docs: clarify custom provider protocol support

maintainer edit: spell out that arbitrary named custom providers use the OpenAI-compatible request format only, and point Anthropic-compatible proxies to the built-in anthropic provider with apiBase.
This commit is contained in:
chengyongru 2026-06-11 15:25:48 +08:00 committed by Xubin Ren
parent 69d66e0d6a
commit a9308eb8e2
3 changed files with 58 additions and 3 deletions

View File

@ -205,7 +205,7 @@ Tracing covers the providers that go through nanobot's OpenAI-compatible client
> - **Step Fun (Mainland China)**: If your API key is from Step Fun's mainland China platform (stepfun.com), set `"apiBase": "https://api.stepfun.com/v1"` in your stepfun provider config. > - **Step Fun (Mainland China)**: If your API key is from Step Fun's mainland China platform (stepfun.com), set `"apiBase": "https://api.stepfun.com/v1"` in your stepfun provider config.
> - **Xiaomi MiMo thinking mode**: MiMo models (e.g. `mimo-v2.5-pro`) default to enabled thinking. Use `agents.defaults.reasoningEffort: "none"` to disable it, or `"low"` / `"medium"` / `"high"` to keep it on. Omitting the field preserves the provider's per-model default. > - **Xiaomi MiMo thinking mode**: MiMo models (e.g. `mimo-v2.5-pro`) default to enabled thinking. Use `agents.defaults.reasoningEffort: "none"` to disable it, or `"low"` / `"medium"` / `"high"` to keep it on. Omitting the field preserves the provider's per-model default.
> - **Xiaomi MiMo Token Plan**: If you're on MiMo's token plan, set `"apiBase": "https://token-plan-sgp.xiaomimimo.com/v1"` in your xiaomi_mimo provider config. > - **Xiaomi MiMo Token Plan**: If you're on MiMo's token plan, set `"apiBase": "https://token-plan-sgp.xiaomimimo.com/v1"` in your xiaomi_mimo provider config.
> - **Custom OpenAI-compatible providers**: Besides the built-in `custom` provider, any extra key under `providers` can define its own OpenAI-compatible endpoint. For example, `providers.companyProxy.apiBase` plus `modelPresets.primary.provider: "companyProxy"` creates a separate custom provider. Set `apiBase`; set `apiKey` only when the endpoint requires it. > - **Custom OpenAI-compatible providers**: Besides the built-in `custom` provider, any extra key under `providers` can define its own OpenAI-compatible endpoint. For example, `providers.companyProxy.apiBase` plus `modelPresets.primary.provider: "companyProxy"` creates a separate custom provider. Set `apiBase`; set `apiKey` only when the endpoint requires it. This named-custom path uses the OpenAI-compatible request format only. For Anthropic-compatible proxies, use `providers.anthropic.apiBase` with `provider: "anthropic"`.
| Provider | Purpose | Get API Key | | Provider | Purpose | Get API Key |
|----------|---------|-------------| |----------|---------|-------------|
@ -859,7 +859,9 @@ Connects directly to any OpenAI-compatible endpoint — llama.cpp, Together AI,
> } > }
> ``` > ```
> >
> In short: **chat-completions-compatible endpoint → `custom`**; **Responses-compatible endpoint → `azure_openai`**. > Anthropic-compatible endpoints are separate: use `providers.anthropic.apiBase` and set the preset provider to `anthropic`. Arbitrary custom provider names do not use the Anthropic Messages API format.
>
> In short: **chat-completions-compatible endpoint → `custom` or a named custom provider**; **Responses-compatible endpoint → `azure_openai`**; **Anthropic-compatible endpoint → `anthropic` with `apiBase`**.
Some OpenAI-compatible gateways expose request-body extensions such as vLLM guided decoding or local sampling controls. Put those under `extraBody`; nanobot merges them into the chat-completions request body after its provider defaults: Some OpenAI-compatible gateways expose request-body extensions such as vLLM guided decoding or local sampling controls. Put those under `extraBody`; nanobot merges them into the chat-completions request body after its provider defaults:

