refactor: improve code readability and consistency across multiple files

apps/infrastructure/src/subagent/engine.rs

@@ -26,7 +26,7 @@ const MAX_ITERATIONS: u32 = 25;
 ///      a. Call the LLM (non-streaming) with accumulated messages + tool defs.
 ///      b. If the response has no tool calls → return the text content.
 ///      c. Otherwise execute each tool call and append the result as a
-///         tool-role message.
+///      tool-role message.
 ///      d. If the response also contained text, append an assistant message.
 ///   4. If the loop exits naturally, return the iteration-limit message.
 pub async fn run_agent(

apps/infrastructure/src/subagent/provider.rs

@@ -3,7 +3,7 @@
 //!
 //! Flow: `resolve_subagent_provider` is called at startup to pick a provider
 //! + model → `SubagentProvider` wraps that pair around an `LlmClient` for use
-//! inside the subagent engine loop.
+//!   inside the subagent engine loop.
 
 use anyhow::Result;
 

apps/infrastructure/src/subagent/workspace.rs

@@ -1,9 +1,9 @@
 //! Subagent workspace management — create isolated workspaces for subagents.
 
-use std::path::PathBuf;
+use std::path::{Path, PathBuf};
 
 /// Create an isolated workspace directory for a subagent.
-pub fn create_subagent_workspace(base_dir: &PathBuf, agent_id: &str) -> anyhow::Result<PathBuf> {
+pub fn create_subagent_workspace(base_dir: &Path, agent_id: &str) -> anyhow::Result<PathBuf> {
     let ws = base_dir.join("subagent-workspaces").join(agent_id);
     std::fs::create_dir_all(&ws)?;
     Ok(ws)