feat: long-running session improvements

- Hang fix: 120s timeout on compression LLM call + raw_stream
  channel-close handling (None => break instead of spinning)
- Supervisor effective active count: stop counting finished
  JoinHandles as occupying capacity slots
- Universal tool result size cap: truncate_if_needed() on
  ToolResult, applied in eval_tool_calls() after escalation block;
  configurable via max_tool_result_chars in AppConfig/AgentConfig
- Windowed compression: compression_keep_last config param keeps
  the N most recent messages visible after compression
- Fix pre-existing flaky test: add #[serial] to
  handle_list_available_unrestricted_when_no_whitelist so it does
  not race with TestConfigDirGuard-based tests that temporarily
  populate the agents data dir

src/function/supervisor.rs

@@ -1446,6 +1446,7 @@ mod tests {
     use crate::config::{AppState, WorkingMode};
     use crate::supervisor::escalation::{EscalationQueue, EscalationRequest};
     use serde_json::json;
+    use serial_test::serial;
 
     fn default_app_state() -> Arc<AppState> {
         Arc::new(AppState::test_default())
@@ -1537,6 +1538,7 @@ mod tests {
     }
 
     #[test]
+    #[serial]
     fn handle_list_available_unrestricted_when_no_whitelist() {
         let ctx = ctx_with_supervisor(4, 3);
         let result = handle_list_available(&ctx).unwrap();