mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-08 03:01:47 +00:00
9022804d78
Every provider profile is now a self-contained plugin under plugins/model-providers/<name>/, mirroring the plugins/platforms/ pattern established for IRC and Teams. The ProviderProfile ABC stays in providers/; the per-provider profile data moves out. - plugins/model-providers/<name>/__init__.py calls register_provider() - plugins/model-providers/<name>/plugin.yaml declares kind: model-provider - providers/__init__.py._discover_providers() lazily scans bundled plugins then $HERMES_HOME/plugins/model-providers/<name>/ (user override path) - User plugins with the same name override bundled ones (last-writer-wins in register_provider) - Legacy providers/<name>.py layout still supported for back-compat with out-of-tree editable installs - Hermes PluginManager: new kind=model-provider; skipped like memory plugins (providers/ discovery owns them); standalone plugins with register_provider+ProviderProfile in their __init__.py auto-coerce to this kind (same heuristic as memory providers) - skip_names extended to include 'model-providers' so the general PluginManager doesn't double-scan the category - 4 new tests in tests/providers/test_plugin_discovery.py covering bundled discovery, user override, and general-loader isolation - Docs updated: website/docs/developer-guide/adding-providers.md, provider-runtime.md, providers/README.md, plugins/model-providers/README.md No API break: auth.py / config.py / doctor.py / models.py / runtime_provider.py / model_metadata.py / auxiliary_client.py / chat_completions.py / run_agent.py all still consume providers via get_provider_profile() / list_providers() — they just now see plugin-discovered entries instead of pkgutil-iterated ones. Third parties can now drop a single directory into ~/.hermes/plugins/model-providers/<name>/ to add or override an inference provider without touching the repo.
68 lines
1.9 KiB
Python
68 lines
1.9 KiB
Python
"""Custom / Ollama (local) provider profile.
|
|
|
|
Covers any endpoint registered as provider="custom", including local
|
|
Ollama instances. Key quirks:
|
|
- ollama_num_ctx → extra_body.options.num_ctx (local context window)
|
|
- reasoning_config disabled → extra_body.think = False
|
|
"""
|
|
|
|
from typing import Any
|
|
|
|
from providers import register_provider
|
|
from providers.base import ProviderProfile
|
|
|
|
|
|
class CustomProfile(ProviderProfile):
|
|
"""Custom/Ollama local provider — think=false and num_ctx support."""
|
|
|
|
def build_api_kwargs_extras(
|
|
self,
|
|
*,
|
|
reasoning_config: dict | None = None,
|
|
ollama_num_ctx: int | None = None,
|
|
**ctx: Any,
|
|
) -> tuple[dict[str, Any], dict[str, Any]]:
|
|
extra_body: dict[str, Any] = {}
|
|
|
|
# Ollama context window
|
|
if ollama_num_ctx:
|
|
options = extra_body.get("options", {})
|
|
options["num_ctx"] = ollama_num_ctx
|
|
extra_body["options"] = options
|
|
|
|
# Disable thinking when reasoning is turned off
|
|
if reasoning_config and isinstance(reasoning_config, dict):
|
|
_effort = (reasoning_config.get("effort") or "").strip().lower()
|
|
_enabled = reasoning_config.get("enabled", True)
|
|
if _effort == "none" or _enabled is False:
|
|
extra_body["think"] = False
|
|
|
|
return extra_body, {}
|
|
|
|
def fetch_models(
|
|
self,
|
|
*,
|
|
api_key: str | None = None,
|
|
timeout: float = 8.0,
|
|
) -> list[str] | None:
|
|
"""Custom/Ollama: base_url is user-configured; fetch if set."""
|
|
if not self.base_url:
|
|
return None
|
|
return super().fetch_models(api_key=api_key, timeout=timeout)
|
|
|
|
|
|
custom = CustomProfile(
|
|
name="custom",
|
|
aliases=(
|
|
"ollama",
|
|
"local",
|
|
"vllm",
|
|
"llamacpp",
|
|
"llama.cpp",
|
|
"llama-cpp",
|
|
),
|
|
env_vars=(), # No fixed key — custom endpoint
|
|
base_url="", # User-configured
|
|
)
|
|
|
|
register_provider(custom)
|