@brizz/sdk 0.1.22 → 0.1.25

package/README.md

@@ -16,7 +16,7 @@ libraries including OpenAI, Anthropic, Vercel AI SDK, and more.
   - [ESM Projects](#esm-projects)
 - [Module System Support](#module-system-support)
 - [Supported Libraries](#supported-libraries)
-- [PII Protection & Data Masking](#pii-protection--data-masking)
+- [PII Masking](#pii-masking)
 - [Session Tracking](#session-tracking)
 - [Custom Events & Logging](#custom-events--logging)
 - [Environment Variables](#environment-variables)
@@ -33,7 +33,7 @@ libraries including OpenAI, Anthropic, Vercel AI SDK, and more.
 
 - 🔍 **Automatic Instrumentation** - Zero-code setup for popular AI libraries
 - 📊 **OpenTelemetry Native** - Standards-compliant tracing, metrics, and logs
-- 🛡️ **PII Protection** - Built-in masking for sensitive data
+- 🛡️ **PII Masking** - Optional masking for sensitive data
 - 🔄 **Session Tracking** - Group related operations and traces
 - 📦 **Dual Module Support** - Works with both ESM and CommonJS
 - ⚡ **Multiple Initialization Methods** - Preload, ESM loader, or manual setup
@@ -223,11 +223,18 @@ This enables automatic tracing of:
 - Tool calls and executions
 - Streaming data
 
-## PII Protection & Data Masking
+## PII Masking
 
-Automatically protects sensitive data in traces and logs:
+Optional masking for span attributes.
 
 ```typescript
+// Enable default masking
+Brizz.initialize({
+  apiKey: 'your-api-key',
+  masking: true,
+});
+
+// Custom masking configuration
 Brizz.initialize({
   apiKey: 'your-api-key',
   masking: {
@@ -236,16 +243,7 @@ Brizz.initialize({
         {
           attributePattern: 'gen_ai\\.(prompt|completion)',
           mode: 'partial', // 'partial' or 'full'
-          patterns: ['sk-[a-zA-Z0-9]{48}'], // Custom API key pattern
-        },
-      ],
-    },
-    logMasking: {
-      rules: [
-        {
-          attributePattern: 'message',
-          mode: 'full',
-          patterns: ['\\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\\.[A-Z|a-z]{2,}\\b'],
+          patterns: ['sk-[a-zA-Z0-9]{48}'],
         },
       ],
     },
@@ -253,8 +251,7 @@ Brizz.initialize({
 });
 ```
 
-**Built-in PII patterns** automatically detect and mask emails, phone numbers, SSNs, credit cards,
-API keys, crypto addresses, IPs, and more.
+When enabled, defaults cover a curated set of common secret patterns. Add custom rules for anything else you need masked.
 
 ## Session Tracking
 
@@ -286,9 +283,12 @@ const result = await startSession(
 ```
 
 **Session Methods:**
+
 - `session.updateProperties({ key: value })` - Add custom properties to the session span
-- `session.setInput(text, context?)` - (Optional) Manually track input text; optional context bag attaches per-turn metadata rendered in the dashboard's Context panel
-- `session.setOutput(text, context?)` - (Optional) Manually track output text; optional context bag attaches per-turn metadata rendered in the dashboard's Context panel
+- `session.setInput(text, context?)` - (Optional) Manually track input text; optional context bag
+  attaches per-turn metadata rendered in the dashboard's Context panel
+- `session.setOutput(text, context?)` - (Optional) Manually track output text; optional context bag
+  attaches per-turn metadata rendered in the dashboard's Context panel
 - `session.setTitle(text)` - Set a session title (typically used with `mode: 'title'`)
 
 **Per-turn context example:**
@@ -306,7 +306,8 @@ await startSession('session-123', async (session) => {
 
 **When to use manual input/output tracking:**
 
-In most cases, Brizz automatically captures inputs and outputs from your LLM calls. Use `setInput`/`setOutput` for special scenarios:
+In most cases, Brizz automatically captures inputs and outputs from your LLM calls. Use
+`setInput`/`setOutput` for special scenarios:
 
 - **Multi-agent flows**: Track only user-facing input/output, not intermediate agent communications
 - **Structured data extraction**: Track a specific field from complex JSON requests
@@ -330,7 +331,8 @@ await startSession('session-456', async (session) => {
 
 ### Session Title Generation
 
-If you use an LLM call to generate session titles, wrap it so those spans don't appear as part of the conversation:
+If you use an LLM call to generate session titles, wrap it so those spans don't appear as part of
+the conversation:
 
 ```typescript
 import { startSession, startSessionTitle } from '@brizz/sdk';
@@ -362,7 +364,8 @@ await startSessionTitle(async (title) => {
 
 ### Accessing the Active Session
 
-Use `getActiveSession()` to retrieve the current session from anywhere within a `startSession` scope — no need to pass the session object through your call stack:
+Use `getActiveSession()` to retrieve the current session from anywhere within a `startSession` scope
+— no need to pass the session object through your call stack:
 
 ```typescript
 import { startSession, getActiveSession } from '@brizz/sdk';
@@ -400,7 +403,9 @@ async function processUserWorkflow(userId: string) {
 
 // Create a wrapped function that always executes with session context
 // withSessionId(sessionId, fn, thisArg?, extraProperties?)
-const sessionedWorkflow = withSessionId('session-123', processUserWorkflow, undefined, { feature: 'workflow' });
+const sessionedWorkflow = withSessionId('session-123', processUserWorkflow, undefined, {
+  feature: 'workflow',
+});
 
 // Call multiple times, each with the same session context
 await sessionedWorkflow('user-456');
@@ -531,9 +536,9 @@ OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT=true    # Capture AI content
 
 ## Disable Span Export
 
-Keep `Brizz.initialize()` in your code without sending any spans — useful for dev/test
-environments. When enabled, the SDK skips span exporter and processor setup, so no
-spans are exported. Metrics and logs continue to work.
+Keep `Brizz.initialize()` in your code without sending any spans — useful for dev/test environments.
+When enabled, the SDK skips span exporter and processor setup, so no spans are exported. Metrics and
+logs continue to work.
 
 ```typescript
 Brizz.initialize({ apiKey: 'your-api-key', disableSpanExporter: true });