mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +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).
131 lines
3.9 KiB
Python
131 lines
3.9 KiB
Python
"""Tests for agent.rate_limit_tracker — header parsing and formatting."""
|
|
|
|
import time
|
|
import pytest
|
|
from agent.rate_limit_tracker import (
|
|
RateLimitBucket,
|
|
RateLimitState,
|
|
parse_rate_limit_headers,
|
|
format_rate_limit_display,
|
|
format_rate_limit_compact,
|
|
_fmt_count,
|
|
_fmt_seconds,
|
|
_bar,
|
|
)
|
|
|
|
|
|
# ── Sample headers from Nous inference API ──────────────────────────────
|
|
|
|
NOUS_HEADERS = {
|
|
"x-ratelimit-limit-requests": "800",
|
|
"x-ratelimit-limit-requests-1h": "33600",
|
|
"x-ratelimit-limit-tokens": "8000000",
|
|
"x-ratelimit-limit-tokens-1h": "336000000",
|
|
"x-ratelimit-remaining-requests": "795",
|
|
"x-ratelimit-remaining-requests-1h": "33590",
|
|
"x-ratelimit-remaining-tokens": "7999500",
|
|
"x-ratelimit-remaining-tokens-1h": "335999000",
|
|
"x-ratelimit-reset-requests": "45.5",
|
|
"x-ratelimit-reset-requests-1h": "3500.0",
|
|
"x-ratelimit-reset-tokens": "42.3",
|
|
"x-ratelimit-reset-tokens-1h": "3490.0",
|
|
}
|
|
|
|
|
|
class TestParseHeaders:
|
|
def test_basic_parsing(self):
|
|
state = parse_rate_limit_headers(NOUS_HEADERS, provider="nous")
|
|
assert state is not None
|
|
assert state.provider == "nous"
|
|
assert state.has_data
|
|
|
|
assert state.requests_min.limit == 800
|
|
assert state.requests_min.remaining == 795
|
|
assert state.requests_min.reset_seconds == 45.5
|
|
|
|
assert state.requests_hour.limit == 33600
|
|
assert state.requests_hour.remaining == 33590
|
|
|
|
assert state.tokens_min.limit == 8000000
|
|
assert state.tokens_min.remaining == 7999500
|
|
|
|
assert state.tokens_hour.limit == 336000000
|
|
assert state.tokens_hour.remaining == 335999000
|
|
assert state.tokens_hour.reset_seconds == 3490.0
|
|
|
|
def test_no_headers(self):
|
|
state = parse_rate_limit_headers({})
|
|
assert state is None
|
|
|
|
|
|
|
|
|
|
|
|
class TestBucket:
|
|
|
|
def test_usage_pct(self):
|
|
b = RateLimitBucket(limit=100, remaining=20, reset_seconds=30.0, captured_at=time.time())
|
|
assert b.usage_pct == pytest.approx(80.0)
|
|
|
|
|
|
def test_remaining_seconds_now(self):
|
|
now = time.time()
|
|
b = RateLimitBucket(limit=800, remaining=795, reset_seconds=60.0, captured_at=now - 10)
|
|
# ~50 seconds should remain
|
|
assert 49 <= b.remaining_seconds_now <= 51
|
|
|
|
|
|
|
|
class TestFormatting:
|
|
|
|
|
|
|
|
def test_fmt_seconds_short(self):
|
|
assert _fmt_seconds(45) == "45s"
|
|
assert _fmt_seconds(0) == "0s"
|
|
|
|
|
|
|
|
def test_bar(self):
|
|
bar = _bar(50.0, width=10)
|
|
assert bar == "[█████░░░░░]"
|
|
assert _bar(0.0, width=10) == "[░░░░░░░░░░]"
|
|
assert _bar(100.0, width=10) == "[██████████]"
|
|
|
|
|
|
|
|
|
|
def test_format_compact(self):
|
|
state = parse_rate_limit_headers(NOUS_HEADERS, provider="nous")
|
|
result = format_rate_limit_compact(state)
|
|
assert "RPM:" in result
|
|
assert "RPH:" in result
|
|
assert "TPM:" in result
|
|
assert "TPH:" in result
|
|
assert "resets" in result
|
|
|
|
|
|
|
|
class TestAgentIntegration:
|
|
"""Test that AIAgent captures rate limit state correctly."""
|
|
|
|
def test_capture_rate_limits_from_headers(self):
|
|
"""Simulate the header capture path without a real API call."""
|
|
# Use a mock httpx-like response
|
|
class MockResponse:
|
|
headers = NOUS_HEADERS
|
|
|
|
# Import AIAgent minimally
|
|
|
|
# Test the parsing directly
|
|
state = parse_rate_limit_headers(MockResponse.headers, provider="nous")
|
|
assert state is not None
|
|
assert state.requests_min.limit == 800
|
|
assert state.tokens_hour.limit == 336000000
|
|
|
|
def test_capture_rate_limits_none_response(self):
|
|
"""_capture_rate_limits should handle None gracefully."""
|
|
from agent.rate_limit_tracker import parse_rate_limit_headers
|
|
# None should not crash
|
|
result = parse_rate_limit_headers({})
|
|
assert result is None
|