hermes-agent/tests/tools/test_web_extract_robustness.py
Teknium 39975613b1
test: prune wave 2 + speed fixes — 28,106 → 19,757 test functions, suite wall 315s → 294s
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.
2026-07-29 13:39:40 -07:00

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