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

feat: Add Alibaba Cloud Coding Plan API support

Browse Source 
Add dashscope_coding_plan provider to registry with OpenAI-compatible
endpoint for BaiLian coding assistance.

- Supports API key detection by 'sk-sp-' prefix pattern
- Adds provider config schema entry for proper loading
- Updates documentation with configuration instructions
- Fixes duplicate MatrixConfig class issue in schema
- Follow existing nanobot provider patterns for consistency
This commit is contained in:
ouyangwulin
2026-03-05 16:54:15 +08:00
parent fb74281434
commit cf3e7e3f38
3 changed files with 109 additions and 84 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@@ -656,6 +656,7 @@ Config file: `~/.nanobot/config.json`
> [!TIP] > [!TIP]
> - **Groq** provides free voice transcription via Whisper. If configured, Telegram voice messages will be automatically transcribed. > - **Groq** provides free voice transcription via Whisper. If configured, Telegram voice messages will be automatically transcribed.
> - **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. > - **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.
> - **Alibaba Cloud Coding Plan**: If you're on the Alibaba Cloud Coding Plan (BaiLian coding assistance), add configuration for `dashscope_coding_plan` provider with an API key starting with `sk-sp-` in your config. This provider uses OpenAI-compatible endpoint `https://coding.dashscope.aliyuncs.com/v1`.
> - **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. > - **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. > - **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.

62
nanobot/config/schema.py
View File

@@ -29,7 +29,9 @@ class TelegramConfig(Base):
enabled: bool = False enabled: bool = False
token: str = "" # Bot token from @BotFather token: str = "" # Bot token from @BotFather
allow_from: list[str] = Field(default_factory=list) # Allowed user IDs or usernames allow_from: list[str] = Field(default_factory=list) # Allowed user IDs or usernames
proxy: str | None = None # HTTP/SOCKS5 proxy URL, e.g. "http://127.0.0.1:7890" or "socks5://127.0.0.1:1080" proxy: str | None = (
None # HTTP/SOCKS5 proxy URL, e.g. "http://127.0.0.1:7890" or "socks5://127.0.0.1:1080"
)
reply_to_message: bool = False # If true, bot replies quote the original message reply_to_message: bool = False # If true, bot replies quote the original message
@@ -42,7 +44,9 @@ class FeishuConfig(Base):
encrypt_key: str = "" # Encrypt Key for event subscription (optional) encrypt_key: str = "" # Encrypt Key for event subscription (optional)
verification_token: str = "" # Verification Token for event subscription (optional) verification_token: str = "" # Verification Token for event subscription (optional)
allow_from: list[str] = Field(default_factory=list) # Allowed user open_ids allow_from: list[str] = Field(default_factory=list) # Allowed user open_ids
react_emoji: str = "THUMBSUP" # Emoji type for message reactions (e.g. THUMBSUP, OK, DONE, SMILE) react_emoji: str = (
"THUMBSUP" # Emoji type for message reactions (e.g. THUMBSUP, OK, DONE, SMILE)
)
class DingTalkConfig(Base): class DingTalkConfig(Base):
@@ -72,9 +76,13 @@ class MatrixConfig(Base):
access_token: str = "" access_token: str = ""
user_id: str = "" # @bot:matrix.org user_id: str = "" # @bot:matrix.org
device_id: str = "" device_id: str = ""
e2ee_enabled: bool = True # Enable Matrix E2EE support (encryption + encrypted room handling). e2ee_enabled: bool = True # Enable Matrix E2EE support (encryption + encrypted room handling).
sync_stop_grace_seconds: int = 2 # Max seconds to wait for sync_forever to stop gracefully before cancellation fallback. sync_stop_grace_seconds: int = (
max_media_bytes: int = 20 * 1024 * 1024 # Max attachment size accepted for Matrix media handling (inbound + outbound). 2 # Max seconds to wait for sync_forever to stop gracefully before cancellation fallback.
