v7 mech-7: scorecard user_side_items + three-table rule (code unchanged, production forced not_pass on user-side pending/unknown/invalid)
(cherry picked from commit 59b4c49a896972501aeeb8472a9fc2918ec226fa)
This commit is contained in:
host committed
1 parent
f8a6a9d258
commit
f406398ce2
2 files changed
+495
-8
No files matched your search
+231
-8
@@ -59,11 +59,13 @@
|
||||
- 文档与技能并入架构与契约一致性
|
||||
（技能文本、附录溯源、移植规则最终都是契约一致性的一部分）。
|
||||
|
||||
输入格式：build_scorecard(evidence, thresholds=None, rubric_version=None)
|
||||
输入格式：build_scorecard(evidence, thresholds=None, rubric_version=None,
|
||||
baseline_head=None, evidence_rows=None, user_side_items=None,
|
||||
product_evidence=None)
|
||||
rubric_version 只是卡片上的版本锚点（版本化持久存储见
|
||||
cloud/scorecard_rubric.py：标尺改动写新版本行、旧行只读，
|
||||
本函数不查库、不改旧分）。
|
||||
evidence: dict，键为上面 7 个维 id，值为该维的证据 dict。
|
||||
输入格式：build_scorecard(evidence, thresholds=None, user_side_items=None) evidence: dict，键为上面 7 个维 id，值为该维的证据 dict。
|
||||
每个维的证据字段见各 _score_* 函数的 docstring。
|
||||
调用方必须带来源、时间、检查名；本模块不自动从测试文件、
|
||||
摘要文档、PR 描述里拼凑分数。
|
||||
@@ -76,8 +78,26 @@
|
||||
产品轮证据时恒 not_pass；这只是评分卡输入结构拆分，
|
||||
不代表任何产品功能已落地。build_scorecard 的返回 dict
|
||||
同时带 code/production/product 三个子对象，GET /audit-scorecard
|
||||
端点返回的示例卡因此也带这三个子对象（端点已接线）。
|
||||
"""
|
||||
端点返回的示例卡因此也带这三个子对象（端点已接线）。v7 机制第 7 项 user_side_items（本模块内实现，不依赖第 2 项的三张表函数）：
|
||||
- evidence 可带可选键 "user_side_items"，或由 build_scorecard 的
|
||||
user_side_items 关键字参数显式传入（关键字参数优先于 evidence 键）。
|
||||
每项至少含 id、status（pending/done/blocked）、blocked_by
|
||||
（pending/blocked 时必填，例如 user/host_env/contract_decision）。
|
||||
- 非法项绝不静默丢弃、绝不编造状态：记入
|
||||
user_side_items["invalid_items"]（含下标与原因），不进 items。
|
||||
- 输出增加 user_side_items 字段：原样透传有效项（多余字段保留），
|
||||
并附汇总 pending_ids、done_ids、blocked_ids、blocked_by_summary。
|
||||
- 三表规则见 apply_user_side_three_table_rule()：代码表结论
|
||||
（code_overall）绝不因用户侧 pending 被拉低；用户侧有未完成项
|
||||
（pending/blocked）或非法项时，生产表结论强制为 not_pass，
|
||||
原因字段明确指向用户侧（如 "user_side_pending: B1,B2,..."）；
|
||||
user_side_items 为空/缺失时，输出 user_side_unknown=True，
|
||||
生产表原因写 user_side_unknown，绝不把“无用户侧项”写成
|
||||
“用户侧已完成”。
|
||||
- 本项不做 B/C 拍板、不改阈值：阈值仍为 test_default_unapproved；
|
||||
B/C 清单只是 id 与标题常量（见 USER_SIDE_ITEM_IDS），未知 id
|
||||
不因此判非法（清单可能扩展），非法只按缺字段/未知状态/缺
|
||||
blocked_by/重复 id 判定。"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -124,6 +144,190 @@ DEFAULT_THRESHOLDS = {
|
||||
UNTESTED_KINDS = {"fixture", "viewport_substitute", "code_review_only",
|
||||
"fixture_simulated", "dry_run", "estimated"}
|
||||
|
||||
# v7 审计 B/C 用户侧清单（id 与标题；仅作常量与测试证据，不作拍板）。
|
||||
USER_SIDE_ITEM_IDS = [
|
||||
"B1", "B2", "B3", "B4", "B5", "B6", "B7", "B8", "B9",
|
||||
"C1", "C2", "C3", "C4",
|
||||
]
|
||||
|
||||
USER_SIDE_ITEM_TITLES = {
|
||||
"B1": "分支保护",
