diff --git a/README.md b/README.md index fc0a1fb..0c49608 100644 --- a/README.md +++ b/README.md @@ -664,6 +664,7 @@ Config file: `~/.nanobot/config.json` > - **Zhipu Coding Plan**: If you're on Zhipu's coding plan, set `"apiBase": "https://open.bigmodel.cn/api/coding/paas/v4"` in your zhipu provider config. > - **MiniMax (Mainland China)**: If your API key is from MiniMax's mainland China platform (minimaxi.com), set `"apiBase": "https://api.minimaxi.com/v1"` in your minimax provider config. > - **VolcEngine Coding Plan**: If you're on VolcEngine's coding plan, set `"apiBase": "https://ark.cn-beijing.volces.com/api/coding/v3"` in your volcengine provider config. +> - **Alibaba Cloud Coding Plan**: If you're on the Alibaba Cloud Coding Plan (BaiLian), set `"apiBase": "https://coding.dashscope.aliyuncs.com/v1"` in your dashscope provider config. | Provider | Purpose | Get API Key | |----------|---------|-------------| diff --git a/nanobot/config/schema.py b/nanobot/config/schema.py index 1f2f946..2073eeb 100644 --- a/nanobot/config/schema.py +++ b/nanobot/config/schema.py @@ -199,21 +199,6 @@ class QQConfig(Base): ) # Allowed user openids (empty = public access) -class MatrixConfig(Base): - """Matrix (Element) channel configuration.""" - - enabled: bool = False - homeserver: str = "https://matrix.org" - access_token: str = "" - user_id: str = "" # e.g. @bot:matrix.org - device_id: str = "" - e2ee_enabled: bool = True # end-to-end encryption support - sync_stop_grace_seconds: int = 2 # graceful sync_forever shutdown timeout - max_media_bytes: int = 20 * 1024 * 1024 # inbound + outbound attachment limit - allow_from: list[str] = Field(default_factory=list) - group_policy: Literal["open", "mention", "allowlist"] = "open" - group_allow_from: list[str] = Field(default_factory=list) - allow_room_mentions: bool = False class ChannelsConfig(Base): @@ -278,12 +263,8 @@ class ProvidersConfig(Base): moonshot: ProviderConfig = Field(default_factory=ProviderConfig) minimax: ProviderConfig = Field(default_factory=ProviderConfig) aihubmix: ProviderConfig = Field(default_factory=ProviderConfig) # AiHubMix API gateway - siliconflow: ProviderConfig = Field( - default_factory=ProviderConfig - ) # SiliconFlow (硅基流动) API gateway - volcengine: ProviderConfig = Field( - default_factory=ProviderConfig - ) # VolcEngine (火山引擎) API gateway + siliconflow: ProviderConfig = Field(default_factory=ProviderConfig) # SiliconFlow (硅基流动) + volcengine: ProviderConfig = Field(default_factory=ProviderConfig) # VolcEngine (火山引擎) openai_codex: ProviderConfig = Field(default_factory=ProviderConfig) # OpenAI Codex (OAuth) github_copilot: ProviderConfig = Field(default_factory=ProviderConfig) # Github Copilot (OAuth) diff --git a/nanobot/providers/registry.py b/nanobot/providers/registry.py index df915b7..59ba31a 100644 --- a/nanobot/providers/registry.py +++ b/nanobot/providers/registry.py @@ -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", @@ -80,17 +79,15 @@ 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, @@ -102,16 +99,15 @@ 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, @@ -119,10 +115,9 @@ 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", @@ -140,7 +135,6 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( strip_model_prefix=False, model_overrides=(), ), - # VolcEngine (火山引擎): OpenAI-compatible gateway ProviderSpec( name="volcengine", @@ -158,9 +152,7 @@ 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", @@ -179,7 +171,6 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( model_overrides=(), supports_prompt_caching=True, ), - # OpenAI: LiteLLM recognizes "gpt-*" natively, no prefix needed. ProviderSpec( name="openai", @@ -197,14 +188,13 @@ 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, @@ -214,16 +204,15 @@ 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, @@ -233,17 +222,16 @@ 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, @@ -253,15 +241,14 @@ 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, @@ -271,7 +258,6 @@ 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. @@ -280,11 +266,9 @@ 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="", @@ -293,14 +277,13 @@ 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, @@ -311,7 +294,6 @@ 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. @@ -320,22 +302,17 @@ 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( @@ -343,7 +320,7 @@ 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, @@ -354,9 +331,7 @@ 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( @@ -364,20 +339,18 @@ 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( @@ -385,8 +358,8 @@ 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, @@ -403,6 +376,7 @@ 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.""" @@ -418,7 +392,9 @@ 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