mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-08 03:01:47 +00:00
20a4f79ed1
Introduces providers/ package — single source of truth for every inference provider. Adding a simple api-key provider now requires one providers/<name>.py file with zero edits anywhere else. What this PR ships: - providers/ package (ProviderProfile ABC + 33 profiles across 4 api_modes) - ProviderProfile declarative fields: name, api_mode, aliases, display_name, env_vars, base_url, models_url, auth_type, fallback_models, hostname, default_headers, fixed_temperature, default_max_tokens, default_aux_model - 4 overridable hooks: prepare_messages, build_extra_body, build_api_kwargs_extras, fetch_models - chat_completions.build_kwargs: profile path via _build_kwargs_from_profile, legacy flag path retained for lmstudio/tencent-tokenhub (which have session-aware reasoning probing that doesn't map cleanly to hooks yet) - run_agent.py: profile path for all registered providers; legacy path variable scoping fixed (all flags defined before branching) - Auto-wires: auth.PROVIDER_REGISTRY, models.CANONICAL_PROVIDERS, doctor health checks, config.OPTIONAL_ENV_VARS, model_metadata._URL_TO_PROVIDER - GeminiProfile: thinking_config translation (native + openai-compat nested) - New tests/providers/ (79 tests covering profile declarations, transport parity, hook overrides, e2e kwargs assembly) Deltas vs original PR (salvaged onto current main): - Added profiles: alibaba-coding-plan, azure-foundry, minimax-oauth (were added to main since original PR) - Skipped profiles: lmstudio, tencent-tokenhub stay on legacy path (their reasoning_effort probing has no clean hook equivalent yet) - Removed lmstudio alias from custom profile (it's a separate provider now) - Skipped openrouter/custom from PROVIDER_REGISTRY auto-extension (resolve_provider special-cases them; adding breaks runtime resolution) - runtime_provider: profile.api_mode only as fallback when URL detection finds nothing (was breaking minimax /v1 override) - Preserved main's legacy-path improvements: deepseek reasoning_content preserve, gemini Gemma skip, OpenRouter response caching, Anthropic 1M beta recovery, etc. - Kept agent/copilot_acp_client.py in place (rejected PR's relocation — main has 7 fixes landed since; relocation would revert them) - _API_KEY_PROVIDER_AUX_MODELS alias kept for backward compat with existing test imports Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com> Closes #14418
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)
|