Fix llama-server startup and enable LangSearch via shell tool

README.md

@@ -79,7 +79,9 @@ Expected: 3-5 t/s generation speed (vs 2-3 t/s with default settings).
 
 ## Web Search Tool (Standalone)
 
-The search tool is **not callable via model tool calling** (llama.cpp's `--tools` only supports built-in file/shell operations).
+When `LANGSEARCH_API_KEY` is set, `start.sh` enables llama.cpp's shell tool so the model can launch the local LangSearch wrapper.
+
+llama.cpp does not expose arbitrary external HTTP APIs as first-class built-in tools, so LangSearch is still implemented as a local wrapper that runs through the shell tool.
 
 **Use cases:**
 - Call from your application layer to augment model responses
@@ -105,7 +107,7 @@ response = requests.post(
 latest_response = response.json()['choices'][0]['message']['content']
 ```
 
-Then separately call search tool from your backend:
+Then call the search tool from your backend or from the shell tool:
 
 ```bash
 python3 /app/search_tool.py "latest AI news" 5 true noLimit

start.sh

@@ -18,6 +18,7 @@ export CACHE_TYPE_V="${CACHE_TYPE_V:-f16}"
 export REASONING="${REASONING:-auto}"
 export TOOLS="${TOOLS:-}"
 export NO_WARMUP="${NO_WARMUP:-0}"
+export LANGSEARCH_API_KEY="${LANGSEARCH_API_KEY:-}"
 
 # Ensure data directories exist and are writable. Run as root in container startup.
 echo "preparing storage: $HF_HOME and $MODEL_DIR"
@@ -116,7 +117,6 @@ server_args=(
   --cache-type-k "${CACHE_TYPE_K}"
   --cache-type-v "${CACHE_TYPE_V}"
   --metrics
-  --continuous-batching
 )
 
 if [ "${NO_WARMUP}" = "1" ]; then
@@ -139,6 +139,10 @@ case "${REASONING,,}" in
     ;;
 esac
 
+if [ -n "$LANGSEARCH_API_KEY" ] && [ -z "$TOOLS" ]; then
+  TOOLS="exec_shell_command"
+fi
+
 if [[ -n "${TOOLS}" ]]; then
   server_args+=(--tools "$TOOLS")
   echo "enabled tools: $TOOLS"