mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
6b81590c55
Systematic prune per AGENTS.md test policy, one pass over every major test tree (gateway, hermes_cli, tools, agent, run_agent, plugins, cli, cron, tui_gateway, honcho/openviking, root-level): - DELETE: source-reading tests (read_text/getsource on prod files), change-detector tests (exact catalog counts, model-name snapshots, config version literals), mock-echo tests (assert a mock returns what it was told), assertion-free/trivial tests, near-duplicate parametrizations (boundaries + one representative kept), async/sync twin duplicates, cosmetic within-file variations. - KEEP (mandatory): security/redaction/approval guards, message-role alternation invariants, prompt-caching/deterministic-call-id invariants, issue-number regression tests (deduped), E2E tests. - 6 test files deleted outright (script-style/no-assert or fully redundant); conftest.py, fakes/, fixtures/ untouched. - tests/acp/conftest.py added: autouse fixture stubs the live models.dev/GitHub/Copilot/Anthropic inventory fetches that ACP server tests performed on every session create — test_server.py 147s → 3.4s, and the tests are now genuinely hermetic. - Sleep-based slowness shrunk where safe (codex_ttfb_watchdog, compression_concurrent_fork, etc.); no wall-clock assertion tightened. Verification: full hermetic suite via scripts/run_tests.sh — 2439 files, 31,130 tests passed, 0 failed, 0 flaky retries, 315s wall (baseline: 583s wall, 13,564s subprocess CPU).
57 lines
1.8 KiB
Python
57 lines
1.8 KiB
Python
"""Tests for hermes -z --usage-file (per-run JSON usage report)."""
|
|
|
|
import json
|
|
|
|
from hermes_cli.oneshot import _write_usage_file
|
|
|
|
|
|
def _result(**overrides):
|
|
base = {
|
|
"estimated_cost_usd": 0.1234,
|
|
"cost_status": "estimated",
|
|
"cost_source": "pricing-table",
|
|
"input_tokens": 1000,
|
|
"output_tokens": 200,
|
|
"cache_read_tokens": 800,
|
|
"cache_write_tokens": 0,
|
|
"reasoning_tokens": 50,
|
|
"total_tokens": 1250,
|
|
"api_calls": 3,
|
|
"model": "openai/gpt-5.5",
|
|
"provider": "openrouter",
|
|
"session_id": "abc123",
|
|
"completed": True,
|
|
"failed": False,
|
|
}
|
|
base.update(overrides)
|
|
return base
|
|
|
|
|
|
class TestWriteUsageFile:
|
|
def test_writes_report_with_cost_and_tokens(self, tmp_path):
|
|
path = tmp_path / "usage.json"
|
|
_write_usage_file(str(path), _result())
|
|
report = json.loads(path.read_text())
|
|
assert report["estimated_cost_usd"] == 0.1234
|
|
assert report["input_tokens"] == 1000
|
|
assert report["output_tokens"] == 200
|
|
assert report["model"] == "openai/gpt-5.5"
|
|
assert report["api_calls"] == 3
|
|
assert report["failed"] is False
|
|
assert "failure" not in report
|
|
|
|
def test_none_path_is_noop(self, tmp_path):
|
|
# Must not raise and must not create a report file.
|
|
_write_usage_file(None, _result())
|
|
assert not (tmp_path / "usage.json").exists()
|
|
|
|
def test_failure_marks_failed_and_records_message(self, tmp_path):
|
|
path = tmp_path / "usage.json"
|
|
_write_usage_file(str(path), {}, failure="boom")
|
|
report = json.loads(path.read_text())
|
|
assert report["failed"] is True
|
|
assert report["failure"] == "boom"
|
|
# Missing result fields serialize as null, not KeyError.
|
|
assert report["estimated_cost_usd"] is None
|
|
|
|
|