)
max_media_bytes: int = (
20 * 1024 * 1024
) # Max attachment size accepted for Matrix media handling (inbound + outbound).
allow_from: list[str] = Field(default_factory=list) allow_from: list[str] = Field(default_factory=list)
group_policy: Literal["open", "mention", "allowlist"] = "open" group_policy: Literal["open", "mention", "allowlist"] = "open"
group_allow_from: list[str] = Field(default_factory=list) group_allow_from: list[str] = Field(default_factory=list)
@@ -105,7 +113,9 @@ class EmailConfig(Base):
from_address: str = "" from_address: str = ""
# Behavior # Behavior
auto_reply_enabled: bool = True # If false, inbound email is read but no automatic reply is sent auto_reply_enabled: bool = (
True # If false, inbound email is read but no automatic reply is sent
)
poll_interval_seconds: int = 30 poll_interval_seconds: int = 30
mark_seen: bool = True mark_seen: bool = True
max_body_chars: int = 12000 max_body_chars: int = 12000
@@ -183,27 +193,32 @@ class QQConfig(Base):
enabled: bool = False enabled: bool = False
app_id: str = "" # 机器人 ID (AppID) from q.qq.com app_id: str = "" # 机器人 ID (AppID) from q.qq.com
secret: str = "" # 机器人密钥 (AppSecret) from q.qq.com secret: str = "" # 机器人密钥 (AppSecret) from q.qq.com
allow_from: list[str] = Field(default_factory=list) # Allowed user openids (empty = public access) allow_from: list[str] = Field(
default_factory=list
) # Allowed user openids (empty = public access)
class MatrixConfig(Base): class MatrixConfig(Base):
"""Matrix (Element) channel configuration.""" """Matrix (Element) channel configuration."""
enabled: bool = False enabled: bool = False
homeserver: str = "https://matrix.org" homeserver: str = "https://matrix.org"
access_token: str = "" access_token: str = ""
user_id: str = "" # e.g. @bot:matrix.org user_id: str = "" # e.g. @bot:matrix.org
device_id: str = "" device_id: str = ""
e2ee_enabled: bool = True # end-to-end encryption support e2ee_enabled: bool = True # end-to-end encryption support
sync_stop_grace_seconds: int = 2 # graceful sync_forever shutdown timeout sync_stop_grace_seconds: int = 2 # graceful sync_forever shutdown timeout
max_media_bytes: int = 20 * 1024 * 1024 # inbound + outbound attachment limit max_media_bytes: int = 20 * 1024 * 1024 # inbound + outbound attachment limit
allow_from: list[str] = Field(default_factory=list) allow_from: list[str] = Field(default_factory=list)
group_policy: Literal["open", "mention", "allowlist"] = "open" group_policy: Literal["open", "mention", "allowlist"] = "open"
group_allow_from: list[str] = Field(default_factory=list) group_allow_from: list[str] = Field(default_factory=list)
allow_room_mentions: bool = False allow_room_mentions: bool = False
class ChannelsConfig(Base): class ChannelsConfig(Base):
"""Configuration for chat channels.""" """Configuration for chat channels."""
