fix: quiet mode (-Q) outputs only raw response text (#11024)

Two issues when running hermes chat -Q -q:
1. The streaming 'Hermes' response box was rendering to stdout because
   stream_delta_callback was wired during _init_agent() before quiet_mode
   was set. This caused the response to appear twice — once in the styled
   box and once as plain text.
2. session_id was printed to stdout, making piped output unusable.

Fix: null out stream_delta_callback and tool_gen_callback after agent init
in the quiet-mode path, and redirect session_id to stderr.

Now 'hermes chat -Q -q "prompt" | cat' produces only the answer text.
session_id is still available on stderr for scripts that need it.

Reported by @nixpiper on X.

cli.py

@@ -10039,6 +10039,11 @@ def main(
                 ):
                     cli.agent.quiet_mode = True
                     cli.agent.suppress_status_output = True
+                    # Suppress streaming display callbacks so stdout stays
+                    # machine-readable (no styled "Hermes" box, no tool-gen
+                    # status lines).  The response is printed once below.
+                    cli.agent.stream_delta_callback = None
+                    cli.agent.tool_gen_callback = None
                     result = cli.agent.run_conversation(
                         user_message=effective_query,
                         conversation_history=cli.conversation_history,
@@ -10046,7 +10051,8 @@ def main(
                     response = result.get("final_response", "") if isinstance(result, dict) else str(result)
                     if response:
                         print(response)
-                    print(f"\nsession_id: {cli.session_id}")
+                    # Session ID goes to stderr so piped stdout is clean.
+                    print(f"\nsession_id: {cli.session_id}", file=sys.stderr)
                     
                     # Ensure proper exit code for automation wrappers
                     sys.exit(1 if isinstance(result, dict) and result.get("failed") else 0)