lobster-full-engine-validation-20260701-131601.json 86 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871
  1. {
  2. "companyId": 338,
  3. "includeTravelChain": false,
  4. "includeTravelStress": false,
  5. "startedAt": "2026-07-01 13:16:01",
  6. "sections": {
  7. "engineHealth": {
  8. "passed": true,
  9. "health": {
  10. "companyId": 338,
  11. "healthy": true,
  12. "missingCore": [
  13. ],
  14. "missingOptional": [
  15. ],
  16. "passThreshold": 120
  17. },
  18. "message": "core beans wired"
  19. },
  20. "integrationTests": {
  21. "passed": true,
  22. "summary": "4/4 tests passed in 91635ms",
  23. "details": [
  24. "[PASS] NodeTypeService: All tests passed",
  25. "[PASS] DynamicNodeExecutor: All tests passed",
  26. "[PASS] MultiModelWorkflowGenerator: All tests passed",
  27. "[PASS] ModelConfigService: All tests passed"
  28. ],
  29. "executionTimeMs": 91635,
  30. "message": "4/4 tests passed in 91635ms"
  31. },
  32. "phase2Replay": {
  33. "passed": true,
  34. "verify": {
  35. "companyId": 338,
  36. "archiveTableExists": true,
  37. "hotIndexExists": true,
  38. "hotReplayRows": 82,
  39. "eventLogRows": 82,
  40. "archiveRows": 0,
  41. "status": "ok"
  42. },
  43. "message": "phase2 replay verify ok"
  44. },
  45. "pageLinkProbes": {
  46. "totalPages": 29,
  47. "requiredTotal": 15,
  48. "requiredPassed": 15,
  49. "optionalSkipped": 0,
  50. "failures": [
  51. ],
  52. "passed": true,
  53. "durationMs": 3020,
  54. "pages": [
  55. {
  56. "path": "/lobster/company-workflowLobster",
  57. "title": "Workflow templates",
  58. "probe": "templateList",
  59. "required": true,
  60. "passed": true,
  61. "status": "OK",
  62. "message": "templates=50"
  63. },
  64. {
  65. "path": "/lobster/workflow-execution",
  66. "title": "Workflow execution tasks",
  67. "probe": "instanceList",
  68. "required": true,
  69. "passed": true,
  70. "status": "OK",
  71. "message": "instances=649"
  72. },
  73. {
  74. "path": "/lobster/instance",
  75. "title": "Instance monitor",
  76. "probe": "instanceMonitor",
  77. "required": true,
  78. "passed": true,
  79. "status": "OK",
  80. "message": "monitor list ok, count=649"
  81. },
  82. {
  83. "path": "/lobster/prompt",
  84. "title": "Prompt management",
  85. "probe": "promptList",
  86. "required": true,
  87. "passed": true,
  88. "status": "OK",
  89. "message": "prompt rows=70"
  90. },
  91. {
  92. "path": "/lobster/sensitive-words",
  93. "title": "Sensitive words",
  94. "probe": "sensitiveWords",
  95. "required": true,
  96. "passed": true,
  97. "status": "OK",
  98. "message": "words=151"
  99. },
  100. {
  101. "path": "/lobster/forbidden-words",
  102. "title": "Forbidden words",
  103. "probe": "forbiddenWords",
  104. "required": false,
  105. "passed": true,
  106. "status": "OK",
  107. "message": "forbidden=32"
  108. },
  109. {
  110. "path": "/lobster/typo-words",
  111. "title": "Typo words",
  112. "probe": "typoWords",
  113. "required": false,
  114. "passed": true,
  115. "status": "OK",
  116. "message": "typo=3"
  117. },
  118. {
  119. "path": "/lobster/conversation-summary",
  120. "title": "Conversation summary",
  121. "probe": "conversationSummary",
  122. "required": true,
  123. "passed": true,
  124. "status": "OK",
  125. "message": "summaries=0"
  126. },
  127. {
  128. "path": "/lobster/profile-config",
  129. "title": "Profile config",
  130. "probe": "profileConfig",
  131. "required": false,
  132. "passed": true,
  133. "status": "OK",
  134. "message": "profile fields=43"
  135. },
  136. {
  137. "path": "/lobster/channel-config",
