fix: add missing argument to CMD in Dockerfile

Dockerfile

@@ -11,8 +11,9 @@ RUN apt-get update && apt-get install -y \
 
 WORKDIR /build
 
-# Pin a known-good release; bump as needed
-RUN git clone --depth 1 --branch b3600 https://github.com/ggerganov/llama.cpp.git
+# Pin a known-good release that supports --jinja (added after b3600).
+# Bump this periodically; check https://github.com/ggml-org/llama.cpp/releases
+RUN git clone --depth 1 --branch b4996 https://github.com/ggml-org/llama.cpp.git
 
 WORKDIR /build/llama.cpp
 
@@ -39,11 +40,17 @@ WORKDIR /app
 
 COPY --from=builder /build/llama.cpp/build/bin/llama-server /app/llama-server
 
-ARG MODEL_URL=https://huggingface.co/bartowski/Qwen2.5-7B-Instruct-GGUF/resolve/main/Qwen2.5-7B-Instruct-Q4_K_M.gguf
+# Qwen2.5-3B is a better fit than 7B for a 2-thread CPU-only box —
+# noticeably faster time-to-first-token for tool-calling latency.
+# Override with --build-arg MODEL_URL=... if you want to go back to 7B.
+ARG MODEL_URL=https://huggingface.co/bartowski/Qwen2.5-3B-Instruct-GGUF/resolve/main/Qwen2.5-3B-Instruct-Q4_K_M.gguf
 RUN curl -L -o /app/model.gguf "${MODEL_URL}"
 
 EXPOSE 7860
 
+HEALTHCHECK --interval=30s --timeout=5s --start-period=60s --retries=3 \
+    CMD curl -f http://localhost:7860/health || exit 1
+
 CMD ["/app/llama-server", \
      "-m", "/app/model.gguf", \
      "--host", "0.0.0.0", \