send_progress: bool = True # stream agent's text progress to the channel send_progress: bool = True # stream agent's text progress to the channel
send_tool_hints: bool = False # stream tool-call hints (e.g. read_file("…")) send_tool_hints: bool = False # stream tool-call hints (e.g. read_file("…"))
whatsapp: WhatsAppConfig = Field(default_factory=WhatsAppConfig) whatsapp: WhatsAppConfig = Field(default_factory=WhatsAppConfig)
telegram: TelegramConfig = Field(default_factory=TelegramConfig) telegram: TelegramConfig = Field(default_factory=TelegramConfig)
@@ -222,7 +237,9 @@ class AgentDefaults(Base):
workspace: str = "~/.nanobot/workspace" workspace: str = "~/.nanobot/workspace"
model: str = "anthropic/claude-opus-4-5" model: str = "anthropic/claude-opus-4-5"
provider: str = "auto" # Provider name (e.g. "anthropic", "openrouter") or "auto" for auto-detection provider: str = (
"auto" # Provider name (e.g. "anthropic", "openrouter") or "auto" for auto-detection
)
max_tokens: int = 8192 max_tokens: int = 8192
temperature: float = 0.1 temperature: float = 0.1
max_tool_iterations: int = 40 max_tool_iterations: int = 40
@@ -255,13 +272,20 @@ class ProvidersConfig(Base):
groq: ProviderConfig = Field(default_factory=ProviderConfig) groq: ProviderConfig = Field(default_factory=ProviderConfig)
zhipu: ProviderConfig = Field(default_factory=ProviderConfig) zhipu: ProviderConfig = Field(default_factory=ProviderConfig)
dashscope: ProviderConfig = Field(default_factory=ProviderConfig) # 阿里云通义千问 dashscope: ProviderConfig = Field(default_factory=ProviderConfig) # 阿里云通义千问
dashscope_coding_plan: ProviderConfig = Field(
default_factory=ProviderConfig
) # 阿里云百炼Coding Plan
vllm: ProviderConfig = Field(default_factory=ProviderConfig) vllm: ProviderConfig = Field(default_factory=ProviderConfig)
gemini: ProviderConfig = Field(default_factory=ProviderConfig) gemini: ProviderConfig = Field(default_factory=ProviderConfig)
moonshot: ProviderConfig = Field(default_factory=ProviderConfig) moonshot: ProviderConfig = Field(default_factory=ProviderConfig)
minimax: ProviderConfig = Field(default_factory=ProviderConfig) minimax: ProviderConfig = Field(default_factory=ProviderConfig)
aihubmix: ProviderConfig = Field(default_factory=ProviderConfig) # AiHubMix API gateway aihubmix: ProviderConfig = Field(default_factory=ProviderConfig) # AiHubMix API gateway
siliconflow: ProviderConfig = Field(default_factory=ProviderConfig) # SiliconFlow (硅基流动) API gateway siliconflow: ProviderConfig = Field(
volcengine: ProviderConfig = Field(default_factory=ProviderConfig) # VolcEngine (火山引擎) API gateway default_factory=ProviderConfig
) # SiliconFlow (硅基流动) API gateway
volcengine: ProviderConfig = Field(
default_factory=ProviderConfig
) # VolcEngine (火山引擎) API gateway
openai_codex: ProviderConfig = Field(default_factory=ProviderConfig) # OpenAI Codex (OAuth) openai_codex: ProviderConfig = Field(default_factory=ProviderConfig) # OpenAI Codex (OAuth)
github_copilot: ProviderConfig = Field(default_factory=ProviderConfig) # Github Copilot (OAuth) github_copilot: ProviderConfig = Field(default_factory=ProviderConfig) # Github Copilot (OAuth)
@@ -291,7 +315,9 @@ class WebSearchConfig(Base):
class WebToolsConfig(Base): class WebToolsConfig(Base):
"""Web tools configuration.""" """Web tools configuration."""
proxy: str | None = None # HTTP/SOCKS5 proxy URL, e.g. "http://127.0.0.1:7890" or "socks5://127.0.0.1:1080" proxy: str | None = (
None # HTTP/SOCKS5 proxy URL, e.g. "http://127.0.0.1:7890" or "socks5://127.0.0.1:1080"
)
search: WebSearchConfig = Field(default_factory=WebSearchConfig) search: WebSearchConfig = Field(default_factory=WebSearchConfig)
@@ -336,7 +362,9 @@ class Config(BaseSettings):
"""Get expanded workspace path.""" """Get expanded workspace path."""
