kiku-agent 1.3.1 → 1.3.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (119) hide show
  1. package/README.md +1 -1
  2. package/package.json +4 -12
  3. package/server/agent/eval/AGENTS.md +228 -0
  4. package/server/agent/eval/analyze.py +684 -0
  5. package/server/agent/eval/gates.json +15 -0
  6. package/server/agent/eval/modules/analysis/compare.js +198 -0
  7. package/server/agent/eval/modules/analysis/gates.js +72 -0
  8. package/server/agent/eval/modules/analysis/judge.js +70 -0
  9. package/server/agent/eval/modules/core/cli.js +453 -0
  10. package/server/agent/eval/modules/core/config.js +60 -0
  11. package/server/agent/eval/modules/core/store.js +236 -0
  12. package/server/agent/eval/modules/evaluation/cases.js +689 -0
  13. package/server/agent/eval/modules/evaluation/runner.js +298 -0
  14. package/server/agent/eval/modules/evaluation/scoring.js +351 -0
  15. package/server/agent/eval/modules/evaluation/worker.js +122 -0
  16. package/server/agent/eval/modules/reporting/benchmark.js +265 -0
  17. package/server/agent/eval/modules/reporting/benchmarkPng.js +487 -0
  18. package/server/agent/eval/modules/reporting/dashboard.js +1406 -0
  19. package/server/agent/eval/modules/server/evalApi.js +1099 -0
  20. package/server/agent/eval/modules/ui/evalUi.js +4796 -0
  21. package/server/agent/eval/modules/utils/smokes.js +119 -0
  22. package/server/agent/tests/agentBubbleSystem.test.js +65 -0
  23. package/server/agent/tests/agentFollowUps.test.js +127 -0
  24. package/server/agent/tests/apiRouter.test.js +108 -0
  25. package/server/agent/tests/architectureFixes.test.js +81 -0
  26. package/server/agent/tests/architectureRefactoring.test.js +194 -0
  27. package/server/agent/tests/autoResearch.test.js +64 -0
  28. package/server/agent/tests/bilibiliEmbed.test.js +251 -0
  29. package/server/agent/tests/catalogSync.test.js +130 -0
  30. package/server/agent/tests/citations.test.js +180 -0
  31. package/server/agent/tests/clarificationAnalytics.test.js +219 -0
  32. package/server/agent/tests/clarifyingQuestions.test.js +594 -0
  33. package/server/agent/tests/cliAutomation.test.js +121 -0
  34. package/server/agent/tests/cloudProviders.test.js +234 -0
  35. package/server/agent/tests/commandInput.test.js +24 -0
  36. package/server/agent/tests/commands.test.js +417 -0
  37. package/server/agent/tests/contextIntelligence.test.js +162 -0
  38. package/server/agent/tests/conversationSafety.test.js +53 -0
  39. package/server/agent/tests/decisionAndSearchEnhancements.test.js +135 -0
  40. package/server/agent/tests/dramaAnswerQuality.test.js +73 -0
  41. package/server/agent/tests/dynamicCatalogIngestion.test.js +285 -0
  42. package/server/agent/tests/dynamicRoutingAndSearch.test.js +92 -0
  43. package/server/agent/tests/edgeCasesScenarios.test.js +49 -0
  44. package/server/agent/tests/entertainmentMetrics.test.js +126 -0
  45. package/server/agent/tests/envBootstrap.test.js +87 -0
  46. package/server/agent/tests/envCommand.test.js +215 -0
  47. package/server/agent/tests/errorHandling.test.js +80 -0
  48. package/server/agent/tests/errors.test.js +13 -0
  49. package/server/agent/tests/evalAnalyze.test.js +54 -0
  50. package/server/agent/tests/evalCommand.test.js +54 -0
  51. package/server/agent/tests/evalCorpus.test.js +126 -0
  52. package/server/agent/tests/evalHarness.test.js +62 -0
