kiku-agent 1.3.0 → 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.
- package/README.md +7 -7
- package/package.json +4 -7
- package/server/agent/agentCore.js +2 -2
- package/server/agent/catalogEntityResolver.js +8 -0
- package/server/agent/cli.js +4 -0
- package/server/agent/eval/AGENTS.md +228 -0
- package/server/agent/eval/analyze.py +684 -0
- package/server/agent/eval/gates.json +15 -0
- package/server/agent/eval/modules/analysis/compare.js +198 -0
- package/server/agent/eval/modules/analysis/gates.js +72 -0
- package/server/agent/eval/modules/analysis/judge.js +70 -0
- package/server/agent/eval/modules/core/cli.js +453 -0
- package/server/agent/eval/modules/core/config.js +60 -0
- package/server/agent/eval/modules/core/store.js +236 -0
- package/server/agent/eval/modules/evaluation/cases.js +689 -0
- package/server/agent/eval/modules/evaluation/runner.js +298 -0
- package/server/agent/eval/modules/evaluation/scoring.js +351 -0
- package/server/agent/eval/modules/evaluation/worker.js +122 -0
- package/server/agent/eval/modules/reporting/benchmark.js +265 -0
- package/server/agent/eval/modules/reporting/benchmarkPng.js +487 -0
- package/server/agent/eval/modules/reporting/dashboard.js +1406 -0
- package/server/agent/eval/modules/server/evalApi.js +1099 -0
- package/server/agent/eval/modules/ui/evalUi.js +4796 -0
- package/server/agent/eval/modules/utils/smokes.js +119 -0
- package/server/agent/ink/App.jsx +348 -0
- package/server/agent/ink/Panel.jsx +54 -0
- package/server/agent/ink/PromptInput.jsx +321 -0
- package/server/agent/ink/TaskPlanPanel.jsx +88 -0
- package/server/agent/ink/ThinkingPanel.jsx +68 -0
- package/server/agent/ink/ToolResult.jsx +133 -0
- package/server/agent/ink/main.jsx +195 -0
- package/server/agent/ink/useEventBus.js +218 -0
- package/server/agent/memory/contextAllocator.js +214 -0
- package/server/agent/memory/hierarchicalStore.js +523 -0
- package/server/agent/memory/reflectionWorker.js +110 -0
- package/server/agent/prompts.js +1 -1
- package/server/agent/telemetry/hardwareTiers.js +332 -0
- package/server/agent/telemetry/runtimeWatchdog.js +66 -0
- package/server/agent/telemetry/techPowerUpClient.js +682 -0
- package/server/agent/telemetry/techpowerup-mcp.json +22 -0
- package/server/agent/tests/agentBubbleSystem.test.js +65 -0
- package/server/agent/tests/agentFollowUps.test.js +127 -0
- package/server/agent/tests/apiRouter.test.js +108 -0
- package/server/agent/tests/architectureFixes.test.js +81 -0
- package/server/agent/tests/architectureRefactoring.test.js +194 -0
- package/server/agent/tests/autoResearch.test.js +64 -0
- package/server/agent/tests/bilibiliEmbed.test.js +251 -0
- package/server/agent/tests/catalogSync.test.js +130 -0
- package/server/agent/tests/citations.test.js +180 -0
- package/server/agent/tests/clarificationAnalytics.test.js +219 -0
- package/server/agent/tests/clarifyingQuestions.test.js +594 -0
- package/server/agent/tests/cliAutomation.test.js +121 -0
- package/server/agent/tests/cloudProviders.test.js +234 -0
- package/server/agent/tests/commandInput.test.js +24 -0
- package/server/agent/tests/commands.test.js +417 -0