return Path(self.agents.defaults.workspace).expanduser() return Path(self.agents.defaults.workspace).expanduser()
def _match_provider(self, model: str | None = None) -> tuple["ProviderConfig | None", str | None]: def _match_provider(
self, model: str | None = None
) -> tuple["ProviderConfig | None", str | None]:
"""Match provider config and its registry name. Returns (config, spec_name).""" """Match provider config and its registry name. Returns (config, spec_name)."""
from nanobot.providers.registry import PROVIDERS from nanobot.providers.registry import PROVIDERS

130
nanobot/providers/registry.py
View File

@@ -26,33 +26,33 @@ class ProviderSpec:
""" """
# identity # identity
name: str # config field name, e.g. "dashscope" name: str # config field name, e.g. "dashscope"
keywords: tuple[str, ...] # model-name keywords for matching (lowercase) keywords: tuple[str, ...] # model-name keywords for matching (lowercase)
env_key: str # LiteLLM env var, e.g. "DASHSCOPE_API_KEY" env_key: str # LiteLLM env var, e.g. "DASHSCOPE_API_KEY"
display_name: str = "" # shown in `nanobot status` display_name: str = "" # shown in `nanobot status`
# model prefixing # model prefixing
litellm_prefix: str = "" # "dashscope" → model becomes "dashscope/{model}" litellm_prefix: str = "" # "dashscope" → model becomes "dashscope/{model}"
skip_prefixes: tuple[str, ...] = () # don't prefix if model already starts with these skip_prefixes: tuple[str, ...] = () # don't prefix if model already starts with these
# extra env vars, e.g. (("ZHIPUAI_API_KEY", "{api_key}"),) # extra env vars, e.g. (("ZHIPUAI_API_KEY", "{api_key}"),)
env_extras: tuple[tuple[str, str], ...] = () env_extras: tuple[tuple[str, str], ...] = ()
# gateway / local detection # gateway / local detection
is_gateway: bool = False # routes any model (OpenRouter, AiHubMix) is_gateway: bool = False # routes any model (OpenRouter, AiHubMix)
is_local: bool = False # local deployment (vLLM, Ollama) is_local: bool = False # local deployment (vLLM, Ollama)
detect_by_key_prefix: str = "" # match api_key prefix, e.g. "sk-or-" detect_by_key_prefix: str = "" # match api_key prefix, e.g. "sk-or-"
detect_by_base_keyword: str = "" # match substring in api_base URL detect_by_base_keyword: str = "" # match substring in api_base URL
default_api_base: str = "" # fallback base URL default_api_base: str = "" # fallback base URL
# gateway behavior # 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}),) # per-model param overrides, e.g. (("kimi-k2.5", {"temperature": 1.0}),)
model_overrides: tuple[tuple[str, dict[str, Any]], ...] = () model_overrides: tuple[tuple[str, dict[str, Any]], ...] = ()
# OAuth-based providers (e.g., OpenAI Codex) don't use API keys # 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) # Direct providers bypass LiteLLM entirely (e.g., CustomProvider)
is_direct: bool = False is_direct: bool = False
@@ -70,7 +70,6 @@ class ProviderSpec:
# --------------------------------------------------------------------------- # ---------------------------------------------------------------------------
PROVIDERS: tuple[ProviderSpec, ...] = ( PROVIDERS: tuple[ProviderSpec, ...] = (
# === Custom (direct OpenAI-compatible endpoint, bypasses LiteLLM) ====== # === Custom (direct OpenAI-compatible endpoint, bypasses LiteLLM) ======
ProviderSpec( ProviderSpec(
name="custom", name="custom",
@@ -80,17 +79,15 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
litellm_prefix="", litellm_prefix="",
is_direct=True, is_direct=True,
), ),
# === Gateways (detected by api_key / api_base, not model name) ========= # === Gateways (detected by api_key / api_base, not model name) =========