  53. package/server/agent/tests/evalJudgeContext.test.js +38 -0
  54. package/server/agent/tests/evalMetrics.test.js +312 -0
  55. package/server/agent/tests/evalStore.test.js +190 -0
  56. package/server/agent/tests/evalStudio.test.js +179 -0
  57. package/server/agent/tests/feedbackLearning.test.js +186 -0
  58. package/server/agent/tests/firstRun.test.js +44 -0
  59. package/server/agent/tests/gemma4eOptimization.test.js +95 -0
  60. package/server/agent/tests/hardwareTiers.test.js +206 -0
  61. package/server/agent/tests/hybridWebSearch.test.js +192 -0
  62. package/server/agent/tests/judgeService.test.js +251 -0
  63. package/server/agent/tests/lanDiscovery.test.js +319 -0
  64. package/server/agent/tests/mcpClient.test.js +201 -0
  65. package/server/agent/tests/modelManager.test.js +109 -0
  66. package/server/agent/tests/multilingualScenarios.test.js +69 -0
  67. package/server/agent/tests/newCommands.test.js +347 -0
  68. package/server/agent/tests/newCommandsTui.test.js +141 -0
  69. package/server/agent/tests/newTools.test.js +113 -0
  70. package/server/agent/tests/newsIntelligence.test.js +178 -0
  71. package/server/agent/tests/nextGenArchitecture.test.js +99 -0
  72. package/server/agent/tests/offlineInput.test.js +217 -0
  73. package/server/agent/tests/packagingGuard.test.js +57 -0
  74. package/server/agent/tests/presentation.test.js +61 -0
  75. package/server/agent/tests/providerPersistence.test.js +39 -0
  76. package/server/agent/tests/queryBenchmarks.test.js +83 -0
  77. package/server/agent/tests/queryDetails.test.js +126 -0
  78. package/server/agent/tests/realWorldValidation.test.js +391 -0
  79. package/server/agent/tests/resilienceAndConcurrency.test.js +117 -0
  80. package/server/agent/tests/runtimeWatchdog.test.js +32 -0
  81. package/server/agent/tests/sanitizer.test.js +37 -0
  82. package/server/agent/tests/scenariosData.js +378 -0
  83. package/server/agent/tests/schemaRouting.test.js +54 -0
  84. package/server/agent/tests/securityAuditRemediation.test.js +214 -0
  85. package/server/agent/tests/securityHardening.test.js +146 -0
  86. package/server/agent/tests/securitySanitizer.test.js +38 -0
  87. package/server/agent/tests/sessionAndCopy.test.js +232 -0
  88. package/server/agent/tests/sidebarControls.test.js +101 -0
  89. package/server/agent/tests/statefulMemory.test.js +270 -0
  90. package/server/agent/tests/subagent.test.js +216 -0
  91. package/server/agent/tests/subagentProgress.test.js +109 -0
  92. package/server/agent/tests/subagentTextFallback.test.js +115 -0
  93. package/server/agent/tests/suggestions.test.js +199 -0
  94. package/server/agent/tests/suggestionsTui.test.js +251 -0
  95. package/server/agent/tests/telemetryAndProfiles.test.js +179 -0
  96. package/server/agent/tests/terminalImage.test.js +80 -0
  97. package/server/agent/tests/terminalMarkdown.test.js +166 -0
  98. package/server/agent/tests/terminalText.test.js +133 -0
  99. package/server/agent/tests/textProtocolLoop.test.js +126 -0
  100. package/server/agent/tests/textToolParsing.test.js +139 -0
  101. package/server/agent/tests/theme.test.js +26 -0
  102. package/server/agent/tests/toolRegistryParity.test.js +53 -0
  103. package/server/agent/tests/toolRoutingRegressions.test.js +119 -0
  104. package/server/agent/tests/tools.test.js +259 -0
  105. package/server/agent/tests/unifiedEndpoints.test.js +152 -0
