mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(cli): wrap /compress in _busy_command to block input during compression

Browse source 
Before this, typing during /compress was accepted by the classic CLI
prompt and landed in the next prompt after compression finished,
effectively consuming a keystroke for a prompt that was about to be
replaced. Wrapping the body in self._busy_command('Compressing
context...') blocks input rendering for the duration, matching the
pattern /skills install and other slow commands already use.

Salvages the useful part of #10303 (@iRonin). The `_compressing` flag
added to run_agent.py in the original PR was dead code (set in 3 spots,
read nowhere — not by cli.py, not by run_agent.py, not by the Ink TUI
which doesn't use _busy_command at all) and was dropped.
This commit is contained in:
Cyprian Kowalczyk 2026-04-24 15:19:44 -07:00 • committed by Teknium
parent 8ea389a7f8
commit fd3864d8bd
1 changed files with 44 additions and 43 deletions
Download patch file Download diff file Expand all files Collapse all files

87
cli.py
View file

@ -7011,51 +7011,52 @@ class HermesCLI:
focus_topic = parts[1].strip() focus_topic = parts[1].strip()
original_count = len(self.conversation_history) original_count = len(self.conversation_history)
try: with self._busy_command("Compressing context..."):
from agent.model_metadata import estimate_messages_tokens_rough try:
from agent.manual_compression_feedback import summarize_manual_compression from agent.model_metadata import estimate_messages_tokens_rough
original_history = list(self.conversation_history) from agent.manual_compression_feedback import summarize_manual_compression
approx_tokens = estimate_messages_tokens_rough(original_history) original_history = list(self.conversation_history)
if focus_topic: approx_tokens = estimate_messages_tokens_rough(original_history)
print(f"🗜️ Compressing {original_count} messages (~{approx_tokens:,} tokens), " if focus_topic:
f"focus: \"{focus_topic}\"...") print(f"🗜️ Compressing {original_count} messages (~{approx_tokens:,} tokens), "
else: f"focus: \"{focus_topic}\"...")
print(f"🗜️ Compressing {original_count} messages (~{approx_tokens:,} tokens)...") else:
print(f"🗜️ Compressing {original_count} messages (~{approx_tokens:,} tokens)...")
compressed, _ = self.agent._compress_context( compressed, _ = self.agent._compress_context(
original_history, original_history,
self.agent._cached_system_prompt or "", self.agent._cached_system_prompt or "",
approx_tokens=approx_tokens, approx_tokens=approx_tokens,
focus_topic=focus_topic or None, focus_topic=focus_topic or None,
) )
self.conversation_history = compressed self.conversation_history = compressed
# _compress_context ends the old session and creates a new child # _compress_context ends the old session and creates a new child
# session on the agent (run_agent.py::_compress_context). Sync the # session on the agent (run_agent.py::_compress_context). Sync the
# CLI's session_id so /status, /resume, exit summary, and title # CLI's session_id so /status, /resume, exit summary, and title
# generation all point at the live continuation session, not the # generation all point at the live continuation session, not the
# ended parent. Without this, subsequent end_session() calls target # ended parent. Without this, subsequent end_session() calls target
# the already-closed parent and the child is orphaned. # the already-closed parent and the child is orphaned.
if ( if (
getattr(self.agent, "session_id", None) getattr(self.agent, "session_id", None)
and self.agent.session_id != self.session_id and self.agent.session_id != self.session_id
): ):
self.session_id = self.agent.session_id self.session_id = self.agent.session_id
self._pending_title = None self._pending_title = None
new_tokens = estimate_messages_tokens_rough(self.conversation_history) new_tokens = estimate_messages_tokens_rough(self.conversation_history)
summary = summarize_manual_compression( summary = summarize_manual_compression(
original_history, original_history,
self.conversation_history, self.conversation_history,
approx_tokens, approx_tokens,
new_tokens, new_tokens,
) )
icon = "🗜️" if summary["noop"] else "✅" icon = "🗜️" if summary["noop"] else "✅"
print(f" {icon} {summary['headline']}") print(f" {icon} {summary['headline']}")
print(f" {summary['token_line']}") print(f" {summary['token_line']}")
if summary["note"]: if summary["note"]:
print(f" {summary['note']}") print(f" {summary['note']}")
except Exception as e: except Exception as e:
print(f" ❌ Compression failed: {e}") print(f" ❌ Compression failed: {e}")
def _handle_debug_command(self): def _handle_debug_command(self):
"""Handle /debug — upload debug report + logs and print paste URLs.""" """Handle /debug — upload debug report + logs and print paste URLs."""