ppef 1.0.0 → 1.1.0

package/dist/types/result.d.ts

@@ -0,0 +1,150 @@
+/**
+ * Evaluation Result Type Definitions
+ *
+ * The canonical schema for individual evaluation results. Each result
+ * captures everything needed for reproducibility and auditing:
+ * - Deterministic run identity
+ * - Correctness assessment
+ * - Output artefacts and metrics
+ * - Provenance information
+ */
+import type { ArtefactReference, Primitive } from "./case.js";
+import type { SutRole } from "./sut.js";
+/**
+ * Categories of evaluation failure.
+ */
+export type FailureType = "no_output" | "invalid_structure" | "constraint_violation" | "exception" | "oracle_mismatch" | "timeout";
+/**
+ * Run identity and context.
+ */
+export interface RunContext {
+    /** Deterministic run ID (hash of inputs) */
+    runId: string;
+    /** SUT identifier */
+    sut: string;
+    /** SUT role (primary/baseline/oracle) */
+    sutRole: SutRole;
+    /** SUT version for reproducibility */
+    sutVersion?: string;
+    /** Case identifier */
+    caseId: string;
+    /** Case class for grouping */
+    caseClass?: string;
+    /** Configuration overrides for this run */
+    config?: Record<string, Primitive>;
+    /** Random seed if applicable */
+    seed?: number;
+    /** Repetition number for statistical runs */
+    repetition?: number;
+}
+/**
+ * Correctness assessment.
+ */
+export interface CorrectnessResult {
+    /** Whether expected output exists (oracle available) */
+    expectedExists: boolean;
+    /** Whether the SUT produced any output */
+    producedOutput: boolean;
+    /** Whether output is structurally valid */
+    valid: boolean;
+    /** Whether output matches expected (null if no oracle) */
+    matchesExpected: boolean | null;
+    /** Failure classification if applicable */
+    failureType?: FailureType;
+    /** Human-readable failure notes */
+    notes?: string[];
+}
+/**
+ * A ranked item for ranking tasks.
+ */
+export interface RankedItem {
+    /** Item identifier */
+    itemId: string;
+    /** Score or rank value */
+    score: number;
+    /** Optional additional metadata */
+    metadata?: Record<string, Primitive>;
+}
+/**
+ * Output artefacts and summaries.
+ */
+export interface ResultOutputs {
+    /** Scalar summary values */
+    summary?: Record<string, Primitive | Primitive[]>;
+    /** Classification labels */
+    labels?: Record<string, Primitive>;
+    /** Ranking results */
+    ranking?: RankedItem[];
+    /** References to generated artefacts */
+    artefacts?: ArtefactReference[];
+    /** Additional untyped outputs */
+    extra?: Record<string, unknown>;
+}
+/**
+ * Numeric metrics collected during evaluation.
+ */
+export interface ResultMetrics {
+    /** Primary numeric metrics */
+    numeric: Record<string, number>;
+    /** Additional metrics (overflow) */
+    extra?: Record<string, number>;
+}
+/**
+ * Provenance information for reproducibility.
+ */
+export interface Provenance {
+    /** Execution environment */
+    runtime: {
+        platform: string;
+        arch: string;
+        nodeVersion: string;
+    };
+    /** Git commit hash */
+    gitCommit?: string;
+    /** Whether working directory had uncommitted changes */
+    dirty?: boolean;
+    /** Hash of package-lock.json for dependency pinning */
+    dependencyLockHash?: string;
+    /** Parent run IDs (for derived results) */
+    parentRunIds?: string[];
+    /** Execution timestamp */
+    timestamp?: string;
+    /** Wall-clock execution time in milliseconds */
+    executionTimeMs?: number;
+    /** Peak memory usage during execution (bytes) */
+    peakMemoryBytes?: number;
+    /** Memory usage at completion (bytes) */
+    finalMemoryBytes?: number;
+}
+/**
+ * Complete evaluation result.
+ *
+ * This is the canonical schema for all evaluation outputs. Every experiment
+ * produces results in this format for consistent aggregation and rendering.
+ */
+export interface EvaluationResult {
+    /** Run identity and context */
+    run: RunContext;
+    /** Correctness assessment */
+    correctness: CorrectnessResult;
+    /** Output artefacts and summaries */
+    outputs: ResultOutputs;
+    /** Numeric metrics */
+    metrics: ResultMetrics;
+    /** Provenance for reproducibility */
+    provenance: Provenance;
+}
+/**
+ * Batch of evaluation results.
+ */
+export interface ResultBatch {
+    /** Schema version */
+    version: string;
+    /** Generation timestamp */
+    timestamp: string;
+    /** All results in this batch */
+    results: EvaluationResult[];
+    /** Optional batch-level metadata */
+    metadata?: Record<string, Primitive>;
+}
+//# sourceMappingURL=result.d.ts.map

