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

Merge branch 'main' of https://github.com/kunalk16/nanobot into feat-support-azure-openai

Browse Source
This commit is contained in:
Kunal Karmakar
2026-03-06 10:39:29 +00:00
parent 0b0f47f09f 473ae5ef18
commit 33c52cfb74
12 changed files with 386 additions and 159 deletions
Download Patch File Download Diff File Expand all files Collapse all files

110
nanobot/providers/registry.py
View File

@@ -26,33 +26,33 @@ 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"
display_name: str = "" # shown in `nanobot status`
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"
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
litellm_prefix: str = "" # "dashscope" → model becomes "dashscope/{model}"
skip_prefixes: tuple[str, ...] = () # don't prefix if model already starts with these
# extra env vars, e.g. (("ZHIPUAI_API_KEY", "{api_key}"),)
env_extras: tuple[tuple[str, str], ...] = ()
# gateway / local detection
is_gateway: bool = False # routes any model (OpenRouter, AiHubMix)
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
is_gateway: bool = False # routes any model (OpenRouter, AiHubMix)
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
# gateway behavior
strip_model_prefix: bool = False # strip "provider/" before re-prefixing
strip_model_prefix: bool = False # strip "provider/" before re-prefixing
# 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 # if True, uses OAuth flow instead of API key
# Direct providers bypass LiteLLM entirely (e.g., CustomProvider)
is_direct: bool = False
@@ -70,7 +70,6 @@ class ProviderSpec:
# ---------------------------------------------------------------------------
PROVIDERS: tuple[ProviderSpec, ...] = (
# === Custom (direct OpenAI-compatible endpoint, bypasses LiteLLM) ======
ProviderSpec(
name="custom",
@@ -90,17 +89,15 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
litellm_prefix="",
is_direct=True,
),
# === Gateways (detected by api_key / api_base, not model name) =========
# Gateways can route any model, so they win in fallback.
# OpenRouter: global gateway, keys start with "sk-or-"
ProviderSpec(
name="openrouter",
keywords=("openrouter",),
env_key="OPENROUTER_API_KEY",
display_name="OpenRouter",
litellm_prefix="openrouter", # claude-3 → openrouter/claude-3
litellm_prefix="openrouter", # claude-3 → openrouter/claude-3
skip_prefixes=(),
env_extras=(),
is_gateway=True,
@@ -112,16 +109,15 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
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".
ProviderSpec(
name="aihubmix",
keywords=("aihubmix",),
env_key="OPENAI_API_KEY", # OpenAI-compatible
env_key="OPENAI_API_KEY", # OpenAI-compatible
display_name="AiHubMix",
litellm_prefix="openai", # → openai/{model}
litellm_prefix="openai", # → openai/{model}
skip_prefixes=(),
env_extras=(),
is_gateway=True,
@@ -129,10 +125,9 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
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
strip_model_prefix=True, # anthropic/claude-3 → claude-3 → openai/claude-3
model_overrides=(),
),
# SiliconFlow (硅基流动): OpenAI-compatible gateway, model names keep org prefix
ProviderSpec(
name="siliconflow",
@@ -150,7 +145,6 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
strip_model_prefix=False,
model_overrides=(),
),
# VolcEngine (火山引擎): OpenAI-compatible gateway
ProviderSpec(
name="volcengine",
@@ -168,9 +162,7 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
strip_model_prefix=False,
model_overrides=(),
),
# === Standard providers (matched by model-name keywords) ===============
# Anthropic: LiteLLM recognizes "claude-*" natively, no prefix needed.
ProviderSpec(
name="anthropic",
@@ -189,7 +181,6 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
model_overrides=(),
supports_prompt_caching=True,
),
# OpenAI: LiteLLM recognizes "gpt-*" natively, no prefix needed.
ProviderSpec(
name="openai",
@@ -207,14 +198,13 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
strip_model_prefix=False,
model_overrides=(),
),
# OpenAI Codex: uses OAuth, not API key.
ProviderSpec(
name="openai_codex",
keywords=("openai-codex",),
env_key="", # OAuth-based, no API key
env_key="", # OAuth-based, no API key
display_name="OpenAI Codex",
litellm_prefix="", # Not routed through LiteLLM
litellm_prefix="", # Not routed through LiteLLM
skip_prefixes=(),
env_extras=(),
is_gateway=False,
@@ -224,16 +214,15 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
default_api_base="https://chatgpt.com/backend-api",
strip_model_prefix=False,
model_overrides=(),
is_oauth=True, # OAuth-based authentication
is_oauth=True, # OAuth-based authentication
),
# Github Copilot: uses OAuth, not API key.
ProviderSpec(
name="github_copilot",
keywords=("github_copilot", "copilot"),
env_key="", # OAuth-based, no API key
env_key="", # OAuth-based, no API key
display_name="Github Copilot",
litellm_prefix="github_copilot", # github_copilot/model → github_copilot/model
litellm_prefix="github_copilot", # github_copilot/model → github_copilot/model
