mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-23 16:36:23 +00:00
4c64ff3aa0
* feat(nous): send top-level session_id for provider sticky routing The Nous Portal profile only embedded the session id inside portal tags, so Claude traffic through the portal had no sticky-routing key. Multi-turn sessions could reroute between upstream endpoints (Anthropic/Vertex/ Bedrock), cold-writing a fresh prompt cache on every reroute since each provider's cache is instance-local. Mirror the OpenRouter profile: emit extra_body.session_id whenever the agent has one, pinning every turn of a session to the same endpoint so explicit cache_control breakpoints stay warm. * test: expect top-level session_id in Nous max-iterations summary body Sibling site of the profile change — the max-iterations summary path builds its request through the same NousProfile.build_extra_body(), so its exact-shape assertion now includes the sticky-routing session_id when the agent has a session.
67 lines
2.4 KiB
Python
67 lines
2.4 KiB
Python
"""Nous Portal provider profile."""
|
|
|
|
from typing import Any
|
|
|
|
from agent.portal_tags import nous_portal_tags
|
|
from providers import register_provider
|
|
from providers.base import ProviderProfile
|
|
|
|
|
|
class NousProfile(ProviderProfile):
|
|
"""Nous Portal — product tags, reasoning with Nous-specific omission."""
|
|
|
|
def build_extra_body(
|
|
self, *, session_id: str | None = None, **context
|
|
) -> dict[str, Any]:
|
|
body: dict[str, Any] = {"tags": nous_portal_tags(session_id=session_id)}
|
|
if session_id:
|
|
# Top-level session_id → provider sticky routing key. Pins every
|
|
# turn of a session to the same upstream endpoint so explicit
|
|
# Anthropic cache_control breakpoints stay warm instead of
|
|
# cold-writing a fresh cache on each reroute (Anthropic/Vertex/
|
|
# Bedrock caches are instance-local). Mirrors the OpenRouter
|
|
# profile; without it the portal falls back to hashing the opening
|
|
# messages, which breaks pinning whenever those shift.
|
|
body["session_id"] = session_id
|
|
provider_preferences = context.get("provider_preferences")
|
|
if provider_preferences:
|
|
body["provider"] = provider_preferences
|
|
return body
|
|
|
|
def build_api_kwargs_extras(
|
|
self,
|
|
*,
|
|
reasoning_config: dict | None = None,
|
|
supports_reasoning: bool = False,
|
|
**context,
|
|
) -> tuple[dict[str, Any], dict[str, Any]]:
|
|
"""Nous: passes full reasoning_config, but OMITS when disabled."""
|
|
extra_body = {}
|
|
if supports_reasoning:
|
|
if reasoning_config is not None:
|
|
rc = dict(reasoning_config)
|
|
if rc.get("enabled") is False:
|
|
pass # Nous omits reasoning when disabled
|
|
else:
|
|
extra_body["reasoning"] = rc
|
|
else:
|
|
extra_body["reasoning"] = {"enabled": True, "effort": "medium"}
|
|
return extra_body, {}
|
|
|
|
|
|
nous = NousProfile(
|
|
name="nous",
|
|
aliases=("nous-portal", "nousresearch"),
|
|
env_vars=("NOUS_API_KEY",),
|
|
display_name="Nous Research",
|
|
description="Nous Research — Hermes model family",
|
|
signup_url="https://nousresearch.com/",
|
|
fallback_models=(
|
|
"hermes-3-405b",
|
|
"hermes-3-70b",
|
|
),
|
|
base_url="https://inference-api.nousresearch.com/v1",
|
|
auth_type="oauth_device_code",
|
|
)
|
|
|
|
register_provider(nous)
|