docs: update README and CLAUDE.md to v2.2.0

- Added documentation for audit tracking (IP address, invocation method).
- Updated database model descriptions for enhanced WorkOrder and Conversation fields.
- Documented the new UnifiedConfig system.
- Reflected enhanced logging transparency for knowledge base parsing.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

.env.example

@@ -0,0 +1,93 @@
+# .env.example
+# This file contains all the environment variables needed to run the application.
+# Copy this file to .env and fill in the values for your environment.
+
+# ============================================================================
+# SERVER CONFIGURATION
+# ============================================================================
+# The host the web server will bind to.
+SERVER_HOST=0.0.0.0
+
+# The port for the main Flask web server.
+SERVER_PORT=5000
+
+# The port for the WebSocket server for real-time chat.
+WEBSOCKET_PORT=8765
+
+# Set to "True" for development to enable debug mode and auto-reloading.
+# Set to "False" for production.
+DEBUG_MODE=True
+
+# Logging level for the application. Options: DEBUG, INFO, WARNING, ERROR, CRITICAL
+LOG_LEVEL=INFO
+
+
+# ============================================================================
+# DATABASE CONFIGURATION
+# ============================================================================
+# The connection string for the primary database.
+# Format for MySQL: mysql+pymysql://<user>:<password>@<host>:<port>/<dbname>?charset=utf8mb4
+# Format for SQLite: sqlite:///./local_test.db
+DATABASE_URL=mysql+pymysql://tsp_assistant:123456@jeason.online/tsp_assistant?charset=utf8mb4
+
+# ============================================================================
+# LARGE LANGUAGE MODEL (LLM) CONFIGURATION
+# ============================================================================
+# The provider of the LLM. Supported: "qwen", "openai", "anthropic"
+LLM_PROVIDER=qwen
+
+# The API key for your chosen LLM provider.
+LLM_API_KEY=sk-c0dbefa1718d46eaa897199135066f00
+
+# The base URL for the LLM API. This is often needed for OpenAI-compatible endpoints.
+LLM_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1
+
+# The specific model to use, e.g., "qwen-plus-latest", "gpt-3.5-turbo", "claude-3-sonnet-20240229"
+LLM_MODEL=qwen-plus-latest
+
+# The temperature for the model's responses (0.0 to 2.0).
+LLM_TEMPERATURE=0.7
+
+# The maximum number of tokens to generate in a response.
+LLM_MAX_TOKENS=2000
+
+# The timeout in seconds for API calls to the LLM.
+LLM_TIMEOUT=30
+
+
+# ============================================================================
+# FEISHU (LARK) INTEGRATION CONFIGURATION
+# ============================================================================
+# The App ID of your Feishu enterprise application.
+FEISHU_APP_ID=cli_a8b50ec0eed1500d
+
+# The App Secret of your Feishu enterprise application.
+FEISHU_APP_SECRET=ccxkE7ZCFQZcwkkM1rLy0ccZRXYsT2xK
+
+# The Verification Token for validating event callbacks (if configured).
+FEISHU_VERIFICATION_TOKEN=
+
+# The Encrypt Key for decrypting event data (if configured).
+FEISHU_ENCRYPT_KEY=
+
+# The ID of the Feishu multi-dimensional table for data synchronization.
+FEISHU_TABLE_ID=tblnl3vJPpgMTSiP
+
+
+# ============================================================================
+# AI ACCURACY CONFIGURATION
+# ============================================================================
+# The similarity threshold (0.0 to 1.0) for auto-approving an AI suggestion.
+AI_AUTO_APPROVE_THRESHOLD=0.95
+
+# The similarity threshold below which the human-provided resolution is preferred.
+AI_USE_HUMAN_RESOLUTION_THRESHOLD=0.90
+
+# The similarity threshold for flagging a suggestion for manual review.
+AI_MANUAL_REVIEW_THRESHOLD=0.80
+
+# The default confidence score for an AI suggestion.
+AI_SUGGESTION_CONFIDENCE=0.95
+
+# The confidence score assigned when a human resolution is used.
+AI_HUMAN_RESOLUTION_CONFIDENCE=0.90