mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-11 03:31:55 +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
71 lines
2.3 KiB
Python
71 lines
2.3 KiB
Python
"""Kimi / Moonshot provider profiles.
|
|
|
|
Kimi has dual endpoints:
|
|
- sk-kimi-* keys → api.kimi.com/coding (Anthropic Messages API)
|
|
- legacy keys → api.moonshot.ai/v1 (OpenAI chat completions)
|
|
|
|
This module covers the chat_completions path (/v1 endpoint).
|
|
"""
|
|
|
|
from typing import Any
|
|
|
|
from providers import register_provider
|
|
from providers.base import OMIT_TEMPERATURE, ProviderProfile
|
|
|
|
|
|
class KimiProfile(ProviderProfile):
|
|
"""Kimi/Moonshot — temperature omitted, thinking + reasoning_effort."""
|
|
|
|
def build_api_kwargs_extras(
|
|
self, *, reasoning_config: dict | None = None, **context
|
|
) -> tuple[dict[str, Any], dict[str, Any]]:
|
|
"""Kimi uses extra_body.thinking + top-level reasoning_effort."""
|
|
extra_body = {}
|
|
top_level = {}
|
|
|
|
if not reasoning_config or not isinstance(reasoning_config, dict):
|
|
# No config → thinking enabled, default effort
|
|
extra_body["thinking"] = {"type": "enabled"}
|
|
top_level["reasoning_effort"] = "medium"
|
|
return extra_body, top_level
|
|
|
|
enabled = reasoning_config.get("enabled", True)
|
|
if enabled is False:
|
|
extra_body["thinking"] = {"type": "disabled"}
|
|
return extra_body, top_level
|
|
|
|
# Enabled
|
|
extra_body["thinking"] = {"type": "enabled"}
|
|
effort = (reasoning_config.get("effort") or "").strip().lower()
|
|
if effort in ("low", "medium", "high"):
|
|
top_level["reasoning_effort"] = effort
|
|
else:
|
|
top_level["reasoning_effort"] = "medium"
|
|
|
|
return extra_body, top_level
|
|
|
|
|
|
kimi = KimiProfile(
|
|
name="kimi-coding",
|
|
aliases=("kimi", "moonshot", "kimi-for-coding"),
|
|
env_vars=("KIMI_API_KEY", "KIMI_CODING_API_KEY"),
|
|
base_url="https://api.moonshot.ai/v1",
|
|
fixed_temperature=OMIT_TEMPERATURE,
|
|
default_max_tokens=32000,
|
|
default_headers={"User-Agent": "hermes-agent/1.0"},
|
|
default_aux_model="kimi-k2-turbo-preview",
|
|
)
|
|
|
|
kimi_cn = KimiProfile(
|
|
name="kimi-coding-cn",
|
|
aliases=("kimi-cn", "moonshot-cn"),
|
|
env_vars=("KIMI_CN_API_KEY",),
|
|
base_url="https://api.moonshot.cn/v1",
|
|
fixed_temperature=OMIT_TEMPERATURE,
|
|
default_max_tokens=32000,
|
|
default_headers={"User-Agent": "hermes-agent/1.0"},
|
|
default_aux_model="kimi-k2-turbo-preview",
|
|
)
|
|
|
|
register_provider(kimi)
|
|
register_provider(kimi_cn)
|