xsl
67d9754823
tests/golden：JSON 用例 + 阈值配置 + runner（规则 pass_rate=1.0、检索 0.8 起步）+ pytest 壳；规则/检索两子集种子，Agent/报告子集占位（T-P2-11）。 实现： - runner.py 为普通模块（不依赖 pytest）：加载/执行/指标（pass_rate、 first_hit_in_top3）/逐用例差异明细；test_golden.py 只是薄壳（marker=golden， 无 MEIDA_RUN_INTEGRATION 时整体 skip）。用例与 expect 的未知键一律判 fail（封闭词汇表，防断言静默失效）。 - 规则子集 13 例（rules_cases.json，走 packages.rules DSL/evaluate）： 含 3 个硬禁忌场景（无条件合规硬拦、正式场合硬拦、复合优先级链 100硬>95禁忌>90体型>50趋势）+ 禁忌压制/维度隔离/多规则叠加/温度边界/ 缺字段静默/include 子集语义等。 - 检索子集 13 例（retrieval_cases.json，DeterministicEmbedder+hybrid_search）： 含 7 个 must_miss 红线场景（禁忌体型/draft/archived/场景外/类型外/组合红线）。 种子实体以 golden: 前缀命名，跑前先删（幂等重跑）；跑后也删——CI 防线 5c 与集成测试共用长活库，留下假实体会破坏其它用例对结果列表的精确断言。 确定性策略：query=目标 chunk 原文（余弦距离 0 必排第 1）+ 每例独立 marker token（gqNN）隔离关键词路；检索参数（1024 维/top_k 50/默认 RRF 权重）钉死在 runner，不读 env。 - thresholds.json：规则 pass_rate_min=1.0（硬结论子集一条不许退）； 检索 pass_rate_min=0.8 + first_hit_in_top3_min=0.8 起步。 - README.md：四子集 330 例规划、两格式 spec、加用例流程、阈值口径与 “为什么规则必须 1.0”。 测试： - MEIDA_RUN_INTEGRATION=1 pytest -m golden --no-cov：2 passed（规则 13/13=1.0，检索 13/13=1.0、first_hit_in_top3=13/13）；连续重跑幂等， 跑后库内 golden:% 残留为 0；不设 env 时 2 skipped；基线单测 473 passed、 集成 38 passed 不受影响；ruff check/format、lint-imports 全绿。 - 阻断语义自证（已改回，提交里只有正确版本）：临时把规则用例 user-taboo-overrides-trend-recommendation 的 must_avoid 改成不存在的 取值并把 hard_blocks_nonempty 翻转为 true → 规则子集 12/13=0.9231 <1.0 fail，明细输出“must_avoid 未命中：期望 top[length=九分裤脚]，实际 avoid=[top[length=[短款, 露脐]]]”与“hard_blocks_nonempty 期望 True， 实际 False（硬拦截规则：无）”；再临时破坏 3 条检索用例（2 条 must_hit 换成不存在的实体名、1 条 must_miss 加入本应命中的实体）→ 检索子集 10/13=0.7692<0.8 fail，明细含“must_miss 红线违规：golden:r12-good 出现在第 1 位——硬过滤零漏被破坏”。验证完三条全部改回，复跑全绿。 （注：检索阈值 0.8 起步，单条退化 0.92 尚不拦截、≥3 条即拦截，符合 种子期口径；规则阈值 1.0 单条即拦截。） 偏差说明：无
515 lines
16 KiB
JSON
515 lines
16 KiB
JSON
[
|
|
{
|
|
"name": "unconditional-hard-compliance-blocks-exotic-leather",
|
|
"rules": [
|
|
{
|
|
"rule_key": "G-RULES-01-HARD-EXOTIC",
|
|
"category": "compliance",
|
|
"priority": 100,
|
|
"confidence": 1.0,
|
|
"is_hard": true,
|
|
"conditions": {},
|
|
"effects": {
|
|
"avoid": [
|
|
{"slot": "accessory", "attrs": {"material": ["真兽皮"]}},
|
|
{"slot": "shoes", "attrs": {"material": ["真皮"]}}
|
|
],
|
|
"explanation": "合规红线：任何场景都不推荐真兽皮材质。"
|
|
}
|
|
}
|
|
],
|
|
"context": {},
|
|
"expect": {
|
|
"must_avoid": [
|
|
{"slot": "accessory", "attrs_include": {"material": ["真兽皮"]}},
|
|
{"slot": "shoes", "attrs_include": {"material": ["真皮"]}}
|
|
],
|
|
"forbidden_recommend": [
|
|
{"slot": "accessory", "attrs_include": {"material": ["真兽皮"]}}
|
|
],
|
|
"hard_blocks_nonempty": true
|
|
}
|
|
},
|
|
{
|
|