  138. "title": "Channel config",
  139. "probe": "channelTypes",
  140. "required": true,
  141. "passed": true,
  142. "status": "OK",
  143. "message": "channels=14"
  144. },
  145. {
  146. "path": "/lobster/channel-plugin",
  147. "title": "Channel plugins",
  148. "probe": "channelPlugins",
  149. "required": true,
  150. "passed": true,
  151. "status": "OK",
  152. "message": "plugins=3"
  153. },
  154. {
  155. "path": "/lobster/api-registry",
  156. "title": "API registry",
  157. "probe": "apiRegistry",
  158. "required": true,
  159. "passed": true,
  160. "status": "OK",
  161. "message": "apis=0"
  162. },
  163. {
  164. "path": "/lobster/sales-corpus",
  165. "title": "Sales corpus",
  166. "probe": "salesCorpus",
  167. "required": false,
  168. "passed": false,
  169. "status": "WARN",
  170. "message": "\r\n### Error querying database. Cause: java.sql.SQLSyntaxErrorException: Unknown column \u0027corpus_kind\u0027 in \u0027where clause\u0027\r\n### The error may exist in URL [jar:file:/D:/ylrz_saas_new/java/fs-saas-company/target/fs-saas-company.jar!/BOOT-INF/lib/fs-service-1.1.0.jar!/mapper/company/LobsterSalesCorpusMapper.xml]\r\n### The error may involve defaultParameterMap\r\n### The error occurred while setting parameters\r\n### SQL: select count(*) from lobster_sales_corpus where company_id = ? and (corpus_kind is null or corpus_kind = \u0027\u0027 or corpus_kind = \u0027sales_champion\u0027)\r\n### Cause: java.sql.SQLSyntaxErrorException: Unknown column \u0027corpus_kind\u0027 in \u0027where clause\u0027\n; bad SQL grammar []; nested exception is java.sql.SQLSyntaxErrorException: Unknown column \u0027corpus_kind\u0027 in \u0027where clause\u0027"
  171. },
  172. {
  173. "path": "/lobster/chat-aggregate",
  174. "title": "Chat aggregate",
  175. "probe": "chatAggregate",
  176. "required": false,
  177. "passed": true,
  178. "status": "OK",
  179. "message": "sessions=0"
  180. },
  181. {
  182. "path": "/lobster/industry-bootstrap",
  183. "title": "Industry bootstrap",
  184. "probe": "industryPacks",
  185. "required": true,
  186. "passed": true,
  187. "status": "OK",
  188. "message": "packs=3"
  189. },
  190. {
  191. "path": "/lobster/identity-config",
  192. "title": "External role config",
  193. "probe": "identityConfig",
  194. "required": false,
  195. "passed": true,
  196. "status": "OK",
  197. "message": "identity config loaded"
  198. },
  199. {
  200. "path": "/lobster/semantic-keywords",
  201. "title": "Semantic keywords",
  202. "probe": "semanticKeywords",
  203. "required": true,
  204. "passed": true,
  205. "status": "OK",
  206. "message": "keywords=0"
  207. },
  208. {
  209. "path": "/lobster/optimization",
  210. "title": "AI optimization audit",
  211. "probe": "optimization",
  212. "required": true,
  213. "passed": true,
  214. "status": "OK",
  215. "message": "optimization stats=5"
  216. },
  217. {
  218. "path": "/lobster/dynamic-impl",
  219. "title": "Dynamic node approval",
  220. "probe": "dynamicImpl",
  221. "required": true,
  222. "passed": true,
  223. "status": "OK",
  224. "message": "pending impls=0"
  225. },
  226. {
  227. "path": "/lobster/dashboard",
  228. "title": "Engine dashboard",
  229. "probe": "dashboard",
  230. "required": true,
  231. "passed": true,
  232. "status": "OK",
  233. "message": "dashboard keys=8"
  234. },
  235. {
  236. "path": "/lobster/token-stats",
  237. "title": "Token stats",
  238. "probe": "tokenStats",
  239. "required": false,
  240. "passed": true,
  241. "status": "OK",
  242. "message": "token summary loaded"
  243. },
  244. {
  245. "path": "/lobster/evolution",
