hermes-agent/tests/cli/test_manual_compress.py
Teknium 8a6aa5882e
fix(cli): sync session_id after compression and preserve original end_reason (#12920)
After context compression (manual /compress or auto), run_agent's
_compress_context ends the current session and creates a new continuation
child session, mutating agent.session_id. The classic CLI held its own
self.session_id that never resynced, so /status showed the ended parent,
the exit-summary --resume hint pointed at a closed row, and any later
end_session() call (from /resume <other> or /branch) targeted the wrong
row AND overwrote the parent's 'compression' end_reason.

This only affected the classic prompt_toolkit CLI. The gateway path was
already fixed in PR #1160 (March 2026); --tui and ACP use different
session plumbing and were unaffected.

Changes:
- cli.py::_manual_compress — sync self.session_id from self.agent.session_id
  after _compress_context, clear _pending_title
- cli.py chat loop — same sync post-run_conversation for auto-compression
- cli.py hermes -q single-query mode — same sync so stderr session_id
  output points at the continuation
- hermes_state.py::end_session — guard UPDATE with 'ended_at IS NULL' so
  the first end_reason wins; reopen_session() remains the explicit
  escape hatch for re-ending a closed row

Tests:
- 3 new in tests/cli/test_manual_compress.py (split sync, no-op guard,
  pending_title behavior)
- 2 new in tests/test_hermes_state.py (preserve compression end_reason
  on double-end; reopen-then-re-end still works)

Closes #12483. Credits @steve5636 for the same-day bug report and
@dieutx for PR #3529 which proposed the CLI sync approach.
2026-04-20 01:48:20 -07:00

129 lines
4.7 KiB
Python

"""Tests for CLI manual compression messaging."""
from unittest.mock import MagicMock, patch
from tests.cli.test_cli_init import _make_cli
def _make_history() -> list[dict[str, str]]:
return [
{"role": "user", "content": "one"},
{"role": "assistant", "content": "two"},
{"role": "user", "content": "three"},
{"role": "assistant", "content": "four"},
]
def test_manual_compress_reports_noop_without_success_banner(capsys):
shell = _make_cli()
history = _make_history()
shell.conversation_history = history
shell.agent = MagicMock()
shell.agent.compression_enabled = True
shell.agent._cached_system_prompt = ""
shell.agent.session_id = shell.session_id # no-op compression: no split
shell.agent._compress_context.return_value = (list(history), "")
def _estimate(messages):
assert messages == history
return 100
with patch("agent.model_metadata.estimate_messages_tokens_rough", side_effect=_estimate):
shell._manual_compress()
output = capsys.readouterr().out
assert "No changes from compression" in output
assert "✅ Compressed" not in output
assert "Rough transcript estimate: ~100 tokens (unchanged)" in output
def test_manual_compress_explains_when_token_estimate_rises(capsys):
shell = _make_cli()
history = _make_history()
compressed = [
history[0],
{"role": "assistant", "content": "Dense summary that still counts as more tokens."},
history[-1],
]
shell.conversation_history = history
shell.agent = MagicMock()
shell.agent.compression_enabled = True
shell.agent._cached_system_prompt = ""
shell.agent.session_id = shell.session_id # no-op: no split
shell.agent._compress_context.return_value = (compressed, "")
def _estimate(messages):
if messages == history:
return 100
if messages == compressed:
return 120
raise AssertionError(f"unexpected transcript: {messages!r}")
with patch("agent.model_metadata.estimate_messages_tokens_rough", side_effect=_estimate):
shell._manual_compress()
output = capsys.readouterr().out
assert "✅ Compressed: 4 → 3 messages" in output
assert "Rough transcript estimate: ~100 → ~120 tokens" in output
assert "denser summaries" in output
def test_manual_compress_syncs_session_id_after_split():
"""Regression for cli.session_id desync after /compress.
_compress_context ends the parent session and creates a new child session,
mutating agent.session_id. Without syncing, cli.session_id still points
at the ended parent — causing /status, /resume, exit summary, and the
next end_session() call (e.g. from /resume <id>) to target the wrong row.
"""
shell = _make_cli()
history = _make_history()
old_id = shell.session_id
new_child_id = "20260101_000000_child1"
compressed = [
{"role": "user", "content": "[summary]"},
history[-1],
]
shell.conversation_history = history
shell.agent = MagicMock()
shell.agent.compression_enabled = True
shell.agent._cached_system_prompt = ""
# Simulate _compress_context mutating agent.session_id as a side effect.
def _fake_compress(*args, **kwargs):
shell.agent.session_id = new_child_id
return (compressed, "")
shell.agent._compress_context.side_effect = _fake_compress
shell.agent.session_id = old_id # starts in sync
shell._pending_title = "stale title"
with patch("agent.model_metadata.estimate_messages_tokens_rough", return_value=100):
shell._manual_compress()
# CLI session_id must now point at the continuation child, not the parent.
assert shell.session_id == new_child_id
assert shell.session_id != old_id
# Pending title must be cleared — titles belong to the parent lineage and
# get regenerated for the continuation.
assert shell._pending_title is None
def test_manual_compress_no_sync_when_session_id_unchanged():
"""If compression is a no-op (agent.session_id didn't change), the CLI
must NOT clear _pending_title or otherwise disturb session state.
"""
shell = _make_cli()
history = _make_history()
shell.conversation_history = history
shell.agent = MagicMock()
shell.agent.compression_enabled = True
shell.agent._cached_system_prompt = ""
shell.agent.session_id = shell.session_id
shell.agent._compress_context.return_value = (list(history), "")
shell._pending_title = "keep me"
with patch("agent.model_metadata.estimate_messages_tokens_rough", return_value=100):
shell._manual_compress()
# No split → pending title untouched.
assert shell._pending_title == "keep me"