promptspeak-mcp-server 0.1.0

package/dist/recon/templates/types.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"types.js","sourceRoot":"","sources":["../../../src/recon/templates/types.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;GAUG;AAyLH;;GAEG;AACH,MAAM,UAAU,gBAAgB,CAC9B,QAAgB,EAChB,MAAuB;IAEvB,IAAI,IAAI,GAAG,QAAQ,CAAC;IAEpB,IAAI,MAAM,EAAE,gBAAgB,EAAE,CAAC;QAC7B,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,WAAW,EAAE,MAAM,CAAC,gBAAgB,CAAC,CAAC;IAC5D,CAAC;IAED,IAAI,MAAM,EAAE,MAAM,EAAE,CAAC;QACnB,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,UAAU,EAAE,IAAI,MAAM,CAAC,MAAM,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC;IAClE,CAAC;IAED,IAAI,MAAM,EAAE,UAAU,EAAE,CAAC;QACvB,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,QAAQ,EAAE,MAAM,CAAC,UAAU,CAAC,CAAC;IACnD,CAAC;IAED,IAAI,MAAM,EAAE,eAAe,EAAE,CAAC;QAC5B,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,aAAa,EAAE,MAAM,CAAC,eAAe,CAAC,CAAC;IAC7D,CAAC;IAED,OAAO,IAAI,CAAC;AACd,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,eAAe,CAC7B,aAAyB,EACzB,SAA+B;IAE/B,OAAO;QACL,GAAG,aAAa;QAChB,GAAG,SAAS;KACb,CAAC;AACJ,CAAC"}

package/dist/recon/testing/index.d.ts

@@ -0,0 +1,43 @@
+/**
+ * ═══════════════════════════════════════════════════════════════════════════════
+ * RECON TESTING INFRASTRUCTURE
+ * ═══════════════════════════════════════════════════════════════════════════════
+ *
+ * Testing infrastructure for real-world recon mission testing.
+ * Provides mock chatbots, scenario runners, and metrics collection.
+ *
+ * Components:
+ * - **MockChatbot**: Simulates AI customer service agents with configurable personalities
+ * - **ScenarioRunner**: Automates end-to-end scenario testing
+ * - **TestScenarios**: Pre-built scenarios for common testing needs
+ * - **MetricsCollector**: Aggregates and reports test metrics
+ *
+ * Usage:
+ * ```typescript
+ * import {
+ *   MockChatbot,
+ *   ScenarioRunner,
+ *   SCENARIOS,
+ *   MetricsCollector,
+ * } from './testing';
+ *
+ * // Create a mock chatbot
+ * const chatbot = new MockChatbot({ personality: 'resistant' });
+ *
+ * // Run a scenario
+ * const runner = new ScenarioRunner();
+ * const result = await runner.run(symbol, chatbot, { maxTurns: 20 });
+ *
+ * // Collect metrics
+ * const collector = new MetricsCollector();
+ * collector.recordScenarioResult(result);
+ * console.log(collector.generateReport());
+ * ```
+ *
+ * ═══════════════════════════════════════════════════════════════════════════════
+ */
+export { MockChatbot, createMockChatbot, type ChatbotPersonality, type ChatbotConfig, type ChatbotState, type ChatbotTactic, type ChatbotResponse, } from './mock-chatbot';
+export { ScenarioRunner, createScenarioRunner, type ScenarioRunnerConfig, type ScenarioResult, type TurnRecord, type ScenarioStatus, } from './scenario-runner';
+export { SCENARIOS, createScenario, createCustomScenario, createTestBatch, getScenariosByTag, happyPathScenario, resistantAgentScenario, manipulativeAgentScenario, detectionTestScenario, type TestScenarioDefinition, type ScenarioExpectation, } from './test-scenarios';
+export { MetricsCollector, createMetricsCollector, type TestMetrics, type ScenarioMetrics, type TestSummaryReport, type MetricsSnapshot, } from './metrics-collector';
+//# sourceMappingURL=index.d.ts.map

