mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-24 16:54:43 +00:00
3ea35d6711
The Vertex AI provider (added same-day, commit c73e74386) was never added to
either of the two provider registries that agent/auxiliary_client.py and the
MoA slot-resolution chain depend on, breaking Vertex outside the main
conversation loop:
1. hermes_cli/auth.py::PROVIDER_REGISTRY had no "vertex" entry. The
plugin-auto-extend loop that normally fills gaps explicitly skips
non-api_key auth types (`if _pp.auth_type != "api_key": continue`), and
Vertex was never hand-declared like "bedrock" is. Because
resolve_provider_client() in agent/auxiliary_client.py gates everything
on `pconfig = PROVIDER_REGISTRY.get(provider)` and returns (None, None)
immediately when pconfig is None, its `elif pconfig.auth_type == "vertex"`
branch was permanently dead code — every auxiliary Vertex call (vision,
title generation, reflection, context compression, MoA reference/
aggregator slots) failed outright, not just a MoA-specific edge case.
2. hermes_cli/providers.py::HERMES_OVERLAYS also had no "vertex" entry, so
hermes_cli.providers.get_provider("vertex") returned None. This backs
_preserve_provider_with_base_url() in agent/auxiliary_client.py, which a
MoA slot's resolved (base_url, api_key) pair needs to keep its "vertex"
identity instead of silently collapsing to "custom" — losing the
identity _refresh_provider_credentials() needs to re-mint an expired
OAuth2 token (~1h lifetime) on a 401, and permanently breaking every
subsequent call in that MoA preset for the rest of the session.
Fix mirrors the existing "bedrock"/aws_sdk entries in both registries
exactly, plus adds a "vertex" branch to _refresh_provider_credentials() (it
had branches for openai-codex/nous/anthropic/xai-oauth but not vertex,
so a 401 fell through to `return False` without evicting the stale cached
client).
- hermes_cli/auth.py: hand-declared vertex ProviderConfig(auth_type="vertex")
in PROVIDER_REGISTRY, matching bedrock's shape.
- hermes_cli/providers.py: vertex HermesOverlay(auth_type="vertex") in
HERMES_OVERLAYS + "Google Vertex AI" label override.
- agent/auxiliary_client.py: vertex branch in _refresh_provider_credentials
that re-mints the token via get_vertex_config() and evicts the stale
cached client.
- 8 new regression tests across tests/hermes_cli/test_vertex_provider.py and
tests/agent/test_auxiliary_client.py: registry membership, end-to-end
resolve_provider_client("vertex", ...) building a working client (proving
the previously-dead branch is now reachable), and the 401-refresh/cache-
eviction path.
128 lines
4.6 KiB
Python
128 lines
4.6 KiB
Python
"""Tests for Vertex AI runtime-provider resolution and profile registration.
|
|
|
|
Covers: provider-profile registration + aliases, alias canonicalization,
|
|
resolve_runtime_provider(vertex) minting an OAuth token, and the friendly
|
|
AuthError when credentials can't be resolved. No network calls.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
|
|
def test_vertex_profile_registered():
|
|
from providers import get_provider_profile
|
|
|
|
p = get_provider_profile("vertex")
|
|
assert p is not None
|
|
assert p.name == "vertex"
|
|
assert p.api_mode == "chat_completions"
|
|
assert p.auth_type == "vertex"
|
|
|
|
|
|
@pytest.mark.parametrize("alias", ["google-vertex", "vertex-ai", "gcp-vertex"])
|
|
def test_vertex_aliases_resolve(alias):
|
|
from providers import get_provider_profile
|
|
|
|
assert get_provider_profile(alias).name == "vertex"
|
|
|
|
|
|
@pytest.mark.parametrize("alias", ["google-vertex", "vertex-ai", "gcp-vertex", "vertexai"])
|
|
def test_alias_canonicalizes_to_vertex(alias):
|
|
from hermes_cli.models import _PROVIDER_ALIASES
|
|
|
|
assert _PROVIDER_ALIASES[alias] == "vertex"
|
|
|
|
|
|
def test_google_vertex_not_confused_with_gemini():
|
|
"""`google-vertex` must map to vertex, not the AI-Studio `gemini` provider."""
