src/openhuman/mcp_client/registry.rs (1)

135-141: 💤 Low value

Consider adding a debug log when blocking disallowed tools.

Per coding guidelines, error paths benefit from diagnostic logging. A tracing::debug! here would help operators trace tool-blocking decisions without needing to surface the error through call stacks.

🔧 Suggested enhancement

 let tool = tool.trim();
 if !server.is_tool_allowed(tool) {
+    tracing::debug!(
+        server = %server.name,
+        tool = %tool,
+        "[mcp_client] blocking disallowed tool call"
+    );
     anyhow::bail!(
         "MCP tool `{tool}` is not allowed for server `{}`",
         server.name
     );
 }

As per coding guidelines: "Use log / tracing at debug or trace level on ... error paths."

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@src/openhuman/mcp_client/registry.rs` around lines 135 - 141, Add a
debug-level tracing log when a tool is rejected so operators can trace blocking
decisions: inside the block where you call server.is_tool_allowed(tool) and
before calling anyhow::bail!, emit a tracing::debug! (or tracing::trace! per
verbosity) that includes the tool and server.name (and optionally caller context
if available) to record why the path is taken without changing the error
behavior in the is_tool_allowed / bail branch.