package/dist/recon/testing/index.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/recon/testing/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAqCG;AAMH,OAAO,EACL,WAAW,EACX,iBAAiB,EACjB,KAAK,kBAAkB,EACvB,KAAK,aAAa,EAClB,KAAK,YAAY,EACjB,KAAK,aAAa,EAClB,KAAK,eAAe,GACrB,MAAM,gBAAgB,CAAC;AAMxB,OAAO,EACL,cAAc,EACd,oBAAoB,EACpB,KAAK,oBAAoB,EACzB,KAAK,cAAc,EACnB,KAAK,UAAU,EACf,KAAK,cAAc,GACpB,MAAM,mBAAmB,CAAC;AAM3B,OAAO,EACL,SAAS,EACT,cAAc,EACd,oBAAoB,EACpB,eAAe,EACf,iBAAiB,EACjB,iBAAiB,EACjB,sBAAsB,EACtB,yBAAyB,EACzB,qBAAqB,EACrB,KAAK,sBAAsB,EAC3B,KAAK,mBAAmB,GACzB,MAAM,kBAAkB,CAAC;AAM1B,OAAO,EACL,gBAAgB,EAChB,sBAAsB,EACtB,KAAK,WAAW,EAChB,KAAK,eAAe,EACpB,KAAK,iBAAiB,EACtB,KAAK,eAAe,GACrB,MAAM,qBAAqB,CAAC"}

package/dist/recon/testing/index.js

@@ -0,0 +1,55 @@
+/**
+ * ═══════════════════════════════════════════════════════════════════════════════
+ * RECON TESTING INFRASTRUCTURE
+ * ═══════════════════════════════════════════════════════════════════════════════
+ *
+ * Testing infrastructure for real-world recon mission testing.
+ * Provides mock chatbots, scenario runners, and metrics collection.
+ *
+ * Components:
+ * - **MockChatbot**: Simulates AI customer service agents with configurable personalities
+ * - **ScenarioRunner**: Automates end-to-end scenario testing
+ * - **TestScenarios**: Pre-built scenarios for common testing needs
+ * - **MetricsCollector**: Aggregates and reports test metrics
+ *
+ * Usage:
+ * ```typescript
+ * import {
+ *   MockChatbot,
+ *   ScenarioRunner,
+ *   SCENARIOS,
+ *   MetricsCollector,
+ * } from './testing';
+ *
+ * // Create a mock chatbot
+ * const chatbot = new MockChatbot({ personality: 'resistant' });
+ *
+ * // Run a scenario
+ * const runner = new ScenarioRunner();
+ * const result = await runner.run(symbol, chatbot, { maxTurns: 20 });
+ *
+ * // Collect metrics
+ * const collector = new MetricsCollector();
+ * collector.recordScenarioResult(result);
+ * console.log(collector.generateReport());
+ * ```
+ *
+ * ═══════════════════════════════════════════════════════════════════════════════
+ */
+// ═══════════════════════════════════════════════════════════════════════════════
+// MOCK CHATBOT
+// ═══════════════════════════════════════════════════════════════════════════════
+export { MockChatbot, createMockChatbot, } from './mock-chatbot';
+// ═══════════════════════════════════════════════════════════════════════════════
+// SCENARIO RUNNER
+// ═══════════════════════════════════════════════════════════════════════════════
+export { ScenarioRunner, createScenarioRunner, } from './scenario-runner';
+// ═══════════════════════════════════════════════════════════════════════════════
+// TEST SCENARIOS
+// ═══════════════════════════════════════════════════════════════════════════════
+export { SCENARIOS, createScenario, createCustomScenario, createTestBatch, getScenariosByTag, happyPathScenario, resistantAgentScenario, manipulativeAgentScenario, detectionTestScenario, } from './test-scenarios';
+// ═══════════════════════════════════════════════════════════════════════════════
+// METRICS COLLECTOR
+// ═══════════════════════════════════════════════════════════════════════════════
+export { MetricsCollector, createMetricsCollector, } from './metrics-collector';
+//# sourceMappingURL=index.js.map

package/dist/recon/testing/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/recon/testing/index.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAqCG;AAEH,kFAAkF;AAClF,eAAe;AACf,kFAAkF;AAElF,OAAO,EACL,WAAW,EACX,iBAAiB,GAMlB,MAAM,gBAAgB,CAAC;AAExB,kFAAkF;AAClF,kBAAkB;AAClB,kFAAkF;AAElF,OAAO,EACL,cAAc,EACd,oBAAoB,GAKrB,MAAM,mBAAmB,CAAC;AAE3B,kFAAkF;AAClF,iBAAiB;AACjB,kFAAkF;AAElF,OAAO,EACL,SAAS,EACT,cAAc,EACd,oBAAoB,EACpB,eAAe,EACf,iBAAiB,EACjB,iBAAiB,EACjB,sBAAsB,EACtB,yBAAyB,EACzB,qBAAqB,GAGtB,MAAM,kBAAkB,CAAC;AAE1B,kFAAkF;AAClF,oBAAoB;AACpB,kFAAkF;AAElF,OAAO,EACL,gBAAgB,EAChB,sBAAsB,GAKvB,MAAM,qBAAqB,CAAC"}

