feat(bench): LLM benchmarks, regression baselines, and bundle size tracking

.env.example

@@ -0,0 +1,14 @@
+# LLM provider API keys for benchmark comparisons (npm run bench:llm)
+# Copy to .env and uncomment the providers you want to test.
+
+# OpenAI (default model: gpt-4.1-mini)
+# OPENAI_API_KEY=sk-...
+# OPENAI_MODEL=gpt-4.1-mini
+
+# Anthropic (default model: claude-haiku-4-5-20251001)
+# ANTHROPIC_API_KEY=sk-ant-...
+# ANTHROPIC_MODEL=claude-haiku-4-5-20251001
+
+# Ollama (auto-detected when running locally — no env vars required)
+# OLLAMA_HOST=http://localhost:11434
+# OLLAMA_MODEL=llama3.2

CLAUDE.md

@@ -13,6 +13,7 @@ npm run lint             # ESLint check
 npm run format           # Prettier write
 npm run format:check     # Prettier check
 npm run bench            # Run benchmark suite
+npm run bench:save       # Run, save baseline, regenerate docs/benchmark-results.md
 ```
 
 Run a single test file:

README.md

@@ -32,7 +32,7 @@ const { messages: originals } = uncompress(compressed, verbatim);
 
 No API keys. No network calls. Runs synchronously by default. Under 2ms for typical conversations.
 
-The classifier is content-aware, not domain-specific. It preserves structured data (code, JSON, SQL, tables, citations, formulas) and compresses surrounding prose — making it useful anywhere dense reference material is mixed with natural language: LLM conversations, legal briefs, medical records, technical documentation, support logs.
+The classifier is content-aware, not domain-specific. It preserves structured data (code, JSON, SQL, tables, citations, formulas) and compresses surrounding prose — optimized for LLM conversations and technical documentation.
 
 ## Key findings