id, content, principal=principal, hide=hider.hide,
|
||
artifact=recorded.artifact, retro=recorded.retro)
|
||
async with SessionLocal() as session:
|
||
issued = [ledger_issue.issued_view(r) for r in await ledger_issue.issued_runs(session, run_id)]
|
||
reconciled = [ledger_reconcile.reconciled_view(r) for r in await ledger_reconcile.reconciled_runs(session, run_id)]
|
||
# 对账结果上的「说明有用 / 看不懂」（ledger/feedback）：看的这个人给过哪一个、各几个
|
||
votes = await ledger_feedback.feedback_of(session, [r["run_id"] for r in reconciled], principal)
|
||
reconciled = [{**r, "feedback": votes[r["run_id"]]} for r in reconciled]
|
||
return {
|
||
**base, "state": "matched", **_stamp(recorded),
|
||
"calibers": [{**{k: c.get(k) for k in ("caliber", "workflow_id", "version", "level", "graph_hash")},
|
||
"workflow_name": names.get(str(c.get("workflow_id") or "")),
|
||
"level_text": ledger_labels.LEVEL_TEXT.get(str(c.get("level") or ""), "")}
|
||
for c in content.get("calibers") or []],
|
||
"queries": [_query_view(q, hider, names) for q in content.get("queries") or []],
|
||
"reports": _labels_view(content, hider, names),
|
||
"primary": content.get("primary"),
|
||
"whole": _whole_view(content.get("whole") or {}, hider, names),
|
||
"actions": [*(p.action() for p in plans), *ledger_reconcile.actions_of(content, names, hider.hide)],
|
||
"issued": issued,
|
||
"reconciled": reconciled,
|
||
}
|
||
|
||
|
||
async def report_labels(sealed: Any, report_node: str) -> dict[str, Any] | None:
|
||
"""一份报告里每个数的标签（遮过的），给证据片段接口和报告导出：{labels: {片段 id: 标签}, 来历}。没比对过、比对记录读不出、
|
||
这份报告没有标签的为 None（片段接口就不加 ledger 键，老运行的返回一字不差）。"""
|
||
recorded = await store.latest(sealed.run_id)
|
||
if recorded is None or recorded.content is None:
|
||
return None
|
||
report = (recorded.content.get("reports") or {}).get(report_node)
|
||
if not isinstance(report, dict):
|
||
return None
|
||
hider = await _hider(sealed)
|
||
names = await _names(_workflow_ids(recorded.content))
|
||
return {"labels": {sid: ledger_labels.view_label(label, hide=hider.hide, shown=hider.shown, names=names)
|
||
for sid, label in (report.get("labels") or {}).items()}, **_stamp(recorded)}
|
||
|
||
|
||
async def segment_label(sealed: Any, report_node: str, segment_id: str) -> dict[str, Any] | None:
|
||
"""证据片段接口的 ledger 键：{label: 这个片段的标签, 比对的来历（artifact 是比对工件）}；这个片段没有标签（不是数、没比对过）
|
||
为 None。"""
|
||
found = await report_labels(sealed, report_node)
|
||
if found is None or segment_id not in found["labels"]:
|
||
return None
|
||
return {"label": found["labels"][segment_id], **{k: v for k, v in found.items() if k != "labels"}}
|
||
|
||
|
||
__all__ = ["STATES", "report_labels", "run_view", "segment_label"]
|