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.
47 lines
1.6 KiB
Python
47 lines
1.6 KiB
Python
"""Guard test for the MEDIA:<path> caption chokepoint (_media_caption_split).
|
|
|
|
`hermes send` strips the MEDIA: tag and leaves the remaining prose as the
|
|
accompanying text. Historically every standalone sender posted that text as a
|
|
*separate* message before an uncaptioned media bubble, splitting
|
|
``hermes send --to whatsapp "MEDIA:/x.png This Caption"`` into two parts.
|
|
|
|
`_media_caption_split` is the single enforced decision point that all standalone
|
|
senders (WhatsApp, Telegram, Discord) consult to decide whether the text should
|
|
ride on the media bubble as a native caption. This test pins that contract so
|
|
the platforms can't diverge.
|
|
"""
|
|
|
|
from tools.send_message_tool import (
|
|
_DEFAULT_CAPTION_LIMIT,
|
|
_TELEGRAM_CAPTION_LIMIT,
|
|
_media_caption_split,
|
|
)
|
|
|
|
|
|
def test_single_image_short_text_becomes_caption():
|
|
caption, body = _media_caption_split(
|
|
"This Caption", [("/tmp/F22.png", False)], max_caption_len=_DEFAULT_CAPTION_LIMIT
|
|
)
|
|
assert caption == "This Caption"
|
|
assert body == ""
|
|
|
|
|
|
def test_multi_file_keeps_separate_body():
|
|
text = "two photos"
|
|
caption, body = _media_caption_split(
|
|
text,
|
|
[("/tmp/a.png", False), ("/tmp/b.png", False)],
|
|
max_caption_len=_DEFAULT_CAPTION_LIMIT,
|
|
)
|
|
assert caption is None
|
|
assert body == text
|
|
|
|
|
|
def test_unknown_extension_keeps_separate_body():
|
|
# A non-captionable kind (e.g. an audio note that isn't flagged voice)
|
|
text = "some audio"
|
|
caption, body = _media_caption_split(
|
|
text, [("/tmp/song.mp3", False)], max_caption_len=_DEFAULT_CAPTION_LIMIT
|
|
)
|
|
assert caption is None
|
|
assert body == text
|