Grayscale/nanobot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: replace litellm with native openai + anthropic SDKs

Browse Source 
- Remove litellm dependency entirely (supply chain risk mitigation)
- Add AnthropicProvider (native SDK) and OpenAICompatProvider (unified)
- Merge CustomProvider into OpenAICompatProvider, delete custom_provider.py
- Add ProviderSpec.backend field for declarative provider routing
- Remove _resolve_model, find_gateway, find_by_model (dead heuristics)
- Pass resolved spec directly into provider — zero internal lookups
- Stub out litellm-dependent model database (cli/models.py)
- Add anthropic>=0.45.0 to dependencies, remove litellm
- 593 tests passed, net -1034 lines
This commit is contained in:
Xubin Ren
2026-03-25 01:58:48 +08:00
committed by Xubin Ren
parent 38ce054b31
commit 3dfdab704e
18 changed files with 1019 additions and 1263 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nanobot/providers/registry.py
+65 -274
View File
@@ -4,7 +4,7 @@ Provider Registry — single source of truth for LLM provider metadata.
Adding a new provider:
1. Add a ProviderSpec to PROVIDERS below.
2. Add a field to ProvidersConfig in config/schema.py.
Done. Env vars, prefixing, config matching, status display all derive from here.
Done. Env vars, config matching, status display all derive from here.
Order matters — it controls match priority and fallback. Gateways first.
Every entry writes out all fields so you can copy-paste as a template.
@@ -12,7 +12,7 @@ Every entry writes out all fields so you can copy-paste as a template.
from __future__ import annotations
from dataclasses import dataclass, field
from dataclasses import dataclass
from typing import Any
from pydantic.alias_generators import to_snake
@@ -30,12 +30,12 @@ class ProviderSpec:
# identity
name: str # config field name, e.g. "dashscope"
keywords: tuple[str, ...] # model-name keywords for matching (lowercase)
env_key: str # LiteLLM env var, e.g. "DASHSCOPE_API_KEY"
env_key: str # env var for API key, e.g. "DASHSCOPE_API_KEY"
display_name: str = "" # shown in `nanobot status`
# model prefixing
litellm_prefix: str = "" # "dashscope" → model becomes "dashscope/{model}"
skip_prefixes: tuple[str, ...] = () # don't prefix if model already starts with these
# which provider implementation to use
# "openai_compat" | "anthropic" | "azure_openai" | "openai_codex"
backend: str = "openai_compat"
# extra env vars, e.g. (("ZHIPUAI_API_KEY", "{api_key}"),)
env_extras: tuple[tuple[str, str], ...] = ()
@@ -45,19 +45,18 @@ class ProviderSpec:
is_local: bool = False # local deployment (vLLM, Ollama)
detect_by_key_prefix: str = "" # match api_key prefix, e.g. "sk-or-"
detect_by_base_keyword: str = "" # match substring in api_base URL
default_api_base: str = "" # fallback base URL
default_api_base: str = "" # OpenAI-compatible base URL for this provider
# gateway behavior
strip_model_prefix: bool = False # strip "provider/" before re-prefixing
litellm_kwargs: dict[str, Any] = field(default_factory=dict) # extra kwargs passed to LiteLLM
strip_model_prefix: bool = False # strip "provider/" before sending to gateway
# per-model param overrides, e.g. (("kimi-k2.5", {"temperature": 1.0}),)
model_overrides: tuple[tuple[str, dict[str, Any]], ...] = ()
# OAuth-based providers (e.g., OpenAI Codex) don't use API keys
is_oauth: bool = False # if True, uses OAuth flow instead of API key
is_oauth: bool = False
# Direct providers bypass LiteLLM entirely (e.g., CustomProvider)
# Direct providers skip API-key validation (user supplies everything)
is_direct: bool = False
# Provider supports cache_control on content blocks (e.g. Anthropic prompt caching)
@@ -73,13 +72,13 @@ class ProviderSpec:
# ---------------------------------------------------------------------------
PROVIDERS: tuple[ProviderSpec, ...] = (
# === Custom (direct OpenAI-compatible endpoint, bypasses LiteLLM) ======
# === Custom (direct OpenAI-compatible endpoint) ========================
ProviderSpec(
name="custom",
keywords=(),
env_key="",
display_name="Custom",
litellm_prefix="",
backend="openai_compat",
is_direct=True,
),
@@ -89,7 +88,7 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
keywords=("azure", "azure-openai"),
env_key="",
display_name="Azure OpenAI",
litellm_prefix="",
backend="azure_openai",
is_direct=True,
),
# === Gateways (detected by api_key / api_base, not model name) =========
@@ -100,36 +99,26 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
keywords=("openrouter",),
env_key="OPENROUTER_API_KEY",
display_name="OpenRouter",
litellm_prefix="openrouter", # anthropic/claude-3 → openrouter/anthropic/claude-3
