feat: Implement SS evaluator

sdks/typescript/README.md

@@ -40,7 +40,7 @@ Evaluates vocabulary complexity using the Qual Text Complexity rubric (SAP).
 
 **Supported Grades:** 3-12
 
-**Uses:** Google Gemini 2.5 Pro + OpenAI GPT-4o
+**Uses:** OpenAI GPT-4o (background knowledge) + Google Gemini 2.5 Pro (grades 3–4) / OpenAI GPT-4.1 (grades 5–12)
 
 **Constructor:**
 ```typescript
@@ -74,6 +74,53 @@ await evaluator.evaluate(text: string, grade: string)
 }
 ```
 
+---
+
+### 2. Sentence Structure Evaluator
+
+Evaluates sentence structure complexity based on grammatical features.
+
+**Supported Grades:** K-12
+
+**Uses:** OpenAI GPT-4o
+
+**Constructor:**
+```typescript
+const evaluator = new SentenceStructureEvaluator({
+  openaiApiKey: string;   // Required - OpenAI API key
+  maxRetries?: number;    // Optional - Max retry attempts (default: 2)
+  telemetry?: boolean | TelemetryOptions; // Optional (default: true)
+  logger?: Logger;        // Optional - Custom logger
+  logLevel?: LogLevel;    // Optional - Logging verbosity (default: WARN)
+});
+```
+
+**API:**
+```typescript
+await evaluator.evaluate(text: string, grade: string)
+```
+
+**Returns:**
+```typescript
+{
+  score: 'Slightly Complex' | 'Moderately Complex' | 'Very Complex' | 'Exceedingly Complex';
+  reasoning: string;
+  metadata: {
+    promptVersion: string;
+    model: string;
+    timestamp: Date;
+    processingTimeMs: number;
+  };
+  _internal: {
+    sentenceAnalysis: SentenceAnalysis;
+    features: SentenceFeatures;
+    complexity: ComplexityClassification;
+  };
+}
+```
+
+---
+
 ## Error Handling
 
 The SDK provides specific error types to help you handle different scenarios:

sdks/typescript/docs/telemetry.md

@@ -25,11 +25,11 @@ If you prefer not to send any telemetry, you can disable it entirely — see [Di
   "timestamp": "2026-02-05T19:30:00.000Z",
   "sdk_version": "0.1.0",
   "evaluator_type": "vocabulary",
-  "grade": "5",
+  "grade": "3",
   "status": "success",
   "latency_ms": 3500,
   "text_length_chars": 456,
-  "provider": "google:gemini-2.5-pro+openai:gpt-4o",
+  "provider": "openai:gpt-4o-2024-11-20 + google:gemini-2.5-pro",
   "token_usage": {
     "input_tokens": 650,
     "output_tokens": 350
@@ -72,7 +72,7 @@ If you prefer not to send any telemetry, you can disable it entirely — see [Di
 | `latency_ms` | Total evaluation time in milliseconds |
 | `text_length_chars` | Length of input text in characters |
 | `provider` | LLM provider(s) used (e.g., "openai:gpt-4o", "google:gemini-2.5-pro+openai:gpt-4o") |
-| `token_usage` | Total tokens consumed (input, output, total) |
+| `token_usage` | Total tokens consumed (input, output) |
 | `input_text` | The text being evaluated (only included if `recordInputs: true`) |
 | `metadata.stage_details` | Per-stage breakdown for multi-stage evaluators (optional) |
 

sdks/typescript/src/evaluators/index.ts

@@ -5,3 +5,9 @@ export {
   evaluateVocabulary,
   type VocabularyEvaluatorConfig,
 } from './vocabulary.js';
+
+export {
+  SentenceStructureEvaluator,
+  evaluateSentenceStructure,
+  type SentenceStructureEvaluatorConfig,
+} from './sentence-structure.js';