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.
110 lines
4.2 KiB
Python
110 lines
4.2 KiB
Python
"""Unit tests for the truncate-and-store web_extract path (no LLM).
|
|
|
|
Covers convert_base64_images_to_links, _truncate_with_footer, _store_full_text,
|
|
_get_extract_char_limit, and the end-to-end web_extract_tool truncation behavior.
|
|
"""
|
|
import asyncio
|
|
import json
|
|
import os
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
import tools.web_tools as wt
|
|
|
|
|
|
class TestImageConversion:
|
|
def test_markdown_base64_image_keeps_alt_drops_blob(self):
|
|
blob = "A" * 5000
|
|
text = f"before  after"
|
|
out = wt.convert_base64_images_to_links(text)
|
|
assert "[IMAGE: a cat]" in out
|
|
assert "base64" not in out
|
|
assert blob not in out
|
|
assert "before" in out and "after" in out
|
|
|
|
|
|
def test_bare_and_parenthesised_base64_become_placeholder(self):
|
|
blob = "Z" * 3000
|
|
bare = wt.convert_base64_images_to_links(f"data:image/gif;base64,{blob}")
|
|
assert bare == "[IMAGE]"
|
|
paren = wt.convert_base64_images_to_links(f"(data:image/gif;base64,{blob})")
|
|
assert paren == "[IMAGE]"
|
|
|
|
|
|
class TestTruncation:
|
|
def test_short_content_returned_whole(self):
|
|
content = "# Title\n\nshort body\n"
|
|
out, truncated = wt._truncate_with_footer(content, "https://e.com", 15000)
|
|
assert out == content
|
|
assert truncated is False
|
|
|
|
|
|
def test_truncation_stores_full_text_readable(self, tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_HOME", str(tmp_path / ".hermes"))
|
|
body = "UNIQUE_MIDDLE_MARKER\n" + ("\n".join(f"row {i}" for i in range(5000)))
|
|
out, truncated = wt._truncate_with_footer(body, "https://example.com/doc", 3000)
|
|
assert truncated is True
|
|
# Extract the stored path from the footer and confirm full text is there.
|
|
path_line = next(ln for ln in out.splitlines() if "Full text saved to:" in ln)
|
|
stored_path = path_line.split("Full text saved to:", 1)[1].strip()
|
|
assert os.path.exists(stored_path)
|
|
full = open(stored_path).read()
|
|
assert "UNIQUE_MIDDLE_MARKER" in full
|
|
assert "row 2500" in full # the omitted-middle row is in the stored file
|
|
|
|
|
|
class TestCharLimitConfig:
|
|
def test_default_when_unset(self):
|
|
with patch("tools.web_tools._load_web_config", return_value={}):
|
|
assert wt._get_extract_char_limit() == wt.DEFAULT_EXTRACT_CHAR_LIMIT
|
|
|
|
|
|
def test_bad_value_falls_back(self):
|
|
with patch("tools.web_tools._load_web_config", return_value={"extract_char_limit": "nope"}):
|
|
assert wt._get_extract_char_limit() == wt.DEFAULT_EXTRACT_CHAR_LIMIT
|
|
|
|
|
|
class TestEndToEnd:
|
|
def test_web_extract_truncates_large_page_no_llm(self, tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_HOME", str(tmp_path / ".hermes"))
|
|
big = "\n".join(f"para {i} " + "y" * 80 for i in range(3000))
|
|
|
|
class FakeProvider:
|
|
name = "fake"
|
|
display_name = "Fake"
|
|
|
|
def supports_extract(self):
|
|
return True
|
|
|
|
async def extract(self, urls, **kwargs):
|
|
return [{"url": urls[0], "title": "Big Page", "content": big,
|
|
"raw_content": big, "metadata": {}}]
|
|
|
|
with patch("tools.web_tools._ensure_web_plugins_loaded"), \
|
|
patch("tools.web_tools._get_extract_backend", return_value="fake"), \
|
|
patch("tools.web_tools.async_is_safe_url", new=_AsyncTrue()), \
|
|
patch("agent.web_search_registry.get_provider", return_value=FakeProvider()):
|
|
result = json.loads(asyncio.new_event_loop().run_until_complete(
|
|
wt.web_extract_tool(["https://example.com/big"], char_limit=5000)
|
|
))
|
|
|
|
assert "results" in result
|
|
content = result["results"][0]["content"]
|
|
assert "[TRUNCATED]" in content
|
|
assert "Full text saved to:" in content
|
|
# No LLM was involved: para 0 (head) and the last para (tail) are verbatim.
|
|
assert "para 0 " in content
|
|
assert "para 2999 " in content
|
|
|
|
|
|
def _make_awaitable(value):
|
|
async def _coro(*a, **k):
|
|
return value
|
|
return _coro()
|
|
|
|
|
|
class _AsyncTrue:
|
|
"""Async callable that always returns True (re-awaitable per call)."""
|
|
async def __call__(self, *a, **k):
|
|
return True
|