diff --git a/README.md b/README.md
index d1cb121..3bd91d9 100644
--- a/README.md
+++ b/README.md
@@ -59,11 +59,20 @@ All configurable via `backend/.env`:
 | `LLM_BASE_URL` | `https://openrouter.ai/api/v1` | LLM API endpoint |
 | `LLM_API_KEY` | — | API key for LLM provider |
 | `LLM_MODEL_NAME` | `qwen/qwen3.5-35b-a3b` | Chat model |
+| `LLM_TIMEOUT` | `60.0` | LLM request timeout in seconds |
+| `LLM_ENABLE_THINKING` | `false` | Enable LLM thinking/reasoning tokens |
+| `VLLM_ENGINE` | `false` | Use vLLM-format `extra_body` instead of OpenRouter |
 | `EMBEDDING_MODEL` | `qwen/qwen3-embedding-4b` | Embedding model |
+| `EMBEDDING_BASE_URL` | `https://openrouter.ai/api/v1` | Embedding API endpoint |
 | `EMBEDDING_API_KEY` | — | API key for embeddings (falls back to `LLM_API_KEY`) |
+| `CHROMA_DB_PATH` | `./chroma_db` | ChromaDB persistent storage |
+| `CHUNK_SIZE` | `1000` | Token chunk size |
+| `CHUNK_OVERLAP` | `200` | Token chunk overlap |
 | `RETRIEVAL_N_RESULTS` | `10` | Chunks per sub-question |
 | `RELEVANCE_THRESHOLD` | `7.0` | Min relevance score (0-10) |
-| `LLM_TIMEOUT` | `60.0` | LLM request timeout in seconds |
+| `PROMPTS_DB_PATH` | `./data/prompts.db` | Prompt templates SQLite |
+| `HISTORY_DB_PATH` | `./data/history.db` | Query history SQLite |
+| `CORS_ORIGINS` | `["http://localhost:5173","http://localhost:3000"]` | Allowed CORS origins |
 
 ### Production: Nginx Reverse Proxy
 
@@ -156,6 +165,8 @@ docker run -d --name legco_test -p 8888:8000 \
   -e LLM_API_KEY=your_key_here \
   -e LLM_MODEL_NAME=qwen/qwen3.6-35b-a3b \
   -e LLM_TIMEOUT=60.0 \
+  -e LLM_ENABLE_THINKING=false \
+  -e VLLM_ENGINE=false \
   -e EMBEDDING_MODEL=qwen/qwen3-embedding-4b \
   -e EMBEDDING_BASE_URL=https://openrouter.ai/api/v1 \
   -e EMBEDDING_API_KEY=your_key_here \
diff --git a/backend/.env.example b/backend/.env.example
index 72c025b..4725b33 100644
--- a/backend/.env.example
+++ b/backend/.env.example
@@ -2,6 +2,8 @@ LLM_BASE_URL=https://openrouter.ai/api/v1
 LLM_API_KEY=your_openrouter_key_here
 LLM_MODEL_NAME=qwen/qwen3.5-35b-a3b
 LLM_TIMEOUT=60.0
+LLM_ENABLE_THINKING=false
+VLLM_ENGINE=false
 
 EMBEDDING_MODEL=qwen/qwen3-embedding-4b
 EMBEDDING_BASE_URL=https://openrouter.ai/api/v1