mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +00:00
6b81590c55
Systematic prune per AGENTS.md test policy, one pass over every major test tree (gateway, hermes_cli, tools, agent, run_agent, plugins, cli, cron, tui_gateway, honcho/openviking, root-level): - DELETE: source-reading tests (read_text/getsource on prod files), change-detector tests (exact catalog counts, model-name snapshots, config version literals), mock-echo tests (assert a mock returns what it was told), assertion-free/trivial tests, near-duplicate parametrizations (boundaries + one representative kept), async/sync twin duplicates, cosmetic within-file variations. - KEEP (mandatory): security/redaction/approval guards, message-role alternation invariants, prompt-caching/deterministic-call-id invariants, issue-number regression tests (deduped), E2E tests. - 6 test files deleted outright (script-style/no-assert or fully redundant); conftest.py, fakes/, fixtures/ untouched. - tests/acp/conftest.py added: autouse fixture stubs the live models.dev/GitHub/Copilot/Anthropic inventory fetches that ACP server tests performed on every session create — test_server.py 147s → 3.4s, and the tests are now genuinely hermetic. - Sleep-based slowness shrunk where safe (codex_ttfb_watchdog, compression_concurrent_fork, etc.); no wall-clock assertion tightened. Verification: full hermetic suite via scripts/run_tests.sh — 2439 files, 31,130 tests passed, 0 failed, 0 flaky retries, 315s wall (baseline: 583s wall, 13,564s subprocess CPU).
68 lines
1.8 KiB
Python
68 lines
1.8 KiB
Python
"""Behavioral coverage for manual compression status messages."""
|
|
|
|
from types import SimpleNamespace
|
|
|
|
from agent.manual_compression_feedback import (
|
|
describe_compression_lock_skip,
|
|
summarize_manual_compression,
|
|
)
|
|
|
|
|
|
def _messages(count: int) -> list[dict[str, str]]:
|
|
return [
|
|
{"role": "user" if index % 2 == 0 else "assistant", "content": str(index)}
|
|
for index in range(count)
|
|
]
|
|
|
|
|
|
|
|
|
|
def test_failure_reason_redaction_is_forced_at_ui_boundary(monkeypatch):
|
|
messages = _messages(12)
|
|
fake_secret = "sk-proj-" + "X" * 40
|
|
state = SimpleNamespace(
|
|
_last_compress_aborted=True,
|
|
_last_summary_fallback_used=False,
|
|
_last_summary_error=f"provider rejected OPENAI_API_KEY={fake_secret}",
|
|
)
|
|
monkeypatch.setattr("agent.redact._REDACT_ENABLED", False, raising=False)
|
|
|
|
feedback = summarize_manual_compression(
|
|
messages,
|
|
list(messages),
|
|
120_000,
|
|
120_000,
|
|
compression_state=state,
|
|
)
|
|
|
|
assert fake_secret not in feedback["note"]
|
|
assert "OPENAI_API_KEY=" in feedback["note"]
|
|
|
|
|
|
def test_fallback_compression_reports_dropped_message_count():
|
|
before = _messages(12)
|
|
after = before[:2] + before[-2:]
|
|
state = SimpleNamespace(
|
|
_last_compress_aborted=False,
|
|
_last_summary_fallback_used=True,
|
|
_last_summary_dropped_count=8,
|
|
_last_summary_error="summary provider returned an invalid response",
|
|
)
|
|
|
|
feedback = summarize_manual_compression(
|
|
before,
|
|
after,
|
|
120_000,
|
|
40_000,
|
|
compression_state=state,
|
|
)
|
|
|
|
assert feedback["aborted"] is False
|
|
assert feedback["fallback_used"] is True
|
|
assert feedback["headline"] == "Compressed with fallback: 12 → 4 messages"
|
|
assert "removed 8 message(s)" in feedback["note"]
|
|
assert "invalid response" in feedback["note"]
|
|
|
|
|
|
|
|
|