skip_prefixes=(),
env_extras=(),
backend="openai_compat",
is_gateway=True,
is_local=False,
detect_by_key_prefix="sk-or-",
detect_by_base_keyword="openrouter",
default_api_base="https://openrouter.ai/api/v1",
strip_model_prefix=False,
model_overrides=(),
supports_prompt_caching=True,
),
# AiHubMix: global gateway, OpenAI-compatible interface.
# strip_model_prefix=True: it doesn't understand "anthropic/claude-3",
# so we strip to bare "claude-3" then re-prefix as "openai/claude-3".
# strip_model_prefix=True: doesn't understand "anthropic/claude-3",
# strips to bare "claude-3".
ProviderSpec(
name="aihubmix",
keywords=("aihubmix",),
env_key="OPENAI_API_KEY", # OpenAI-compatible
env_key="OPENAI_API_KEY",
display_name="AiHubMix",
litellm_prefix="openai", # → openai/{model}
skip_prefixes=(),
env_extras=(),
backend="openai_compat",
is_gateway=True,
is_local=False,
detect_by_key_prefix="",
detect_by_base_keyword="aihubmix",
default_api_base="https://aihubmix.com/v1",
strip_model_prefix=True, # anthropic/claude-3 → claude-3 → openai/claude-3
model_overrides=(),
strip_model_prefix=True,
),
# SiliconFlow (硅基流动): OpenAI-compatible gateway, model names keep org prefix
ProviderSpec(
@@ -137,16 +126,10 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
keywords=("siliconflow",),
env_key="OPENAI_API_KEY",
display_name="SiliconFlow",
litellm_prefix="openai",
skip_prefixes=(),
env_extras=(),
backend="openai_compat",
is_gateway=True,
is_local=False,
detect_by_key_prefix="",
detect_by_base_keyword="siliconflow",
default_api_base="https://api.siliconflow.cn/v1",
strip_model_prefix=False,
model_overrides=(),
),
# VolcEngine (火山引擎): OpenAI-compatible gateway, pay-per-use models
@@ -155,16 +138,10 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
keywords=("volcengine", "volces", "ark"),
env_key="OPENAI_API_KEY",
display_name="VolcEngine",
litellm_prefix="volcengine",
skip_prefixes=(),
env_extras=(),
backend="openai_compat",
is_gateway=True,
is_local=False,
detect_by_key_prefix="",
detect_by_base_keyword="volces",
default_api_base="https://ark.cn-beijing.volces.com/api/v3",
strip_model_prefix=False,
model_overrides=(),
),
# VolcEngine Coding Plan (火山引擎 Coding Plan): same key as volcengine
@@ -173,16 +150,10 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
keywords=("volcengine-plan",),
env_key="OPENAI_API_KEY",
display_name="VolcEngine Coding Plan",
litellm_prefix="volcengine",
skip_prefixes=(),
env_extras=(),
backend="openai_compat",
is_gateway=True,
is_local=False,
detect_by_key_prefix="",
detect_by_base_keyword="",
default_api_base="https://ark.cn-beijing.volces.com/api/coding/v3",
strip_model_prefix=True,
model_overrides=(),
),
# BytePlus: VolcEngine international, pay-per-use models
@@ -191,16 +162,11 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
keywords=("byteplus",),
env_key="OPENAI_API_KEY",
display_name="BytePlus",
litellm_prefix="volcengine",
skip_prefixes=(),
env_extras=(),
backend="openai_compat",
is_gateway=True,
is_local=False,
detect_by_key_prefix="",