skip_prefixes=("github_copilot/",),
env_extras=(),
is_gateway=False,
@@ -243,17 +232,16 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
default_api_base="",
strip_model_prefix=False,
model_overrides=(),
is_oauth=True, # OAuth-based authentication
is_oauth=True, # OAuth-based authentication
),
# DeepSeek: needs "deepseek/" prefix for LiteLLM routing.
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
litellm_prefix="deepseek", # deepseek-chat → deepseek/deepseek-chat
skip_prefixes=("deepseek/",), # avoid double-prefix
env_extras=(),
is_gateway=False,
is_local=False,
@@ -263,15 +251,14 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
strip_model_prefix=False,
model_overrides=(),
),
# Gemini: needs "gemini/" prefix for LiteLLM.
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
litellm_prefix="gemini", # gemini-pro → gemini/gemini-pro
skip_prefixes=("gemini/",), # avoid double-prefix
env_extras=(),
is_gateway=False,
is_local=False,
@@ -281,7 +268,6 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
strip_model_prefix=False,
model_overrides=(),
),
# 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.
@@ -290,11 +276,9 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
keywords=("zhipu", "glm", "zai"),
env_key="ZAI_API_KEY",
display_name="Zhipu AI",
litellm_prefix="zai", # glm-4 → zai/glm-4
litellm_prefix="zai", # glm-4 → zai/glm-4
skip_prefixes=("zhipu/", "zai/", "openrouter/", "hosted_vllm/"),
env_extras=(
("ZHIPUAI_API_KEY", "{api_key}"),
),
env_extras=(("ZHIPUAI_API_KEY", "{api_key}"),),
is_gateway=False,
is_local=False,
detect_by_key_prefix="",
@@ -303,14 +287,13 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
strip_model_prefix=False,
model_overrides=(),
),
# DashScope: Qwen models, needs "dashscope/" prefix.
ProviderSpec(
name="dashscope",
keywords=("qwen", "dashscope"),
env_key="DASHSCOPE_API_KEY",
display_name="DashScope",
litellm_prefix="dashscope", # qwen-max → dashscope/qwen-max
litellm_prefix="dashscope", # qwen-max → dashscope/qwen-max
skip_prefixes=("dashscope/", "openrouter/"),
env_extras=(),
is_gateway=False,
@@ -321,7 +304,6 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
strip_model_prefix=False,
model_overrides=(),
),
# 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.
@@ -330,22 +312,17 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
keywords=("moonshot", "kimi"),
env_key="MOONSHOT_API_KEY",
display_name="Moonshot",
litellm_prefix="moonshot", # kimi-k2.5 → moonshot/kimi-k2.5
litellm_prefix="moonshot", # kimi-k2.5 → moonshot/kimi-k2.5
skip_prefixes=("moonshot/", "openrouter/"),
env_extras=(
("MOONSHOT_API_BASE", "{api_base}"),
),
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
default_api_base="https://api.moonshot.ai/v1", # intl; use api.moonshot.cn for China
strip_model_prefix=False,
model_overrides=(
("kimi-k2.5", {"temperature": 1.0}),
),
model_overrides=(("kimi-k2.5", {"temperature": 1.0}),),
),
# MiniMax: needs "minimax/" prefix for LiteLLM routing.
# Uses OpenAI-compatible API at api.minimax.io/v1.
ProviderSpec(
@@ -353,7 +330,7 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
keywords=("minimax",),
env_key="MINIMAX_API_KEY",
display_name="MiniMax",
litellm_prefix="minimax", # MiniMax-M2.1 → minimax/MiniMax-M2.1
litellm_prefix="minimax", # MiniMax-M2.1 → minimax/MiniMax-M2.1
skip_prefixes=("minimax/", "openrouter/"),
env_extras=(),
is_gateway=False,
@@ -364,9 +341,7 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
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").
ProviderSpec(
@@ -374,20 +349,18 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
keywords=("vllm",),
env_key="HOSTED_VLLM_API_KEY",
display_name="vLLM/Local",
litellm_prefix="hosted_vllm", # Llama-3-8B → hosted_vllm/Llama-3-8B
litellm_prefix="hosted_vllm", # Llama-3-8B → hosted_vllm/Llama-3-8B
skip_prefixes=(),
env_extras=(),
is_gateway=False,
is_local=True,
detect_by_key_prefix="",
detect_by_base_keyword="",
default_api_base="", # user must provide in config
default_api_base="", # user must provide in config
strip_model_prefix=False,
model_overrides=(),
),
# === 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.
ProviderSpec(
@@ -395,8 +368,8 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
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
litellm_prefix="groq", # llama3-8b-8192 → groq/llama3-8b-8192
skip_prefixes=("groq/",), # avoid double-prefix
env_extras=(),
is_gateway=False,
is_local=False,
@@ -413,6 +386,7 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
# Lookup helpers
# ---------------------------------------------------------------------------
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."""
@@ -428,7 +402,9 @@ def find_by_model(model: str) -> ProviderSpec | None:
return spec
for spec in std_specs:
if any(kw in model_lower or kw.replace("-", "_") in model_normalized for kw in spec.keywords):
if any(
kw in model_lower or kw.replace("-", "_") in model_normalized for kw in spec.keywords
):
return spec
return None