fix(agent): prevent safety guard false positives and streamed message drop

Three independent fixes for issues exposed by PR #3493:

1. shell.py: allow /dev/* paths in workspace guard
   Commands like `rm file.txt 2>/dev/null` were blocked because
   _extract_absolute_paths captured /dev/null as a path outside
   the workspace. Allow /dev like media_path is already allowed.

2. shell.py: remove | from home_paths regex prefix
   Loki query operator `|~` was misinterpreted as pipe + home
   directory, causing false workspace violation errors.

3. loop.py: change _streamed from blacklist to whitelist
   stop_reason "tool_error" was not in the exclusion set
   {"ask_user", "error"}, so _streamed=True was set on fatal
   errors. channel manager then skipped channel.send() because
   it assumed the content was already streamed — but it never
   was. Whitelist to only {"stop", "end_turn", "max_tokens"}.

Also fixes a pre-existing Windows bug in _spawn where
create_subprocess_exec + list2cmdline breaks commands with
paths containing spaces (e.g. D:\Program Files\python.exe).

Closes: #3599, #3605

nanobot/agent/loop.py

@@ -1135,7 +1135,7 @@ class AgentLoop:
             ask_user_options_from_messages(all_msgs) if stop_reason == "ask_user" else [],
             msg.channel,
         )
-        if on_stream is not None and stop_reason not in {"ask_user", "error"}:
+        if on_stream is not None and stop_reason not in {"ask_user", "error", "tool_error"}:
             meta["_streamed"] = True
         return OutboundMessage(
             channel=msg.channel,