shumengya/sproutclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(ai): add Together AI provider

Browse Source
This commit is contained in:
Mario Zechner
2026-05-08 16:44:18 +02:00
parent 9751057be9
commit 7adb8e7634
30 changed files with 714 additions and 56 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
packages/coding-agent/docs/custom-provider.md
View File

@@ -226,7 +226,7 @@ models: [{
}]
```
Use `qwen-chat-template` instead for local Qwen-compatible servers that read `chat_template_kwargs.enable_thinking`.
Use `openrouter` for OpenRouter-style `reasoning: { effort }` controls. Use `together` for Together-style `reasoning: { enabled }` controls; with `supportsReasoningEffort`, it also sends `reasoning_effort`. Use `qwen-chat-template` instead for local Qwen-compatible servers that read `chat_template_kwargs.enable_thinking`.
Use `cacheControlFormat: "anthropic"` for OpenAI-compatible providers that expose Anthropic-style prompt caching via `cache_control` on the system prompt, last tool definition, and last user/assistant text content.
> Migration note: Mistral moved from `openai-completions` to `mistral-conversations`.
@@ -636,11 +636,11 @@ interface ProviderModelConfig {
requiresAssistantAfterToolResult?: boolean;
requiresThinkingAsText?: boolean;
requiresReasoningContentOnAssistantMessages?: boolean;
thinkingFormat?: "openai" | "deepseek" | "zai" | "qwen" | "qwen-chat-template";
thinkingFormat?: "openai" | "openrouter" | "deepseek" | "together" | "zai" | "qwen" | "qwen-chat-template";
cacheControlFormat?: "anthropic";
};
}
```
`deepseek` sends `thinking: { type: "enabled" | "disabled" }` and `reasoning_effort` when enabled. `qwen` is for DashScope-style top-level `enable_thinking`. Use `qwen-chat-template` for local Qwen-compatible servers that read `chat_template_kwargs.enable_thinking`.
`openrouter` sends `reasoning: { effort }`. `deepseek` sends `thinking: { type: "enabled" | "disabled" }` and `reasoning_effort` when enabled. `together` sends `reasoning: { enabled }` and also `reasoning_effort` when `supportsReasoningEffort` is enabled. `qwen` is for DashScope-style top-level `enable_thinking`. Use `qwen-chat-template` for local Qwen-compatible servers that read `chat_template_kwargs.enable_thinking`.
`cacheControlFormat: "anthropic"` applies Anthropic-style `cache_control` markers to the system prompt, last tool definition, and last user/assistant text content.

4
packages/coding-agent/docs/models.md
View File

@@ -381,14 +381,14 @@ For providers with partial OpenAI compatibility, use the `compat` field.
| `requiresAssistantAfterToolResult` | Insert an assistant message before a user message after tool results |
| `requiresThinkingAsText` | Convert thinking blocks to plain text |
| `requiresReasoningContentOnAssistantMessages` | Include empty `reasoning_content` on all replayed assistant messages when reasoning is enabled |
| `thinkingFormat` | Use `reasoning_effort`, `deepseek`, `zai`, `qwen`, or `qwen-chat-template` thinking parameters |
| `thinkingFormat` | Use `reasoning_effort`, `openrouter`, `deepseek`, `together`, `zai`, `qwen`, or `qwen-chat-template` thinking parameters |
| `cacheControlFormat` | Use Anthropic-style `cache_control` markers on the system prompt, last tool definition, and last user/assistant text content. Currently only `anthropic` is supported. |
| `supportsStrictMode` | Include the `strict` field in tool definitions |
| `supportsLongCacheRetention` | Whether the provider accepts long cache retention when cache retention is `long`: `prompt_cache_retention: "24h"` for OpenAI prompt caching, or `cache_control.ttl: "1h"` when `cacheControlFormat` is `anthropic`. Default: `true`. |
| `openRouterRouting` | OpenRouter provider routing preferences. This object is sent as-is in the `provider` field of the [OpenRouter API request](https://openrouter.ai/docs/guides/routing/provider-selection). |
| `vercelGatewayRouting` | Vercel AI Gateway routing config for provider selection (`only`, `order`) |
`qwen` uses top-level `enable_thinking`. Use `qwen-chat-template` for local Qwen-compatible servers that require `chat_template_kwargs.enable_thinking`.
`openrouter` uses `reasoning: { effort }`. `together` uses `reasoning: { enabled }` and also `reasoning_effort` when `supportsReasoningEffort` is enabled. `qwen` uses top-level `enable_thinking`. Use `qwen-chat-template` for local Qwen-compatible servers that require `chat_template_kwargs.enable_thinking`.
`cacheControlFormat: "anthropic"` is for OpenAI-compatible providers that expose Anthropic-style prompt caching through `cache_control` markers on text content and tool definitions.

2
packages/coding-agent/docs/providers.md
View File

@@ -66,6 +66,7 @@ pi
| OpenCode Go | `OPENCODE_API_KEY` | `opencode-go` |
| Hugging Face | `HF_TOKEN` | `huggingface` |
| Fireworks | `FIREWORKS_API_KEY` | `fireworks` |
| Together AI | `TOGETHER_API_KEY` | `together` |
| Kimi For Coding | `KIMI_API_KEY` | `kimi-coding` |
| MiniMax | `MINIMAX_API_KEY` | `minimax` |
| MiniMax (China) | `MINIMAX_CN_API_KEY` | `minimax-cn` |
@@ -88,6 +89,7 @@ Store credentials in `~/.pi/agent/auth.json`:
"google": { "type": "api_key", "key": "..." },
"opencode": { "type": "api_key", "key": "..." },
"opencode-go": { "type": "api_key", "key": "..." },
"together": { "type": "api_key", "key": "..." },
"xiaomi": { "type": "api_key", "key": "..." },
"xiaomi-token-plan-cn": { "type": "api_key", "key": "..." },
"xiaomi-token-plan-ams": { "type": "api_key", "key": "..." },