Fix: Tool name consistency across TOOLS registry and TOOL_FUNCTIONS

Resolved mismatch between:
- TOOLS registry (src/tools/__init__.py): "web_search", "calculator", "vision"
- TOOL_FUNCTIONS (src/agent/graph.py): Was using "search", "safe_eval", "analyze_image"

Changes:
- Updated TOOL_FUNCTIONS to match TOOLS registry names
- Updated fallback_tool_selection() to use correct names
- Fixed test mock to use "web_search" instead of "search"

Result: HuggingFace LLM function calling now works correctly
Tests: 99/99 passing ✅

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

src/agent/graph.py

@@ -108,10 +108,10 @@ def fallback_tool_selection(question: str, plan: str) -> List[dict]:
         # Extract search query - use first sentence or full question
         query = question.split('.')[0] if '.' in question else question
         tool_calls.append({
-            "tool": "search",
+            "tool": "web_search",
             "params": {"query": query}
         })
-        logger.info(f"[fallback_tool_selection] Added search tool with query: {query}")
+        logger.info(f"[fallback_tool_selection] Added web_search tool with query: {query}")
 
     # Math tool: keywords like "calculate", "compute", "+", "-", "*", "/", "="
     math_keywords = ["calculate", "compute", "math", "sum", "multiply", "divide", "+", "-", "*", "/", "="]
@@ -123,10 +123,10 @@ def fallback_tool_selection(question: str, plan: str) -> List[dict]:
         if expr_match:
             expression = expr_match.group().strip()
             tool_calls.append({
-                "tool": "safe_eval",
+                "tool": "calculator",
                 "params": {"expression": expression}
             })
-            logger.info(f"[fallback_tool_selection] Added safe_eval tool with expression: {expression}")
+            logger.info(f"[fallback_tool_selection] Added calculator tool with expression: {expression}")
 
     # File tool: keywords like "file", "parse", "read", "csv", "json", "txt"
     file_keywords = ["file", "parse", "read", "csv", "json", "txt", "document"]
@@ -144,7 +144,7 @@ def fallback_tool_selection(question: str, plan: str) -> List[dict]:
         logger.warning("[fallback_tool_selection] No tools selected by fallback - adding default search")
         # Default: just search the question
         tool_calls.append({
-            "tool": "search",
+            "tool": "web_search",
             "params": {"query": question}
         })
 
@@ -220,11 +220,12 @@ def execute_node(state: AgentState) -> AgentState:
     logger.info(f"[execute_node] Question: {state['question']}")
 
     # Map tool names to actual functions
+    # NOTE: Keys must match TOOLS registry in src/tools/__init__.py
     TOOL_FUNCTIONS = {
-        "search": search,
+        "web_search": search,
         "parse_file": parse_file,
-        "safe_eval": safe_eval,
-        "analyze_image": analyze_image,
+        "calculator": safe_eval,
+        "vision": analyze_image,
     }
 
     # Initialize results lists
@@ -315,11 +316,12 @@ def execute_node(state: AgentState) -> AgentState:
                 logger.info(f"[execute_node] Fallback after exception returned {len(tool_calls)} tool(s)")
 
                 # Try to execute fallback tools
+                # NOTE: Keys must match TOOLS registry in src/tools/__init__.py
                 TOOL_FUNCTIONS = {
-                    "search": search,
+                    "web_search": search,
                     "parse_file": parse_file,
-                    "safe_eval": safe_eval,
-                    "analyze_image": analyze_image,
+                    "calculator": safe_eval,
+                    "vision": analyze_image,
                 }
 
                 for tool_call in tool_calls:

test/test_llm_integration.py

@@ -234,7 +234,7 @@ class TestEndToEndWorkflow:
         mock_tool_response = MagicMock()
         mock_tool_use = MagicMock()
         mock_tool_use.type = "tool_use"
-        mock_tool_use.name = "search"
+        mock_tool_use.name = "web_search"
         mock_tool_use.input = {"query": "capital of France"}
         mock_tool_use.id = "call_001"
         mock_tool_response.content = [mock_tool_use]