mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-14 14:12:44 +00:00
0fce82164a
Move provider adapters (anthropic, bedrock, azure), platform adapters (telegram, slack, discord, feishu, dingtalk, matrix), and terminal backends (modal, daytona) out of core into plugins/ workspace members. Core references them via the plugin registries (get_provider_namespace / get_provider_service / get_tool_provider / get_credential_pool_hook) instead of direct imports. - Provider/platform/terminal adapters relocated under plugins/; pyproject extras reference workspace members; nix variants aggregate per-platform extras. - Anthropic credential discovery + OAuth-masquerade guard live in the plugin's credential_pool_hook; browser-open guarded by _can_open_graphical_browser. - Vercel AI Gateway + Vercel Sandbox removed (upstream deletion); get_bedrock_model_ids removed (replaced by bedrock_model_ids_or_none + discover_bedrock_models). - Terminal backends resolve ModalEnvironment / DaytonaEnvironment lazily from the plugin registry. - uv.lock regenerated against the pluginified workspace. Plugin test suites updated for the relocation: imports point at hermes_agent_<plat>.adapter, caplog logger-name filters and monkeypatch targets use the new module paths, and credential/rollback tests patch registries.get_provider_service rather than the removed agent.*_adapter modules. Verified: zero dead imports of relocated modules in core (import smoke test + rename-map grep); nix develop succeeds; targeted plugin suites green (bedrock, anthropic-auxiliary, matrix, dingtalk, feishu, credential_pool, switch_model_rollback). Remaining full-suite failures are pre-existing on the pre-merge tree (telegram setUpModule __code__) or environmental (voice/media/ PTY/network-dependent), not introduced here.
74 lines
2 KiB
Python
74 lines
2 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)
|
|
|
|
|
|
def register(ctx):
|
|
"""No-op — this provider has no workspace package yet."""
|
|
pass
|
|
|