- package/server/agent/tests/contextIntelligence.test.js +162 -0
- package/server/agent/tests/conversationSafety.test.js +53 -0
- package/server/agent/tests/decisionAndSearchEnhancements.test.js +135 -0
- package/server/agent/tests/dramaAnswerQuality.test.js +73 -0
- package/server/agent/tests/dynamicCatalogIngestion.test.js +285 -0
- package/server/agent/tests/dynamicRoutingAndSearch.test.js +92 -0
- package/server/agent/tests/edgeCasesScenarios.test.js +49 -0
- package/server/agent/tests/entertainmentMetrics.test.js +126 -0
- package/server/agent/tests/envBootstrap.test.js +87 -0
- package/server/agent/tests/envCommand.test.js +215 -0
- package/server/agent/tests/errorHandling.test.js +80 -0
- package/server/agent/tests/errors.test.js +13 -0
- package/server/agent/tests/evalAnalyze.test.js +54 -0
- package/server/agent/tests/evalCommand.test.js +54 -0
- package/server/agent/tests/evalCorpus.test.js +126 -0
- package/server/agent/tests/evalHarness.test.js +62 -0
- package/server/agent/tests/evalJudgeContext.test.js +38 -0
- package/server/agent/tests/evalMetrics.test.js +312 -0
- package/server/agent/tests/evalStore.test.js +190 -0
- package/server/agent/tests/evalStudio.test.js +179 -0
- package/server/agent/tests/feedbackLearning.test.js +186 -0
- package/server/agent/tests/firstRun.test.js +44 -0
- package/server/agent/tests/gemma4eOptimization.test.js +95 -0
- package/server/agent/tests/hardwareTiers.test.js +206 -0
- package/server/agent/tests/hybridWebSearch.test.js +192 -0
- package/server/agent/tests/judgeService.test.js +251 -0
- package/server/agent/tests/lanDiscovery.test.js +319 -0
- package/server/agent/tests/mcpClient.test.js +201 -0
- package/server/agent/tests/modelManager.test.js +109 -0
- package/server/agent/tests/multilingualScenarios.test.js +69 -0
- package/server/agent/tests/newCommands.test.js +347 -0
- package/server/agent/tests/newCommandsTui.test.js +141 -0
- package/server/agent/tests/newTools.test.js +113 -0
- package/server/agent/tests/newsIntelligence.test.js +178 -0
- package/server/agent/tests/nextGenArchitecture.test.js +99 -0
- package/server/agent/tests/offlineInput.test.js +217 -0
- package/server/agent/tests/packagingGuard.test.js +57 -0
- package/server/agent/tests/presentation.test.js +61 -0
- package/server/agent/tests/providerPersistence.test.js +39 -0
- package/server/agent/tests/queryBenchmarks.test.js +83 -0
- package/server/agent/tests/queryDetails.test.js +126 -0
- package/server/agent/tests/realWorldValidation.test.js +391 -0
- package/server/agent/tests/resilienceAndConcurrency.test.js +117 -0
- package/server/agent/tests/runtimeWatchdog.test.js +32 -0
- package/server/agent/tests/sanitizer.test.js +37 -0
- package/server/agent/tests/scenariosData.js +378 -0
- package/server/agent/tests/schemaRouting.test.js +54 -0
- package/server/agent/tests/securityAuditRemediation.test.js +214 -0
- package/server/agent/tests/securityHardening.test.js +146 -0
- package/server/agent/tests/securitySanitizer.test.js +38 -0
- package/server/agent/tests/sessionAndCopy.test.js +232 -0
- package/server/agent/tests/sidebarControls.test.js +101 -0
