fix idle timer: daemon agent calls were resetting user activity

The daemon's claude -p subprocesses inherit hooks config, so every
agent LLM call triggered UserPromptSubmit → signal_user(), making the
idle timer think Kent was always active. The daemon was petting its
own tail.

Fix: set POC_AGENT=1 env var on all daemon claude subprocesses, and
return early from poc-hook when it's set.

src/bin/poc-hook.rs

@@ -140,6 +140,13 @@ fn main() {
         .filter(|p| !p.is_empty())
         .map(PathBuf::from);
 
+    // Daemon agent calls set POC_AGENT=1 — skip all signaling.
+    // Without this, the daemon's claude -p calls trigger hooks that
+    // signal "user active", keeping the idle timer permanently reset.
+    if std::env::var("POC_AGENT").is_ok() {
+        return;
+    }
+
     match hook_type {
         "UserPromptSubmit" => {
             signal_user();

src/llm.rs

@@ -59,6 +59,9 @@ fn call_model(agent: &str, model: &str, prompt: &str) -> Result<String, String>
         cmd.env("CLAUDE_CONFIG_DIR", dir);
     }
 
+    // Tell hooks this is a daemon agent call, not interactive
+    cmd.env("POC_AGENT", "1");
+
     let start = std::time::Instant::now();
 
     let result = unsafe {