fix(ai): expose provider response ids on assistant messages fixes #2245

This commit is contained in:
Mario Zechner
2026-03-17 17:11:18 +01:00
parent 18d90b5c48
commit dd53eb56ee
11 changed files with 174 additions and 1 deletions

View File

@@ -519,6 +519,8 @@ Every `AssistantMessage` includes a `stopReason` field that indicates how the ge
- `"error"` - An error occurred during generation
- `"aborted"` - Request was cancelled via abort signal
`AssistantMessage` may also include `responseId`, a provider-specific upstream response or message identifier when the underlying API exposes one. Do not assume it is always present across providers.
## Error Handling
When a request ends with an error (including aborts and tool call validation errors), the streaming API emits an error event: