mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
Third-party gateways that speak the native Anthropic protocol (MiniMax,
Zhipu GLM, Alibaba DashScope, Kimi, LiteLLM proxies) now work end-to-end
with the same feature set as direct api.anthropic.com callers. Synthesizes
eight stale community PRs into one consolidated change.
Five fixes:
- URL detection: consolidate three inline `endswith("/anthropic")`
checks in runtime_provider.py into the shared _detect_api_mode_for_url
helper. Third-party /anthropic endpoints now auto-resolve to
api_mode=anthropic_messages via one code path instead of three.
- OAuth leak-guard: all five sites that assign `_is_anthropic_oauth`
(__init__, switch_model, _try_refresh_anthropic_client_credentials,
_swap_credential, _try_activate_fallback) now gate on
`provider == "anthropic"` so a stale ANTHROPIC_TOKEN never trips
Claude-Code identity injection on third-party endpoints. Previously
only 2 of 5 sites were guarded.
- Prompt caching: new method `_anthropic_prompt_cache_policy()` returns
`(should_cache, use_native_layout)` per endpoint. Replaces three
inline conditions and the `native_anthropic=(api_mode=='anthropic_messages')`
call-site flag. Native Anthropic and third-party Anthropic gateways
both get the native cache_control layout; OpenRouter gets envelope
layout. Layout is persisted in `_primary_runtime` so fallback
restoration preserves the per-endpoint choice.
- Auxiliary client: `_try_custom_endpoint` honors
`api_mode=anthropic_messages` and builds `AnthropicAuxiliaryClient`
instead of silently downgrading to an OpenAI-wire client. Degrades
gracefully to OpenAI-wire when the anthropic SDK isn't installed.
- Config hygiene: `_update_config_for_provider` (hermes_cli/auth.py)
clears stale `api_key`/`api_mode` when switching to a built-in
provider, so a previous MiniMax custom endpoint's credentials can't
leak into a later OpenRouter session.
- Truncation continuation: length-continuation and tool-call-truncation
retry now cover `anthropic_messages` in addition to `chat_completions`
and `bedrock_converse`. Reuses the existing `_build_assistant_message`
path via `normalize_anthropic_response()` so the interim message
shape is byte-identical to the non-truncated path.
Tests: 6 new files, 42 test cases. Targeted run + tests/run_agent,
tests/agent, tests/hermes_cli all pass (4554 passed).
Synthesized from (credits preserved via Co-authored-by trailers):
#7410 @nocoo — URL detection helper
#7393 @keyuyuan — OAuth 5-site guard
#7367 @n-WN — OAuth guard (narrower cousin, kept comment)
#8636 @sgaofen — caching helper + native-vs-proxy layout split
#10954 @Only-Code-A — caching on anthropic_messages+Claude
#7648 @zhongyueming1121 — aux client anthropic_messages branch
#6096 @hansnow — /model switch clears stale api_mode
#9691 @TroyMitchell911 — anthropic_messages truncation continuation
Closes: #7366, #8294 (third-party Anthropic identity + caching).
Supersedes: #7410, #7367, #7393, #8636, #10954, #7648, #6096, #9691.
Rejects: #9621 (OpenAI-wire caching with incomplete blocklist — risky),
#7242 (superseded by #9691, stale branch),
#8321 (targets smart_model_routing which was removed in #12732).
Co-authored-by: nocoo <nocoo@users.noreply.github.com>
Co-authored-by: Keyu Yuan <leoyuan0099@gmail.com>
Co-authored-by: Zoee <30841158+n-WN@users.noreply.github.com>
Co-authored-by: sgaofen <135070653+sgaofen@users.noreply.github.com>
Co-authored-by: Only-Code-A <bxzt2006@163.com>
Co-authored-by: zhongyueming <mygamez@163.com>
Co-authored-by: Xiaohan Li <hansnow@users.noreply.github.com>
Co-authored-by: Troy Mitchell <i@troy-y.org>
107 lines
3.9 KiB
Python
107 lines
3.9 KiB
Python
"""Tests for agent.auxiliary_client._try_custom_endpoint's anthropic_messages branch.
