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).
88 lines
3.4 KiB
Python
88 lines
3.4 KiB
Python
"""Tests for local provider stream read timeout auto-detection.
|
|
|
|
When a local LLM provider is detected (Ollama, llama.cpp, vLLM, etc.),
|
|
the httpx stream read timeout should be automatically increased from the
|
|
default 60s to HERMES_API_TIMEOUT (1800s) to avoid premature connection
|
|
kills during long prefill phases.
|
|
"""
|
|
|
|
import os
|
|
import pytest
|
|
from unittest.mock import patch
|
|
|
|
from agent.model_metadata import is_local_endpoint
|
|
|
|
|
|
class TestLocalStreamReadTimeout:
|
|
"""Verify stream read timeout auto-detection logic."""
|
|
|
|
@pytest.mark.parametrize("base_url", [
|
|
"http://localhost:11434",
|
|
"http://127.0.0.1:8080",
|
|
"http://0.0.0.0:5000",
|
|
"http://192.168.1.100:8000",
|
|
"http://10.0.0.5:1234",
|
|
"http://host.docker.internal:11434",
|
|
"http://host.containers.internal:11434",
|
|
"http://host.lima.internal:11434",
|
|
])
|
|
def test_local_endpoint_bumps_read_timeout(self, base_url):
|
|
"""Local endpoint + default timeout -> bumps to base_timeout."""
|
|
with patch.dict(os.environ, {}, clear=False):
|
|
os.environ.pop("HERMES_STREAM_READ_TIMEOUT", None)
|
|
_base_timeout = float(os.getenv("HERMES_API_TIMEOUT", 1800.0))
|
|
_stream_read_timeout = float(os.getenv("HERMES_STREAM_READ_TIMEOUT", 120.0))
|
|
if _stream_read_timeout == 120.0 and base_url and is_local_endpoint(base_url):
|
|
_stream_read_timeout = _base_timeout
|
|
assert _stream_read_timeout == 1800.0
|
|
|
|
def test_user_override_respected_for_local(self):
|
|
"""User sets HERMES_STREAM_READ_TIMEOUT -> keep their value even for local."""
|
|
with patch.dict(os.environ, {"HERMES_STREAM_READ_TIMEOUT": "300"}, clear=False):
|
|
_base_timeout = float(os.getenv("HERMES_API_TIMEOUT", 1800.0))
|
|
_stream_read_timeout = float(os.getenv("HERMES_STREAM_READ_TIMEOUT", 120.0))
|
|
base_url = "http://localhost:11434"
|
|
if _stream_read_timeout == 120.0 and base_url and is_local_endpoint(base_url):
|
|
_stream_read_timeout = _base_timeout
|
|
assert _stream_read_timeout == 300.0
|
|
|
|
|
|
def test_empty_base_url_keeps_default(self):
|
|
"""No base_url set -> keep 120s default."""
|
|
with patch.dict(os.environ, {}, clear=False):
|
|
os.environ.pop("HERMES_STREAM_READ_TIMEOUT", None)
|
|
_base_timeout = float(os.getenv("HERMES_API_TIMEOUT", 1800.0))
|
|
_stream_read_timeout = float(os.getenv("HERMES_STREAM_READ_TIMEOUT", 120.0))
|
|
base_url = ""
|
|
if _stream_read_timeout == 120.0 and base_url and is_local_endpoint(base_url):
|
|
_stream_read_timeout = _base_timeout
|
|
assert _stream_read_timeout == 120.0
|
|
|
|
|
|
class TestIsLocalEndpoint:
|
|
"""Direct unit tests for is_local_endpoint."""
|
|
|
|
@pytest.mark.parametrize("url", [
|
|
"http://localhost:11434",
|
|
"http://127.0.0.1:8080",
|
|
"http://0.0.0.0:5000",
|
|
"http://[::1]:11434",
|
|
"http://192.168.1.100:8000",
|
|
"http://10.0.0.5:1234",
|
|
"http://172.17.0.1:11434",
|
|
])
|
|
def test_classic_local_addresses(self, url):
|
|
assert is_local_endpoint(url) is True
|
|
|
|
|
|
|
|
@pytest.mark.parametrize("url", [
|
|
"https://api.openai.com",
|
|
"https://openrouter.ai/api",
|
|
"https://api.anthropic.com",
|
|
"https://evil.docker.internal.example.com",
|
|
])
|
|
def test_remote_endpoints(self, url):
|
|
assert is_local_endpoint(url) is False
|
|
|
|
|