getcompanion-ai/co-mono
1
0
Fork 0
mirror of https://github.com/getcompanion-ai/co-mono.git synced 2026-04-21 07:02:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(ai): add strictResponsesPairing for Azure OpenAI Responses API

Browse source 
Split OpenAICompat into OpenAICompletionsCompat and OpenAIResponsesCompat
for type-safe API-specific compat settings. Added strictResponsesPairing
option to suppress orphaned reasoning/tool calls on incomplete turns,
fixing 400 errors on Azure's Responses API which requires strict pairing.

Closes #768
This commit is contained in:
Mario Zechner 2026-01-18 20:15:26 +01:00
parent def9e4e9a9
commit d43930c818
17 changed files with 112 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

8
packages/ai/README.md
View file

@ -703,16 +703,20 @@ 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:
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.
```typescript
interface OpenAICompat {
interface OpenAICompletionsCompat {
supportsStore?: boolean; // Whether provider supports the `store` field (default: true)
supportsDeveloperRole?: boolean; // Whether provider supports `developer` role vs `system` (default: true)
supportsReasoningEffort?: boolean; // Whether provider supports `reasoning_effort` (default: true)
maxTokensField?: 'max_completion_tokens' | 'max_tokens'; // Which field name to use (default: max_completion_tokens)
thinkingFormat?: 'openai' | 'zai'; // Format for reasoning param: 'openai' uses reasoning_effort, 'zai' uses thinking: { type: "enabled" } (default: openai)
}
interface OpenAIResponsesCompat {
strictResponsesPairing?: boolean; // Enforce strict reasoning/message pairing for OpenAI Responses history replay on providers like Azure (default: false)
}
```
If `compat` is not set, the library falls back to URL-based detection. If `compat` is partially set, unspecified fields use the detected defaults. This is useful for: