mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-30 19:09:28 +00:00
63fc810b95
gemini-2.5-flash shuts down Oct 16 2026 (Google deprecation schedule) and gemini-3-flash-preview is superseded. Update every hardcoded default to the current GA flash model: - gemini_native_adapter: probe_gemini_tier + _create_chat_completion default params; free-tier guidance de-pinned from a specific model's RPD number so it doesn't stale again - auxiliary_client: gemini/kilocode fallback aux models, _OPENROUTER_MODEL, _NOUS_MODEL -> google/gemini-3.6-flash (verified live on both OpenRouter and Nous portal /models) - provider plugins: kilocode + vertex default_aux_model - hindsight memory plugin: gemini provider default - setup wizard gemini list: 3-flash-preview -> 3.6-flash (matches the curated picker catalog) - tests: aux-client assertions that pinned the old default literal now reference the _NOUS_MODEL constant, so the next default bump can't break them (change-detector cleanup) Fixes #32360.
75 lines
2.8 KiB
Python
75 lines
2.8 KiB
Python
"""Google Vertex AI provider profile.
|
|
|
|
vertex: Gemini models via Google Cloud's OpenAI-compatible endpoint.
|
|
|
|
Auth is OAuth2 — short-lived access tokens minted from a service-account JSON
|
|
or Application Default Credentials (ADC), NOT a static API key. Token
|
|
resolution and refresh live in ``agent/vertex_adapter.py``; runtime_provider.py
|
|
calls it to obtain a fresh ``(token, base_url)`` pair, then hands the token to
|
|
the standard OpenAI client as ``api_key``. Because the wire format is the
|
|
OpenAI-compatible chat/completions surface, no message translation is needed —
|
|
the only Gemini-specific concern is the ``thinking_config`` reasoning hook,
|
|
which is emitted here exactly as the ``gemini`` provider does for its
|
|
OpenAI-compat subpath (``extra_body.google.thinking_config``).
|
|
|
|
``auth_type="vertex"`` marks this as an OAuth-token provider (resolved
|
|
specially, like bedrock's ``aws_sdk``) so it is never treated as an
|
|
api_key provider that would mistake a credentials-file path for a key.
|
|
"""
|
|
|
|
from typing import Any
|
|
|
|
from providers import register_provider
|
|
from providers.base import ProviderProfile
|
|
|
|
|
|
class VertexProfile(ProviderProfile):
|
|
"""Vertex AI — reuse Gemini's thinking_config translation for extra_body."""
|
|
|
|
def build_extra_body(
|
|
self, *, session_id: str | None = None, **context: Any
|
|
) -> dict[str, Any]:
|
|
"""Emit ``extra_body.google.thinking_config`` for the OpenAI-compat
|
|
Vertex surface, mirroring the ``gemini`` provider's behavior.
|
|
"""
|
|
from agent.transports.chat_completions import (
|
|
_build_gemini_thinking_config,
|
|
_snake_case_gemini_thinking_config,
|
|
)
|
|
|
|
model = context.get("model") or ""
|
|
reasoning_config = context.get("reasoning_config")
|
|
|
|
raw_thinking_config = _build_gemini_thinking_config(model, reasoning_config)
|
|
if not raw_thinking_config:
|
|
return {}
|
|
|
|
thinking_config = _snake_case_gemini_thinking_config(raw_thinking_config)
|
|
if not thinking_config:
|
|
return {}
|
|
return {"extra_body": {"google": {"thinking_config": thinking_config}}}
|
|
|
|
def fetch_models(
|
|
self,
|
|
*,
|
|
api_key: str | None = None,
|
|
base_url: str | None = None,
|
|
timeout: float = 8.0,
|
|
) -> list[str] | None:
|
|
"""Vertex's OpenAI-compat endpoint has no ``/models`` listing route;
|
|
model discovery is not available. The setup wizard ships a curated list.
|
|
"""
|
|
return None
|
|
|
|
|
|
vertex = VertexProfile(
|
|
name="vertex",
|
|
aliases=("google-vertex", "vertex-ai", "gcp-vertex"),
|
|
api_mode="chat_completions",
|
|
env_vars=(), # OAuth2 via service account / ADC — not a static key env var
|
|
base_url="https://aiplatform.googleapis.com", # real base_url computed at runtime
|
|
auth_type="vertex",
|
|
default_aux_model="google/gemini-3.6-flash",
|
|
)
|
|
|
|
register_provider(vertex)
|