# Gateways can route any model, so they win in fallback. # Gateways can route any model, so they win in fallback.
# OpenRouter: global gateway, keys start with "sk-or-" # OpenRouter: global gateway, keys start with "sk-or-"
ProviderSpec( ProviderSpec(
name="openrouter", name="openrouter",
keywords=("openrouter",), keywords=("openrouter",),
env_key="OPENROUTER_API_KEY", env_key="OPENROUTER_API_KEY",
display_name="OpenRouter", display_name="OpenRouter",
litellm_prefix="openrouter", # claude-3 → openrouter/claude-3 litellm_prefix="openrouter", # claude-3 → openrouter/claude-3
skip_prefixes=(), skip_prefixes=(),
env_extras=(), env_extras=(),
is_gateway=True, is_gateway=True,
@@ -102,16 +99,15 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
model_overrides=(), model_overrides=(),
supports_prompt_caching=True, supports_prompt_caching=True,
), ),
# AiHubMix: global gateway, OpenAI-compatible interface. # AiHubMix: global gateway, OpenAI-compatible interface.
# strip_model_prefix=True: it doesn't understand "anthropic/claude-3", # 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". # so we strip to bare "claude-3" then re-prefix as "openai/claude-3".
ProviderSpec( ProviderSpec(
name="aihubmix", name="aihubmix",
keywords=("aihubmix",), keywords=("aihubmix",),
env_key="OPENAI_API_KEY", # OpenAI-compatible env_key="OPENAI_API_KEY", # OpenAI-compatible
display_name="AiHubMix", display_name="AiHubMix",
litellm_prefix="openai", # → openai/{model} litellm_prefix="openai", # → openai/{model}
skip_prefixes=(), skip_prefixes=(),
env_extras=(), env_extras=(),
is_gateway=True, is_gateway=True,
@@ -119,10 +115,9 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
detect_by_key_prefix="", detect_by_key_prefix="",
detect_by_base_keyword="aihubmix", detect_by_base_keyword="aihubmix",
default_api_base="https://aihubmix.com/v1", 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=(), model_overrides=(),
), ),
# SiliconFlow (硅基流动): OpenAI-compatible gateway, model names keep org prefix # SiliconFlow (硅基流动): OpenAI-compatible gateway, model names keep org prefix
ProviderSpec( ProviderSpec(
name="siliconflow", name="siliconflow",
@@ -140,7 +135,6 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
strip_model_prefix=False, strip_model_prefix=False,
model_overrides=(), model_overrides=(),
), ),
# VolcEngine (火山引擎): OpenAI-compatible gateway # VolcEngine (火山引擎): OpenAI-compatible gateway
ProviderSpec( ProviderSpec(
name="volcengine", name="volcengine",
@@ -158,9 +152,7 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
strip_model_prefix=False, strip_model_prefix=False,
model_overrides=(), model_overrides=(),
), ),
# === Standard providers (matched by model-name keywords) =============== # === Standard providers (matched by model-name keywords) ===============
# Anthropic: LiteLLM recognizes "claude-*" natively, no prefix needed. # Anthropic: LiteLLM recognizes "claude-*" natively, no prefix needed.
ProviderSpec( ProviderSpec(
name="anthropic", name="anthropic",
@@ -179,7 +171,6 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
model_overrides=(), model_overrides=(),
supports_prompt_caching=True, supports_prompt_caching=True,
), ),
# OpenAI: LiteLLM recognizes "gpt-*" natively, no prefix needed. # OpenAI: LiteLLM recognizes "gpt-*" natively, no prefix needed.
