mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +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.
71 lines
2.3 KiB
Python
71 lines
2.3 KiB
Python
"""Tests for /init — generate or update AGENTS.md from a project scan.
|
|
|
|
Covers the shared prompt builder (hermes_cli.init_command.build_init_prompt)
|
|
and the slash-command registry wiring. /init has no engine and no model tool:
|
|
it builds a guidance-laden prompt that the live agent runs as a normal turn
|
|
(the /learn pattern), so these are the load-bearing behavior contracts.
|
|
"""
|
|
|
|
from hermes_cli.init_command import (
|
|
_QUALITY_BAR,
|
|
build_init_prompt,
|
|
build_init_prompt_for_cwd,
|
|
)
|
|
|
|
|
|
class TestBuildInitPrompt:
|
|
|
|
|
|
|
|
def test_merge_not_overwrite_when_existing_file_passed(self):
|
|
existing = "# My Project\n\nAlways run `make lint` before committing.\n"
|
|
prompt = build_init_prompt("/tmp/proj", existing_file=existing)
|
|
low = prompt.lower()
|
|
# Update mode, with explicit merge-not-overwrite discipline.
|
|
assert "UPDATE the existing AGENTS.md" in prompt
|
|
assert "merge" in low
|
|
assert "do not overwrite" in low or "not overwrite" in low
|
|
assert "preserve" in low
|
|
# And it carries the current content so the agent can merge.
|
|
assert existing.strip() in prompt
|
|
|
|
|
|
def test_includes_extra_notes_verbatim(self):
|
|
notes = "focus on the test setup, and mention the flaky e2e suite"
|
|
prompt = build_init_prompt("/tmp/proj", extra=notes)
|
|
assert notes in prompt
|
|
|
|
|
|
|
|
|
|
|
|
class TestBuildInitPromptForCwd:
|
|
|
|
def test_reads_existing_agents_md(self, tmp_path):
|
|
(tmp_path / "AGENTS.md").write_text(
|
|
"# Existing\n\nRun `tox -e py311`.\n", encoding="utf-8"
|
|
)
|
|
prompt = build_init_prompt_for_cwd(cwd=str(tmp_path))
|
|
assert "UPDATE the existing AGENTS.md" in prompt
|
|
assert "Run `tox -e py311`." in prompt
|
|
|
|
def test_passes_extra_through(self, tmp_path):
|
|
prompt = build_init_prompt_for_cwd(cwd=str(tmp_path), extra="keep it short")
|
|
assert "keep it short" in prompt
|
|
|
|
|
|
class TestInitRegistryWiring:
|
|
def test_init_is_registered_and_resolves(self):
|
|
from hermes_cli.commands import resolve_command
|
|
|
|
cmd = resolve_command("init")
|
|
assert cmd is not None
|
|
assert cmd.name == "init"
|
|
|
|
|
|
def test_init_works_on_the_gateway(self):
|
|
# /init is a both-surfaces command like /learn, not CLI-only.
|
|
from hermes_cli.commands import GATEWAY_KNOWN_COMMANDS
|
|
|
|
assert "init" in GATEWAY_KNOWN_COMMANDS
|
|
|