- package/server/agent/tests/statefulMemory.test.js +270 -0
- package/server/agent/tests/subagent.test.js +216 -0
- package/server/agent/tests/subagentProgress.test.js +109 -0
- package/server/agent/tests/subagentTextFallback.test.js +115 -0
- package/server/agent/tests/suggestions.test.js +199 -0
- package/server/agent/tests/suggestionsTui.test.js +251 -0
- package/server/agent/tests/telemetryAndProfiles.test.js +179 -0
- package/server/agent/tests/terminalImage.test.js +80 -0
- package/server/agent/tests/terminalMarkdown.test.js +166 -0
- package/server/agent/tests/terminalText.test.js +133 -0
- package/server/agent/tests/textProtocolLoop.test.js +126 -0
- package/server/agent/tests/textToolParsing.test.js +139 -0
- package/server/agent/tests/theme.test.js +26 -0
- package/server/agent/tests/toolRegistryParity.test.js +53 -0
- package/server/agent/tests/toolRoutingRegressions.test.js +119 -0
- package/server/agent/tests/tools.test.js +259 -0
- package/server/agent/tests/unifiedEndpoints.test.js +152 -0
- package/server/agent/tests/v110Features.test.js +262 -0
- package/server/agent/tests/versionBump.test.js +69 -0
- package/server/agent/tests/vramEstimator.test.js +520 -0
- package/server/agent/tests/webChatInspection.test.js +300 -0
- package/server/agent/tests/webChatMemory.test.js +112 -0
- package/server/agent/tests/webChatSecurity.test.js +169 -0
- package/server/agent/tests/webExtract.test.js +261 -0
- package/server/agent/tests/webSources.test.js +247 -0
- package/server/agent/websearch/adapters/duckduckgo.js +97 -0
- package/server/agent/websearch/adapters/jina.js +77 -0
- package/server/agent/websearch/adapters/searxng.js +57 -0
- package/server/agent/websearch/core/canonical.js +89 -0
- package/server/agent/websearch/core/fusion.js +81 -0
- package/server/agent/websearch/core/types.js +29 -0
- package/server/agent/websearch/extract.js +605 -0
- package/server/agent/websearch/index.js +43 -0
- package/server/agent/websearch/orchestrator.js +266 -0
- package/server/agent/websearch/resilience/breaker.js +97 -0
- package/server/agent/websearch/resilience/cache.js +59 -0
- package/server/agent/websearch/resilience/limiter.js +93 -0
- package/server/agent/websearch/security/filter.js +36 -0
- package/server/agent/websearch/security/ssrf.js +289 -0
- package/server/agent/websearch/telemetry.js +71 -0
- package/server/apiRouter.js +7 -11
- package/server/eval/judgeRubrics.js +110 -0
- package/server/eval/judgeService.js +290 -0
- package/server/eval/runBenchmark.js +182 -0
- package/server/mcp/examples/librechat.example.yaml +16 -0
- package/server/mcp/tests/connection.test.js +156 -0
- package/server/routes/agent.js +55 -0
- package/server/supabase_schema.sql +63 -0
|
@@ -0,0 +1,219 @@
|
|
|
1
|
+
import { describe, it, beforeEach } from 'node:test';
|
|
2
|
+
import assert from 'node:assert/strict';
|
|
3
|
+
import { ClarificationAnalytics, ClarificationConfig, formatAnalyticsForCLI, formatConfigForCLI } from '../clarificationAnalytics.js';
|
|
4
|
+
import { existsSync, unlinkSync, mkdirSync } from 'node:fs';
|
|
5
|
+
import { join } from 'node:path';
|
|
6
|
+
|
|
7
|
+