"name": "hard-compliance-fires-on-formal-occasion",
|
|
"rules": [
|
|
{
|
|
"rule_key": "G-RULES-02-HARD-FORMAL",
|
|
"category": "compliance",
|
|
"priority": 100,
|
|
"confidence": 1.0,
|
|
"is_hard": true,
|
|
"conditions": {"occasion": {"include": ["红毯", "晚宴"]}},
|
|
"effects": {
|
|
"avoid": [
|
|
{"slot": "shoes", "attrs": {"material": ["真皮"]}},
|
|
{"slot": "accessory", "attrs": {"material": ["真兽皮"]}}
|
|
],
|
|
"explanation": "正式场合合规红线：不推荐真皮与真兽皮。"
|
|
}
|
|
}
|
|
],
|
|
"context": {"occasion": "晚宴"},
|
|
"expect": {
|
|
"must_avoid": [
|
|
{"slot": "shoes", "attrs_include": {"material": ["真皮"]}}
|
|
],
|
|
"forbidden_recommend": [
|
|
{"slot": "shoes", "attrs_include": {"material": ["真皮"]}}
|
|
],
|
|
"hard_blocks_nonempty": true
|
|
}
|
|
},
|
|
{
|
|
"name": "hard-compliance-silent-on-daily-occasion",
|
|
"rules": [
|
|
{
|
|
"rule_key": "G-RULES-03-HARD-FORMAL",
|
|
"category": "compliance",
|
|
"priority": 100,
|
|
"confidence": 1.0,
|
|
"is_hard": true,
|
|
"conditions": {"occasion": {"include": ["红毯", "晚宴"]}},
|
|
"effects": {
|
|
"avoid": [{"slot": "shoes", "attrs": {"material": ["真皮"]}}],
|
|
"explanation": "正式场合合规红线：不推荐真皮。"
|
|
}
|
|
}
|
|
],
|
|
"context": {"occasion": "通勤"},
|
|
"expect": {
|
|
"forbidden_recommend": [
|
|
{"slot": "shoes", "attrs_include": {"material": ["真皮"]}}
|
|
],
|
|
"hard_blocks_nonempty": false
|
|
}
|
|
},
|
|
{
|
|
"name": "user-taboo-overrides-trend-recommendation",
|
|
"rules": [
|
|
{
|
|
"rule_key": "G-RULES-04-TREND-CROP",
|
|
"category": "trend",
|
|
"priority": 50,
|
|
"confidence": 0.7,
|
|
"conditions": {"style": "甜酷"},
|
|
"effects": {
|
|
"recommend": [{"slot": "top", "attrs": {"length": ["短款"]}}],
|
|
"explanation": "短款上衣是当季甜酷风的核心单品。"
|
|
}
|
|
},
|
|
{
|
|
"rule_key": "G-RULES-05-TABOO-MIDRIFF",
|
|
"category": "user_taboo",
|
|
"priority": 95,
|
|
"confidence": 1.0,
|
|
"conditions": {"user_taboos": {"include": ["露脐"]}},
|
|
"effects": {
|
|
"avoid": [{"slot": "top", "attrs": {"length": ["短款", "露脐"]}}],
|
|
"explanation": "用户不接受露脐，已剔除相关单品。"
|
|
}
|
|
}
|
|
],
|
|
"context": {"style": "甜酷", "user_taboos": ["露脐"]},
|
|
"expect": {
|
|
"must_avoid": [
|
|
{"slot": "top", "attrs_include": {"length": ["短款", "露脐"]}}
|
|
],
|
|
"forbidden_recommend": [
|
|
{"slot": "top", "attrs_include": {"length": ["短款"]}}
|
|
],
|
|
"hard_blocks_nonempty": false
|
|
}
|
|
},
|
|
{
|
|
"name": "user-taboo-limited-to-conflicting-dimension",
|
|
"rules": [
|
|
{
|
|
"rule_key": "G-RULES-06-BODY-H-BOTTOM",
|
|
"category": "body_shape",
|
|
"priority": 90,
|
|
"confidence": 0.9,
|
|
"conditions": {"body_shape": "H型"},
|
|
"effects": {