View File

@ -168,6 +168,36 @@ ANTHROPIC_API_KEY="sk-ant-..." nanobot agent -m "Hello!"
If you copied a model name such as `anthropic/claude-sonnet-4.5`, that is a gateway-style model path and belongs under `provider: "openrouter"`, not `provider: "anthropic"`. If you copied a model name such as `anthropic/claude-sonnet-4.5`, that is a gateway-style model path and belongs under `provider: "openrouter"`, not `provider: "anthropic"`.
If you use an Anthropic-compatible proxy, keep the preset provider as `anthropic` and set `providers.anthropic.apiBase`:
```json
{
"providers": {
"anthropic": {
"apiKey": "${ANTHROPIC_API_KEY}",
"apiBase": "https://anthropic-proxy.example.com"
}
},
"modelPresets": {
"primary": {
"label": "Anthropic proxy",
"provider": "anthropic",
"model": "claude-sonnet-4-5",
"maxTokens": 4096,
"contextWindowTokens": 200000,
"temperature": 0.1
}
},
"agents": {
"defaults": {
"modelPreset": "primary"
}
}
}
```
Do not configure Anthropic-compatible endpoints as arbitrary custom provider names; named custom providers use the OpenAI-compatible request format.
## Recipe: Custom OpenAI-Compatible Provider ## Recipe: Custom OpenAI-Compatible Provider
This recipe applies to an OpenAI-compatible service that is not a named nanobot provider. This recipe applies to an OpenAI-compatible service that is not a named nanobot provider.
@ -246,7 +276,7 @@ For multiple custom endpoints, do not overload the single `custom` block. Name e
} }
``` ```
These custom names behave like direct OpenAI-compatible providers: `apiBase` is required, `apiKey` is optional when the endpoint allows anonymous or placeholder credentials, and `apiType` should be left unset. These custom names behave like direct OpenAI-compatible providers: `apiBase` is required, `apiKey` is optional when the endpoint allows anonymous or placeholder credentials, and `apiType` should be left unset. They do not support Anthropic-compatible endpoints; use the `anthropic` provider with `apiBase` for that case.
## Recipe: Ollama Local Model ## Recipe: Ollama Local Model

View File

@ -121,6 +121,27 @@ Use the model ID exactly as OpenRouter lists it.
Anthropic direct uses the native Anthropic provider. Do not use an OpenRouter model ID unless the provider is OpenRouter. Anthropic direct uses the native Anthropic provider. Do not use an OpenRouter model ID unless the provider is OpenRouter.
If you use an Anthropic-compatible proxy, keep the provider as `anthropic` and override `apiBase`:
```json
{
"providers": {
"anthropic": {
"apiKey": "${ANTHROPIC_API_KEY}",
"apiBase": "https://anthropic-proxy.example.com"
}
},
"modelPresets": {
"primary": {
"provider": "anthropic",
"model": "claude-sonnet-4-5"
}
}
}
```
Arbitrary custom provider names are OpenAI-compatible only; they do not use the Anthropic Messages API request format.
### OpenAI Direct ### OpenAI Direct
```json ```json
@ -215,6 +236,8 @@ If you have more than one custom OpenAI-compatible endpoint, give each endpoint
Custom provider keys are treated as direct OpenAI-compatible providers. `apiBase` is required because nanobot cannot know the endpoint URL. `apiKey` is optional for local servers or private proxies that do not require one. Do not set `apiType` on custom provider keys; `apiType` is only for `providers.openai`. Custom provider keys are treated as direct OpenAI-compatible providers. `apiBase` is required because nanobot cannot know the endpoint URL. `apiKey` is optional for local servers or private proxies that do not require one. Do not set `apiType` on custom provider keys; `apiType` is only for `providers.openai`.
This named custom provider path is not for Anthropic-compatible endpoints. For Anthropic-compatible proxies, use `providers.anthropic.apiBase` and set the preset provider to `anthropic`.
### Ollama ### Ollama
Start Ollama separately, then point nanobot at the OpenAI-compatible endpoint. Start Ollama separately, then point nanobot at the OpenAI-compatible endpoint.