detect_by_base_keyword="bytepluses",
default_api_base="https://ark.ap-southeast.bytepluses.com/api/v3",
strip_model_prefix=True,
model_overrides=(),
),
# BytePlus Coding Plan: same key as byteplus
@@ -209,250 +175,137 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
keywords=("byteplus-plan",),
env_key="OPENAI_API_KEY",
display_name="BytePlus Coding Plan",
litellm_prefix="volcengine",
skip_prefixes=(),
env_extras=(),
backend="openai_compat",
is_gateway=True,
is_local=False,
detect_by_key_prefix="",
detect_by_base_keyword="",
default_api_base="https://ark.ap-southeast.bytepluses.com/api/coding/v3",
strip_model_prefix=True,
model_overrides=(),
),
# === Standard providers (matched by model-name keywords) ===============
# Anthropic: LiteLLM recognizes "claude-*" natively, no prefix needed.
# Anthropic: native Anthropic SDK
ProviderSpec(
name="anthropic",
keywords=("anthropic", "claude"),
env_key="ANTHROPIC_API_KEY",
display_name="Anthropic",
litellm_prefix="",
skip_prefixes=(),
env_extras=(),
is_gateway=False,
is_local=False,
detect_by_key_prefix="",
detect_by_base_keyword="",
default_api_base="",
strip_model_prefix=False,
model_overrides=(),
backend="anthropic",
supports_prompt_caching=True,
),
# OpenAI: LiteLLM recognizes "gpt-*" natively, no prefix needed.
# OpenAI: SDK default base URL (no override needed)
ProviderSpec(
name="openai",
keywords=("openai", "gpt"),
env_key="OPENAI_API_KEY",
display_name="OpenAI",
litellm_prefix="",
skip_prefixes=(),
env_extras=(),
is_gateway=False,
is_local=False,
detect_by_key_prefix="",
detect_by_base_keyword="",
default_api_base="",
strip_model_prefix=False,
model_overrides=(),
backend="openai_compat",
),
# OpenAI Codex: uses OAuth, not API key.
# OpenAI Codex: OAuth-based, dedicated provider
ProviderSpec(
name="openai_codex",
keywords=("openai-codex",),
env_key="", # OAuth-based, no API key
env_key="",
display_name="OpenAI Codex",
litellm_prefix="", # Not routed through LiteLLM
skip_prefixes=(),
env_extras=(),
is_gateway=False,
is_local=False,
detect_by_key_prefix="",
backend="openai_codex",
detect_by_base_keyword="codex",
default_api_base="https://chatgpt.com/backend-api",
strip_model_prefix=False,
model_overrides=(),
is_oauth=True, # OAuth-based authentication
is_oauth=True,
),
# Github Copilot: uses OAuth, not API key.
# GitHub Copilot: OAuth-based
ProviderSpec(
name="github_copilot",
keywords=("github_copilot", "copilot"),
env_key="", # OAuth-based, no API key
env_key="",
display_name="Github Copilot",
litellm_prefix="github_copilot", # github_copilot/model → github_copilot/model
skip_prefixes=("github_copilot/",),
env_extras=(),
is_gateway=False,
is_local=False,
detect_by_key_prefix="",
detect_by_base_keyword="",
default_api_base="",
strip_model_prefix=False,
model_overrides=(),
is_oauth=True, # OAuth-based authentication
backend="openai_compat",
default_api_base="https://api.githubcopilot.com",
is_oauth=True,
),
# DeepSeek: needs "deepseek/" prefix for LiteLLM routing.
# DeepSeek: OpenAI-compatible at api.deepseek.com
ProviderSpec(