|
||||
"B2": "合并部署窗口",
|
||||
"B3": "阈值拍板",
|
||||
"B4": "金任务人工审定",
|
||||
"B5": "真实 PG 环境",
|
||||
"B6": "真实 App 安装",
|
||||
"B7": "第二台主机与账单",
|
||||
"B8": "v1.1 确认",
|
||||
"B9": "回滚演练窗口",
|
||||
"C1": "证据绑定强制化与签名",
|
||||
"C2": "live 验证接线",
|
||||
"C3": "锚点策略",
|
||||
"C4": "actual-only 语义",
|
||||
}
|
||||
|
||||
VALID_USER_SIDE_STATUSES = {"pending", "done", "blocked"}
|
||||
|
||||
|
||||
def normalize_user_side_items(raw):
|
||||
"""归一化用户侧项：有效项原样透传，非法项记入 invalid_items。
|
||||
|
||||
返回 dict，键：items、pending_ids、done_ids、blocked_ids、
|
||||
unfinished_ids、blocked_by_summary、invalid_items、count、
|
||||
all_pending、all_done、user_side_unknown。
|
||||
user_side_unknown 仅在 raw 为 None 或空列表时为 True；
|
||||
非列表、非法项等情形不算 unknown，而是 invalid（生产表
|
||||
同样不能因此通过，原因指向 invalid，见三表规则）。
|
||||
本函数不修改调用方传入的原始项（逐项浅拷贝）。
|
||||
"""
|
||||
summary = {
|
||||
"items": [],
|
||||
"pending_ids": [],
|
||||
"done_ids": [],
|
||||
"blocked_ids": [],
|
||||
"unfinished_ids": [],
|
||||
"blocked_by_summary": {},
|
||||
"invalid_items": [],
|
||||
"count": 0,
|
||||
"all_pending": False,
|
||||
"all_done": False,
|
||||
"user_side_unknown": False,
|
||||
}
|
||||
if raw is None:
|
||||
summary["user_side_unknown"] = True
|
||||
return summary
|
||||
if isinstance(raw, (str, bytes)) or not isinstance(raw, (list, tuple)):
|
||||
summary["invalid_items"].append({
|
||||
"index": None,
|
||||
"reason": "user_side_items_not_a_list",
|
||||
"raw_type": type(raw).__name__,
|
||||
})
|
||||
return summary
|
||||
if len(raw) == 0:
|
||||
summary["user_side_unknown"] = True
|
||||
return summary
|
||||
seen_ids = set()
|
||||
for index, item in enumerate(raw):
|
||||
if not isinstance(item, dict):
|
||||
summary["invalid_items"].append({
|
||||
"index": index,
|
||||
"reason": "item_not_a_dict",
|
||||
"raw_type": type(item).__name__,
|
||||
})
|
||||
continue
|
||||
item_id = item.get("id")
|
||||
if not isinstance(item_id, str) or not item_id:
|
||||
summary["invalid_items"].append({
|
||||
"index": index,
|
||||
"reason": "id_missing",
|
||||
})
|
||||
continue
|
||||
if item_id in seen_ids:
|
||||
summary["invalid_items"].append({
|
||||
"index": index,
|
||||
"id": item_id,
|
||||
"reason": "duplicate_id",
|
||||
})
|
||||
continue
|
||||
status = item.get("status")
|
||||
if status not in VALID_USER_SIDE_STATUSES:
|
||||
summary["invalid_items"].append({
|
||||
"index": index,
|
||||
"id": item_id,
|
||||
"reason": "status_missing_or_unknown",
|
||||
"status": status,
|
||||
})
|
||||
continue
|
||||
blocked_by = item.get("blocked_by")
|
||||
if status in ("pending", "blocked"):
|
||||
if not isinstance(blocked_by, str) or not blocked_by:
|
||||
summary["invalid_items"].append({
|
||||
"index": index,
|
||||
"id": item_id,
|
||||
"reason": "blocked_by_missing",