  246. "title": "Evolution engine",
  247. "probe": "evolution",
  248. "required": true,
  249. "passed": true,
  250. "status": "OK",
  251. "message": "evolution metrics=6"
  252. },
  253. {
  254. "path": "/lobster/chat-test",
  255. "title": "Chat test",
  256. "probe": "chatTest",
  257. "required": false,
  258. "passed": true,
  259. "status": "OK",
  260. "message": "e2e test service ready"
  261. },
  262. {
  263. "path": "/lobster/ab-test",
  264. "title": "AB / GEPA optimization",
  265. "probe": "abTest",
  266. "required": false,
  267. "passed": true,
  268. "status": "OK",
  269. "message": "active ab tests=0"
  270. },
  271. {
  272. "path": "/lobster/profile",
  273. "title": "Customer profile hub",
  274. "probe": "userProfile",
  275. "required": false,
  276. "passed": true,
  277. "status": "OK",
  278. "message": "profiles=65, domain=true"
  279. },
  280. {
  281. "path": "/lobster/profile-domain",
  282. "title": "Unified profile domain",
  283. "probe": "profileDomain",
  284. "required": false,
  285. "passed": true,
  286. "status": "OK",
  287. "message": "profile domain ready, mode=async"
  288. },
  289. {
  290. "path": "/lobster/qdrant",
  291. "title": "Vector knowledge base",
  292. "probe": "qdrant",
  293. "required": false,
  294. "passed": true,
  295. "status": "OK",
  296. "message": "vectors=0"
  297. },
  298. {
  299. "path": "/lobster/global-stats",
  300. "title": "Global evolution stats",
  301. "probe": "globalStats",
  302. "required": false,
  303. "passed": true,
  304. "status": "OK",
  305. "message": "global metrics=6"
  306. },
  307. {
  308. "path": "/lobster/event-audit",
  309. "title": "Event node audit",
  310. "probe": "eventAudit",
  311. "required": false,
  312. "passed": true,
  313. "status": "OK",
  314. "message": "audits=0"
  315. }
  316. ]
  317. },
  318. "travelFullChain": {
  319. "passed": true,
  320. "skipped": true,
  321. "message": "includeTravelChain=false"
  322. },
  323. "profileDomain": {
  324. "basic": {
  325. "enabled": true,
  326. "projectionMode": "async",
  327. "searchMode": "db",
  328. "esEnabled": false,
  329. "mqConsumerEnabled": true,
  330. "missingBeans": [
  331. ],
  332. "beansOk": true,
  333. "simulationMode": "basic",
  334. "runtime": {
  335. "unifiedSearchTotal": 47,
  336. "unifiedSearchMode": "db",
  337. "searchTotal": 47,
  338. "searchMode": "db",
  339. "identityCount": 47,
  340. "orderStatsSample": 0,
  341. "qwContactSample": 0
  342. },
  343. "passed": true,
  344. "message": "profile domain ready"
  345. },
  346. "fullSimulation": {
  347. "enabled": true,
  348. "projectionMode": "async",
  349. "searchMode": "db",
  350. "esEnabled": false,
  351. "mqConsumerEnabled": true,
  352. "missingBeans": [
  353. ],
  354. "beansOk": true,
  355. "simulationMode": "full",
  356. "runtime": {
  357. "unifiedSearchTotal": 47,
  358. "unifiedSearchMode": "db",
  359. "searchTotal": 47,
  360. "searchMode": "db",
  361. "identityCount": 47,
  362. "orderStatsSample": 0,
  363. "qwContactSample": 0
  364. },
  365. "simulation": {
  366. "patchAdapter": true,
  367. "writePath": {
  368. "published": true,
  369. "readBack": true
  370. },
  371. "backfillLegacy": {
  372. "type": "legacy",
  373. "page": 1,
  374. "size": 5,
  375. "processed": 5,
  376. "published": 5
  377. },
  378. "backfillOrders": {
  379. "type": "order",
  380. "page": 1,
  381. "size": 5,
  382. "processed": 0,
  383. "published": 0
  384. },
  385. "backfillQwContacts": {
  386. "type": "qw_contact",
  387. "page": 1,
  388. "size": 5,
  389. "processed": 0,
  390. "published": 0
  391. },
