mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
39975613b1
Second, deeper pass over tools/gateway/hermes_cli plus first pass over the trees wave 1 missed (acp, acp_adapter, skills, computer_use, docker, dashboard, conformance, monitoring, secret_sources, hermes_state, providers). Same rubric as wave 1 (AGENTS.md test policy); security, alternation/caching invariants, issue-number regressions, and E2E kept. Real test-quality fixes found and rooted out along the way: - tests/tools/test_command_guards.py made real auxiliary-LLM HTTPS calls (DEFAULT_CONFIG smart-approval leaked in) — pinned approval mode=manual via autouse fixture: 17.4s → 0.4s. - test_model_switch_custom_providers.py / test_user_providers_model_switch.py silently probed live provider catalogs (~2s/test) — stubbed cached_provider_model_ids/provider_model_ids/fetch_api_models. - test_telegram_noise_filter.py: 15-platform copy-paste matrix over shared gateway.run logic → 3 representative platforms (55s → 3.9s). - test_gateway_shutdown.py: stop()'s 5s interrupt-deadline loop spun on MagicMock agents — interrupt.side_effect now clears _running_agents (22s → 1.0s). - test_gateway_inactivity_timeout.py poll-harness timings shrunk 3-5x (24s → 1.1s); test_mcp_stability.py backoff/SIGTERM-grace sleeps patched (15.4s → 2.5s); test_async_delegation.py negative-drain wait 5s → 0.5s. - test_telegram_init_deadline.py: loop-block margin restored to 1.0s with rationale comment — the watchdog-dump assertion needs the loop blocked well past deadline+grace under parallel load (flaked once in the 40-worker verification run at a 0.2s margin). Verification: full hermetic suite via scripts/run_tests.sh — 2,438 files, 21,718 tests passed, 0 failed, 293.9s wall. Suite totals vs original baseline: 46,820 → 19,757 test functions (−57.8%), wall 583.5s → 293.9s (−50%), subprocess CPU 13,564s → 11,623s.
62 lines
1.3 KiB
Python
62 lines
1.3 KiB
Python
"""Unit tests for hermes_cli.session_recap."""
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
|
|
|
|
from hermes_cli.session_recap import build_recap
|
|
|
|
|
|
def _user(text):
|
|
return {"role": "user", "content": text}
|
|
|
|
|
|
def _assistant(text=None, tool_calls=None):
|
|
msg = {"role": "assistant", "content": text}
|
|
if tool_calls:
|
|
msg["tool_calls"] = tool_calls
|
|
return msg
|
|
|
|
|
|
def _tool_call(name, args):
|
|
return {
|
|
"id": f"call_{name}",
|
|
"type": "function",
|
|
"function": {"name": name, "arguments": json.dumps(args)},
|
|
}
|
|
|
|
|
|
def _tool_result(content="ok"):
|
|
return {"role": "tool", "content": content}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_tool_preview_length_truncates_long_user_prompt():
|
|
long = "x " * 500
|
|
out = build_recap([_user(long)])
|
|
ask_line = [l for l in out.splitlines() if "Last ask" in l][0]
|
|
assert len(ask_line) < 300 # truncated with ellipsis
|
|
assert "…" in ask_line
|
|
|
|
|
|
|
|
|
|
def test_escape_sequences_sanitized_in_previews():
|
|
"""Recap previews must not carry raw terminal escapes (codex#31494 class)."""
|
|
msgs = [
|
|
_user("please \x1b[2J\x1b]0;pwned\x07 do the thing"),
|
|
_assistant("done \x9b31m with it\x07"),
|
|
]
|
|
out = build_recap(msgs)
|
|
assert "\x1b" not in out
|
|
assert "\x9b" not in out
|
|
assert "\x07" not in out
|
|
assert "do the thing" in out
|
|
assert "with it" in out
|