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).
62 lines
2.1 KiB
Python
62 lines
2.1 KiB
Python
"""Transient-transport retry count + per-model client-cache isolation.
|
|
|
|
Two related hardening behaviors for auxiliary calls (which include MoA
|
|
reference advisors, a pinned-model path where provider fallback is not a
|
|
meaningful recovery):
|
|
|
|
1. A transient transport blip (connection reset / timeout / 5xx) is retried
|
|
on the SAME provider several times with backoff before giving up — a single
|
|
upstream blip should not silently lose a pinned auxiliary call (root of the
|
|
run2 double-advisor "Connection error" collapse).
|
|
2. Two auxiliary calls to the same provider/base_url/key but DIFFERENT models
|
|
get DISTINCT client-cache keys, so a concurrent fan-out (e.g. opus + gpt-5.5
|
|
advisors) never shares one client entry.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
import types
|
|
from unittest.mock import patch
|
|
|
|
import pytest
|
|
|
|
|
|
|
|
|
|
def test_transient_retry_count_default(monkeypatch):
|
|
from agent import auxiliary_client as ac
|
|
|
|
# No config value -> default.
|
|
monkeypatch.setattr(ac, "load_config", lambda: {}, raising=False)
|
|
with patch("hermes_cli.config.load_config", return_value={}), \
|
|
patch("hermes_cli.config.cfg_get", return_value=None):
|
|
assert ac._transient_retry_count() == ac._DEFAULT_TRANSIENT_RETRIES
|
|
|
|
|
|
|
|
|
|
def test_model_participates_in_client_cache_key():
|
|
"""Same provider/base_url/key, different model -> different cache key.
|
|
|
|
This is what stops two concurrent advisors from sharing (and racing on)
|
|
one cached client entry."""
|
|
from agent.auxiliary_client import _client_cache_key
|
|
|
|
k_opus = _client_cache_key(
|
|
"openrouter", async_mode=False, base_url="https://openrouter.ai/api/v1",
|
|
api_key="K", model="anthropic/claude-opus-4.8",
|
|
)
|
|
k_gpt = _client_cache_key(
|
|
"openrouter", async_mode=False, base_url="https://openrouter.ai/api/v1",
|
|
api_key="K", model="openai/gpt-5.5",
|
|
)
|
|
assert k_opus != k_gpt
|
|
# Same model still collides (cache still works for reuse).
|
|
k_opus2 = _client_cache_key(
|
|
"openrouter", async_mode=False, base_url="https://openrouter.ai/api/v1",
|
|
api_key="K", model="anthropic/claude-opus-4.8",
|
|
)
|
|
assert k_opus == k_opus2
|
|
|
|
|