Files
hermes-agent/tests/cli/test_manual_compress.py
Teknium f0dc919f92 fix(compression): include system prompt + tool schemas in token estimates (#18265)
The user-visible /compress banner and the post-compression last_prompt_tokens
writeback both counted only the raw message transcript (chars/4). With a 15KB
system prompt and 30 tool schemas (~26KB), a 4-message transcript that looks
like ~45 tokens to the transcript-only estimator is really ~10.5K tokens of
request pressure — a 234x gap.

Two user-facing consequences:
- Banner shows 'Compressing … (~45 tokens)…' while compression is actually
  firing on 10K+ tokens of real pressure, confusing users about why
  compression triggered (reported by @codecovenant on X; #6217).
- Post-compression last_prompt_tokens writeback omits tool schemas, so the
  next should_compress() check compares real usage against a stale
  underestimate — compression triggers late, potentially past the model's
  context limit on small-context models (#14695).

Swap estimate_messages_tokens_rough() for estimate_request_tokens_rough()
at every user-visible banner and at the post-compression writeback.
estimate_request_tokens_rough() already existed for exactly this purpose
and includes system prompt + tool schemas.

Touched call sites:
- run_agent.py: post-compression last_prompt_tokens writeback, post-tool
  call should_compress() fallback when provider usage is missing
- cli.py: /compress banner + summary
- gateway/run.py: gateway /compress banner + summary
- tui_gateway/server.py: TUI /compress status + summary
- acp_adapter/server.py: ACP /compact before/after

Left intentionally alone:
- Session-hygiene fallback and the 'no agent' /status path in gateway/run.py
  — no agent instance is in scope to query for system prompt/tools, and the
  existing 30-50% overestimate wobble on hygiene is safety-accepted.
- Verbose-mode 'Request size' logging — informational only, already counts
  system prompt via api_messages[0].

Also relabels the feedback line from 'Rough transcript estimate' to
'Approx request size' so the metric label matches what it actually measures.

Credits: diagnoses from @devilardis (#14695) and @Jackten (#6217);
user report @codecovenant on X (2026-04-30).

Closes #14695
Closes #6217
2026-04-30 23:03:54 -07:00

134 lines
4.8 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.tools = None
shell.agent.session_id = shell.session_id # no-op compression: no split
shell.agent._compress_context.return_value = (list(history), "")
def _estimate(messages, **_kwargs):
assert messages == history
return 100
with patch("agent.model_metadata.estimate_request_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 "Approx request size: ~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.tools = None
shell.agent.session_id = shell.session_id # no-op: no split
shell.agent._compress_context.return_value = (compressed, "")
def _estimate(messages, **_kwargs):
if messages == history:
return 100
if messages == compressed:
return 120
raise AssertionError(f"unexpected transcript: {messages!r}")
with patch("agent.model_metadata.estimate_request_tokens_rough", side_effect=_estimate):
shell._manual_compress()
output = capsys.readouterr().out
assert "✅ Compressed: 4 → 3 messages" in output
assert "Approx request size: ~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 = ""
shell.agent.tools = None
# 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_request_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.tools = None
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_request_tokens_rough", return_value=100):
shell._manual_compress()
# No split → pending title untouched.
assert shell._pending_title == "keep me"