  392. "backfillWxClients": {
  393. "type": "wx_contact",
  394. "page": 1,
  395. "size": 5,
  396. "processed": 0,
  397. "published": 0
  398. }
  399. },
  400. "passed": true,
  401. "message": "profile domain ready"
  402. },
  403. "sourceHooks": {
  404. "companyId": 338,
  405. "simulationMode": "source-hooks",
  406. "sources": [
  407. {
  408. "source": "wx_call",
  409. "eventCount": 1,
  410. "eventOk": true,
  411. "shardId": 18,
  412. "profileKey": "__val_src_wx_call__",
  413. "channelType": "WX",
  414. "sourceVersion": "val:wx_call:1782883057485",
  415. "readBack": true,
  416. "passed": true
  417. },
  418. {
  419. "source": "qw_voice",
  420. "eventCount": 1,
  421. "eventOk": true,
  422. "shardId": 3,
  423. "profileKey": "__val_src_qw_voice__",
  424. "channelType": "QW",
  425. "sourceVersion": "val:qw_voice:1782883057485",
  426. "readBack": true,
  427. "passed": true
  428. },
  429. {
  430. "source": "lobster_chat",
  431. "eventCount": 1,
  432. "eventOk": true,
  433. "shardId": 3,
  434. "profileKey": "__val_src_lobster_chat__",
  435. "channelType": "QW",
  436. "sourceVersion": "val:lobster_chat:1782883057485",
  437. "readBack": true,
  438. "passed": true
  439. },
  440. {
  441. "source": "crm_analyze",
  442. "eventCount": 1,
  443. "eventOk": true,
  444. "shardId": 18,
  445. "profileKey": "__val_src_crm_analyze__",
  446. "channelType": "QW",
  447. "sourceVersion": "val:crm_analyze:1782883057485",
  448. "readBack": true,
  449. "passed": true
  450. },
  451. {
  452. "source": "qw_ai_analyze",
  453. "eventCount": 1,
  454. "eventOk": true,
  455. "shardId": 11,
  456. "profileKey": "__val_src_qw_ai_analyze__",
  457. "channelType": "QW",
  458. "sourceVersion": "val:qw_ai_analyze:1782883057485",
  459. "readBack": true,
  460. "passed": true
  461. },
  462. {
  463. "source": "qw_contact",
  464. "eventCount": 1,
  465. "eventOk": true,
  466. "shardId": 14,
  467. "profileKey": "__val_src_qw_contact__",
  468. "channelType": "QW",
  469. "sourceVersion": "val:qw_contact:1782883057485",
  470. "readBack": true,
  471. "passed": true
  472. },
  473. {
  474. "source": "qw_tag",
  475. "eventCount": 1,
  476. "eventOk": true,
  477. "shardId": 27,
  478. "profileKey": "__val_src_qw_tag__",
  479. "channelType": "QW",
  480. "sourceVersion": "val:qw_tag:1782883057485",
  481. "readBack": true,
  482. "passed": true
  483. },
  484. {
  485. "source": "order",
  486. "eventCount": 1,
  487. "eventOk": true,
  488. "shardId": 29,
  489. "profileKey": "__val_src_order__",
  490. "channelType": "QW",
  491. "sourceVersion": "val:order:1782883057485",
  492. "readBack": true,
  493. "passed": true
  494. },
  495. {
  496. "source": "course_watch",
  497. "eventCount": 1,
  498. "eventOk": true,
  499. "shardId": 20,
  500. "profileKey": "__val_src_course_watch__",
  501. "channelType": "QW",
  502. "sourceVersion": "val:course_watch:1782883057485",
  503. "readBack": true,
  504. "passed": true
  505. },
  506. {
  507. "source": "live_watch",
  508. "variant": "meta",
  509. "eventCount": 1,
  510. "eventOk": true,
  511. "shardId": 15,
  512. "profileKey": "__val_src_live_watch__",
  513. "channelType": "QW",
  514. "sourceVersion": "val:live:1782883057485:meta",
  515. "readBack": true,
  516. "passed": true
  517. },
  518. {
  519. "source": "live_watch",
  520. "variant": "counter",
  521. "eventCount": 1,
  522. "eventOk": true,
  523. "shardId": 15,
  524. "profileKey": "__val_src_live_watch__",
  525. "channelType": "QW",
  526. "sourceVersion": "val:live:1782883057485:cnt:1",
  527. "readBack": true,
  528. "passed": true
