@inspectr/mcplab 0.1.0 → 0.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +43 -4
- package/dist/app/assets/{index-DT-Z4AVG.js → index-Dy2-RWt3.js} +68 -68
- package/dist/app/index.html +1 -1
- package/dist/app-server/config-store.d.ts +19 -11
- package/dist/app-server/libraries-store.d.ts.map +1 -1
- package/dist/app-server/libraries-store.js +30 -10
- package/dist/app-server/libraries-store.js.map +1 -1
- package/dist/app-server/markdown-reports.d.ts.map +1 -1
- package/dist/app-server/markdown-reports.js +42 -1
- package/dist/app-server/markdown-reports.js.map +1 -1
- package/dist/app-server/router.js +2 -2
- package/dist/app-server/router.js.map +1 -1
- package/dist/cli.js +1 -86
- package/dist/cli.js.map +1 -1
- package/package.json +4 -5
package/README.md
CHANGED
|
@@ -73,6 +73,8 @@ cp .env.example .env
|
|
|
73
73
|
# OPENAI_API_KEY=sk-...
|
|
74
74
|
```
|
|
75
75
|
|
|
76
|
+
Add your API keys to `.env`. See [Environment Variables](#-environment-variables) for full examples.
|
|
77
|
+
|
|
76
78
|
### 3. Run your first evaluation
|
|
77
79
|
|
|
78
80
|
```bash
|
|
@@ -290,6 +292,43 @@ run_defaults:
|
|
|
290
292
|
|
|
291
293
|
---
|
|
292
294
|
|
|
295
|
+
## 🔑 Environment Variables
|
|
296
|
+
|
|
297
|
+
Add your LLM Agent API keys to `.env` for each provider you want to use:
|
|
298
|
+
|
|
299
|
+
**Anthropic (Claude models):**
|
|
300
|
+
```env
|
|
301
|
+
# -----------------------------------------------------------------------------
|
|
302
|
+
# Anthropic Configuration
|
|
303
|
+
# -----------------------------------------------------------------------------
|
|
304
|
+
# Required for testing Claude models (claude-haiku-4, claude-sonnet-4)
|
|
305
|
+
|
|
306
|
+
ANTHROPIC_API_KEY=sk-ant-api03-XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
|
|
307
|
+
```
|
|
308
|
+
|
|
309
|
+
**Azure OpenAI (GPT models):**
|
|
310
|
+
```env
|
|
311
|
+
# -----------------------------------------------------------------------------
|
|
312
|
+
# Azure OpenAI Configuration
|
|
313
|
+
# -----------------------------------------------------------------------------
|
|
314
|
+
# Required for testing GPT models (gpt-4o-mini, gpt-4o, etc.)
|
|
315
|
+
|
|
316
|
+
AZURE_OPENAI_API_KEY=XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
|
|
317
|
+
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com
|
|
318
|
+
AZURE_OPENAI_DEPLOYMENT="gpt-5.2-chat"
|
|
319
|
+
AZURE_OPENAI_API_VERSION="2025-04-01-preview"
|
|
320
|
+
```
|
|
321
|
+
|
|
322
|
+
**OpenAI:**
|
|
323
|
+
```env
|
|
324
|
+
# -----------------------------------------------------------------------------
|
|
325
|
+
# OpenAI Configuration
|
|
326
|
+
# -----------------------------------------------------------------------------
|
|
327
|
+
OPENAI_API_KEY=sk-XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
|
|
328
|
+
```
|
|
329
|
+
|
|
330
|
+
---
|
|
331
|
+
|
|
293
332
|
## 💡 Usage Examples
|
|
294
333
|
|
|
295
334
|
### Basic Usage
|
|
@@ -347,9 +386,9 @@ Output:
|
|
|
347
386
|
|
|
348
387
|
LLM | Pass Rate | Avg Tools/Run | Avg Duration (ms)
|
|
349
388
|
-----------------|-----------|---------------|------------------
|
|
350
|
-
claude-haiku |
|
|
351
|
-
gpt-4o-mini |
|
|
352
|
-
gpt-4o |
|
|
389
|
+
claude-haiku | 100.0% | 2.5 | 850
|
|
390
|
+
gpt-4o-mini | 88.9% | 2.8 | 950
|
|
391
|
+
gpt-4o | 88.9% | 3.2 | 1200
|
|
353
392
|
|
|
354
393
|
💡 Key Insights
|
|
355
394
|
• Highest Pass Rate: claude-haiku (100.0%)
|
|
@@ -706,7 +745,7 @@ npm run build
|
|
|
706
745
|
# Run CLI directly with tsx (no build needed)
|
|
707
746
|
npm run dev -- app --dev
|
|
708
747
|
|
|
709
|
-
# Or run just the frontend
|
|
748
|
+
# Or run just the frontend dev server
|
|
710
749
|
npm run app:dev:ui
|
|
711
750
|
```
|
|
712
751
|
|