mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-25 00:51:20 +00:00
fix(aux): honor api_mode for custom auxiliary endpoints
This commit is contained in:
Billard
Teknium
parent
c1f832a610
commit
475cbce775
2 changed files with 162 additions and 8 deletions
|
|
@ -857,7 +857,7 @@ def _read_main_provider() -> str:
|
|||
return ""
|
||||
|
||||
|
||||
def _resolve_custom_runtime() -> Tuple[Optional[str], Optional[str]]:
|
||||
def _resolve_custom_runtime() -> Tuple[Optional[str], Optional[str], Optional[str]]:
|
||||
"""Resolve the active custom/main endpoint the same way the main CLI does.
|
||||
|
||||
This covers both env-driven OPENAI_BASE_URL setups and config-saved custom
|
||||
|
|
@ -870,18 +870,29 @@ def _resolve_custom_runtime() -> Tuple[Optional[str], Optional[str]]:
|
|||
runtime = resolve_runtime_provider(requested="custom")
|
||||
except Exception as exc:
|
||||
logger.debug("Auxiliary client: custom runtime resolution failed: %s", exc)
|
||||
return None, None
|
||||
runtime = None
|
||||
|
||||
if not isinstance(runtime, dict):
|
||||
openai_base = os.getenv("OPENAI_BASE_URL", "").strip().rstrip("/")
|
||||
openai_key = os.getenv("OPENAI_API_KEY", "").strip()
|
||||
if not openai_base:
|
||||
return None, None, None
|
||||
runtime = {
|
||||
"base_url": openai_base,
|
||||
"api_key": openai_key,
|
||||
}
|
||||
|
||||
custom_base = runtime.get("base_url")
|
||||
custom_key = runtime.get("api_key")
|
||||
custom_mode = runtime.get("api_mode")
|
||||
if not isinstance(custom_base, str) or not custom_base.strip():
|
||||
return None, None
|
||||
return None, None, None
|
||||
|
||||
custom_base = custom_base.strip().rstrip("/")
|
||||
if "openrouter.ai" in custom_base.lower():
|
||||
# requested='custom' falls back to OpenRouter when no custom endpoint is
|
||||
# configured. Treat that as "no custom endpoint" for auxiliary routing.
|
||||
return None, None
|
||||
return None, None, None
|
||||
|
||||
# Local servers (Ollama, llama.cpp, vLLM, LM Studio) don't require auth.
|
||||
# Use a placeholder key — the OpenAI SDK requires a non-empty string but
|
||||
|
|
@ -890,20 +901,33 @@ def _resolve_custom_runtime() -> Tuple[Optional[str], Optional[str]]:
|
|||
if not isinstance(custom_key, str) or not custom_key.strip():
|
||||
custom_key = "no-key-required"
|
||||
|
||||
return custom_base, custom_key.strip()
|
||||
if not isinstance(custom_mode, str) or not custom_mode.strip():
|
||||
custom_mode = None
|
||||
|
||||
return custom_base, custom_key.strip(), custom_mode
|
||||
|
||||
|
||||
def _current_custom_base_url() -> str:
|
||||
custom_base, _ = _resolve_custom_runtime()
|
||||
custom_base, _, _ = _resolve_custom_runtime()
|
||||
return custom_base or ""
|
||||
|
||||
|
||||
def _try_custom_endpoint() -> Tuple[Optional[OpenAI], Optional[str]]:
|
||||
custom_base, custom_key = _resolve_custom_runtime()
|
||||
runtime = _resolve_custom_runtime()
|
||||
if len(runtime) == 2:
|
||||
custom_base, custom_key = runtime
|
||||
custom_mode = None
|
||||
else:
|
||||
custom_base, custom_key, custom_mode = runtime
|
||||
if not custom_base or not custom_key:
|
||||
return None, None
|
||||
if custom_base.lower().startswith(_CODEX_AUX_BASE_URL.lower()):
|
||||
return None, None
|
||||
model = _read_main_model() or "gpt-4o-mini"
|
||||
logger.debug("Auxiliary client: custom endpoint (%s)", model)
|
||||
logger.debug("Auxiliary client: custom endpoint (%s, api_mode=%s)", model, custom_mode or "chat_completions")
|
||||
if custom_mode == "codex_responses":
|
||||