  529. },
  530. {
  531. "source": "sop",
  532. "eventCount": 1,
  533. "eventOk": true,
  534. "shardId": 20,
  535. "profileKey": "__val_src_sop__",
  536. "channelType": "QW",
  537. "sourceVersion": "val:sop:1782883057485",
  538. "readBack": true,
  539. "passed": true
  540. }
  541. ],
  542. "passedCount": 12,
  543. "totalCount": 12,
  544. "passed": true,
  545. "message": "all source hooks simulated and verified"
  546. },
  547. "passed": true,
  548. "message": "profile domain all validations passed"
  549. },
  550. "semanticFull": {
  551. "companyId": 338,
  552. "sections": {
  553. "semanticKeywordContext": {
  554. "passed": true,
  555. "caseCount": 8,
  556. "message": "all semantic context cases passed"
  557. },
  558. "catalogValidation": {
  559. "companyId": 338,
  560. "categories": {
  561. "custom_keywords": {
  562. "keywordCount": 116,
  563. "totalCases": 232,
  564. "passedCases": 232,
  565. "passed": true,
  566. "failures": [
  567. ],
  568. "failureSampleCount": 0,
  569. "message": "all 232 checks passed for 116 words"
  570. },
  571. "positive_custom": {
  572. "keywordCount": 90,
  573. "totalCases": 180,
  574. "passedCases": 180,
  575. "passed": true,
  576. "failures": [
  577. ],
  578. "failureSampleCount": 0,
  579. "message": "all 180 checks passed for 90 words"
  580. },
  581. "negative_custom": {
  582. "keywordCount": 79,
  583. "totalCases": 158,
  584. "passedCases": 158,
  585. "passed": true,
  586. "failures": [
  587. ],
  588. "failureSampleCount": 0,
  589. "message": "all 158 checks passed for 79 words"
  590. },
  591. "soft_refusal": {
  592. "keywordCount": 59,
  593. "totalCases": 177,
  594. "passedCases": 137,
  595. "passed": false,
  596. "failures": [
  597. "soft_refusal:下个月 positive-block",
  598. "soft_refusal:以后再说 positive-block",
  599. "soft_refusal:暂时不需要 positive-block",
  600. "soft_refusal:过段时间 positive-block",
  601. "soft_refusal:下次吧 positive-block",
  602. "soft_refusal:改天 positive-block",
  603. "soft_refusal:回头再说 positive-block",
  604. "soft_refusal:再看看 positive-block",
  605. "soft_refusal:再考虑 positive-block",
  606. "soft_refusal:考虑考虑 positive-block",
  607. "soft_refusal:问问家人 positive-block",
  608. "soft_refusal:问问朋友 positive-block",
  609. "soft_refusal:需要审批 positive-block",
  610. "soft_refusal:现在不方便 positive-block",
  611. "soft_refusal:在开车 positive-block",
  612. "soft_refusal:稍后再说 positive-block",
  613. "soft_refusal:晚点再说 positive-block",
  614. "soft_refusal:有空再说 positive-block",
  615. "soft_refusal:待定 positive-block",
  616. "soft_refusal:再议 positive-block",
  617. "soft_refusal:看看再说 positive-block",
  618. "soft_refusal:想想再说 positive-block",
  619. "soft_refusal:再想想 positive-block",
  620. "soft_refusal:暂时算了 positive-block",
  621. "soft_refusal:先这样 positive-block",
  622. "soft_refusal:以后再聊 positive-block",
  623. "soft_refusal:以后再联系 positive-block",
  624. "soft_refusal:以后需要再说 positive-block",
  625. "soft_refusal:目前不需要 positive-block",
  626. "soft_refusal:近期不需要 positive-block",
  627. "soft_refusal:这段时间不需要 positive-block",
  628. "soft_refusal:先商量 positive-block",
  629. "soft_refusal:先考虑 positive-block",
  630. "soft_refusal:先观望 positive-block",
  631. "soft_refusal:等等再说 positive-block",
  632. "soft_refusal:看看效果再说 positive-block",
  633. "soft_refusal:看看评价再说 positive-block",
  634. "soft_refusal:最近没空 positive-block",
  635. "soft_refusal:暂时搁置 positive-block",
  636. "soft_refusal:回头再聊 positive-block"
  637. ],
  638. "failureSampleCount": 40,
  639. "message": "40 failed of 177"
  640. },
  641. "handoff_trigger": {
  642. "keywordCount": 81,
  643. "totalCases": 405,
  644. "passedCases": 405,
  645. "passed": true,
  646. "failures": [
  647. ],
  648. "failureSampleCount": 0,
  649. "message": "all 405 checks passed for 81 words"
  650. },
  651. "sarcasm": {
  652. "keywordCount": 65,
  653. "totalCases": 130,
  654. "passedCases": 130,
  655. "passed": true,
  656. "failures": [
  657. ],
  658. "failureSampleCount": 0,
  659. "message": "all 130 checks passed for 65 words"
  660. },
  661. "_combos": {
  662. "totalCases": 6,
  663. "passedCases": 6,
  664. "passed": true,
  665. "failures": [
  666. ],
  667. "message": "combo checks ok"
  668. }
  669. },
  670. "categoryCount": 6,
  671. "totalCases": 1288,
  672. "passedCases": 1248,
  673. "failedCases": 40,
  674. "failures": [
  675. "soft_refusal:下个月 positive-block",
  676. "soft_refusal:以后再说 positive-block",
  677. "soft_refusal:暂时不需要 positive-block",
  678. "soft_refusal:过段时间 positive-block",
  679. "soft_refusal:下次吧 positive-block",
  680. "soft_refusal:改天 positive-block",
  681. "soft_refusal:回头再说 positive-block",
  682. "soft_refusal:再看看 positive-block",
  683. "soft_refusal:再考虑 positive-block",
  684. "soft_refusal:考虑考虑 positive-block",
  685. "soft_refusal:问问家人 positive-block",
  686. "soft_refusal:问问朋友 positive-block",
  687. "soft_refusal:需要审批 positive-block",
  688. "soft_refusal:现在不方便 positive-block",
  689. "soft_refusal:在开车 positive-block",
  690. "soft_refusal:稍后再说 positive-block",
  691. "soft_refusal:晚点再说 positive-block",
  692. "soft_refusal:有空再说 positive-block",
  693. "soft_refusal:待定 positive-block",
  694. "soft_refusal:再议 positive-block",
  695. "soft_refusal:看看再说 positive-block",
  696. "soft_refusal:想想再说 positive-block",
  697. "soft_refusal:再想想 positive-block",
  698. "soft_refusal:暂时算了 positive-block",
  699. "soft_refusal:先这样 positive-block",
  700. "soft_refusal:以后再聊 positive-block",
  701. "soft_refusal:以后再联系 positive-block",
  702. "soft_refusal:以后需要再说 positive-block",
  703. "soft_refusal:目前不需要 positive-block",
  704. "soft_refusal:近期不需要 positive-block",
  705. "soft_refusal:这段时间不需要 positive-block",
  706. "soft_refusal:先商量 positive-block",
  707. "soft_refusal:先考虑 positive-block",
  708. "soft_refusal:先观望 positive-block",
  709. "soft_refusal:等等再说 positive-block",
  710. "soft_refusal:看看效果再说 positive-block",
  711. "soft_refusal:看看评价再说 positive-block",
  712. "soft_refusal:最近没空 positive-block",
  713. "soft_refusal:暂时搁置 positive-block",
  714. "soft_refusal:回头再聊 positive-block"
  715. ],
  716. "failureTruncated": false,
  717. "passed": false,
  718. "durationMs": 169969,
  719. "message": "40 failure(s), showing up to 40"
  720. },
  721. "replaceWord": {
  722. "layers": {
  723. "forbiddenReplace": {
  724. "raw": "这个产品稳赚不赔,绝对保本",
  725. "replaced": "这个产品有较好表现,相对稳健。",
  726. "passed": true
  727. },
  728. "typoReplace": {
  729. "raw": "您好,LOBSTER_TYPO_338咨询",
  730. "replaced": "您好,LOBSTER_TYPO_338咨询。",
  731. "passed": false
  732. },
  733. "compliancePipeline": {
  734. "out": "这个产品***,相对稳健。",
  735. "passed": true
  736. }
  737. },
  738. "passed": false,
  739. "message": "typo replace failed"
  740. }
  741. },
  742. "contextCases": [
  743. {
  744. "id": "soft_refusal_first",
  745. "input": "下个月再说 (empty ctx)",
  746. "expected": "L2 pause, not exclude",
  747. "actual": "L2_SOFT_REFUSAL exclude=false reason=soft_refusal",
  748. "passed": true
  749. },
  750. {
  751. "id": "soft_refusal_second",
  752. "input": "下个月再说 (_softRefusalCount=1)",
  753. "expected": "L4 exclude (repeated)",
  754. "actual": "L4_EXCLUDE exclude=true reason=repeated_soft_refusal",
  755. "passed": true
  756. },
  757. {
  758. "id": "handoff_first_neutral",