|
||||
})
|
||||
continue
|
||||
seen_ids.add(item_id)
|
||||
copied = dict(item)
|
||||
summary["items"].append(copied)
|
||||
if status == "pending":
|
||||
summary["pending_ids"].append(item_id)
|
||||
summary["unfinished_ids"].append(item_id)
|
||||
elif status == "blocked":
|
||||
summary["blocked_ids"].append(item_id)
|
||||
summary["unfinished_ids"].append(item_id)
|
||||
else:
|
||||
summary["done_ids"].append(item_id)
|
||||
if isinstance(blocked_by, str) and blocked_by:
|
||||
summary["blocked_by_summary"].setdefault(blocked_by, []).append(item_id)
|
||||
summary["count"] = len(summary["items"])
|
||||
if summary["items"]:
|
||||
summary["all_pending"] = all(
|
||||
it["status"] == "pending" for it in summary["items"])
|
||||
summary["all_done"] = all(
|
||||
it["status"] == "done" for it in summary["items"])
|
||||
return summary
|
||||
|
||||
|
||||
def _extract_overall(value):
|
||||
"""从字符串或评分卡 dict 里取出 overall（字符串原样返回）。"""
|
||||
if isinstance(value, dict):
|
||||
for key in ("overall", "code_overall", "production_overall"):
|
||||
if isinstance(value.get(key), str):
|
||||
return value[key]
|
||||
return None
|
||||
if isinstance(value, str):
|
||||
return value
|
||||
return None
|
||||
|
||||
|
||||
def apply_user_side_three_table_rule(code_overall, production_overall,
|
||||
user_side_items):
|
||||
"""三表规则（v7 机制第 7 项；位置：本模块）。
|
||||
|
||||
输入：代码表结论、生产表结论（各为 "pass"/"not_pass" 字符串，
|
||||
或含 overall 键的评分卡 dict）、user_side_items 原始列表。
|
||||
输出：代码表结论原样不动；生产表结论在用户侧未完成/非法/
|
||||
未知时强制为 not_pass，原因明确指向用户侧；用户侧全部 done
|
||||
且无非法项时，生产表结论跟随其自身输入结论，不被本规则改写。
|
||||
本函数是纯函数，不读库、不改阈值、不做 B/C 拍板。
|
||||
"""
|
||||
normalized = normalize_user_side_items(user_side_items)
|
||||
code = _extract_overall(code_overall)
|
||||
production = _extract_overall(production_overall)
|
||||
forced = False
|
||||
reason = None
|
||||
if normalized["user_side_unknown"]:
|
||||
production = "not_pass"
|
||||
reason = ("user_side_unknown: no user_side_items supplied; "
|
||||
"not equivalent to user_side_done")
|
||||
forced = True
|
||||
elif normalized["invalid_items"]:
|
||||
production = "not_pass"
|
||||
reasons = "; ".join(
|
||||
"%s(%s)" % (inv.get("reason", "invalid"),
|
||||
inv.get("id", inv.get("index")))
|
||||
for inv in normalized["invalid_items"])
|
||||
reason = "user_side_invalid: %s" % reasons
|
||||
if normalized["unfinished_ids"]:
|
||||
reason += "; user_side_pending: %s" % ",".join(
|
||||
normalized["unfinished_ids"])
|
||||
forced = True
|
||||
elif normalized["unfinished_ids"]:
|
||||
production = "not_pass"
|
||||
reason = "user_side_pending: %s" % ",".join(
|
||||
normalized["unfinished_ids"])
|
||||
forced = True
|
||||
return {
|
||||
"code_overall": code,
|
||||
"production_overall": production,
|
||||
"production_reason": reason,