package/dist/recon/testing/metrics-collector.d.ts

@@ -0,0 +1,185 @@
+/**
+ * ═══════════════════════════════════════════════════════════════════════════════
+ * METRICS COLLECTOR
+ * ═══════════════════════════════════════════════════════════════════════════════
+ *
+ * Collects and aggregates test metrics from scenario runs.
+ * Provides summary reports and analysis of test outcomes.
+ *
+ * Features:
+ * - Track success rates across scenarios
+ * - Measure detection avoidance effectiveness
+ * - Calculate average drift scores
+ * - Generate comprehensive test summary reports
+ * - Export metrics in various formats
+ *
+ * ═══════════════════════════════════════════════════════════════════════════════
+ */
+import { ManipulationTactic } from '../types';
+import { ScenarioResult, ScenarioStatus } from './scenario-runner';
+/**
+ * Metrics for a single scenario type.
+ */
+export interface ScenarioMetrics {
+    /** Scenario name/type */
+    scenarioName: string;
+    /** Total runs */
+    totalRuns: number;
+    /** Successful runs */
+    successCount: number;
+    /** Success rate (0-1) */
+    successRate: number;
+    /** Average turns to completion */
+    averageTurns: number;
+    /** Average duration (ms) */
+    averageDurationMs: number;
+    /** Average drift score */
+    averageDriftScore: number;
+    /** Max drift score observed */
+    maxDriftScore: number;
+    /** Detection avoidance rate */
+    detectionAvoidanceRate: number;
+    /** Times AI was detected */
+    detectedCount: number;
+    /** Average blocked responses */
+    averageBlockedResponses: number;
+    /** Average modified responses */
+    averageModifiedResponses: number;
+    /** Tactics detected frequency */
+    tacticFrequency: Record<ManipulationTactic, number>;
+    /** Status distribution */
+    statusDistribution: Record<ScenarioStatus, number>;
+    /** Results */
+    results: ScenarioResult[];
+}
+/**
+ * Overall test metrics.
+ */
+export interface TestMetrics {
+    /** Total scenarios run */
+    totalScenarios: number;
+    /** Total individual runs */
+    totalRuns: number;
+    /** Overall success rate */
+    overallSuccessRate: number;
+    /** Overall detection avoidance rate */
+    overallDetectionAvoidanceRate: number;
+    /** Average drift across all scenarios */
+    overallAverageDrift: number;
+    /** Average turns across all scenarios */
+    overallAverageTurns: number;
+    /** Average duration across all scenarios */
+    overallAverageDurationMs: number;
+    /** Total blocked responses */
+    totalBlockedResponses: number;
+    /** Total modified responses */
+    totalModifiedResponses: number;
+    /** Most common tactics detected */
+    topTactics: Array<{
+        tactic: ManipulationTactic;
+        count: number;
+    }>;
+    /** Metrics by scenario type */
+    byScenario: Record<string, ScenarioMetrics>;
+    /** Collection timestamp */
+    collectedAt: string;
+    /** Collection duration (ms) */
+    collectionDurationMs: number;
+}
+/**
+ * Snapshot of current metrics state.
+ */
+export interface MetricsSnapshot {
+    metrics: TestMetrics;
+    timestamp: string;
+}
+/**
+ * Test summary report.
+ */
+export interface TestSummaryReport {
+    /** Report title */
+    title: string;
+    /** Report generation time */
+    generatedAt: string;
+    /** Executive summary */
+    summary: {
+        totalTests: number;
+        successRate: string;
+        detectionAvoidanceRate: string;
+        averageDrift: string;
+        recommendation: string;
+    };
+    /** Detailed metrics */
+    metrics: TestMetrics;
+    /** Scenario breakdowns */
+    scenarios: Array<{
+        name: string;
+        successRate: string;
+        averageTurns: number;
+        topIssue: string;
+    }>;
+    /** Key findings */
+    findings: string[];
+    /** Recommendations */
+    recommendations: string[];
+}
+/**
+ * Collects and aggregates test metrics.
+ */
+export declare class MetricsCollector {
+    private results;
+    private startTime;
+    constructor();
+    /**
+     * Record a scenario result.
+     */
+    recordScenarioResult(result: ScenarioResult): void;
+    /**
+     * Record multiple scenario results.
+     */
+    recordBatchResults(results: ScenarioResult[]): void;
+    /**
+     * Clear all recorded results.
+     */
+    clear(): void;
+    /**
+     * Get all recorded results.
+     */
+    getResults(): ScenarioResult[];
+    /**
+     * Calculate metrics for a specific scenario name.
+     */
+    getScenarioMetrics(scenarioName: string): ScenarioMetrics | null;
+    /**
+     * Calculate overall test metrics.
+     */
+    getTestMetrics(): TestMetrics;
+    /**
+     * Create a snapshot of current metrics.
+     */
+    getSnapshot(): MetricsSnapshot;
+    /**
+     * Generate a comprehensive test summary report.
+     */
+    generateReport(): TestSummaryReport;
+    /**
+     * Generate a text summary suitable for logging.
+     */
+    generateTextSummary(): string;
+    /**
+     * Export metrics as JSON.
+     */
+    exportJSON(): string;
+    private groupByScenario;
+    private calculateScenarioMetrics;
+    private generateFindings;
+    private generateRecommendations;
+    private determineOverallRecommendation;
+    private determineTopIssue;
+    private emptyMetrics;
+}
+/**
+ * Create a metrics collector.
+ */
+export declare function createMetricsCollector(): MetricsCollector;
+//# sourceMappingURL=metrics-collector.d.ts.map

