get_thread polls a Thread. While the agent works, status is running. When it’s idle, the result carries the agent’s answer: markdown with inline citations, the grounding quotes, the cited papers, and a ready-to-write document.
Your assistant calls it after create_thread or add_to_thread, about every 30 seconds. A pro run usually finishes within about 3 minutes, and a deep run within about 10 minutes. Polling faster returns the same running result and doesn’t speed up the agent.
Requires a signed-in Consensus account, over OAuth or an API key as a Bearer token. You can read only your own Threads.
Parameters
Response
render_instructions and a schema_note for your assistant.
Only an
idle interaction carries the full response and citations. Evidence-strength scores, top authors, the results timeline, the research-gap matrix, and the search funnel come back as text and tables inside response and document.
How assistants show the result
get_thread tells your assistant to:
- Share the View this in Consensus link first.
- Write
documentto the file named infilename, or render it in an artifact, canvas, or side panel, instead of pasting it into chat. - Keep every citation marker exactly as written.
- Reply in chat with a 2–3 sentence summary and the Consensus link.
Good to know
- Rate limit: up to three
get_threadcalls per second. - Wrong interaction: an
interaction_idfrom another Thread returns an error. Poll with thethread_idalone to get the latest interaction.