package/dist/types/result.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"result.d.ts","sourceRoot":"","sources":["../../src/types/result.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAEH,OAAO,KAAK,EAAE,iBAAiB,EAAE,SAAS,EAAE,MAAM,WAAW,CAAC;AAC9D,OAAO,KAAK,EAAE,OAAO,EAAE,MAAM,UAAU,CAAC;AAExC;;GAEG;AACH,MAAM,MAAM,WAAW,GACpB,WAAW,GACX,mBAAmB,GACnB,sBAAsB,GACtB,WAAW,GACX,iBAAiB,GACjB,SAAS,CAAC;AAEb;;GAEG;AACH,MAAM,WAAW,UAAU;IAC1B,4CAA4C;IAC5C,KAAK,EAAE,MAAM,CAAC;IAEd,qBAAqB;IACrB,GAAG,EAAE,MAAM,CAAC;IAEZ,yCAAyC;IACzC,OAAO,EAAE,OAAO,CAAC;IAEjB,sCAAsC;IACtC,UAAU,CAAC,EAAE,MAAM,CAAC;IAEpB,sBAAsB;IACtB,MAAM,EAAE,MAAM,CAAC;IAEf,8BAA8B;IAC9B,SAAS,CAAC,EAAE,MAAM,CAAC;IAEnB,2CAA2C;IAC3C,MAAM,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,SAAS,CAAC,CAAC;IAEnC,gCAAgC;IAChC,IAAI,CAAC,EAAE,MAAM,CAAC;IAEd,6CAA6C;IAC7C,UAAU,CAAC,EAAE,MAAM,CAAC;CACpB;AAED;;GAEG;AACH,MAAM,WAAW,iBAAiB;IACjC,wDAAwD;IACxD,cAAc,EAAE,OAAO,CAAC;IAExB,0CAA0C;IAC1C,cAAc,EAAE,OAAO,CAAC;IAExB,2CAA2C;IAC3C,KAAK,EAAE,OAAO,CAAC;IAEf,0DAA0D;IAC1D,eAAe,EAAE,OAAO,GAAG,IAAI,CAAC;IAEhC,2CAA2C;IAC3C,WAAW,CAAC,EAAE,WAAW,CAAC;IAE1B,mCAAmC;IACnC,KAAK,CAAC,EAAE,MAAM,EAAE,CAAC;CACjB;AAED;;GAEG;AACH,MAAM,WAAW,UAAU;IAC1B,sBAAsB;IACtB,MAAM,EAAE,MAAM,CAAC;IAEf,0BAA0B;IAC1B,KAAK,EAAE,MAAM,CAAC;IAEd,mCAAmC;IACnC,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,SAAS,CAAC,CAAC;CACrC;AAED;;GAEG;AACH,MAAM,WAAW,aAAa;IAC7B,4BAA4B;IAC5B,OAAO,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,SAAS,GAAG,SAAS,EAAE,CAAC,CAAC;IAElD,4BAA4B;IAC5B,MAAM,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,SAAS,CAAC,CAAC;IAEnC,sBAAsB;IACtB,OAAO,CAAC,EAAE,UAAU,EAAE,CAAC;IAEvB,wCAAwC;IACxC,SAAS,CAAC,EAAE,iBAAiB,EAAE,CAAC;IAEhC,iCAAiC;IACjC,KAAK,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;CAChC;AAED;;GAEG;AACH,MAAM,WAAW,aAAa;IAC7B,8BAA8B;IAC9B,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IAEhC,oCAAoC;IACpC,KAAK,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;CAC/B;AAED;;GAEG;AACH,MAAM,WAAW,UAAU;IAC1B,4BAA4B;IAC5B,OAAO,EAAE;QACR,QAAQ,EAAE,MAAM,CAAC;QACjB,IAAI,EAAE,MAAM,CAAC;QACb,WAAW,EAAE,MAAM,CAAC;KACpB,CAAC;IAEF,sBAAsB;IACtB,SAAS,CAAC,EAAE,MAAM,CAAC;IAEnB,wDAAwD;IACxD,KAAK,CAAC,EAAE,OAAO,CAAC;IAEhB,uDAAuD;IACvD,kBAAkB,CAAC,EAAE,MAAM,CAAC;IAE5B,2CAA2C;IAC3C,YAAY,CAAC,EAAE,MAAM,EAAE,CAAC;IAExB,0BAA0B;IAC1B,SAAS,CAAC,EAAE,MAAM,CAAC;IAEnB,gDAAgD;IAChD,eAAe,CAAC,EAAE,MAAM,CAAC;IAEzB,iDAAiD;IACjD,eAAe,CAAC,EAAE,MAAM,CAAC;IAEzB,yCAAyC;IACzC,gBAAgB,CAAC,EAAE,MAAM,CAAC;CAC1B;AAED;;;;;GAKG;AACH,MAAM,WAAW,gBAAgB;IAChC,+BAA+B;IAC/B,GAAG,EAAE,UAAU,CAAC;IAEhB,6BAA6B;IAC7B,WAAW,EAAE,iBAAiB,CAAC;IAE/B,qCAAqC;IACrC,OAAO,EAAE,aAAa,CAAC;IAEvB,sBAAsB;IACtB,OAAO,EAAE,aAAa,CAAC;IAEvB,qCAAqC;IACrC,UAAU,EAAE,UAAU,CAAC;CACvB;AAED;;GAEG;AACH,MAAM,WAAW,WAAW;IAC3B,qBAAqB;IACrB,OAAO,EAAE,MAAM,CAAC;IAEhB,2BAA2B;IAC3B,SAAS,EAAE,MAAM,CAAC;IAElB,gCAAgC;IAChC,OAAO,EAAE,gBAAgB,EAAE,CAAC;IAE5B,oCAAoC;IACpC,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,SAAS,CAAC,CAAC;CACrC"}

