mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-08 13:12:08 +00:00
fb403a3a73
Two related hardening fixes for auxiliary calls (which include MoA reference advisors — a pinned-model path where provider fallback is not a meaningful recovery): 1. Transient-transport retries: the same-provider retry on a connection reset / timeout / 5xx / 408 was a single attempt, then fallback. For a pinned aux call a second blip silently loses the call (root of the run2 double-advisor 'Connection error' collapse — a genuine upstream blip). Now retries N times with exponential backoff, N = auxiliary.transient_retries (default 2 -> 3 total attempts, clamped [0,6]). Compression-on-timeout fast-fail carve-out preserved. 2. Per-model client-cache isolation: _client_cache_key excluded the model, so two concurrent auxiliary calls to the same provider/base_url/key but different models (e.g. an opus + gpt-5.5 MoA fan-out) shared one cache entry and could race each other's client lifecycle. Model now participates in the key -> distinct clients, no cross-call races. Same-model reuse unchanged. - agent/auxiliary_client.py: _transient_retry_count() + backoff loop; model in _client_cache_key and both call sites. - hermes_cli/config.py: auxiliary.transient_retries default (2). - tests: new retry/isolation tests; updated 2 stale-expectation tests to the corrected behavior (per-model resolve; N-retry escalation). Backoff base is overridable (_TRANSIENT_RETRY_BACKOFF_BASE) so tests don't sleep.
82 lines
3.2 KiB
Python
82 lines
3.2 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
|
|
|
|
|
|
class _ConnErr(Exception):
|
|
"""Stand-in that the transient detector recognizes as a connection blip."""
|
|
|
|
|
|
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_transient_retry_count_configurable_and_clamped():
|
|
from agent import auxiliary_client as ac
|
|
|
|
with patch("hermes_cli.config.cfg_get", return_value=4):
|
|
assert ac._transient_retry_count() == 4
|
|
with patch("hermes_cli.config.cfg_get", return_value=100):
|
|
assert ac._transient_retry_count() == 6 # clamped high
|
|
with patch("hermes_cli.config.cfg_get", return_value=-3):
|
|
assert ac._transient_retry_count() == 0 # clamped low
|
|
with patch("hermes_cli.config.cfg_get", side_effect=RuntimeError):
|
|
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
|
|
|
|
|
|
def test_missing_model_key_is_stable():
|
|
"""Omitting model (legacy callers) is still a valid, stable key."""
|
|
from agent.auxiliary_client import _client_cache_key
|
|
|
|
a = _client_cache_key("openrouter", async_mode=False, base_url="u", api_key="k")
|
|
b = _client_cache_key("openrouter", async_mode=False, base_url="u", api_key="k")
|
|
assert a == b
|