real_client = OpenAI(api_key=custom_key, base_url=custom_base)
|
||||
return CodexAuxiliaryClient(real_client, model), model
|
||||
return OpenAI(api_key=custom_key, base_url=custom_base), model
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -658,6 +658,19 @@ class TestGetTextAuxiliaryClient:
|
|||
assert client is None
|
||||
assert model is None
|
||||
|
||||
def test_custom_endpoint_uses_codex_wrapper_when_runtime_requests_responses_api(self):
|
||||
with patch("agent.auxiliary_client._resolve_custom_runtime",
|
||||
return_value=("https://api.openai.com/v1", "sk-test", "codex_responses")), \
|
||||
patch("agent.auxiliary_client._read_main_model", return_value="gpt-5.3-codex"), \
|
||||
patch("agent.auxiliary_client.OpenAI") as mock_openai:
|
||||
client, model = get_text_auxiliary_client()
|
||||
|
||||
from agent.auxiliary_client import CodexAuxiliaryClient
|
||||
assert isinstance(client, CodexAuxiliaryClient)
|
||||
assert model == "gpt-5.3-codex"
|
||||
assert mock_openai.call_args.kwargs["base_url"] == "https://api.openai.com/v1"
|
||||
assert mock_openai.call_args.kwargs["api_key"] == "sk-test"
|
||||
|
||||
|
||||
class TestVisionClientFallback:
|
||||
"""Vision client auto mode resolves known-good multimodal backends."""
|
||||
|
|
@ -838,6 +851,123 @@ class TestGetAuxiliaryProvider:
|
|||
assert _get_auxiliary_provider("web_extract") == "main"
|
||||
|
||||
|
||||
class TestResolveForcedProvider:
|
||||
"""Tests for _resolve_forced_provider with explicit provider selection."""
|
||||
|
||||
def test_forced_openrouter(self, monkeypatch):
|
||||
monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
|
||||
with patch("agent.auxiliary_client.OpenAI") as mock_openai:
|
||||
client, model = _resolve_forced_provider("openrouter")
|
||||
assert model == "google/gemini-3-flash-preview"
|
||||
assert client is not None
|
||||
|
||||
def test_forced_openrouter_no_key(self, monkeypatch):
|
||||
with patch("agent.auxiliary_client._read_nous_auth", return_value=None):
|
||||
client, model = _resolve_forced_provider("openrouter")
|
||||
assert client is None
|
||||
assert model is None
|
||||
|
||||
def test_forced_nous(self, monkeypatch):
|
||||
with patch("agent.auxiliary_client._read_nous_auth") as mock_nous, \
|
||||
patch("agent.auxiliary_client.OpenAI"):
|
||||
mock_nous.return_value = {"access_token": "nous-tok"}
|
||||
client, model = _resolve_forced_provider("nous")
|
||||
assert model == "google/gemini-3-flash-preview"
|
||||
assert client is not None
|
||||
|
||||
def test_forced_nous_not_configured(self, monkeypatch):
|
||||
with patch("agent.auxiliary_client._read_nous_auth", return_value=None):
|
||||
client, model = _resolve_forced_provider("nous")
|
||||
assert client is None
|
||||
assert model is None
|
||||
|
||||
def test_forced_main_uses_custom(self, monkeypatch):
|
||||
config = {
|
||||
"model": {
|
||||
"provider": "custom",
|
||||
"base_url": "http://local:8080/v1",
|
||||
"default": "my-local-model",
|
||||
}
|
||||
}
|
||||
monkeypatch.setenv("OPENAI_API_KEY", "local-key")
|
||||
monkeypatch.setattr("hermes_cli.config.load_config", lambda: config)
|
||||
monkeypatch.setattr("hermes_cli.runtime_provider.load_config", lambda: config)
|
||||
with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
|
||||
patch("agent.auxiliary_client.OpenAI") as mock_openai:
|
||||
client, model = _resolve_forced_provider("main")
|
||||
assert model == "my-local-model"
|
||||
|
||||
def test_forced_main_uses_config_saved_custom_endpoint(self, monkeypatch):
|
||||