|
|
from hermes_cli.models import _PROVIDER_ALIASES
|
|
|
|
assert _PROVIDER_ALIASES["google-vertex"] == "vertex"
|
|
assert _PROVIDER_ALIASES["google-gemini"] == "gemini"
|
|
|
|
|
|
def test_resolve_runtime_provider_mints_token(monkeypatch):
|
|
import agent.vertex_adapter as va
|
|
from hermes_cli import runtime_provider as rp
|
|
|
|
monkeypatch.setattr(
|
|
va, "get_vertex_config",
|
|
lambda: ("ya29.TOKEN", "https://aiplatform.googleapis.com/v1beta1/projects/p/locations/global/endpoints/openapi"),
|
|
)
|
|
rt = rp.resolve_runtime_provider(requested="vertex")
|
|
assert rt["provider"] == "vertex"
|
|
assert rt["api_mode"] == "chat_completions"
|
|
assert rt["source"] == "vertex-oauth"
|
|
assert rt["api_key"] == "ya29.TOKEN"
|
|
assert "aiplatform.googleapis.com" in rt["base_url"]
|
|
|
|
|
|
def test_resolve_runtime_provider_alias(monkeypatch):
|
|
import agent.vertex_adapter as va
|
|
from hermes_cli import runtime_provider as rp
|
|
|
|
monkeypatch.setattr(va, "get_vertex_config", lambda: ("t", "https://aiplatform.googleapis.com/v1beta1/projects/p/locations/global/endpoints/openapi"))
|
|
rt = rp.resolve_runtime_provider(requested="google-vertex")
|
|
assert rt["provider"] == "vertex"
|
|
|
|
|
|
def test_resolve_runtime_provider_raises_autherror_when_unresolved(monkeypatch):
|
|
import agent.vertex_adapter as va
|
|
from hermes_cli import runtime_provider as rp
|
|
from hermes_cli.auth import AuthError
|
|
|
|
monkeypatch.setattr(va, "get_vertex_config", lambda: (None, None))
|
|
with pytest.raises(AuthError) as exc:
|
|
rp.resolve_runtime_provider(requested="vertex")
|
|
msg = str(exc.value)
|
|
assert "OAuth2" in msg
|
|
assert "not a static API key" in msg
|
|
|
|
|
|
def test_vertex_extra_body_thinking_config():
|
|
from providers import get_provider_profile
|
|
|
|
p = get_provider_profile("vertex")
|
|
body = p.build_extra_body(
|
|
model="google/gemini-3-pro-preview",
|
|
reasoning_config={"effort": "high"},
|
|
)
|
|
assert "extra_body" in body
|
|
assert "google" in body["extra_body"]
|
|
assert "thinking_config" in body["extra_body"]["google"]
|
|
|
|
|
|
def test_vertex_extra_body_empty_without_reasoning():
|
|
from providers import get_provider_profile
|
|
|
|
p = get_provider_profile("vertex")
|
|
assert p.build_extra_body(model="google/gemini-3-flash-preview") == {}
|
|
|
|
|
|
def test_vertex_registered_in_provider_registry():
|
|
"""PROVIDER_REGISTRY (hermes_cli.auth) is what agent/auxiliary_client.py's
|
|
resolve_provider_client() looks up before dispatching on auth_type. Without
|
|
an entry here, the ``elif pconfig.auth_type == "vertex":`` branch there is
|
|
unreachable dead code — every auxiliary Vertex call (vision, title
|
|
generation, MoA reference/aggregator slots, ...) fails at the
|
|
``pconfig is None`` guard before ever reaching it."""
|
|
from hermes_cli.auth import PROVIDER_REGISTRY
|
|
|
|
cfg = PROVIDER_REGISTRY.get("vertex")
|
|
assert cfg is not None
|
|
assert cfg.auth_type == "vertex"
|
|
|
|
|
|
def test_vertex_registered_in_hermes_overlays():
|
|
"""hermes_cli.providers.get_provider("vertex") backs
|
|
_preserve_provider_with_base_url() in agent/auxiliary_client.py, which
|
|
decides whether a MoA slot's resolved Vertex (base_url, api_key) pair
|
|
keeps its "vertex" provider identity or silently collapses to "custom" —
|
|
losing the identity _refresh_provider_credentials() needs to re-mint an
|
|
expired OAuth2 token on a 401."""
|
|
from hermes_cli.providers import get_provider
|
|
|
|
resolved = get_provider("vertex")
|
|
assert resolved is not None
|
|
assert resolved.auth_type == "vertex"
|