@sentrial/sdk 0.4.4 → 0.4.5

package/README.md

@@ -3,6 +3,7 @@
 TypeScript SDK for [Sentrial](https://sentrial.com) - AI agent observability and monitoring.
 
 Track sessions, tool calls, and metrics to power:
+
 - **Signal detection**: Auto-detect patterns and anomalies
 - **Root cause analysis**: Understand WHY agents fail
 - **Experiments**: A/B test different system prompts
@@ -18,6 +19,35 @@ pnpm add @sentrial/sdk
 yarn add @sentrial/sdk
 ```
 
+## CLI
+
+The SDK package also ships a `sentrial` binary for scriptable workflows. This is the
+first packaging step toward a dedicated `npm install sentrial` style CLI package.
+
+```bash
+# Run the CLI without a global install and set up the current project
+npx --yes --package=@sentrial/sdk@latest sentrial install
+
+# Save credentials locally
+npx sentrial login --api-key sentrial_live_xxx
+
+# Install the SDK package and scaffold a safe example integration
+npx sentrial install
+
+# Or scaffold only, without installing packages
+npx sentrial init
+
+# Inspect production runs
+npx sentrial sessions list --last 7d --status failed --agent support
+npx sentrial sessions get <session-id>
+npx sentrial events list <session-id> --type tool_call
+
+# Review signals and run CI gates
+npx sentrial signals list --type negative --last 30d
+npx sentrial diagnose <session-id>
+npx sentrial evaluate <experiment-id> --min-score 80
+```
+
 ## Quick Start (30 seconds)
 
 ### Option 1: Auto-Wrap LLM Clients (Recommended)
@@ -241,40 +271,61 @@ const cost = calculateOpenAICost({
 
 ## What Gets Tracked
 
-| Data | Auto-tracked | Manual |
-|------|-------------|--------|
-| LLM calls | ✔️ via wrappers | `trackToolCall()` |
-| Token usage | ✔️ via wrappers | `promptTokens` param |
-| Cost (USD) | ✔️ calculated | `estimatedCost` param |
-| Latency | ✔️ always | - |
-| Tool calls | ✔️ via `withTool` | `trackToolCall()` |
-| Errors | ✔️ always | `trackError()` |
-| User ID | ✔️ via session | `userId` param |
-| Custom metrics | - | `customMetrics` param |
+| Data           | Auto-tracked      | Manual                |
+| -------------- | ----------------- | --------------------- |
+| LLM calls      | ✔️ via wrappers   | `trackToolCall()`     |
+| Token usage    | ✔️ via wrappers   | `promptTokens` param  |
+| Cost (USD)     | ✔️ calculated     | `estimatedCost` param |
+| Latency        | ✔️ always         | -                     |
+| Tool calls     | ✔️ via `withTool` | `trackToolCall()`     |
+| Errors         | ✔️ always         | `trackError()`        |
+| User ID        | ✔️ via session    | `userId` param        |
+| Custom metrics | -                 | `customMetrics` param |
 
 ## Framework Compatibility
 
-| Framework | Integration | Status |
-|-----------|-------------|--------|
-| **Direct OpenAI** | `wrapOpenAI()` | ✔️ |
-| **Direct Anthropic** | `wrapAnthropic()` | ✔️ |
-| **Direct Gemini** | `wrapGoogle()` | ✔️ |
-| **Vercel AI SDK** | `wrapAISDK()` | ✔️ |
-| **Express/Fastify** | Decorators | ✔️ |
-| **Next.js** | Decorators | ✔️ |
-| **Custom agents** | Full API | ✔️ |
+| Framework            | Integration       | Status |
+| -------------------- | ----------------- | ------ |
+| **Direct OpenAI**    | `wrapOpenAI()`    | ✔️     |
+| **Direct Anthropic** | `wrapAnthropic()` | ✔️     |
+| **Direct Gemini**    | `wrapGoogle()`    | ✔️     |
+| **Vercel AI SDK**    | `wrapAISDK()`     | ✔️     |
+| **Express/Fastify**  | Decorators        | ✔️     |
+| **Next.js**          | Decorators        | ✔️     |
+| **Custom agents**    | Full API          | ✔️     |
 
 ## Documentation
 
 See the `docs/` folder in the repository:
+
 - `docs/sdks/typescript-sdk.md` - Full SDK reference
 - `docs/integrations/vercel-ai-sdk.md` - Vercel AI SDK integration
 - `docs/features/experiments.md` - Experiments guide
 
 ## Support
+
 - 💬 [Discord](https://discord.gg/9bMmJCXt)
-- 📧 [Email](mailto:neel@sentrial.com)
-- 🐛 [GitHub Issues](https://github.com/neelshar/Sentrial/issues)
+- 📧 [Email](mailto:founders@sentrial.com)
+- 🐛 [GitHub Issues](https://github.com/sentrialdev/Sentrial/issues)
+
+## SDK feature parity (TypeScript ↔ Python)
+
+Both SDKs share the same core API (`begin`/`finish`, tool & LLM tracking, production
+experiments, provider wrappers). Framework integrations currently differ:
+
+| Capability                                            | TypeScript            | Python              |
+| ----------------------------------------------------- | --------------------- | ------------------- |
+| Core tracking (begin/finish, tools, LLM, experiments) | ✓                     | ✓                   |
+| OpenAI / Anthropic / Google wrappers                  | ✓                     | ✓                   |
+| Vercel AI SDK helper                                  | ✓                     | — (JS-only)         |
+| Claude Agent SDK                                      | partial (single-turn) | ✓ (full multi-turn) |
+| OpenTelemetry export                                  | —                     | ✓                   |
+| Langfuse dual-write                                   | —                     | ✓                   |
+| AutoGen / CrewAI / LangChain handlers                 | —                     | ✓                   |
+
+Porting the missing TypeScript integrations (OpenTelemetry, Langfuse, Claude
+multi-turn) is planned; new TS integrations must keep V1 API response shapes
+backward-compatible.
 
 ## License