| title | InternChatCompletionChunk |
|---|
One data: line of the stream. A run streams a role chunk, content and reasoning chunks, then a finish chunk: stop, tool_calls (the run is paused for input) or error (with an error object). A final chunk with empty choices follows in every case, carrying session_id and usage (null unless the daemon reported usage, and always null after tool_calls). Every stream ends with [DONE].
| Field | Type | Required | Description | Example |
|---|---|---|---|---|
choices |
List[components.InternChatChoice] | ✔️ | One choice on content, tool-call and error chunks. Empty on the final chunk that carries session_id. |
|
created |
int | ✔️ | N/A | |
error |
Optional[components.InternChatStreamError] | ➖ | A failure after the response headers were sent. The chunk that carries it has finish_reason: "error", then the final empty-choices chunk and [DONE] follow. Reasons here are attachment_failed, busy, client_closed_request, interaction_not_pending, interaction_unknown, intern_unreachable, run_ended, stream_severed, timeout or turn_failed. run_ended reports an ending the intern confirmed, such as a cancellation or a deadline, while stream_severed reports a connection lost without that confirmation. |
{ "code": 502, "message": "The intern could not continue this run.", "metadata": { "reason": "attachment_failed", "retryable": false } } |
id |
str | ✔️ | The completion id, constant for the whole response. | chatcmpl-f727571a-3bad-4e0d-8a9e-f18f8cda9750 |
model |
str | ✔️ | The runtime's identifier for the model the intern is running, as the intern reports it. Each chunk carries the model from the event behind it: openrouter/intern on chunks emitted before the intern has reported one and on chunks the API emits itself (timeout, run-ended and severed-stream errors and their final usage chunk), even after an earlier chunk named a model. It can change within a stream. It is not an OpenRouter model slug, and the request model is never used. |
|
object |
components.InternChatCompletionChunkObject | ✔️ | N/A | |
session_id |
OptionalNullable[str] | ➖ | On the final chunk of every response, the daemon session to continue with, or null when the run failed before the intern reported one. Send it as session_id on the next request, including the tool reply to an interaction. Session ids are client-visible and scoped to the intern's own daemon. |
ses_7f3c9a |
usage |
OptionalNullable[components.InternChatUsage] | ➖ | Token usage for the run as the daemon reported it, on the final chunk before [DONE]. null when the daemon reported none, and always null after tool_calls because the turn is not over. |
{ "completion_tokens": 12, "prompt_tokens": 40, "total_tokens": 52 } |