const TEST_DIR = join(process.cwd(), '.kiku_test_analytics');
|
|
8
|
+
const TEST_ANALYTICS_PATH = join(TEST_DIR, 'test_analytics.json');
|
|
9
|
+
const TEST_CONFIG_PATH = join(TEST_DIR, 'test_config.json');
|
|
10
|
+
|
|
11
|
+
beforeEach(() => {
|
|
12
|
+
|
|
13
|
+
try {
|
|
14
|
+
if (existsSync(TEST_ANALYTICS_PATH)) unlinkSync(TEST_ANALYTICS_PATH);
|
|
15
|
+
if (existsSync(TEST_CONFIG_PATH)) unlinkSync(TEST_CONFIG_PATH);
|
|
16
|
+
} catch {}
|
|
17
|
+
});
|
|
18
|
+
|
|
19
|
+
describe('ClarificationAnalytics', () => {
|
|
20
|
+
it('initializes with default stats', () => {
|
|
21
|
+
const analytics = new ClarificationAnalytics({ storagePath: TEST_ANALYTICS_PATH });
|
|
22
|
+
assert.equal(analytics.stats.totalClarifications, 0);
|
|
23
|
+
assert.equal(analytics.stats.totalSkipped, 0);
|
|
24
|
+
assert.equal(analytics.stats.totalTimedOut, 0);
|
|
25
|
+
});
|
|
26
|
+
|
|
27
|
+
it('records clarification start', () => {
|
|
28
|
+
const analytics = new ClarificationAnalytics({ storagePath: TEST_ANALYTICS_PATH });
|
|
29
|
+
const questions = [
|
|
30
|
+
{ category: 'timeframe', question: 'When?', options: ['2026', '2025'] },
|
|
31
|
+
];
|
|
32
|
+
|
|
33
|
+
const session = analytics.recordClarificationStart('q_test_1', questions, 0.45);
|
|
34
|
+
assert.equal(session.queryId, 'q_test_1');
|
|
35
|
+
assert.equal(session.totalQuestions, 1);
|
|
36
|
+
assert.equal(analytics.stats.totalClarifications, 1);
|
|
37
|
+
});
|
|
38
|
+
|
|
39
|
+
it('records clarification answer', () => {
|
|
40
|
+
const analytics = new ClarificationAnalytics({ storagePath: TEST_ANALYTICS_PATH });
|
|
41
|
+
const questions = [
|
|
42
|
+
{ category: 'timeframe', question: 'When?', options: ['2026', '2025'] },
|
|
43
|
+
];
|
|
44
|
+
|
|
45
|
+
analytics.recordClarificationStart('q_test_1', questions, 0.45);
|
|
46
|
+
analytics.recordClarificationAnswer('q_test_1', { timeframe: '2026' }, 1, 2500);
|
|
47
|
+
|
|
48
|
+
const session = analytics.stats.recentSessions.find(s => s.queryId === 'q_test_1');
|
|
49
|
+
assert.equal(session.answered, true);
|
|
50
|
+
assert.equal(session.answerSummary.timeframe, '2026');
|
|
51
|
+
assert.equal(analytics.stats.categoryStats.timeframe.answered, 1);
|
|
52
|
+
});
|
|
53
|
+
|
|
54
|
+
it('records clarification skip', () => {
|
|
55
|
+
const analytics = new ClarificationAnalytics({ storagePath: TEST_ANALYTICS_PATH });
|
|
56
|
+
const questions = [
|
|
57
|
+
{ category: 'timeframe', question: 'When?', options: ['2026', '2025'] },
|
|
58
|
+
];
|
|
59
|
+
|
|
60
|
+
analytics.recordClarificationStart('q_test_1', questions, 0.45);
|
|
61
|
+
analytics.recordClarificationSkipped('q_test_1');
|
|
62
|
+
|
|
63
|
+
assert.equal(analytics.stats.totalSkipped, 1);
|
|
64
|
+
const session = analytics.stats.recentSessions.find(s => s.queryId === 'q_test_1');
|
|
65
|
+
assert.equal(session.skipped, true);
|
|
66
|
+
});
|
|
67
|
+
|
|
68
|
+
it('records clarification timeout', () => {
|
|
69
|
+
const analytics = new ClarificationAnalytics({ storagePath: TEST_ANALYTICS_PATH });
|
|
70
|
+
const questions = [
|
|
71
|
+
{ category: 'timeframe', question: 'When?', options: ['2026', '2025'] },