name="deepseek",
keywords=("deepseek",),
env_key="DEEPSEEK_API_KEY",
display_name="DeepSeek",
litellm_prefix="deepseek", # deepseek-chat → deepseek/deepseek-chat
skip_prefixes=("deepseek/",), # avoid double-prefix
env_extras=(),
is_gateway=False,
is_local=False,
detect_by_key_prefix="",
detect_by_base_keyword="",
default_api_base="",
strip_model_prefix=False,
model_overrides=(),
backend="openai_compat",
default_api_base="https://api.deepseek.com",
),
# Gemini: needs "gemini/" prefix for LiteLLM.
# Gemini: Google's OpenAI-compatible endpoint
ProviderSpec(
name="gemini",
keywords=("gemini",),
env_key="GEMINI_API_KEY",
display_name="Gemini",
litellm_prefix="gemini", # gemini-pro → gemini/gemini-pro
skip_prefixes=("gemini/",), # avoid double-prefix
env_extras=(),
is_gateway=False,
is_local=False,
detect_by_key_prefix="",
detect_by_base_keyword="",
default_api_base="",
strip_model_prefix=False,
model_overrides=(),
backend="openai_compat",
default_api_base="https://generativelanguage.googleapis.com/v1beta/openai/",
),
# Zhipu: LiteLLM uses "zai/" prefix.
# Also mirrors key to ZHIPUAI_API_KEY (some LiteLLM paths check that).
# skip_prefixes: don't add "zai/" when already routed via gateway.
# Zhipu (智谱): OpenAI-compatible at open.bigmodel.cn
ProviderSpec(
name="zhipu",
keywords=("zhipu", "glm", "zai"),
env_key="ZAI_API_KEY",
display_name="Zhipu AI",
litellm_prefix="zai", # glm-4 → zai/glm-4
skip_prefixes=("zhipu/", "zai/", "openrouter/", "hosted_vllm/"),
backend="openai_compat",
env_extras=(("ZHIPUAI_API_KEY", "{api_key}"),),
is_gateway=False,
is_local=False,
detect_by_key_prefix="",
detect_by_base_keyword="",
default_api_base="",
strip_model_prefix=False,
model_overrides=(),
default_api_base="https://open.bigmodel.cn/api/paas/v4",
),
# DashScope: Qwen models, needs "dashscope/" prefix.
# DashScope (通义): Qwen models, OpenAI-compatible endpoint
ProviderSpec(
name="dashscope",
keywords=("qwen", "dashscope"),
env_key="DASHSCOPE_API_KEY",
display_name="DashScope",
litellm_prefix="dashscope", # qwen-max → dashscope/qwen-max
skip_prefixes=("dashscope/", "openrouter/"),
env_extras=(),
is_gateway=False,
is_local=False,
detect_by_key_prefix="",
detect_by_base_keyword="",
default_api_base="",
strip_model_prefix=False,
model_overrides=(),
backend="openai_compat",
default_api_base="https://dashscope.aliyuncs.com/compatible-mode/v1",
),
# Moonshot: Kimi models, needs "moonshot/" prefix.
# LiteLLM requires MOONSHOT_API_BASE env var to find the endpoint.
# Kimi K2.5 API enforces temperature >= 1.0.
# Moonshot (月之暗面): Kimi models. K2.5 enforces temperature >= 1.0.
ProviderSpec(
name="moonshot",
keywords=("moonshot", "kimi"),
env_key="MOONSHOT_API_KEY",
display_name="Moonshot",
litellm_prefix="moonshot", # kimi-k2.5 → moonshot/kimi-k2.5
skip_prefixes=("moonshot/", "openrouter/"),
env_extras=(("MOONSHOT_API_BASE", "{api_base}"),),
is_gateway=False,
is_local=False,
detect_by_key_prefix="",
detect_by_base_keyword="",
default_api_base="https://api.moonshot.ai/v1", # intl; use api.moonshot.cn for China