|
|
"recommend": [{"slot": "bottom", "attrs": {"silhouette": ["直筒", "阔腿"]}}],
|
|
"avoid": [{"slot": "bottom", "attrs": {"silhouette": ["紧身"]}}],
|
|
"explanation": "H型宜直线轮廓放大腰线比例。"
|
|
}
|
|
},
|
|
{
|
|
"rule_key": "G-RULES-07-TABOO-MIDRIFF",
|
|
"category": "user_taboo",
|
|
"priority": 95,
|
|
"confidence": 1.0,
|
|
"conditions": {"user_taboos": {"include": ["露脐"]}},
|
|
"effects": {
|
|
"avoid": [{"slot": "top", "attrs": {"length": ["短款", "露脐"]}}],
|
|
"explanation": "用户不接受露脐，已剔除相关单品。"
|
|
}
|
|
}
|
|
],
|
|
"context": {"body_shape": "H型", "user_taboos": ["露脐"]},
|
|
"expect": {
|
|
"must_recommend": [
|
|
{"slot": "bottom", "attrs_include": {"silhouette": ["阔腿"]}}
|
|
],
|
|
"must_avoid": [
|
|
{"slot": "bottom", "attrs_include": {"silhouette": ["紧身"]}}
|
|
],
|
|
"forbidden_recommend": [
|
|
{"slot": "top", "attrs_include": {"length": ["短款"]}}
|
|
],
|
|
"hard_blocks_nonempty": false
|
|
}
|
|
},
|
|
{
|
|
"name": "body-temperature-occasion-stack",
|
|
"rules": [
|
|
{
|
|
"rule_key": "G-RULES-08-BODY-A-SHOULDER",
|
|
"category": "body_shape",
|
|
"priority": 90,
|
|
"confidence": 0.95,
|
|
"conditions": {
|
|
"body_shape": "A型",
|
|
"features": {"include": ["溜肩"]},
|
|
"goals": {"include": ["修饰溜肩"]}
|
|
},
|
|
"effects": {
|
|
"recommend": [
|
|
{"slot": "top", "attrs": {"shoulder": ["垫肩"], "sleeve": ["泡泡袖"]}}
|
|
],
|
|
"avoid": [{"slot": "top", "attrs": {"silhouette": ["修身"]}}],
|
|
"explanation": "溜肩需要用垫肩与泡泡袖在肩部建立结构感。"
|
|
}
|
|
},
|
|
{
|
|
"rule_key": "G-RULES-09-TEMP-18-26",
|
|
"category": "temperature",
|
|
"priority": 75,
|
|
"confidence": 0.85,
|
|
"conditions": {"temperature": {"min": 18, "max": 26}},
|
|
"effects": {
|
|
"recommend": [{"slot": "outer", "attrs": {"thickness": ["薄款"]}}],
|
|
"avoid": [{"slot": "outer", "attrs": {"thickness": ["厚款"]}}],
|
|
"explanation": "18-26℃ 单层薄外套最舒适。"
|
|
}
|
|
},
|
|
{
|
|
"rule_key": "G-RULES-10-OCC-INTERVIEW",
|
|
"category": "occasion",
|
|
"priority": 80,
|
|
"confidence": 0.9,
|
|
"conditions": {"occasion": "面试"},
|
|
"effects": {
|
|
"recommend": [
|
|
{"slot": "top", "attrs": {"collar": ["衬衫领"]}},
|
|
{"slot": "bottom", "attrs": {"silhouette": ["直筒"]}}
|
|
],
|
|
"avoid": [{"slot": "top", "attrs": {"neckline": ["深V"]}}],
|
|
"explanation": "面试场合需要干练可信的轮廓。"
|
|
}
|
|
}
|
|
],
|
|
"context": {
|
|
"body_shape": "A型",
|
|
"features": ["溜肩"],
|
|
"goals": ["修饰溜肩"],
|
|
"temperature": 22.0,
|
|
"occasion": "面试"
|
|
},
|
|
"expect": {
|
|
"must_recommend": [
|
|
{"slot": "top", "attrs_include": {"shoulder": ["垫肩"]}},
|
|
{"slot": "top", "attrs_include": {"sleeve": ["泡泡袖"]}},
|
|
