Upload 2 files

README.md

@@ -36,4 +36,7 @@ itself.
 To run it (locally or as a Space), set the `HF_TOKEN` secret/env var to a
 Hugging Face access token with Inference API permission. Optionally set
 `HF_AGENT_MODEL` to override the default model
-(`Qwen/Qwen2.5-Coder-32B-Instruct`).
+(`Qwen/Qwen2.5-Coder-32B-Instruct`), and `HF_AGENT_PROVIDER` to override the
+default Inference Provider (`together`) — pinned explicitly because the
+router's `auto` selection can land on a provider that doesn't support tool
+calling for a given model (HTTP 422 `UNSUPPORTED_OPENAI_PARAMS`).

agent.py

@@ -32,6 +32,12 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 # HF_AGENT_MODEL env var without touching code.
 HF_MODEL_REPO_ID = os.getenv("HF_AGENT_MODEL", "Qwen/Qwen2.5-Coder-32B-Instruct")
 
+# Left unset ("auto"), the HF router picks whichever provider is cheapest/fastest for the
+# model, and some of those don't support the `tools` param at all (HTTP 422
+# UNSUPPORTED_OPENAI_PARAMS). Pin one that reliably supports tool calling; override via
+# HF_AGENT_PROVIDER if it doesn't happen to host HF_AGENT_MODEL.
+HF_MODEL_PROVIDER = os.getenv("HF_AGENT_PROVIDER", "together")
+
 with open(Path(__file__).parent / "system_prompt.txt", "r", encoding="utf-8") as f:
     SYSTEM_PROMPT = f.read()
 
@@ -269,6 +275,7 @@ def _build_tools():
 def _build_llm():
     endpoint = HuggingFaceEndpoint(
         repo_id=HF_MODEL_REPO_ID,
+        provider=HF_MODEL_PROVIDER,
         huggingfacehub_api_token=os.getenv("HF_TOKEN"),
         temperature=0,
         max_new_tokens=1024,