package/dist/types/result.js

@@ -0,0 +1,12 @@
+/**
+ * Evaluation Result Type Definitions
+ *
+ * The canonical schema for individual evaluation results. Each result
+ * captures everything needed for reproducibility and auditing:
+ * - Deterministic run identity
+ * - Correctness assessment
+ * - Output artefacts and metrics
+ * - Provenance information
+ */
+export {};
+//# sourceMappingURL=result.js.map

package/dist/types/result.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"result.js","sourceRoot":"","sources":["../../src/types/result.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG"}

package/dist/types/sut.d.ts

@@ -0,0 +1,128 @@
+/**
+ * System Under Test (SUT) Type Definitions
+ *
+ * SUTs represent the algorithms being evaluated. Each SUT has a role that
+ * determines how its results are interpreted during evaluation:
+ *
+ * - primary: The algorithm being proposed/evaluated (e.g., Degree-Prioritised)
+ * - baseline: Comparison algorithms (e.g., Standard BFS, Frontier-Balanced)
+ * - oracle: Ground truth provider for correctness validation
+ */
+/**
+ * Role of the SUT in evaluation.
+ *
+ * - `primary`: The algorithm being proposed/evaluated
+ * - `baseline`: Comparison algorithm for relative evaluation
+ * - `oracle`: Ground truth provider for correctness validation
+ */
+export type SutRole = "primary" | "baseline" | "oracle";
+/**
+ * Registration information for a System Under Test.
+ */
+export interface SutRegistration {
+    /** Unique identifier (e.g., "degree-prioritised-v1.0.0") */
+    id: string;
+    /** Human-readable name (e.g., "Degree-Prioritised Expansion") */
+    name: string;
+    /** Version string for reproducibility */
+    version: string;
+    /** Role in evaluation */
+    role: SutRole;
+    /** Configuration parameters (immutable) */
+    config: Readonly<Record<string, unknown>>;
+    /** Searchable tags for filtering */
+    tags: readonly string[];
+    /** Optional description for documentation */
+    description?: string;
+}
+/**
+ * Universal SUT interface for algorithms that take inputs and produce results.
+ *
+ * This is the core abstraction - any algorithm can be evaluated if it:
+ * 1. Takes INPUTS (what it needs to run)
+ * 2. Produces OUTPUTS (what it returns)
+ * 3. Can be measured (metrics extraction)
+ *
+ * @template TInputs - The algorithm-specific inputs type
+ * @template TResult - The algorithm result type
+ */
+export interface SUT<TInputs, TResult> {
+    /** Unique identifier */
+    readonly id: string;
+    /** Immutable configuration */
+    readonly config: Readonly<Record<string, unknown>>;
+    /**
+     * Execute the algorithm.
+     *
+     * @param inputs - Algorithm-specific inputs
+     * @returns Promise resolving to algorithm result
+     */
+    run(inputs: TInputs): Promise<TResult>;
+}
+/**
+ * Factory function type for instantiating SUTs.
+ *
+ * @template TInputs - The algorithm inputs type
+ * @template TResult - The algorithm result type
+ */
+export type SutFactory<TInputs, TResult> = (config?: Record<string, unknown>) => SUT<TInputs, TResult>;
+/**
+ * Runtime instance of a SUT ready for execution.
+ * @deprecated Use SUT<TInputs, TResult> directly
+ */
+export interface SutInstance<TResult> {
+    /** Execute the algorithm and return results */
+    run(): Promise<TResult>;
+}
+/**
+ * Complete SUT definition including factory and metadata.
+ *
+ * @template TInputs - The algorithm inputs type
+ * @template TResult - The algorithm result type
+ */
+export interface SutDefinition<TInputs = unknown, TResult = unknown> {
+    /** Registration metadata */
+    registration: SutRegistration;
+    /** Factory for creating SUT instances */
+    factory: SutFactory<TInputs, TResult>;
+}
+/**
+ * Universal SUT result structure.
+ *
+ * Generic outputs allow any algorithm type to be evaluated:
+ * - Expansion: paths, nodes, edges
+ * - Ranking: ranked paths, scores
+ * - Classification: labels, confidences
+ *
+ * @template TOutputs - The outputs type (generic, not hardcoded)
+ */
+export interface SUTResult<TOutputs = unknown> {
+    /** Unique identifier for this run */
+    runId: string;
+    /** SUT identifier */
+    sutId: string;
+    /** SUT version */
+    sutVersion: string;
+    /** Case identifier */
+    caseId: string;
+    /** Unix timestamp of execution */
+    timestamp: number;
+    /** Execution duration in milliseconds */
+    duration: number;
+    /** Correctness assessment */
+    correctness: {
+        /** Whether an expected output was defined */
+        expectedExists: boolean;
+        /** Whether the SUT produced any output */
+        producedOutput: boolean;
+        /** Whether the output is structurally valid */
+        valid: boolean;
+        /** Whether the output matches the expected output (null if no expected output) */
+        matchesExpected: boolean | null;
+    };
+    /** SUT outputs - generic, not hardcoded to paths */
+    outputs: TOutputs;
+    /** Computed metrics */
+    metrics: Record<string, number>;
+}
+//# sourceMappingURL=sut.d.ts.map

package/dist/types/sut.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"sut.d.ts","sourceRoot":"","sources":["../../src/types/sut.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAEH;;;;;;GAMG;AACH,MAAM,MAAM,OAAO,GAAG,SAAS,GAAG,UAAU,GAAG,QAAQ,CAAC;AAExD;;GAEG;AACH,MAAM,WAAW,eAAe;IAC/B,4DAA4D;IAC5D,EAAE,EAAE,MAAM,CAAC;IAEX,iEAAiE;IACjE,IAAI,EAAE,MAAM,CAAC;IAEb,yCAAyC;IACzC,OAAO,EAAE,MAAM,CAAC;IAEhB,yBAAyB;IACzB,IAAI,EAAE,OAAO,CAAC;IAEd,2CAA2C;IAC3C,MAAM,EAAE,QAAQ,CAAC,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC,CAAC;IAE1C,oCAAoC;IACpC,IAAI,EAAE,SAAS,MAAM,EAAE,CAAC;IAExB,6CAA6C;IAC7C,WAAW,CAAC,EAAE,MAAM,CAAC;CACrB;AAED;;;;;;;;;;GAUG;AACH,MAAM,WAAW,GAAG,CAAC,OAAO,EAAE,OAAO;IACpC,wBAAwB;IACxB,QAAQ,CAAC,EAAE,EAAE,MAAM,CAAC;IAEpB,8BAA8B;IAC9B,QAAQ,CAAC,MAAM,EAAE,QAAQ,CAAC,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC,CAAC;IAEnD;;;;;OAKG;IACH,GAAG,CAAC,MAAM,EAAE,OAAO,GAAG,OAAO,CAAC,OAAO,CAAC,CAAC;CACvC;AAED;;;;;GAKG;AACH,MAAM,MAAM,UAAU,CAAC,OAAO,EAAE,OAAO,IAAI,CAC1C,MAAM,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,KAC5B,GAAG,CAAC,OAAO,EAAE,OAAO,CAAC,CAAC;AAE3B;;;GAGG;AACH,MAAM,WAAW,WAAW,CAAC,OAAO;IACnC,+CAA+C;IAC/C,GAAG,IAAI,OAAO,CAAC,OAAO,CAAC,CAAC;CACxB;AAED;;;;;GAKG;AACH,MAAM,WAAW,aAAa,CAAC,OAAO,GAAG,OAAO,EAAE,OAAO,GAAG,OAAO;IAClE,4BAA4B;IAC5B,YAAY,EAAE,eAAe,CAAC;IAE9B,yCAAyC;IACzC,OAAO,EAAE,UAAU,CAAC,OAAO,EAAE,OAAO,CAAC,CAAC;CACtC;AAED;;;;;;;;;GASG;AACH,MAAM,WAAW,SAAS,CAAC,QAAQ,GAAG,OAAO;IAC5C,qCAAqC;IACrC,KAAK,EAAE,MAAM,CAAC;IAEd,qBAAqB;IACrB,KAAK,EAAE,MAAM,CAAC;IAEd,kBAAkB;IAClB,UAAU,EAAE,MAAM,CAAC;IAEnB,sBAAsB;IACtB,MAAM,EAAE,MAAM,CAAC;IAEf,kCAAkC;IAClC,SAAS,EAAE,MAAM,CAAC;IAElB,yCAAyC;IACzC,QAAQ,EAAE,MAAM,CAAC;IAEjB,6BAA6B;IAC7B,WAAW,EAAE;QACZ,6CAA6C;QAC7C,cAAc,EAAE,OAAO,CAAC;QAExB,0CAA0C;QAC1C,cAAc,EAAE,OAAO,CAAC;QAExB,+CAA+C;QAC/C,KAAK,EAAE,OAAO,CAAC;QAEf,kFAAkF;QAClF,eAAe,EAAE,OAAO,GAAG,IAAI,CAAC;KAChC,CAAC;IAEF,oDAAoD;IACpD,OAAO,EAAE,QAAQ,CAAC;IAElB,uBAAuB;IACvB,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;CAChC"}

package/dist/types/sut.js

@@ -0,0 +1,12 @@
+/**
+ * System Under Test (SUT) Type Definitions
+ *
+ * SUTs represent the algorithms being evaluated. Each SUT has a role that
+ * determines how its results are interpreted during evaluation:
+ *
+ * - primary: The algorithm being proposed/evaluated (e.g., Degree-Prioritised)
+ * - baseline: Comparison algorithms (e.g., Standard BFS, Frontier-Balanced)
+ * - oracle: Ground truth provider for correctness validation
+ */
+export {};
+//# sourceMappingURL=sut.js.map