|
|
72
|
+
];
|
|
73
|
+
|
|
74
|
+
analytics.recordClarificationStart('q_test_1', questions, 0.45);
|
|
75
|
+
analytics.recordClarificationTimeout('q_test_1');
|
|
76
|
+
|
|
77
|
+
assert.equal(analytics.stats.totalTimedOut, 1);
|
|
78
|
+
const session = analytics.stats.recentSessions.find(s => s.queryId === 'q_test_1');
|
|
79
|
+
assert.equal(session.timedOut, true);
|
|
80
|
+
});
|
|
81
|
+
|
|
82
|
+
it('gets analytics summary', () => {
|
|
83
|
+
const analytics = new ClarificationAnalytics({ storagePath: TEST_ANALYTICS_PATH });
|
|
84
|
+
const questions = [
|
|
85
|
+
{ category: 'timeframe', question: 'When?', options: ['2026', '2025'] },
|
|
86
|
+
];
|
|
87
|
+
|
|
88
|
+
analytics.recordClarificationStart('q_test_1', questions, 0.45);
|
|
89
|
+
analytics.recordClarificationAnswer('q_test_1', { timeframe: '2026' }, 1, 2500);
|
|
90
|
+
|
|
91
|
+
const summary = analytics.getAnalytics({ days: 7 });
|
|
92
|
+
assert.ok(summary.summary);
|
|
93
|
+
assert.equal(summary.summary.totalClarifications, 1);
|
|
94
|
+
assert.ok(summary.period);
|
|
95
|
+
assert.ok(summary.categories);
|
|
96
|
+
});
|
|
97
|
+
|
|
98
|
+
it('gets category effectiveness', () => {
|
|
99
|
+
const analytics = new ClarificationAnalytics({ storagePath: TEST_ANALYTICS_PATH });
|
|
100
|
+
const questions = [
|
|
101
|
+
{ category: 'timeframe', question: 'When?', options: ['2026', '2025'] },
|
|
102
|
+
];
|
|
103
|
+
|
|
104
|
+
analytics.recordClarificationStart('q_test_1', questions, 0.45);
|
|
105
|
+
analytics.recordClarificationAnswer('q_test_1', { timeframe: '2026' }, 1, 2000);
|
|
106
|
+
|
|
107
|
+
const effectiveness = analytics.getCategoryEffectiveness('timeframe');
|
|
108
|
+
assert.ok(effectiveness >= 0 && effectiveness <= 100);
|
|
109
|
+
});
|
|
110
|
+
|
|
111
|
+
it('gets top categories', () => {
|
|
112
|
+
const analytics = new ClarificationAnalytics({ storagePath: TEST_ANALYTICS_PATH });
|
|
113
|
+
|
|
114
|
+
analytics.recordClarificationStart('q_1', [{ category: 'timeframe', question: 'When?', options: [] }], 0.5);
|
|
115
|
+
analytics.recordClarificationStart('q_2', [{ category: 'scope', question: 'How much?', options: [] }], 0.5);
|
|
116
|
+
|
|
117
|
+
const top = analytics.getTopCategories(5);
|
|
118
|
+
assert.ok(Array.isArray(top));
|
|
119
|
+
assert.ok(top.length <= 5);
|
|
120
|
+
});
|
|
121
|
+
});
|
|
122
|
+
|
|
123
|
+
describe('ClarificationConfig', () => {
|
|
124
|
+
it('initializes with default config', () => {
|
|
125
|
+
const config = new ClarificationConfig({ storagePath: TEST_CONFIG_PATH });
|
|
126
|
+
const cfg = config.getConfig();
|
|
127
|
+
assert.equal(cfg.enabled, true);
|
|
128
|
+
assert.equal(cfg.confidenceThreshold, 0.65);
|
|
129
|
+
assert.equal(cfg.maxRounds, 2);
|
|
130
|
+
assert.equal(cfg.timeoutMs, 30000);
|
|
131
|
+
});
|
|
132
|
+
|
|
133
|
+
it('updates config', () => {
|
|
134
|
+
const config = new ClarificationConfig({ storagePath: TEST_CONFIG_PATH });
|
|
135
|
+
const newConfig = config.updateConfig({ confidenceThreshold: 0.8 });
|
|
136
|
+
assert.equal(newConfig.confidenceThreshold, 0.8);
|