  106. package/server/agent/tests/v110Features.test.js +262 -0
  107. package/server/agent/tests/versionBump.test.js +69 -0
  108. package/server/agent/tests/vramEstimator.test.js +520 -0
  109. package/server/agent/tests/webChatInspection.test.js +300 -0
  110. package/server/agent/tests/webChatMemory.test.js +112 -0
  111. package/server/agent/tests/webChatSecurity.test.js +169 -0
  112. package/server/agent/tests/webExtract.test.js +261 -0
  113. package/server/agent/tests/webSources.test.js +247 -0
  114. package/server/eval/judgeRubrics.js +110 -0
  115. package/server/eval/judgeService.js +290 -0
  116. package/server/eval/runBenchmark.js +182 -0
  117. package/server/mcp/examples/librechat.example.yaml +16 -0
  118. package/server/mcp/tests/connection.test.js +156 -0
  119. package/server/supabase_schema.sql +63 -0
@@ -0,0 +1,63 @@
1
+ CREATE TABLE IF NOT EXISTS public.api_keys (
2
+ id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
3
+ key_prefix VARCHAR(32) NOT NULL,
4
+ key_hash VARCHAR(64) UNIQUE NOT NULL,
5
+ tier VARCHAR(32) DEFAULT 'developer_vip',
6
+ rate_limit_per_min INT DEFAULT 1000,
7
+ is_active BOOLEAN DEFAULT TRUE,
8
+ created_at TIMESTAMPTZ DEFAULT NOW(),
9
+ last_used_at TIMESTAMPTZ,
10
+ expires_at TIMESTAMPTZ,
11
+ revoked_reason TEXT
12
+ );
13
+
14
+
15
+ CREATE TABLE IF NOT EXISTS public.quiz_sessions (
16
+ session_id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
17
+ challenge_token VARCHAR(64) UNIQUE NOT NULL,
18
+ is_completed BOOLEAN DEFAULT FALSE,
19
+ is_claimed BOOLEAN DEFAULT FALSE,
20
+ created_at TIMESTAMPTZ DEFAULT NOW(),
21
+ expires_at TIMESTAMPTZ DEFAULT (NOW() + INTERVAL '15 minutes')
22
+ );
23
+
24
+
25
+ CREATE TABLE IF NOT EXISTS public.api_request_logs (
26
+ id BIGSERIAL PRIMARY KEY,
27
+ ip_address VARCHAR(45) NOT NULL,
28
+ endpoint VARCHAR(255) NOT NULL,
29
+ method VARCHAR(10) NOT NULL,
30
+ status_code INT NOT NULL,
31
+ response_time_ms NUMERIC(8,2),
32
+ key_prefix VARCHAR(32),
33
+ created_at TIMESTAMPTZ DEFAULT NOW()
34
+ );
35
+
36
+
37
+ ALTER TABLE public.api_keys ENABLE ROW LEVEL SECURITY;
38
+ ALTER TABLE public.quiz_sessions ENABLE ROW LEVEL SECURITY;
39
+ ALTER TABLE public.api_request_logs ENABLE ROW LEVEL SECURITY;
40
+
41
+
42
+ DO $$
43
+ BEGIN
44
+ IF NOT EXISTS (SELECT 1 FROM pg_policies WHERE policyname = 'Service Role Access on api_keys') THEN
45
+ CREATE POLICY "Service Role Access on api_keys"
46
+ ON public.api_keys FOR ALL USING (auth.role() = 'service_role');
47
+ END IF;
48
+
49
+ IF NOT EXISTS (SELECT 1 FROM pg_policies WHERE policyname = 'Service Role Access on quiz_sessions') THEN
50
+ CREATE POLICY "Service Role Access on quiz_sessions"
51
+ ON public.quiz_sessions FOR ALL USING (auth.role() = 'service_role');
52
+ END IF;
53
+
54
+ IF NOT EXISTS (SELECT 1 FROM pg_policies WHERE policyname = 'Service Role Access on api_request_logs') THEN
55
+ CREATE POLICY "Service Role Access on api_request_logs"
56
+ ON public.api_request_logs FOR ALL USING (auth.role() = 'service_role');
57
+ END IF;
58
+ END $$;
59
+
60
+
61
+ CREATE INDEX IF NOT EXISTS idx_api_keys_hash ON public.api_keys (key_hash) WHERE is_active = TRUE;
62
+ CREATE INDEX IF NOT EXISTS idx_quiz_sessions_token ON public.quiz_sessions (challenge_token) WHERE is_claimed = FALSE;
63
+ CREATE INDEX IF NOT EXISTS idx_api_logs_ip_time ON public.api_request_logs (ip_address, created_at DESC);