|
|
|
|
When a user configures a custom endpoint with ``api_mode: anthropic_messages``
|
|
(e.g. MiniMax, Zhipu GLM, LiteLLM in Anthropic-proxy mode), auxiliary tasks
|
|
(compression, web_extract, session_search, title generation) must use the
|
|
native Anthropic transport rather than being silently downgraded to an
|
|
OpenAI-wire client that speaks the wrong protocol.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _clean_env(monkeypatch):
|
|
for key in (
|
|
"OPENAI_API_KEY", "OPENAI_BASE_URL",
|
|
"ANTHROPIC_API_KEY", "ANTHROPIC_TOKEN",
|
|
):
|
|
monkeypatch.delenv(key, raising=False)
|
|
|
|
|
|
def _install_anthropic_adapter_mocks():
|
|
"""Patch build_anthropic_client so the test doesn't need the SDK."""
|
|
fake_client = MagicMock(name="anthropic_client")
|
|
return patch(
|
|
"agent.anthropic_adapter.build_anthropic_client",
|
|
return_value=fake_client,
|
|
), fake_client
|
|
|
|
|
|
def test_custom_endpoint_anthropic_messages_builds_anthropic_wrapper():
|
|
"""api_mode=anthropic_messages → returns AnthropicAuxiliaryClient, not OpenAI."""
|
|
from agent.auxiliary_client import _try_custom_endpoint, AnthropicAuxiliaryClient
|
|
|
|
with patch(
|
|
"agent.auxiliary_client._resolve_custom_runtime",
|
|
return_value=(
|
|
"https://api.minimax.io/anthropic",
|
|
"minimax-key",
|
|
"anthropic_messages",
|
|
),
|
|
), patch(
|
|
"agent.auxiliary_client._read_main_model",
|
|
return_value="claude-sonnet-4-6",
|
|
):
|
|
adapter_patch, fake_client = _install_anthropic_adapter_mocks()
|
|
with adapter_patch:
|
|
client, model = _try_custom_endpoint()
|
|
|
|
assert isinstance(client, AnthropicAuxiliaryClient), (
|
|
"Custom endpoint with api_mode=anthropic_messages must return the "
|
|
f"native Anthropic wrapper, got {type(client).__name__}"
|
|
)
|
|
assert model == "claude-sonnet-4-6"
|
|
# Wrapper should NOT be marked as OAuth — third-party endpoints are
|
|
# always API-key authenticated.
|
|
assert client.api_key == "minimax-key"
|
|
assert client.base_url == "https://api.minimax.io/anthropic"
|
|
|
|
|
|
def test_custom_endpoint_anthropic_messages_falls_back_when_sdk_missing():
|
|
"""Graceful degradation when anthropic SDK is unavailable."""
|
|
from agent.auxiliary_client import _try_custom_endpoint
|
|
|
|
import_error = ImportError("anthropic package not installed")
|
|
|
|
with patch(
|
|
"agent.auxiliary_client._resolve_custom_runtime",
|
|
return_value=("https://api.minimax.io/anthropic", "k", "anthropic_messages"),
|
|
), patch(
|
|
"agent.auxiliary_client._read_main_model",
|
|
return_value="claude-sonnet-4-6",
|
|
), patch(
|
|
"agent.anthropic_adapter.build_anthropic_client",
|
|
side_effect=import_error,
|
|
):
|
|
client, model = _try_custom_endpoint()
|
|
|
|
# Should fall back to an OpenAI-wire client rather than returning
|
|
# (None, None) — the tool still needs to do *something*.
|
|
assert client is not None
|
|
assert model == "claude-sonnet-4-6"
|
|
# OpenAI client, not AnthropicAuxiliaryClient.
|
|
from agent.auxiliary_client import AnthropicAuxiliaryClient
|
|
assert not isinstance(client, AnthropicAuxiliaryClient)
|
|
|
|
|
|
def test_custom_endpoint_chat_completions_still_uses_openai_wire():
|
|
"""Regression: default path (no api_mode) must remain OpenAI client."""
|
|
from agent.auxiliary_client import _try_custom_endpoint, AnthropicAuxiliaryClient
|
|
|
|
with patch(
|
|
"agent.auxiliary_client._resolve_custom_runtime",
|
|
return_value=("https://api.example.com/v1", "key", None),
|
|
), patch(
|
|
"agent.auxiliary_client._read_main_model",
|
|
return_value="my-model",
|
|
):
|
|
client, model = _try_custom_endpoint()
|
|
|
|
assert client is not None
|
|
assert model == "my-model"
|
|
assert not isinstance(client, AnthropicAuxiliaryClient)
|