|
137
|
+
});
|
|
138
|
+
|
|
139
|
+
it('validates confidence threshold', () => {
|
|
140
|
+
const config = new ClarificationConfig({ storagePath: TEST_CONFIG_PATH });
|
|
141
|
+
assert.throws(() => {
|
|
142
|
+
config.updateConfig({ confidenceThreshold: 1.5 });
|
|
143
|
+
});
|
|
144
|
+
assert.throws(() => {
|
|
145
|
+
config.updateConfig({ confidenceThreshold: -0.1 });
|
|
146
|
+
});
|
|
147
|
+
});
|
|
148
|
+
|
|
149
|
+
it('validates maxRounds', () => {
|
|
150
|
+
const config = new ClarificationConfig({ storagePath: TEST_CONFIG_PATH });
|
|
151
|
+
assert.throws(() => {
|
|
152
|
+
config.updateConfig({ maxRounds: 10 });
|
|
153
|
+
});
|
|
154
|
+
assert.throws(() => {
|
|
155
|
+
config.updateConfig({ maxRounds: 0 });
|
|
156
|
+
});
|
|
157
|
+
});
|
|
158
|
+
|
|
159
|
+
it('resets to defaults', () => {
|
|
160
|
+
const config = new ClarificationConfig({ storagePath: TEST_CONFIG_PATH });
|
|
161
|
+
config.updateConfig({ confidenceThreshold: 0.9 });
|
|
162
|
+
const resetConfig = config.reset();
|
|
163
|
+
assert.equal(resetConfig.confidenceThreshold, 0.65);
|
|
164
|
+
});
|
|
165
|
+
|
|
166
|
+
it('gets and sets individual values', () => {
|
|
167
|
+
const config = new ClarificationConfig({ storagePath: TEST_CONFIG_PATH });
|
|
168
|
+
config.set('enabled', false);
|
|
169
|
+
assert.equal(config.get('enabled'), false);
|
|
170
|
+
});
|
|
171
|
+
});
|
|
172
|
+
|
|
173
|
+
describe('formatAnalyticsForCLI', () => {
|
|
174
|
+
it('formats analytics for display', () => {
|
|
175
|
+
const analytics = {
|
|
176
|
+
summary: {
|
|
177
|
+
totalClarifications: 10,
|
|
178
|
+
totalAnswered: 8,
|
|
179
|
+
totalSkipped: 2,
|
|
180
|
+
totalTimedOut: 0,
|
|
181
|
+
overallSkipRate: '20%',
|
|
182
|
+
avgRoundsPerSession: 1.2,
|
|
183
|
+
},
|
|
184
|
+
period: {
|
|
185
|
+
days: 7,
|
|
186
|
+
asked: 5,
|
|
187
|
+
answered: 4,
|
|
188
|
+
skipped: 1,
|
|
189
|
+
},
|
|
190
|
+
categories: {
|
|
191
|
+
timeframe: { asked: 5, answered: 4, skipRate: '20%' },
|
|
192
|
+
},
|
|
193
|
+
};
|
|
194
|
+
|
|
195
|
+
const result = formatAnalyticsForCLI(analytics, { gold: '', reset: '', bold: '', white: '', dim: '', green: '', yellow: '', red: '' });
|
|
196
|
+
assert.ok(result.includes('Clarification Analytics'));
|
|
197
|
+
assert.ok(result.includes('10'));
|
|
198
|
+
assert.ok(result.includes('timeframe'));
|
|
199
|
+
});
|
|
200
|
+
});
|
|
201
|
+
|
|
202
|
+
describe('formatConfigForCLI', () => {
|
|
203
|
+
it('formats config for display', () => {
|
|
204
|
+
const config = {
|
|
205
|
+
enabled: true,
|
|
206
|
+
confidenceThreshold: 0.65,
|
|
207
|
+
maxRounds: 2,
|
|
208
|
+
timeoutMs: 30000,
|
|
209
|
+
preferLLMQuestions: true,
|
|
210
|
+
};
|
|
211
|
+
|
|
212
|
+
const result = formatConfigForCLI(config, { gold: '', reset: '', bold: '', white: '', dim: '', green: '', yellow: '' });
|
|
213
|
+
assert.ok(result.includes('Clarification Settings'));
|
|
214
|
+
assert.ok(result.includes('65%'));
|
|
215
|
+
assert.ok(result.includes('2'));
|
|
216
|
+
});
|
|
217
|
+
});
|
|
218
|
+
|
|
219
|
+
console.log('✅ All clarification analytics tests passed');
|