{"slot": "top", "attrs_include": {"collar": ["衬衫领"]}},
|
|
{"slot": "bottom", "attrs_include": {"silhouette": ["直筒"]}},
|
|
{"slot": "outer", "attrs_include": {"thickness": ["薄款"]}}
|
|
],
|
|
"must_avoid": [
|
|
{"slot": "top", "attrs_include": {"silhouette": ["修身"]}},
|
|
{"slot": "top", "attrs_include": {"neckline": ["深V"]}},
|
|
{"slot": "outer", "attrs_include": {"thickness": ["厚款"]}}
|
|
],
|
|
"hard_blocks_nonempty": false
|
|
}
|
|
},
|
|
{
|
|
"name": "missing-profile-fields-keep-rules-silent",
|
|
"rules": [
|
|
{
|
|
"rule_key": "G-RULES-11-BODY-A-SHOULDER",
|
|
"category": "body_shape",
|
|
"priority": 90,
|
|
"confidence": 0.95,
|
|
"conditions": {
|
|
"body_shape": "A型",
|
|
"features": {"include": ["溜肩"]},
|
|
"goals": {"include": ["修饰溜肩"]}
|
|
},
|
|
"effects": {
|
|
"recommend": [
|
|
{"slot": "top", "attrs": {"shoulder": ["垫肩"], "sleeve": ["泡泡袖"]}}
|
|
],
|
|
"avoid": [{"slot": "top", "attrs": {"silhouette": ["修身"]}}],
|
|
"explanation": "溜肩需要用垫肩与泡泡袖在肩部建立结构感。"
|
|
}
|
|
},
|
|
{
|
|
"rule_key": "G-RULES-12-TEMP-18-26",
|
|
"category": "temperature",
|
|
"priority": 75,
|
|
"confidence": 0.85,
|
|
"conditions": {"temperature": {"min": 18, "max": 26}},
|
|
"effects": {
|
|
"recommend": [{"slot": "outer", "attrs": {"thickness": ["薄款"]}}],
|
|
"avoid": [{"slot": "outer", "attrs": {"thickness": ["厚款"]}}],
|
|
"explanation": "18-26℃ 单层薄外套最舒适。"
|
|
}
|
|
}
|
|
],
|
|
"context": {"features": ["溜肩"], "goals": ["修饰溜肩"]},
|
|
"expect": {
|
|
"forbidden_recommend": [
|
|
{"slot": "top", "attrs_include": {}},
|
|
{"slot": "outer", "attrs_include": {}}
|
|
],
|
|
"hard_blocks_nonempty": false
|
|
}
|
|
},
|
|
{
|
|
"name": "temperature-lower-bound-inclusive",
|
|
"rules": [
|
|
{
|
|
"rule_key": "G-RULES-13-TEMP-18-26",
|
|
"category": "temperature",
|
|
"priority": 75,
|
|
"confidence": 0.85,
|
|
"conditions": {"temperature": {"min": 18, "max": 26}},
|
|
"effects": {
|
|
"recommend": [{"slot": "outer", "attrs": {"thickness": ["薄款"]}}],
|
|
"avoid": [{"slot": "outer", "attrs": {"thickness": ["厚款"]}}],
|
|
"explanation": "18-26℃ 单层薄外套最舒适。"
|
|
}
|
|
}
|
|
],
|
|
"context": {"temperature": 18.0},
|
|
"expect": {
|
|
"must_recommend": [
|
|
{"slot": "outer", "attrs_include": {"thickness": ["薄款"]}}
|
|
],
|
|
"must_avoid": [
|
|
{"slot": "outer", "attrs_include": {"thickness": ["厚款"]}}
|
|
],
|
|
"hard_blocks_nonempty": false
|
|
}
|
|
},
|
|
{
|
|
"name": "temperature-below-range-stays-silent",
|
|
"rules": [
|
|
{
|
|
"rule_key": "G-RULES-14-TEMP-18-26",
|
|
"category": "temperature",
|
|
"priority": 75,
|
|
"confidence": 0.85,
|
|