  759. "input": "了解一下人工 -\u003e keyword 人工 (neutral)",
  760. "expected": "no transfer, count=1",
  761. "actual": "takeover=false count=1 reason=Handoff trigger noted (session 1, awaiting confirmation): 人工",
  762. "passed": true
  763. },
  764. {
  765. "id": "handoff_second_confirm",
  766. "input": "转人工 (_handoffTriggerCount=1)",
  767. "expected": "transfer on 2nd hit",
  768. "actual": "takeover=true reason=Handoff trigger (session escalated x2): 人工",
  769. "passed": true
  770. },
  771. {
  772. "id": "negation_handoff",
  773. "input": "不转人工",
  774. "expected": "no handoff",
  775. "actual": "takeover=false",
  776. "passed": true
  777. },
  778. {
  779. "id": "negation_soft_refusal",
  780. "input": "别下个月",
  781. "expected": "no soft refusal",
  782. "actual": "null reason=null",
  783. "passed": true
  784. },
  785. {
  786. "id": "positive_sentiment_soft",
  787. "input": "很满意,价格多少 (positive ctx)",
  788. "expected": "no soft refusal",
  789. "actual": "null exclude=false",
  790. "passed": true
  791. },
  792. {
  793. "id": "positive_sentiment_handoff",
  794. "input": "很满意,价格多少 (positive ctx, no handoff keyword)",
  795. "expected": "no handoff misfire",
  796. "actual": "takeover=false reason=客户表达满意,仅询问价格,属于常规咨询类问题,无不满、着急情绪,也无复杂问题或敏感话题",
  797. "passed": true
  798. }
  799. ],
  800. "failures": [
  801. "catalog: 40 failure(s), showing up to 40",
  802. "replaceWord: typo replace failed"
  803. ],
  804. "passed": false,
  805. "durationMs": 189703,
  806. "totalCases": 1299,
  807. "passedCases": 1256,
  808. "message": "catalog: 40 failure(s), showing up to 40; replaceWord: typo replace failed",
  809. "catalogFailureSamples": [
  810. "soft_refusal:下个月 positive-block",
  811. "soft_refusal:以后再说 positive-block",
  812. "soft_refusal:暂时不需要 positive-block",
  813. "soft_refusal:过段时间 positive-block",
  814. "soft_refusal:下次吧 positive-block",
  815. "soft_refusal:改天 positive-block",
  816. "soft_refusal:回头再说 positive-block",
  817. "soft_refusal:再看看 positive-block",
  818. "soft_refusal:再考虑 positive-block",
  819. "soft_refusal:考虑考虑 positive-block",
  820. "soft_refusal:问问家人 positive-block",
  821. "soft_refusal:问问朋友 positive-block",
  822. "soft_refusal:需要审批 positive-block",
  823. "soft_refusal:现在不方便 positive-block",
  824. "soft_refusal:在开车 positive-block",
  825. "soft_refusal:稍后再说 positive-block",
  826. "soft_refusal:晚点再说 positive-block",
  827. "soft_refusal:有空再说 positive-block",
  828. "soft_refusal:待定 positive-block",
  829. "soft_refusal:再议 positive-block",
  830. "soft_refusal:看看再说 positive-block",
  831. "soft_refusal:想想再说 positive-block",
  832. "soft_refusal:再想想 positive-block",
  833. "soft_refusal:暂时算了 positive-block",
  834. "soft_refusal:先这样 positive-block",
  835. "soft_refusal:以后再聊 positive-block",
  836. "soft_refusal:以后再联系 positive-block",
  837. "soft_refusal:以后需要再说 positive-block",
  838. "soft_refusal:目前不需要 positive-block",
  839. "soft_refusal:近期不需要 positive-block",
  840. "soft_refusal:这段时间不需要 positive-block",
  841. "soft_refusal:先商量 positive-block",
  842. "soft_refusal:先考虑 positive-block",
  843. "soft_refusal:先观望 positive-block",
  844. "soft_refusal:等等再说 positive-block",
  845. "soft_refusal:看看效果再说 positive-block",
  846. "soft_refusal:看看评价再说 positive-block",
  847. "soft_refusal:最近没空 positive-block",
  848. "soft_refusal:暂时搁置 positive-block",
  849. "soft_refusal:回头再聊 positive-block"
  850. ]
  851. }
  852. },
  853. "failures": [
  854. "semanticFull: catalog: 40 failure(s), showing up to 40"
  855. ],
  856. "passed": false,
  857. "durationMs": 287486,
  858. "pageCount": 29,
  859. "requiredPagesPassed": "15/15"
  860. }