|
||||
"user_side_forced_production_not_pass": forced,
|
||||
"code_unchanged_by_user_side": True,
|
||||
"user_side_unknown": normalized["user_side_unknown"],
|
||||
"user_side_items": normalized,
|
||||
}
|
||||
|
||||
|
||||
def thresholds_source(thresholds):
|
||||
"""阈值来源：只有调用方显式传入 user_approved 才算已拍板。"""
|
||||
@@ -690,18 +894,18 @@ def _build_table(dim_ids, evidence, th):
|
||||
# 钉死：平均分绝不能作为达标依据（各表各自独立判断）。
|
||||
overall_pass = all(d["score"] is not None and d["score"] >= PASS_SCORE
|
||||
for d in dimensions)
|
||||
overall = "pass" if overall_pass else "not_pass"
|
||||
return {
|
||||
"dimensions": dimensions,
|
||||
"average_score": average,
|
||||
"average_is_not_pass_criterion": True,
|
||||
"overall": "pass" if overall_pass else "not_pass",
|
||||
"overall": overall,
|
||||
"overall_pass": overall_pass,
|
||||
"pass_score": PASS_SCORE,
|
||||
"missing_items": missing_all,
|
||||
"untested_items": untested_all,
|
||||
"thresholds_source": thresholds_source(th),
|
||||
"thresholds": _effective_thresholds(th),
|
||||
}
|
||||
"thresholds": _effective_thresholds(th), }
|
||||
|
||||
|
||||
def check_baseline_stale(scorecard, current_main_head):
|
||||
@@ -881,10 +1085,29 @@ def build_scorecard(evidence, thresholds=None, rubric_version=None,
|
||||
report["evidence_row_ids"] = ledger["row_ids"]
|
||||
report["thresholds"] = _effective_thresholds(th)
|
||||
report["code"] = build_code_scorecard(evidence, thresholds)
|
||||
raw_user_side = (user_side_items if user_side_items is not None
|
||||
else evidence.get("user_side_items"))
|
||||
report["production"] = build_production_scorecard(
|
||||
evidence, thresholds, user_side_items)
|
||||
evidence, thresholds, raw_user_side)
|
||||
report["product"] = build_product_scorecard(
|
||||
evidence, thresholds, product_evidence)
|
||||
# v7 机制第 7 项三表规则（合一接线）：代码表结论绝不因用户侧
|
||||
# pending 被拉低；用户侧未完成/非法/未知时顶层
|
||||
# production_overall 强制 not_pass 且原因指向用户侧。注意：
|
||||
# 顶层 production_overall 是规则结论，report["production"]
|
||||
# 子对象仍是第 2 项的证据表（维分数照常展示），两者分工不同，
|
||||
# 顶层字段不回写子对象 overall，以免第 2 项的证据表语义被改。
|
||||
rule = apply_user_side_three_table_rule(
|
||||
report["code"]["overall"], report["production"]["overall"],
|
||||
raw_user_side)
|
||||
report["user_side_items"] = rule["user_side_items"]
|
||||
report["code_overall"] = rule["code_overall"]
|
||||
report["production_overall"] = rule["production_overall"]
|
||||
report["production_reason"] = rule["production_reason"]
|
||||
report["user_side_unknown"] = rule["user_side_unknown"]
|
||||
report["code_unchanged_by_user_side"] = True
|
||||
report["user_side_forced_production_not_pass"] = (
|
||||
rule["user_side_forced_production_not_pass"])
|
||||
return report
|
||||
|
||||
|
||||
|
||||
Reference in new issue
Block a user