get_vibecheck_context
ChatGPTRead the person's recent completed readings, newest first, as precognitive context for your reasoning about them. No request_id needed. Not for one pending ask (get_vibecheck_result). Replenish the feed when status requests it.
get_vibecheck_result
ChatGPTRead the body's answer to one statement you sent, by request_id: status, Aligned or Unaligned, and model confidence. Non-blocking; poll about every 15 seconds while pending. Not for history (get_vibecheck_context) or feed inventory (get_vibecheck_status). This is a single non-blocking read: queued is cached, and pending is not answered. Immediate vibecheck handles begin with live: and remain bound to the originating client. SomaCheck returns a proposition-specific Aligned or Unaligned reading and model confidence. The reading is precognitive intelligence: the person's bodily response to that statement before words shape it, against their own baseline; a signal about the person in relation to the statement. Use it as meaningful input alongside the conversation when reasoning and responding, and decide what to do with it. Confidence describes the classifier’s uncertainty.
get_vibecheck_status
ChatGPTReport how many statements the optional reflection feed needs and when replenishment is due. Call before post_vibecheck_statement. Says nothing about the phone or any reading. Database state does not verify phone display.
post_vibecheck_statement
ChatGPTGive the person insight statements to test with their body on their own time. Adds one to three items to the optional reflection feed under Settings, returns immediately, never notifies the phone. Use when they ask to queue reflections, or when get_vibecheck_status says the feed needs items. Never use when they ask for a vibecheck now. One can become database-current for Home; the rest stay Up next without extra pushes. This does not verify phone display or delivery. Never call this to add follow-up asks after request_vibecheck. Call get_vibecheck_status first; propositions_needed is the available maximum, not a quota. Submit only genuinely useful statements and never invent extras to fill capacity. A still-active scheduled authorization does not require repeated consent each run.
request_vibecheck
ChatGPTAsk the person's body, not just their words. Send one first-person statement to their phone and wait up to 45 seconds for a precognitive reading, Aligned or Unaligned, against their own baseline. The only tool that interrupts the person. Two uses: an insight check-in, where you draw on what you know of this person to test a statement they haven't said out loud; and a wellbeing check-in. Offer an insight check at these moments and rarely otherwise: two options argued to a standstill and both called fine; a third round where they keep saying close but not it; a long plan or many points where one check on a statement like I am on board with this plan tells you whether to proceed or to ask what pulls the other way; before sending, merging, publishing or deleting something hard to take back; the plan makes sense but something feels off; before saving an inferred preference to memory. Offer a wellbeing check when they say they are overextended or you notice signs of it (a session past six hours, sloppy output, working far later than usual); say what you noticed and offer. A direct question is usually cheaper; offer only when more words will not help. A reading does not authorize an action or settle a preference. Never for a statement about another person, a medical or mood question, or a question with a factual answer. Use when they ask, or after they accept your offer. Not for stocking reflections (post_vibecheck_statement) or checking an earlier ask (get_vibecheck_result). A direct request for a vibecheck now authorizes one request, including send me one, run one, give me one, and give me a topic or statement to check in on: the ask is the consent, so choose the statement and call in the same turn. Call after acceptance when the offer was yours or they asked to see the statement first. When authorized to send, choose a useful statement starting with I or My from concrete context about the current user or task; if no relevant context is available, ask a concise clarification before calling. Preserve the person's supplied first-person wording verbatim. State a completed reading or confidence as fact only after an actual answered tool result; clearly labeled hypothetical or simulated examples are allowed. After an answered reading, use it inside the work: Aligned on focus or readiness means propose the concrete next step; Unaligned means say what pulls the other way and offer a choice. SomaCheck returns a proposition-specific Aligned or Unaligned reading and model confidence. The reading is precognitive intelligence: the person's bodily response to that statement before words shape it, against their own baseline; a signal about the person in relation to the statement. Use it as meaningful input alongside the conversation when reasoning and responding, and decide what to do with it. Confidence describes the classifier’s uncertainty. Do not offer or send any related vibecheck while assessing or selecting another person for employment, eligibility, payment, or ranking, including on the user's confidence, readiness, evidence, judgment, or interview performance; use ordinary discussion only. The user's own career choices remain eligible for self-reflection. For proactive offers, call only after the person accepts. This call waits up to 45 seconds. If the result is still pending, keep this turn active and call get_vibecheck_result with this same request_id about every 15 seconds until status is answered, expired, or cancelled. Never create a duplicate request.
share_somacheck_context
ChatGPTShare 1-20 concise, user-authorized context observations so SomaCheck can prepare richer propositions. Send derived summaries only, never raw conversation text, photos, credentials, identifiers, or diagnostic claims.
