getcompanion-ai/co-mono
1
0
Fork 0
mirror of https://github.com/getcompanion-ai/co-mono.git synced 2026-04-15 09:01:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'feat/use-mistral-sdk'

Browse source
This commit is contained in:
Mario Zechner 2026-03-05 23:49:29 +01:00
commit a31065166d
17 changed files with 728 additions and 171 deletions
Download patch file Download diff file Expand all files Collapse all files

7
packages/ai/README.md
View file

@ -627,6 +627,7 @@ The library uses a registry of API implementations. Built-in APIs include:
- **`google-generative-ai`**: Google Generative AI API (`streamGoogle`, `GoogleOptions`)
- **`google-gemini-cli`**: Google Cloud Code Assist API (`streamGoogleGeminiCli`, `GoogleGeminiCliOptions`)
- **`google-vertex`**: Google Vertex AI API (`streamGoogleVertex`, `GoogleVertexOptions`)
- **`mistral-conversations`**: Mistral Conversations API (`streamMistral`, `MistralOptions`)
- **`openai-completions`**: OpenAI Chat Completions API (`streamOpenAICompletions`, `OpenAICompletionsOptions`)
- **`openai-responses`**: OpenAI Responses API (`streamOpenAIResponses`, `OpenAIResponsesOptions`)
- **`openai-codex-responses`**: OpenAI Codex Responses API (`streamOpenAICodexResponses`, `OpenAICodexResponsesOptions`)
@ -639,7 +640,8 @@ A **provider** offers models through a specific API. For example:
- **Anthropic** models use the `anthropic-messages` API
- **Google** models use the `google-generative-ai` API
- **OpenAI** models use the `openai-responses` API
- **Mistral, xAI, Cerebras, Groq, etc.** models use the `openai-completions` API (OpenAI-compatible)
- **Mistral** models use the `mistral-conversations` API
- **xAI, Cerebras, Groq, etc.** models use the `openai-completions` API (OpenAI-compatible)
### Querying Providers and Models
@ -729,7 +731,7 @@ const response = await stream(ollamaModel, context, {
### OpenAI Compatibility Settings
The `openai-completions` API is implemented by many providers with minor differences. By default, the library auto-detects compatibility settings based on `baseUrl` for known providers (Cerebras, xAI, Mistral, Chutes, etc.). For custom proxies or unknown endpoints, you can override these settings via the `compat` field. For `openai-responses` models, the compat field only supports Responses-specific flags.
The `openai-completions` API is implemented by many providers with minor differences. By default, the library auto-detects compatibility settings based on `baseUrl` for a small set of known OpenAI-compatible providers (Cerebras, xAI, Chutes, DeepSeek, zAi, OpenCode, etc.). For custom proxies or unknown endpoints, you can override these settings via the `compat` field. For `openai-responses` models, the compat field only supports Responses-specific flags.
```typescript
interface OpenAICompletionsCompat {
@ -742,7 +744,6 @@ interface OpenAICompletionsCompat {
requiresToolResultName?: boolean; // Whether tool results require the `name` field (default: false)
requiresAssistantAfterToolResult?: boolean; // Whether tool results must be followed by an assistant message (default: false)
requiresThinkingAsText?: boolean; // Whether thinking blocks must be converted to text (default: false)
requiresMistralToolIds?: boolean; // Whether tool call IDs must be normalized to Mistral format (default: false)
thinkingFormat?: 'openai' | 'zai' | 'qwen'; // Format for reasoning param: 'openai' uses reasoning_effort, 'zai' uses thinking: { type: "enabled" }, 'qwen' uses enable_thinking: boolean (default: openai)
openRouterRouting?: OpenRouterRouting; // OpenRouter routing preferences (default: {})
vercelGatewayRouting?: VercelGatewayRouting; // Vercel AI Gateway routing preferences (default: {})