ProviderSpec( ProviderSpec(
name="openai", name="openai",
@@ -197,14 +188,13 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
strip_model_prefix=False, strip_model_prefix=False,
model_overrides=(), model_overrides=(),
), ),
# OpenAI Codex: uses OAuth, not API key. # OpenAI Codex: uses OAuth, not API key.
ProviderSpec( ProviderSpec(
name="openai_codex", name="openai_codex",
keywords=("openai-codex",), keywords=("openai-codex",),
env_key="", # OAuth-based, no API key env_key="", # OAuth-based, no API key
display_name="OpenAI Codex", display_name="OpenAI Codex",
litellm_prefix="", # Not routed through LiteLLM litellm_prefix="", # Not routed through LiteLLM
skip_prefixes=(), skip_prefixes=(),
env_extras=(), env_extras=(),
is_gateway=False, is_gateway=False,
@@ -214,16 +204,15 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
default_api_base="https://chatgpt.com/backend-api", default_api_base="https://chatgpt.com/backend-api",
strip_model_prefix=False, strip_model_prefix=False,
model_overrides=(), model_overrides=(),
is_oauth=True, # OAuth-based authentication is_oauth=True, # OAuth-based authentication
), ),
# Github Copilot: uses OAuth, not API key. # Github Copilot: uses OAuth, not API key.
ProviderSpec( ProviderSpec(
name="github_copilot", name="github_copilot",
keywords=("github_copilot", "copilot"), keywords=("github_copilot", "copilot"),
env_key="", # OAuth-based, no API key env_key="", # OAuth-based, no API key
display_name="Github Copilot", 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/",), skip_prefixes=("github_copilot/",),
env_extras=(), env_extras=(),
is_gateway=False, is_gateway=False,
@@ -233,17 +222,16 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
default_api_base="", default_api_base="",
strip_model_prefix=False, strip_model_prefix=False,
model_overrides=(), model_overrides=(),
is_oauth=True, # OAuth-based authentication is_oauth=True, # OAuth-based authentication
), ),
# DeepSeek: needs "deepseek/" prefix for LiteLLM routing. # DeepSeek: needs "deepseek/" prefix for LiteLLM routing.
ProviderSpec( ProviderSpec(
name="deepseek", name="deepseek",
keywords=("deepseek",), keywords=("deepseek",),
env_key="DEEPSEEK_API_KEY", env_key="DEEPSEEK_API_KEY",
display_name="DeepSeek", display_name="DeepSeek",
litellm_prefix="deepseek", # deepseek-chat → deepseek/deepseek-chat litellm_prefix="deepseek", # deepseek-chat → deepseek/deepseek-chat
skip_prefixes=("deepseek/",), # avoid double-prefix skip_prefixes=("deepseek/",), # avoid double-prefix
env_extras=(), env_extras=(),
is_gateway=False, is_gateway=False,
is_local=False, is_local=False,
@@ -253,15 +241,14 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
strip_model_prefix=False, strip_model_prefix=False,
model_overrides=(), model_overrides=(),
), ),
# Gemini: needs "gemini/" prefix for LiteLLM. # Gemini: needs "gemini/" prefix for LiteLLM.
ProviderSpec( ProviderSpec(
name="gemini", name="gemini",
keywords=("gemini",), keywords=("gemini",),
env_key="GEMINI_API_KEY", env_key="GEMINI_API_KEY",
display_name="Gemini", display_name="Gemini",
litellm_prefix="gemini", # gemini-pro → gemini/gemini-pro litellm_prefix="gemini", # gemini-pro → gemini/gemini-pro
skip_prefixes=("gemini/",), # avoid double-prefix skip_prefixes=("gemini/",), # avoid double-prefix
env_extras=(), env_extras=(),
is_gateway=False, is_gateway=False,
is_local=False, is_local=False,
@@ -271,7 +258,6 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
strip_model_prefix=False, strip_model_prefix=False,
model_overrides=(), model_overrides=(),
), ),
# Zhipu: LiteLLM uses "zai/" prefix. # Zhipu: LiteLLM uses "zai/" prefix.
# Also mirrors key to ZHIPUAI_API_KEY (some LiteLLM paths check that). # Also mirrors key to ZHIPUAI_API_KEY (some LiteLLM paths check that).