"conditions": {"temperature": {"min": 18, "max": 26}},
|
|
"effects": {
|
|
"recommend": [{"slot": "outer", "attrs": {"thickness": ["薄款"]}}],
|
|
"avoid": [{"slot": "outer", "attrs": {"thickness": ["厚款"]}}],
|
|
"explanation": "18-26℃ 单层薄外套最舒适。"
|
|
}
|
|
}
|
|
],
|
|
"context": {"temperature": 17.5},
|
|
"expect": {
|
|
"forbidden_recommend": [
|
|
{"slot": "outer", "attrs_include": {}}
|
|
],
|
|
"hard_blocks_nonempty": false
|
|
}
|
|
},
|
|
{
|
|
"name": "interview-occasion-collar-and-neckline",
|
|
"rules": [
|
|
{
|
|
"rule_key": "G-RULES-15-OCC-INTERVIEW",
|
|
"category": "occasion",
|
|
"priority": 80,
|
|
"confidence": 0.9,
|
|
"conditions": {"occasion": "面试"},
|
|
"effects": {
|
|
"recommend": [
|
|
{"slot": "top", "attrs": {"collar": ["衬衫领"]}},
|
|
{"slot": "bottom", "attrs": {"silhouette": ["直筒"]}}
|
|
],
|
|
"avoid": [{"slot": "top", "attrs": {"neckline": ["深V"]}}],
|
|
"explanation": "面试场合需要干练可信的轮廓。"
|
|
}
|
|
}
|
|
],
|
|
"context": {"occasion": "面试"},
|
|
"expect": {
|
|
"must_recommend": [
|
|
{"slot": "top", "attrs_include": {"collar": ["衬衫领"]}},
|
|
{"slot": "bottom", "attrs_include": {"silhouette": ["直筒"]}}
|
|
],
|
|
"must_avoid": [
|
|
{"slot": "top", "attrs_include": {"neckline": ["深V"]}}
|
|
],
|
|
"hard_blocks_nonempty": false
|
|
}
|
|
},
|
|
{
|
|
"name": "composite-priority-chain-hard-taboo-body",
|
|
"rules": [
|
|
{
|
|
"rule_key": "G-RULES-16-HARD-FORMAL",
|
|
"category": "compliance",
|
|
"priority": 100,
|
|
"confidence": 1.0,
|
|
"is_hard": true,
|
|
"conditions": {"occasion": {"include": ["红毯", "晚宴"]}},
|
|
"effects": {
|
|
"avoid": [
|
|
{"slot": "accessory", "attrs": {"material": ["真兽皮"]}},
|
|
{"slot": "shoes", "attrs": {"material": ["真皮"]}}
|
|
],
|
|
"explanation": "正式场合合规红线：不推荐真兽皮材质。"
|
|
}
|
|
},
|
|
{
|
|
"rule_key": "G-RULES-17-TABOO-MIDRIFF",
|
|
"category": "user_taboo",
|
|
"priority": 95,
|
|
"confidence": 1.0,
|
|
"conditions": {"user_taboos": {"include": ["露脐"]}},
|
|
"effects": {
|
|
"avoid": [{"slot": "top", "attrs": {"length": ["短款", "露脐"]}}],
|
|
"explanation": "用户不接受露脐，已剔除相关单品。"
|
|
}
|
|
},
|
|
{
|
|
"rule_key": "G-RULES-18-BODY-A-SHOULDER",
|
|
"category": "body_shape",
|
|
"priority": 90,
|
|
"confidence": 0.95,
|
|
"conditions": {
|
|
"body_shape": "A型",
|
|
"features": {"include": ["溜肩"]},
|
|
"goals": {"include": ["修饰溜肩"]}
|
|
},
|
|
"effects": {
|
|
"recommend": [
|
|
{"slot": "top", "attrs": {"shoulder": ["垫肩"], "sleeve": ["泡泡袖"]}}
|
|
],
|
|
"avoid": [{"slot": "top", "attrs": {"silhouette": ["修身"]}}],
|
|
"explanation": "溜肩需要用垫肩与泡泡袖在肩部建立结构感。"
|
|
}
|
|
},
|
|
{
|
|
"rule_key": "G-RULES-19-TREND-CROP",
