hermes-agent/tests/agent/test_billing_usage.py
Teknium 6b81590c55
test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions
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).
2026-07-29 13:10:23 -07:00

112 lines
3.8 KiB
Python

"""Tests for the shared dollar usage model (agent/billing_usage.py).
Behavior contracts: status classification, bar math, fail-open, and the
dollars-only / topup-split invariants the billing UX requires.
"""
from __future__ import annotations
from dataclasses import dataclass
from typing import Optional
import pytest
from agent.billing_usage import LOW_BALANCE_THRESHOLD_USD, UsageBar, usage_model_from_account
# ── Lightweight stand-ins for the NousPortalAccountInfo shape ────────────────
@dataclass
class _Access:
subscription_credits_remaining: Optional[float] = None
purchased_credits_remaining: Optional[float] = None
total_usable_credits: Optional[float] = None
@dataclass
class _Sub:
plan: Optional[str] = None
monthly_credits: Optional[float] = None
current_period_end: Optional[str] = None
@dataclass
class _Account:
logged_in: bool = True
paid_service_access: Optional[bool] = None
paid_service_access_info: Optional[_Access] = None
subscription: Optional[_Sub] = None
def _acct(**over):
return _Account(**over)
class _Boom:
@property
def logged_in(self):
raise RuntimeError("kaboom")
@pytest.mark.parametrize(
"account,expected",
[
# no plan, no balance -> free
(_acct(paid_service_access_info=_Access()), "free"),
# paid access explicitly lost -> depleted
(_acct(paid_service_access=False, subscription=_Sub(plan="Plus", monthly_credits=20.0),
paid_service_access_info=_Access(subscription_credits_remaining=0.0, total_usable_credits=0.0)), "depleted"),
# above threshold -> healthy
(_acct(paid_service_access=True, subscription=_Sub(plan="Plus", monthly_credits=20.0),
paid_service_access_info=_Access(subscription_credits_remaining=14.0, total_usable_credits=14.0)), "healthy"),
# under $5 spendable -> low
(_acct(paid_service_access=True, subscription=_Sub(plan="Plus", monthly_credits=20.0),
paid_service_access_info=_Access(subscription_credits_remaining=3.4, total_usable_credits=3.4)), "low"),
# exactly $5 -> healthy (the threshold boundary is exclusive)
(_acct(paid_service_access=True, subscription=_Sub(plan="Plus", monthly_credits=20.0),
paid_service_access_info=_Access(subscription_credits_remaining=5.0, total_usable_credits=5.0)), "healthy"),
# top-up only, no plan -> usable (healthy), not free
(_acct(paid_service_access=True, paid_service_access_info=_Access(purchased_credits_remaining=30.0, total_usable_credits=30.0)), "healthy"),
],
)
def test_status_classification(account, expected):
m = usage_model_from_account(account)
assert m.available is True
assert m.status == expected
def test_plan_bar_spent_and_pct():
m = usage_model_from_account(
_acct(paid_service_access=True, subscription=_Sub(plan="Plus", monthly_credits=20.0),
paid_service_access_info=_Access(subscription_credits_remaining=14.0, total_usable_credits=14.0))
)
bar = m.plan_bar
assert bar is not None and bar.kind == "plan"
assert (bar.remaining_usd, bar.total_usd, bar.pct_used) == (14.0, 20.0, 30)
assert bar.spent_usd == pytest.approx(6.0)
def test_topup_bar_is_full_with_no_denominator():
m = usage_model_from_account(
_acct(paid_service_access=True, subscription=_Sub(plan="Plus", monthly_credits=20.0),
paid_service_access_info=_Access(subscription_credits_remaining=14.0, purchased_credits_remaining=12.0, total_usable_credits=26.0))
)
tb = m.topup_bar
assert tb is not None and tb.kind == "topup"
assert tb.remaining_usd == 12.0 and tb.fill_fraction == 1.0 and tb.pct_used is None
assert m.total_spendable_usd == 26.0 and m.has_topup is True