Unverified50% confidenceFactExact time
In the Responses interface of the Muse Wonder API, reasoning.summary can be set to auto, concise or detailed to request a reasoning summary; summaries are not guaranteed, may return an empty array, and the raw reasoning content is never returned.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedThe Muse Wonder API always reasons, and passing reasoning_effort as none returns an HTTP 400 error.71% similarUnverifiedTool output should return only what the model needs for its next decision, use human-readable values rather than raw nested data, and list-type tools should return a summary and state any truncation.64% similarUnverifiedMuse Wonder's background: true queues the response and returns status: queued, and lifecycle events can be polled via GET /v1/responses/{id}?stream=true; stream: true is not supported on POST, the request body limit is 1 MiB, and cancellation is done via POST /v1/responses/{id}/cancel.63% similarUnverifiedMuse is restrained in terms of content accuracy and will proactively label information it cannot verify or source as "unable to confirm the source."63% similarUnverifiedWhen the retrieval context does not contain the answer, many language models fill the gap with plausible-sounding content, which is exactly the hallucination users notice; fixes include instructing the model to answer only from the provided context, giving it a clear way to opt out, requiring a citation for every claim, setting a retrieval score threshold, and logging rejected questions.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1042940API
curl https://kongchang.com/api/v1/knowledge/claims/1042940MCP
get_claim(id=1042940)