package/dist/recon/testing/metrics-collector.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"metrics-collector.d.ts","sourceRoot":"","sources":["../../../src/recon/testing/metrics-collector.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;GAgBG;AAEH,OAAO,EAAE,kBAAkB,EAAE,MAAM,UAAU,CAAC;AAC9C,OAAO,EAAE,cAAc,EAAE,cAAc,EAAE,MAAM,mBAAmB,CAAC;AAMnE;;GAEG;AACH,MAAM,WAAW,eAAe;IAC9B,yBAAyB;IACzB,YAAY,EAAE,MAAM,CAAC;IAErB,iBAAiB;IACjB,SAAS,EAAE,MAAM,CAAC;IAElB,sBAAsB;IACtB,YAAY,EAAE,MAAM,CAAC;IAErB,yBAAyB;IACzB,WAAW,EAAE,MAAM,CAAC;IAEpB,kCAAkC;IAClC,YAAY,EAAE,MAAM,CAAC;IAErB,4BAA4B;IAC5B,iBAAiB,EAAE,MAAM,CAAC;IAE1B,0BAA0B;IAC1B,iBAAiB,EAAE,MAAM,CAAC;IAE1B,+BAA+B;IAC/B,aAAa,EAAE,MAAM,CAAC;IAEtB,+BAA+B;IAC/B,sBAAsB,EAAE,MAAM,CAAC;IAE/B,4BAA4B;IAC5B,aAAa,EAAE,MAAM,CAAC;IAEtB,gCAAgC;IAChC,uBAAuB,EAAE,MAAM,CAAC;IAEhC,iCAAiC;IACjC,wBAAwB,EAAE,MAAM,CAAC;IAEjC,iCAAiC;IACjC,eAAe,EAAE,MAAM,CAAC,kBAAkB,EAAE,MAAM,CAAC,CAAC;IAEpD,0BAA0B;IAC1B,kBAAkB,EAAE,MAAM,CAAC,cAAc,EAAE,MAAM,CAAC,CAAC;IAEnD,cAAc;IACd,OAAO,EAAE,cAAc,EAAE,CAAC;CAC3B;AAED;;GAEG;AACH,MAAM,WAAW,WAAW;IAC1B,0BAA0B;IAC1B,cAAc,EAAE,MAAM,CAAC;IAEvB,4BAA4B;IAC5B,SAAS,EAAE,MAAM,CAAC;IAElB,2BAA2B;IAC3B,kBAAkB,EAAE,MAAM,CAAC;IAE3B,uCAAuC;IACvC,6BAA6B,EAAE,MAAM,CAAC;IAEtC,yCAAyC;IACzC,mBAAmB,EAAE,MAAM,CAAC;IAE5B,yCAAyC;IACzC,mBAAmB,EAAE,MAAM,CAAC;IAE5B,4CAA4C;IAC5C,wBAAwB,EAAE,MAAM,CAAC;IAEjC,8BAA8B;IAC9B,qBAAqB,EAAE,MAAM,CAAC;IAE9B,+BAA+B;IAC/B,sBAAsB,EAAE,MAAM,CAAC;IAE/B,mCAAmC;IACnC,UAAU,EAAE,KAAK,CAAC;QAAE,MAAM,EAAE,kBAAkB,CAAC;QAAC,KAAK,EAAE,MAAM,CAAA;KAAE,