# skip_prefixes: don't add "zai/" when already routed via gateway. # skip_prefixes: don't add "zai/" when already routed via gateway.
@@ -280,11 +266,9 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
keywords=("zhipu", "glm", "zai"), keywords=("zhipu", "glm", "zai"),
env_key="ZAI_API_KEY", env_key="ZAI_API_KEY",
display_name="Zhipu AI", 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/"), skip_prefixes=("zhipu/", "zai/", "openrouter/", "hosted_vllm/"),
env_extras=( env_extras=(("ZHIPUAI_API_KEY", "{api_key}"),),
("ZHIPUAI_API_KEY", "{api_key}"),
),
is_gateway=False, is_gateway=False,
is_local=False, is_local=False,
detect_by_key_prefix="", detect_by_key_prefix="",
@@ -293,14 +277,13 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
strip_model_prefix=False, strip_model_prefix=False,
model_overrides=(), model_overrides=(),
), ),
# DashScope: Qwen models, needs "dashscope/" prefix. # DashScope: Qwen models, needs "dashscope/" prefix.
ProviderSpec( ProviderSpec(
name="dashscope", name="dashscope",
keywords=("qwen", "dashscope"), keywords=("qwen", "dashscope"),
env_key="DASHSCOPE_API_KEY", env_key="DASHSCOPE_API_KEY",
display_name="DashScope", display_name="DashScope",
litellm_prefix="dashscope", # qwen-max → dashscope/qwen-max litellm_prefix="dashscope", # qwen-max → dashscope/qwen-max
skip_prefixes=("dashscope/", "openrouter/"), skip_prefixes=("dashscope/", "openrouter/"),
env_extras=(), env_extras=(),
is_gateway=False, is_gateway=False,
@@ -311,7 +294,6 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
strip_model_prefix=False, strip_model_prefix=False,
model_overrides=(), model_overrides=(),
), ),
# Moonshot: Kimi models, needs "moonshot/" prefix. # Moonshot: Kimi models, needs "moonshot/" prefix.
# LiteLLM requires MOONSHOT_API_BASE env var to find the endpoint. # LiteLLM requires MOONSHOT_API_BASE env var to find the endpoint.
# Kimi K2.5 API enforces temperature >= 1.0. # Kimi K2.5 API enforces temperature >= 1.0.
@@ -320,22 +302,17 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
keywords=("moonshot", "kimi"), keywords=("moonshot", "kimi"),
env_key="MOONSHOT_API_KEY", env_key="MOONSHOT_API_KEY",
display_name="Moonshot", 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/"), skip_prefixes=("moonshot/", "openrouter/"),
env_extras=( env_extras=(("MOONSHOT_API_BASE", "{api_base}"),),
("MOONSHOT_API_BASE", "{api_base}"),
),
is_gateway=False, is_gateway=False,
is_local=False, is_local=False,
detect_by_key_prefix="", detect_by_key_prefix="",
detect_by_base_keyword="", 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, strip_model_prefix=False,
model_overrides=( model_overrides=(("kimi-k2.5", {"temperature": 1.0}),),
("kimi-k2.5", {"temperature": 1.0}),
),
), ),
# MiniMax: needs "minimax/" prefix for LiteLLM routing. # MiniMax: needs "minimax/" prefix for LiteLLM routing.
# Uses OpenAI-compatible API at api.minimax.io/v1. # Uses OpenAI-compatible API at api.minimax.io/v1.
ProviderSpec( ProviderSpec(
@@ -343,7 +320,7 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
keywords=("minimax",), keywords=("minimax",),
env_key="MINIMAX_API_KEY", env_key="MINIMAX_API_KEY",
display_name="MiniMax", 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/"), skip_prefixes=("minimax/", "openrouter/"),
env_extras=(), env_extras=(),
is_gateway=False, is_gateway=False,
@@ -354,9 +331,7 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
strip_model_prefix=False, strip_model_prefix=False,
model_overrides=(), model_overrides=(),
), ),
# === Local deployment (matched by config key, NOT by api_base) ========= # === Local deployment (matched by config key, NOT by api_base) =========
# vLLM / any OpenAI-compatible local server. # vLLM / any OpenAI-compatible local server.
# Detected when config key is "vllm" (provider_name="vllm"). # Detected when config key is "vllm" (provider_name="vllm").
