mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-18 04:41:56 +00:00
883e11f0a0
Pass session_id through to provider profile build_api_kwargs_extras so the OpenRouter profile can attach an xAI cache-affinity header (x-grok-conv-id: <session-id>) for x-ai/grok-* models. xAI prompt cache requires server affinity via this header — without it the cache is poisoned and Grok prompt-cache hit rates drop dramatically on multi-turn sessions. Carve-out of #22708 by Ninso112. The original PR bundled a /diff slash command, a zsh completion fix (already on main via #22802), and holographic memory null-guards. This salvage keeps just the Grok header work — small, targeted, and well-tested. Other contributors and changes preserved for separate review. Closes #22705.
98 lines
3.2 KiB
Python
98 lines
3.2 KiB
Python
"""OpenRouter provider profile."""
|
|
|
|
import logging
|
|
from typing import Any
|
|
|
|
from providers import register_provider
|
|
from providers.base import ProviderProfile
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
_CACHE: list[str] | None = None
|
|
|
|
|
|
class OpenRouterProfile(ProviderProfile):
|
|
"""OpenRouter aggregator — provider preferences, reasoning config passthrough."""
|
|
|
|
def fetch_models(
|
|
self,
|
|
*,
|
|
api_key: str | None = None,
|
|
timeout: float = 8.0,
|
|
) -> list[str] | None:
|
|
"""Fetch from public OpenRouter catalog — no auth required.
|
|
|
|
Note: Tool-call capability filtering is applied by hermes_cli/models.py
|
|
via fetch_openrouter_models() → _openrouter_model_supports_tools(), not
|
|
here. The picker early-returns via the dedicated openrouter path before
|
|
reaching this method, so filtering here would be unreachable.
|
|
"""
|
|
global _CACHE # noqa: PLW0603
|
|
if _CACHE is not None:
|
|
return _CACHE
|
|
try:
|
|
result = super().fetch_models(api_key=None, timeout=timeout)
|
|
if result is not None:
|
|
_CACHE = result
|
|
return result
|
|
except Exception as exc:
|
|
logger.debug("fetch_models(openrouter): %s", exc)
|
|
return None
|
|
|
|
def build_extra_body(
|
|
self, *, session_id: str | None = None, **context: Any
|
|
) -> dict[str, Any]:
|
|
body: dict[str, Any] = {}
|
|
prefs = context.get("provider_preferences")
|
|
if prefs:
|
|
body["provider"] = prefs
|
|
return body
|
|
|
|
def build_api_kwargs_extras(
|
|
self,
|
|
*,
|
|
reasoning_config: dict | None = None,
|
|
supports_reasoning: bool = False,
|
|
model: str | None = None,
|
|
session_id: str | None = None,
|
|
**context: Any,
|
|
) -> tuple[dict[str, Any], dict[str, Any]]:
|
|
"""OpenRouter passes the full reasoning_config dict as extra_body.reasoning.
|
|
|
|
For xAI Grok models routed through OpenRouter, attach the
|
|
``x-grok-conv-id`` header so that xAI's prompt cache stays pinned to
|
|
the same backend server across turns.
|
|
"""
|
|
extra_body: dict[str, Any] = {}
|
|
if supports_reasoning:
|
|
if reasoning_config is not None:
|
|
extra_body["reasoning"] = dict(reasoning_config)
|
|
else:
|
|
extra_body["reasoning"] = {"enabled": True, "effort": "medium"}
|
|
|
|
extra_headers: dict[str, Any] = {}
|
|
if session_id and model and model.startswith(("x-ai/grok-", "xai/grok-")):
|
|
extra_headers["x-grok-conv-id"] = session_id
|
|
|
|
return extra_body, {"extra_headers": extra_headers} if extra_headers else {}
|
|
|
|
|
|
openrouter = OpenRouterProfile(
|
|
name="openrouter",
|
|
aliases=("or",),
|
|
env_vars=("OPENROUTER_API_KEY",),
|
|
display_name="OpenRouter",
|
|
description="OpenRouter — unified API for 200+ models",
|
|
signup_url="https://openrouter.ai/keys",
|
|
base_url="https://openrouter.ai/api/v1",
|
|
models_url="https://openrouter.ai/api/v1/models",
|
|
fallback_models=(
|
|
"anthropic/claude-sonnet-4.6",
|
|
"openai/gpt-5.4",
|
|
"deepseek/deepseek-chat",
|
|
"google/gemini-3-flash-preview",
|
|
"qwen/qwen3-plus",
|
|
),
|
|
)
|
|
|
|
register_provider(openrouter)
|