package/dist/types/sut.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"sut.js","sourceRoot":"","sources":["../../src/types/sut.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG"}

package/package.json

@@ -1,12 +1,295 @@
 {
   "name": "ppef",
-  "version": "1.0.0",
-  "description": "",
-  "main": "index.js",
+  "version": "1.1.0",
+  "description": "Portable Programmatic Evaluation Framework - Claim-driven, deterministic evaluation for experiments",
+  "type": "module",
+  "main": "dist/index.cjs",
+  "module": "dist/index.js",
+  "types": "dist/index.d.ts",
+  "bin": {
+    "ppef": "./bin/ppef.mjs"
+  },
+  "exports": {
+    ".": {
+      "types": "./dist/index.d.ts",
+      "import": "./dist/index.js",
+      "require": "./dist/index.cjs"
+    },
+    "./types": {
+      "types": "./dist/types/index.d.ts",
+      "import": "./dist/types/index.js"
+    },
+    "./types/*": {
+      "types": "./dist/types/*.d.ts",
+      "import": "./dist/types/*.js"
+    },
+    "./registry": {
+      "types": "./dist/registry/index.d.ts",
+      "import": "./dist/registry/index.js"
+    },
+    "./registry/*": {
+      "types": "./dist/registry/*.d.ts",
+      "import": "./dist/registry/*.js"
+    },
+    "./executor": {
+      "types": "./dist/executor/index.d.ts",
+      "import": "./dist/executor/index.js"
+    },
+    "./executor/*": {
+      "types": "./dist/executor/*.d.ts",
+      "import": "./dist/executor/*.js"
+    },
+    "./collector": {
+      "types": "./dist/collector/index.d.ts",
+      "import": "./dist/collector/index.js"
+    },
+    "./collector/*": {
+      "types": "./dist/collector/*.d.ts",
+      "import": "./dist/collector/*.js"
+    },
+    "./statistical": {
+      "types": "./dist/statistical/index.d.ts",
+      "import": "./dist/statistical/index.js"
+    },
+    "./aggregation": {
+      "types": "./dist/aggregation/index.d.ts",
+      "import": "./dist/aggregation/index.js"
+    },
+    "./aggregation/*": {
+      "types": "./dist/aggregation/*.d.ts",
+      "import": "./dist/aggregation/*.js"
+    },
+    "./claims": {
+      "types": "./dist/claims/index.d.ts",
+      "import": "./dist/claims/index.js"
+    },
+    "./claims/*": {
+      "types": "./dist/claims/*.d.ts",
+      "import": "./dist/claims/*.js"
+    },
+    "./robustness": {
+      "types": "./dist/robustness/index.d.ts",
+      "import": "./dist/robustness/index.js"
+    },
+    "./robustness/*": {
+      "types": "./dist/robustness/*.d.ts",
+      "import": "./dist/robustness/*.js"
+    },
+    "./renderers": {
+      "types": "./dist/renderers/index.d.ts",
+      "import": "./dist/renderers/index.js"
+    },
+    "./renderers/*": {
+      "types": "./dist/renderers/*.d.ts",
+      "import": "./dist/renderers/*.js"
+    }
+  },
+  "files": [
+    "dist"
+  ],
+  "sideEffects": false,
+  "engines": {
+    "node": ">=18"
+  },
+  "c8": {
+    "all": true,
+    "include": [
+      "src/**/*.ts"
+    ],
+    "exclude": [
+      "src/**/*.test.ts",
+      "src/**/*.spec.ts",
+      "src/**/*.diagnostic.test.ts"
+    ],
+    "reporter": [
+      "text",
+      "html",
+      "json-summary"
+    ],
+    "reports-dir": "coverage"
+  },
   "scripts": {
-    "test": "echo \"Error: no test specified\" && exit 1"
+    "typecheck": "tsc --noEmit",
+    "lint": "eslint 'src/**/!(__tests__)/**/*.ts' --fix",
+    "test": "c8 tsx --test src/**/*.test.ts src/**/**/*.test.ts",
+    "build": "tsc && node scripts/generate-cjs-wrapper.mjs",
+    "prepare": "husky"
+  },
+  "keywords": [
+    "evaluation",
+    "framework",
+    "testing",
+    "experiments",
+    "claims-driven"
+  ],
+  "author": "Joseph Mearman",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/Mearman/ppef.git"
+  },
+  "release": {
+    "branches": [
+      "**"
+    ],
+    "plugins": [
+      [
+        "@semantic-release/commit-analyzer",
+        {
+          "preset": "conventionalcommits",
+          "releaseRules": [
+            {
+              "type": "feat",
+              "release": "minor"
+            },
+            {
+              "type": "fix",
+              "release": "patch"
+            },
+            {
+              "type": "perf",
+              "release": "patch"
+            },
+            {
+              "type": "refactor",
+              "release": "patch"
+            },
+            {
+              "type": "docs",
+              "release": "patch"
+            },
+            {
+              "type": "style",
+              "release": "patch"
+            },
+            {
+              "type": "test",
+              "release": "patch"
+            },
+            {
+              "type": "build",
+              "release": "patch"
+            },
+            {
+              "type": "ci",
+              "release": "patch"
+            },
+            {
+              "type": "chore",
+              "release": "patch"
+            },
+            {
+              "type": "revert",
+              "release": "patch"
+            }
+          ]
+        }
+      ],
+      [
+        "@semantic-release/release-notes-generator",
+        {
+          "preset": "conventionalcommits",
+          "presetConfig": {
+            "types": [
+              {
+                "type": "feat",
+                "section": "Features"
+              },
+              {
+                "type": "fix",
+                "section": "Bug Fixes"
+              },
+              {
+                "type": "perf",
+                "section": "Performance Improvements"
+              },
+              {
+                "type": "refactor",
+                "section": "Code Refactoring"
+              },
+              {
+                "type": "docs",
+                "section": "Documentation"
+              },
+              {
+                "type": "style",
+                "section": "Styles"
+              },
+              {
+                "type": "test",
+                "section": "Tests"
+              },
+              {
+                "type": "build",
+                "section": "Build System"
+              },
+              {
+                "type": "ci",
+                "section": "Continuous Integration"
+              },
+              {
+                "type": "chore",
+                "section": "Chores"
+              },
+              {
+                "type": "revert",
+                "section": "Reverts"
+              }
+            ]
+          }
+        }
+      ],
+      "@semantic-release/changelog",
+      "@semantic-release/npm",
+      [
+        "@semantic-release/git",
+        {
+          "assets": [
+            "CHANGELOG.md",
+            "package.json"
+          ],
+          "message": "chore(release): ${nextRelease.version} [skip ci]\n\n${nextRelease.notes}"
+        }
+      ]
+    ]
+  },
+  "lint-staged": {
+    "*.ts": [
+      "eslint --fix"
+    ],
+    "*.js": [
+      "eslint --fix"
+    ]
+  },
+  "devDependencies": {
+    "@commitlint/cli": "20.3.1",
+    "@commitlint/config-conventional": "20.3.1",
+    "@eslint/js": "9.39.2",
+    "@eslint/markdown": "7.5.1",
+    "@semantic-release/changelog": "6.0.3",
+    "@semantic-release/git": "10.0.1",
+    "@types/node": "25.0.10",
+    "c8": "10.1.3",
+    "eslint": "9.39.2",
+    "eslint-config-prettier": "10.1.8",
+    "@eslint-community/eslint-plugin-eslint-comments": "4.6.0",
+    "eslint-plugin-jsonc": "2.21.0",
+    "eslint-plugin-prettier": "5.5.5",
+    "husky": "9.1.7",
+    "jiti": "2.6.1",
+    "lint-staged": "16.2.7",
+    "prettier": "3.8.1",
+    "semantic-release": "25.0.2",
+    "tsx": "4.21.0",
+    "typescript": "5.9.3",
+    "typescript-eslint": "8.53.1"
+  },
+  "peerDependencies": {
+    "typescript": "5.0.0"
+  },
+  "dependencies": {
+    "commander": "^12.0.0"
   },
-  "keywords": [],
-  "author": "",
-  "license": "ISC"
+  "publishConfig": {
+    "provenance": true
+  }
 }