|
|
"category": "trend",
|
|
"priority": 50,
|
|
"confidence": 0.7,
|
|
"conditions": {"style": "甜酷"},
|
|
"effects": {
|
|
"recommend": [{"slot": "top", "attrs": {"length": ["短款"]}}],
|
|
"explanation": "短款上衣是当季甜酷风的核心单品。"
|
|
}
|
|
}
|
|
],
|
|
"context": {
|
|
"body_shape": "A型",
|
|
"features": ["溜肩"],
|
|
"goals": ["修饰溜肩"],
|
|
"style": "甜酷",
|
|
"user_taboos": ["露脐"],
|
|
"occasion": "红毯"
|
|
},
|
|
"expect": {
|
|
"must_recommend": [
|
|
{"slot": "top", "attrs_include": {"shoulder": ["垫肩"]}},
|
|
{"slot": "top", "attrs_include": {"sleeve": ["泡泡袖"]}}
|
|
],
|
|
"must_avoid": [
|
|
{"slot": "top", "attrs_include": {"length": ["露脐"]}},
|
|
{"slot": "shoes", "attrs_include": {"material": ["真皮"]}}
|
|
],
|
|
"forbidden_recommend": [
|
|
{"slot": "top", "attrs_include": {"length": ["短款"]}},
|
|
{"slot": "shoes", "attrs_include": {"material": ["真皮"]}},
|
|
{"slot": "accessory", "attrs_include": {"material": ["真兽皮"]}}
|
|
],
|
|
"hard_blocks_nonempty": true
|
|
}
|
|
},
|
|
{
|
|
"name": "features-superset-still-matches-include",
|
|
"rules": [
|
|
{
|
|
"rule_key": "G-RULES-20-BODY-A-SHOULDER",
|
|
"category": "body_shape",
|
|
"priority": 90,
|
|
"confidence": 0.95,
|
|
"conditions": {
|
|
"body_shape": "A型",
|
|
"features": {"include": ["溜肩"]},
|
|
"goals": {"include": ["修饰溜肩"]}
|
|
},
|
|
"effects": {
|
|
"recommend": [
|
|
{"slot": "top", "attrs": {"shoulder": ["垫肩"], "sleeve": ["泡泡袖"]}}
|
|
],
|
|
"avoid": [{"slot": "top", "attrs": {"silhouette": ["修身"]}}],
|
|
"explanation": "溜肩需要用垫肩与泡泡袖在肩部建立结构感。"
|
|
}
|
|
}
|
|
],
|
|
"context": {
|
|
"body_shape": "A型",
|
|
"features": ["溜肩", "宽胯"],
|
|
"goals": ["修饰溜肩"]
|
|
},
|
|
"expect": {
|
|
"must_recommend": [
|
|
{"slot": "top", "attrs_include": {"shoulder": ["垫肩"]}}
|
|
],
|
|
"hard_blocks_nonempty": false
|
|
}
|
|
},
|
|
{
|
|
"name": "goals-partial-miss-blocks-rule",
|
|
"rules": [
|
|
{
|
|
"rule_key": "G-RULES-21-BODY-A-SHOULDER",
|
|
"category": "body_shape",
|
|
"priority": 90,
|
|
"confidence": 0.95,
|
|
"conditions": {
|
|
"body_shape": "A型",
|
|
"features": {"include": ["溜肩"]},
|
|
"goals": {"include": ["修饰溜肩"]}
|
|
},
|
|
"effects": {
|
|
"recommend": [
|
|
{"slot": "top", "attrs": {"shoulder": ["垫肩"], "sleeve": ["泡泡袖"]}}
|
|
],
|
|
"avoid": [{"slot": "top", "attrs": {"silhouette": ["修身"]}}],
|
|
"explanation": "溜肩需要用垫肩与泡泡袖在肩部建立结构感。"
|
|
}
|
|
}
|
|
],
|
|
"context": {
|
|
"body_shape": "A型",
|
|
"features": ["溜肩"],
|
|
"goals": ["显瘦"]
|
|
},
|
|
"expect": {
|
|
"forbidden_recommend": [
|
|
{"slot": "top", "attrs_include": {}}
|
|
],
|
|
"hard_blocks_nonempty": false
|
|
}
|
|
}
|
|
]
|