CAAC,CAAC;IAEjE,+BAA+B;IAC/B,UAAU,EAAE,MAAM,CAAC,MAAM,EAAE,eAAe,CAAC,CAAC;IAE5C,2BAA2B;IAC3B,WAAW,EAAE,MAAM,CAAC;IAEpB,+BAA+B;IAC/B,oBAAoB,EAAE,MAAM,CAAC;CAC9B;AAED;;GAEG;AACH,MAAM,WAAW,eAAe;IAC9B,OAAO,EAAE,WAAW,CAAC;IACrB,SAAS,EAAE,MAAM,CAAC;CACnB;AAED;;GAEG;AACH,MAAM,WAAW,iBAAiB;IAChC,mBAAmB;IACnB,KAAK,EAAE,MAAM,CAAC;IAEd,6BAA6B;IAC7B,WAAW,EAAE,MAAM,CAAC;IAEpB,wBAAwB;IACxB,OAAO,EAAE;QACP,UAAU,EAAE,MAAM,CAAC;QACnB,WAAW,EAAE,MAAM,CAAC;QACpB,sBAAsB,EAAE,MAAM,CAAC;QAC/B,YAAY,EAAE,MAAM,CAAC;QACrB,cAAc,EAAE,MAAM,CAAC;KACxB,CAAC;IAEF,uBAAuB;IACvB,OAAO,EAAE,WAAW,CAAC;IAErB,0BAA0B;IAC1B,SAAS,EAAE,KAAK,CAAC;QACf,IAAI,EAAE,MAAM,CAAC;QACb,WAAW,EAAE,MAAM,CAAC;QACpB,YAAY,EAAE,MAAM,CAAC;QACrB,QAAQ,EAAE,MAAM,CAAC;KAClB,CAAC,CAAC;IAEH,mBAAmB;IACnB,QAAQ,EAAE,MAAM,EAAE,CAAC;IAEnB,sBAAsB;IACtB,eAAe,EAAE,MAAM,EAAE,CAAC;CAC3B;AAMD;;GAEG;AACH,qBAAa,gBAAgB;IAC3B,OAAO,CAAC,OAAO,CAAwB;IACvC,OAAO,CAAC,SAAS,CAAS;;IAU1B;;OAEG;IACH,oBAAoB,CAAC,MAAM,EAAE,cAAc,GAAG,IAAI;IAIlD;;OAEG;IACH,kBAAkB,CAAC,OAAO,EAAE,cAAc,EAAE,GAAG,IAAI;IAInD;;OAEG;IACH,KAAK,IAAI,IAAI;IAKb;;OAEG;IACH,UAAU,IAAI,cAAc,EAAE;IAQ9B;;OAEG;IACH,kBAAkB,CAAC,YAAY,EAAE,MAAM,GAAG,eAAe,GAAG,IAAI;IAYhE;;OAEG;IACH,cAAc,IAAI,WAAW;IAyD7B;;OAEG;IACH,WAAW,IAAI,eAAe;IAW9B;;OAEG;IACH,cAAc,IAAI,iBAAiB;IAqCnC;;OAEG;IACH,mBAAmB,IAAI,MAAM;IAsC7B;;OAEG;IACH,UAAU,IAAI,MAAM;IAQpB,OAAO,CAAC,eAAe;IA0BvB,OAAO,CAAC,wBAAwB;IA2DhC,OAAO,CAAC,gBAAgB;IAkCxB,OAAO,CAAC,uBAAuB;IAiC/B,OAAO,CAAC,8BAA8B;IAatC,OAAO,CAAC,iBAAiB;IAgBzB,OAAO,CAAC,YAAY;CAiBrB;AAMD;;GAEG;AACH,wBAAgB,sBAAsB,IAAI,gBAAgB,CAEzD"}