mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-10 13:31:38 +00:00
c73e74386b
Adds Vertex AI as a first-class provider for Gemini models via Vertex's OpenAI-compatible endpoint. Vertex authenticates with short-lived OAuth2 access tokens (service-account JSON or ADC), not a static API key — the missing piece behind the recurring requests (#13484, #12639, #56259). - agent/vertex_adapter.py: OAuth2 token minting + refresh-on-expiry (5-min margin), ADC->service-account fallback, global vs regional endpoint URLs. Config precedence: env var > config.yaml > default. - plugins/model-providers/vertex/: provider profile (auth_type=vertex), reuses Gemini's extra_body.google.thinking_config translation. - runtime_provider: vertex short-circuit BEFORE the credential pool so a credentials-file path is never mistaken for a static API key; mints a fresh token + computes base_url per resolve. - run_agent + conversation_loop: _try_refresh_vertex_client_credentials() re-mints the token and rebuilds the client on a mid-session 401, so a long-lived gateway agent survives token expiry (~1h). - auxiliary_client: vertex auth_type branch for side-LLM tasks. - config.yaml: vertex.project_id / vertex.region (non-secret, bridged to env); credential path stays in .env (VERTEX_CREDENTIALS_PATH). - setup wizard + model picker: dedicated _model_flow_vertex; curated google/gemini-* model list; --provider choices. - pricing/metadata: Vertex prices off the gemini docs snapshot; endpoint host auto-maps to the vertex provider (no probe spam). - lazy_deps + pyproject [vertex] extra: google-auth, opt-in only. - docs: guides/google-vertex.md + providers page; tests for adapter + runtime resolution. Salvages and modernizes #8427 by @slawt onto current main: rewired from the legacy PROVIDER_REGISTRY path to the provider-profile architecture, moved non-secret config out of .env into config.yaml, and added the per-turn 401 token-refresh the original lacked.
67 lines
2.3 KiB
Python
67 lines
2.3 KiB
Python
"""Unit tests for TurnRetryState (god-file Phase 1b).
|
|
|
|
The dataclass holds the inner-retry-loop's one-shot recovery guards + restart
|
|
signals. These tests pin its shape and default semantics — the behavioral
|
|
guarantee for the loop itself is the existing recovery-branch tests in
|
|
tests/run_agent/ which now exercise these fields via `_retry.<flag>`.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import fields
|
|
|
|
from agent.turn_retry_state import TurnRetryState
|
|
|
|
|
|
EXPECTED_FIELDS = {
|
|
"codex_auth_retry_attempted",
|
|
"anthropic_auth_retry_attempted",
|
|
"nous_auth_retry_attempted",
|
|
"nous_paid_entitlement_refresh_attempted",
|
|
"copilot_auth_retry_attempted",
|
|
"vertex_auth_retry_attempted",
|
|
"thinking_sig_retry_attempted",
|
|
"invalid_encrypted_content_retry_attempted",
|
|
"image_shrink_retry_attempted",
|
|
"multimodal_tool_content_retry_attempted",
|
|
"oauth_1m_beta_retry_attempted",
|
|
"llama_cpp_grammar_retry_attempted",
|
|
"primary_recovery_attempted",
|
|
"has_retried_429",
|
|
"auth_failover_attempted",
|
|
"restart_with_compressed_messages",
|
|
"restart_with_length_continuation",
|
|
"restart_with_rebuilt_messages",
|
|
}
|
|
|
|
|
|
def test_all_guards_default_false():
|
|
s = TurnRetryState()
|
|
for name, value in s:
|
|
assert value is False, f"{name} should default to False"
|
|
|
|
|
|
def test_field_set_matches_contract():
|
|
names = {f.name for f in fields(TurnRetryState)}
|
|
assert names == EXPECTED_FIELDS, (
|
|
f"unexpected drift: missing={EXPECTED_FIELDS - names} extra={names - EXPECTED_FIELDS}"
|
|
)
|
|
|
|
|
|
def test_loop_control_vars_are_not_on_state():
|
|
# retry_count / max_retries / max_compression_attempts stay as loop locals,
|
|
# NOT on the state object (they are while-mechanics, not recovery bookkeeping).
|
|
names = {f.name for f in fields(TurnRetryState)}
|
|
for loop_local in ("retry_count", "max_retries", "max_compression_attempts"):
|
|
assert loop_local not in names
|
|
|
|
|
|
def test_guards_are_independently_mutable():
|
|
s = TurnRetryState()
|
|
s.codex_auth_retry_attempted = True
|
|
s.restart_with_compressed_messages = True
|
|
assert s.codex_auth_retry_attempted is True
|
|
assert s.restart_with_compressed_messages is True
|
|
# untouched guards stay False
|
|
assert s.has_retried_429 is False
|
|
assert s.anthropic_auth_retry_attempted is False
|