mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +00:00
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.
37 lines
1.5 KiB
Python
37 lines
1.5 KiB
Python
"""Tests for web_extract truncate-store robustness (findings from #54843 review).
|
|
|
|
Covers two robustness gaps left unaddressed when #54843 merged:
|
|
1. _store_full_text bounded by MAX_STORED_TEXT_CHARS (no unbounded disk write).
|
|
2. _truncate_with_footer emits a CONCRETE read_file offset for the omitted
|
|
middle (was a literal `offset=<line>` placeholder the model had to guess).
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import re
|
|
|
|
import tools.web_tools as wt
|
|
|
|
|
|
def test_store_full_text_is_bounded(tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
|
# Force the cache dir under the temp home.
|
|
from hermes_constants import get_hermes_dir # noqa: F401
|
|
huge = "x\n" * (wt.MAX_STORED_TEXT_CHARS) # > MAX_STORED_TEXT_CHARS chars
|
|
assert len(huge) > wt.MAX_STORED_TEXT_CHARS
|
|
path = wt._store_full_text("https://example.com/big", huge)
|
|
assert path is not None
|
|
stored = open(path, encoding="utf-8").read()
|
|
# Stored copy capped (+ short marker), not the full unbounded blob.
|
|
assert len(stored) <= wt.MAX_STORED_TEXT_CHARS + 200
|
|
assert "stored copy truncated" in stored
|
|
|
|
|
|
def test_small_page_not_truncated_no_footer(tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
|
content = "short page\nwith a few lines\n"
|
|
model_text, truncated = wt._truncate_with_footer(
|
|
content, "https://example.com/s", char_limit=15000
|
|
)
|
|
assert not truncated
|
|
assert model_text == content
|
|
assert "[TRUNCATED]" not in model_text
|