config = {
|
||||
"model": {
|
||||
"provider": "custom",
|
||||
"base_url": "http://local:8080/v1",
|
||||
"default": "my-local-model",
|
||||
}
|
||||
}
|
||||
monkeypatch.setenv("OPENAI_API_KEY", "local-key")
|
||||
monkeypatch.setattr("hermes_cli.config.load_config", lambda: config)
|
||||
monkeypatch.setattr("hermes_cli.runtime_provider.load_config", lambda: config)
|
||||
with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
|
||||
patch("agent.auxiliary_client._read_codex_access_token", return_value=None), \
|
||||
patch("agent.auxiliary_client._resolve_api_key_provider", return_value=(None, None)), \
|
||||
patch("agent.auxiliary_client.OpenAI") as mock_openai:
|
||||
client, model = _resolve_forced_provider("main")
|
||||
assert client is not None
|
||||
assert model == "my-local-model"
|
||||
call_kwargs = mock_openai.call_args
|
||||
assert call_kwargs.kwargs["base_url"] == "http://local:8080/v1"
|
||||
|
||||
def test_forced_main_skips_openrouter_nous(self, monkeypatch):
|
||||
"""Even if OpenRouter key is set, 'main' skips it."""
|
||||
config = {
|
||||
"model": {
|
||||
"provider": "custom",
|
||||
"base_url": "http://local:8080/v1",
|
||||
"default": "my-local-model",
|
||||
}
|
||||
}
|
||||
monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")
|
||||
monkeypatch.setenv("OPENAI_API_KEY", "local-key")
|
||||
monkeypatch.setattr("hermes_cli.config.load_config", lambda: config)
|
||||
monkeypatch.setattr("hermes_cli.runtime_provider.load_config", lambda: config)
|
||||
with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
|
||||
patch("agent.auxiliary_client.OpenAI") as mock_openai:
|
||||
client, model = _resolve_forced_provider("main")
|
||||
# Should use custom endpoint, not OpenRouter
|
||||
assert model == "my-local-model"
|
||||
|
||||
def test_forced_main_falls_to_codex(self, codex_auth_dir, monkeypatch):
|
||||
with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
|
||||
patch("agent.auxiliary_client._resolve_custom_runtime", return_value=(None, None, None)), \
|
||||
patch("agent.auxiliary_client.OpenAI"):
|
||||
client, model = _resolve_forced_provider("main")
|
||||
from agent.auxiliary_client import CodexAuxiliaryClient
|
||||
assert isinstance(client, CodexAuxiliaryClient)
|
||||
assert model == "gpt-5.2-codex"
|
||||
|
||||
def test_forced_codex(self, codex_auth_dir, monkeypatch):
|
||||
with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
|
||||
patch("agent.auxiliary_client.OpenAI"):
|
||||
client, model = _resolve_forced_provider("codex")
|
||||
from agent.auxiliary_client import CodexAuxiliaryClient
|
||||
assert isinstance(client, CodexAuxiliaryClient)
|
||||
assert model == "gpt-5.2-codex"
|
||||
|
||||
def test_forced_codex_no_token(self, monkeypatch):
|
||||
with patch("agent.auxiliary_client._read_codex_access_token", return_value=None):
|
||||
client, model = _resolve_forced_provider("codex")
|
||||
assert client is None
|
||||
assert model is None
|
||||
|
||||
def test_forced_unknown_returns_none(self, monkeypatch):
|
||||
with patch("agent.auxiliary_client._read_nous_auth", return_value=None), \
|
||||
patch("agent.auxiliary_client._read_codex_access_token", return_value=None):
|
||||
client, model = _resolve_forced_provider("invalid-provider")
|
||||
assert client is None
|
||||
assert model is None
|
||||
|
||||
|
||||
class TestTaskSpecificOverrides:
|
||||
"""Integration tests for per-task provider routing via get_text_auxiliary_client(task=...)."""
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue