truthguard-ai 0.1.1 → 0.1.3

package/README.md

@@ -126,12 +126,12 @@ app.post('/api/chat', groundingMiddleware({
 
 ## Key Features
 
-- **30 detection rules** across grounding, orchestration, reasoning, and safety categories
-- **Diagnostic advisor** — root cause analysis + remediation hints for every failure
+- **30+ deterministic failure detectors** — fabrication from empty results, math errors, ignored tool data, entity mismatches, and more
 - **Policy engine** — per-failure enforcement (block / warn / observe)
+- **Diagnostic reports** — actionable failure reports with severity levels
 - **Baseline regression** — snapshot comparison to catch quality regressions
-- **Multi-language** — claim extraction supports 13 languages
-- **Configurable tolerances** — numeric, date, name matching thresholds
+- **Multi-language support** — works with responses in 13+ languages
+- **Configurable thresholds** — tune sensitivity to match your use case
 
 ---
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "truthguard-ai",
-  "version": "0.1.1",
+  "version": "0.1.3",
   "description": "TruthGuard — Standardized grounding validation for tool-calling AI agents. Detect, diagnose, and prevent grounding failures.",
   "main": "dist-npm/thin.js",
   "types": "dist-npm/thin.d.ts",

package/README.npm.md

@@ -1,144 +0,0 @@
-# TruthGuard
-
-**Grounding validation for tool-calling AI agents.**
-
-> Detect when an agent's response contradicts the data returned by the tools it called — without LLM-as-judge overhead.
-
-[![npm version](https://img.shields.io/npm/v/truthguard-ai.svg)](https://www.npmjs.com/package/truthguard-ai)
-[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
-
----
-
-## The Problem
-
-Most "hallucinations" in tool-calling agents are **grounding failures** — the agent calls a tool, gets accurate data, then ignores it, miscalculates, or fabricates from empty results.
-
-## The Solution
-
-TruthGuard extracts factual claims from the agent's response and cross-references them against tool outputs. Deterministic. No LLM calls. Runs in <50ms.
-
-```bash
-npm install truthguard-ai
-```
-
----
-
-## Quick Start
-
-### Evaluate a trace
-
-```typescript
-import { TraceBuilder, GroundingEngine, generateReport } from 'truthguard-ai';
-
-const trace = new TraceBuilder({ traceId: 'run-001' })
-  .addUserInput('How many employees are on leave today?')
-  .addToolCall('getLeaveRecords', { date: '2024-03-15' })
-  .addToolOutput('getLeaveRecords', [
-    { employeeId: 'E01', name: 'Ana Jovic', status: 'on_leave' },
-    { employeeId: 'E02', name: 'Ivan Petrovic', status: 'on_leave' },
-  ])
-  .addFinalResponse('There are 3 employees on leave today.')
-  .build();
-
-const engine = new GroundingEngine();
-const report = engine.evaluate(trace);
-
-console.log(report.groundingScore);       // 0.5
-console.log(report.detectedFailures[0]);  // { type: 'grounding.data_ignored', severity: 'high' }
-```
-
-### SDK Wrappers (OpenAI & Anthropic)
-
-```typescript
-import { wrapOpenAI } from 'truthguard-ai';
-import OpenAI from 'openai';
-
-const openai = wrapOpenAI(new OpenAI(), {
-  mode: 'block',
-  threshold: 0.85,
-});
-```
-
-```typescript
-import { wrapAnthropic } from 'truthguard-ai';
-import Anthropic from '@anthropic-ai/sdk';
-
-const anthropic = wrapAnthropic(new Anthropic(), {
-  mode: 'warn',
-  threshold: 0.80,
-});
-```
-
-### Production Monitoring (Proxy Mode)
-
-Works with **any language** — PHP, Python, Go, Java, Ruby, C#:
-
-```bash
-npx truthguard-ai observe --port 3001
-```
-
-Point your AI SDK base URL to the proxy:
-```
-# OpenAI
-OPENAI_BASE_URL=http://localhost:3001/proxy/openai
-
-# Anthropic
-ANTHROPIC_BASE_URL=http://localhost:3001/proxy/anthropic
-```
-
-Your app works identically. TruthGuard evaluates grounding in the background.
-
-### CI Quality Gate
-
-```bash
-npx truthguard-ai run test-cases.jsonl --gate .ai-rcp-gate.yml
-```
-
-### MCP Server (VS Code, Cursor)
-
-Use TruthGuard from your IDE — add to `.vscode/mcp.json`:
-
-```json
-{
-  "servers": {
-    "truthguard": {
-      "type": "stdio",
-      "command": "npx",
-      "args": ["-y", "truthguard-ai", "mcp"]
-    }
-  }
-}
-```
-
-### Express Middleware
-
-```typescript
-import { groundingMiddleware, FileStore } from 'truthguard-ai';
-
-app.post('/api/chat', groundingMiddleware({
-  mode: 'warn',
-  store: new FileStore('./traces/grounding.jsonl'),
-  extractTrace: (req, res, body) => body.trace,
-}));
-```
-
----
-
-## Key Features
-
-- **30 detection rules** across grounding, orchestration, reasoning, and safety categories
-- **Diagnostic advisor** — root cause analysis + remediation hints for every failure
-- **Policy engine** — per-failure enforcement (block / warn / observe)
-- **Baseline regression** — snapshot comparison to catch quality regressions
-- **Multi-language** — claim extraction supports 13 languages
-- **Configurable tolerances** — numeric, date, name matching thresholds
-
----
-
-## Documentation
-
-Full docs, guides, and architecture details: [truthguard.dev](https://truthguard.dev)
-
-## License
-
-MIT