feat(codex-lens): add unified reranker architecture and file watcher

Unified Reranker Architecture:
- Add BaseReranker ABC with factory pattern
- Implement 4 backends: ONNX (default), API, LiteLLM, Legacy
- Add .env configuration parsing for API credentials
- Migrate from sentence-transformers to optimum+onnxruntime

File Watcher Module:
- Add real-time file system monitoring with watchdog
- Implement IncrementalIndexer for single-file updates
- Add WatcherManager with signal handling and graceful shutdown
- Add 'codexlens watch' CLI command
- Event filtering, debouncing, and deduplication
- Thread-safe design with proper resource cleanup

Tests: 16 watcher tests + 5 reranker test files

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

codex-lens/.env.example

@@ -0,0 +1,66 @@
+# CodexLens Environment Configuration
+# Copy this file to .codexlens/.env and fill in your values
+# 
+# Priority order:
+# 1. Environment variables (already set in shell)
+# 2. .codexlens/.env (workspace-local, this file)
+# 3. .env (project root)
+
+# ============================================
+# RERANKER Configuration
+# ============================================
+
+# API key for reranker service (SiliconFlow/Cohere/Jina)
+# Required for 'api' backend
+# RERANKER_API_KEY=sk-xxxx
+
+# Base URL for reranker API (overrides provider default)
+# SiliconFlow: https://api.siliconflow.cn
+# Cohere: https://api.cohere.ai
+# Jina: https://api.jina.ai
+# RERANKER_API_BASE=https://api.siliconflow.cn
+
+# Reranker provider: siliconflow, cohere, jina
+# RERANKER_PROVIDER=siliconflow
+
+# Reranker model name
+# SiliconFlow: BAAI/bge-reranker-v2-m3
+# Cohere: rerank-english-v3.0
+# Jina: jina-reranker-v2-base-multilingual
+# RERANKER_MODEL=BAAI/bge-reranker-v2-m3
+
+# ============================================
+# EMBEDDING Configuration  
+# ============================================
+
+# API key for embedding service (for litellm backend)
+# EMBEDDING_API_KEY=sk-xxxx
+
+# Base URL for embedding API
+# EMBEDDING_API_BASE=https://api.openai.com
+
+# Embedding model name
+# EMBEDDING_MODEL=text-embedding-3-small
+
+# ============================================
+# LITELLM Configuration
+# ============================================
+
+# API key for LiteLLM (for litellm reranker backend)
+# LITELLM_API_KEY=sk-xxxx
+
+# Base URL for LiteLLM
+# LITELLM_API_BASE=
+
+# LiteLLM model name
+# LITELLM_MODEL=gpt-4o-mini
+
+# ============================================
+# General Configuration
+# ============================================
+
+# Custom data directory path (default: ~/.codexlens)
+# CODEXLENS_DATA_DIR=~/.codexlens
+
+# Enable debug mode (true/false)
+# CODEXLENS_DEBUG=false