ProviderSpec( ProviderSpec(
@@ -364,20 +339,38 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
keywords=("vllm",), keywords=("vllm",),
env_key="HOSTED_VLLM_API_KEY", env_key="HOSTED_VLLM_API_KEY",
display_name="vLLM/Local", 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=(), skip_prefixes=(),
env_extras=(), env_extras=(),
is_gateway=False, is_gateway=False,
is_local=True, is_local=True,
detect_by_key_prefix="", detect_by_key_prefix="",
detect_by_base_keyword="", 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=(),
),
# === Coding Plan Gateway Providers =====================================
# Alibaba Cloud Coding Plan: OpenAI-compatible gateway for coding assistance.
# Uses special API key format starting with "sk-sp-" to distinguish it
# from regular dashscope keys. Uses the OpenAI-compatible endpoint.
ProviderSpec(
name="dashscope_coding_plan",
keywords=("dashscope-coding-plan", "coding-plan", "aliyun-coding", "bailian-coding"),
env_key="DASHSCOPE_CODING_PLAN_API_KEY",
display_name="Alibaba Cloud Coding Plan",
litellm_prefix="dashscope", # → dashscope/{model}
skip_prefixes=("dashscope/", "openrouter/"),
env_extras=(),
is_gateway=True,
is_local=False,
detect_by_key_prefix="sk-sp-", # coding plan API keys start with "sk-sp-"
detect_by_base_keyword="coding.dashscope",
default_api_base="https://coding.dashscope.aliyuncs.com/v1",
strip_model_prefix=False, strip_model_prefix=False,
model_overrides=(), model_overrides=(),
), ),
# === Auxiliary (not a primary LLM provider) ============================ # === Auxiliary (not a primary LLM provider) ============================
# Groq: mainly used for Whisper voice transcription, also usable for LLM. # Groq: mainly used for Whisper voice transcription, also usable for LLM.
# Needs "groq/" prefix for LiteLLM routing. Placed last — it rarely wins fallback. # Needs "groq/" prefix for LiteLLM routing. Placed last — it rarely wins fallback.
ProviderSpec( ProviderSpec(
@@ -385,8 +378,8 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
keywords=("groq",), keywords=("groq",),
env_key="GROQ_API_KEY", env_key="GROQ_API_KEY",
display_name="Groq", display_name="Groq",
litellm_prefix="groq", # llama3-8b-8192 → groq/llama3-8b-8192 litellm_prefix="groq", # llama3-8b-8192 → groq/llama3-8b-8192
skip_prefixes=("groq/",), # avoid double-prefix skip_prefixes=("groq/",), # avoid double-prefix
env_extras=(), env_extras=(),
is_gateway=False, is_gateway=False,
is_local=False, is_local=False,
@@ -403,6 +396,7 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
# Lookup helpers # Lookup helpers
# --------------------------------------------------------------------------- # ---------------------------------------------------------------------------
def find_by_model(model: str) -> ProviderSpec | None: def find_by_model(model: str) -> ProviderSpec | None:
"""Match a standard provider by model-name keyword (case-insensitive). """Match a standard provider by model-name keyword (case-insensitive).
Skips gateways/local — those are matched by api_key/api_base instead.""" Skips gateways/local — those are matched by api_key/api_base instead."""
@@ -418,7 +412,9 @@ def find_by_model(model: str) -> ProviderSpec | None:
return spec return spec
for spec in std_specs: 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 spec
return None return None