strip_model_prefix=False,
backend="openai_compat",
default_api_base="https://api.moonshot.ai/v1",
model_overrides=(("kimi-k2.5", {"temperature": 1.0}),),
),
# MiniMax: needs "minimax/" prefix for LiteLLM routing.
# Uses OpenAI-compatible API at api.minimax.io/v1.
# MiniMax: OpenAI-compatible API
ProviderSpec(
name="minimax",
keywords=("minimax",),
env_key="MINIMAX_API_KEY",
display_name="MiniMax",
litellm_prefix="minimax", # MiniMax-M2.1 → minimax/MiniMax-M2.1
skip_prefixes=("minimax/", "openrouter/"),
env_extras=(),
is_gateway=False,
is_local=False,
detect_by_key_prefix="",
detect_by_base_keyword="",
backend="openai_compat",
default_api_base="https://api.minimax.io/v1",
strip_model_prefix=False,
model_overrides=(),
),
# Mistral AI: OpenAI-compatible API at api.mistral.ai/v1.
# Mistral AI: OpenAI-compatible API
ProviderSpec(
name="mistral",
keywords=("mistral",),
env_key="MISTRAL_API_KEY",
display_name="Mistral",
litellm_prefix="mistral", # mistral-large-latest → mistral/mistral-large-latest
skip_prefixes=("mistral/",), # avoid double-prefix
env_extras=(),
is_gateway=False,
is_local=False,
detect_by_key_prefix="",
detect_by_base_keyword="",
backend="openai_compat",
default_api_base="https://api.mistral.ai/v1",
strip_model_prefix=False,
model_overrides=(),
),
# === Local deployment (matched by config key, NOT by api_base) =========
# vLLM / any OpenAI-compatible local server.
# Detected when config key is "vllm" (provider_name="vllm").
# vLLM / any OpenAI-compatible local server
ProviderSpec(
name="vllm",
keywords=("vllm",),
env_key="HOSTED_VLLM_API_KEY",
display_name="vLLM/Local",
litellm_prefix="hosted_vllm", # Llama-3-8B → hosted_vllm/Llama-3-8B
skip_prefixes=(),
env_extras=(),
is_gateway=False,
backend="openai_compat",
is_local=True,
detect_by_key_prefix="",
detect_by_base_keyword="",
default_api_base="", # user must provide in config
strip_model_prefix=False,
model_overrides=(),
),
# === Ollama (local, OpenAI-compatible) ===================================
# Ollama (local, OpenAI-compatible)
ProviderSpec(
name="ollama",
keywords=("ollama", "nemotron"),
env_key="OLLAMA_API_KEY",
display_name="Ollama",
litellm_prefix="ollama_chat", # model → ollama_chat/model
skip_prefixes=("ollama/", "ollama_chat/"),
env_extras=(),
is_gateway=False,
backend="openai_compat",
is_local=True,
detect_by_key_prefix="",
detect_by_base_keyword="11434",
default_api_base="http://localhost:11434",
strip_model_prefix=False,
model_overrides=(),
default_api_base="http://localhost:11434/v1",
),
# === OpenVINO Model Server (direct, local, OpenAI-compatible at /v3) ===
ProviderSpec(
@@ -460,29 +313,20 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
keywords=("openvino", "ovms"),
env_key="",
display_name="OpenVINO Model Server",
litellm_prefix="",
backend="openai_compat",
is_direct=True,
is_local=True,
default_api_base="http://localhost:8000/v3",
),
# === Auxiliary (not a primary LLM provider) ============================
# Groq: mainly used for Whisper voice transcription, also usable for LLM.
# Needs "groq/" prefix for LiteLLM routing. Placed last — it rarely wins fallback.
# Groq: mainly used for Whisper voice transcription, also usable for LLM
ProviderSpec(
name="groq",
keywords=("groq",),
env_key="GROQ_API_KEY",
display_name="Groq",
litellm_prefix="groq", # llama3-8b-8192 → groq/llama3-8b-8192
skip_prefixes=("groq/",), # avoid double-prefix
env_extras=(),
is_gateway=False,
is_local=False,
detect_by_key_prefix="",
detect_by_base_keyword="",
default_api_base="",
strip_model_prefix=False,
model_overrides=(),
backend="openai_compat",
default_api_base="https://api.groq.com/openai/v1",
),
)
@@ -492,59 +336,6 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
# ---------------------------------------------------------------------------
def find_by_model(model: str) -> ProviderSpec | None:
"""Match a standard provider by model-name keyword (case-insensitive).
Skips gateways/local — those are matched by api_key/api_base instead."""
model_lower = model.lower()
model_normalized = model_lower.replace("-", "_")
model_prefix = model_lower.split("/", 1)[0] if "/" in model_lower else ""
normalized_prefix = model_prefix.replace("-", "_")
std_specs = [s for s in PROVIDERS if not s.is_gateway and not s.is_local]
# Prefer explicit provider prefix — prevents `github-copilot/...codex` matching openai_codex.
for spec in std_specs:
if model_prefix and normalized_prefix == spec.name:
return spec
for spec in std_specs:
if any(
kw in model_lower or kw.replace("-", "_") in model_normalized for kw in spec.keywords
):
return spec
return None
def find_gateway(
provider_name: str | None = None,
api_key: str | None = None,
api_base: str | None = None,
) -> ProviderSpec | None:
"""Detect gateway/local provider.
Priority:
1. provider_name — if it maps to a gateway/local spec, use it directly.
2. api_key prefix — e.g. "sk-or-" → OpenRouter.
3. api_base keyword — e.g. "aihubmix" in URL → AiHubMix.
A standard provider with a custom api_base (e.g. DeepSeek behind a proxy)
will NOT be mistaken for vLLM — the old fallback is gone.
"""
# 1. Direct match by config key
if provider_name:
spec = find_by_name(provider_name)
if spec and (spec.is_gateway or spec.is_local):
return spec
# 2. Auto-detect by api_key prefix / api_base keyword
for spec in PROVIDERS:
if spec.detect_by_key_prefix and api_key and api_key.startswith(spec.detect_by_key_prefix):
return spec
if spec.detect_by_base_keyword and api_base and spec.detect_by_base_keyword in api_base:
return spec
return None
def find_by_name(name: str) -> ProviderSpec | None:
"""Find a provider spec by config field name, e.g. "dashscope"."""
normalized = to_snake(name.replace("-", "_"))