queue_clarification
- Category: intel
- Access: write
- Audience: advanced (ordinary users do not normally call this directly)
Purpose
Generates an AWAITING_HUMAN block with focused clarification questions for a chunk. Call it to lock ambiguous context until a human answers.
Arguments
Required: chunk_ref.
Optional: max_questions.
-
chunk_ref. -
max_questions. Note: Capped at 5; defaults 5.
Result
Object with chunk_id, state (awaiting_human), questions array (id, text, type, priority), and the awaiting_human_block text. Question types are scope, time, semantics, action, downstream_use.
Boundaries
Operates inside the selected profile boundary. Frozen chunks are refused; all other states may be queued.
Lifecycle / side effects
Persists up to five typed open questions with history events, writes the AWAITING_HUMAN annotation block, moves the chunk toward awaiting_human where the transition is legal, and records a run-history entry. All-or-nothing.
Errors
Missing chunk_ref rejected by validation. Unknown chunk returns not-found. Frozen chunks return a cannot-queue error payload.
Example
{
"chunk_ref": "<uuid>",
"max_questions": 3
}
Result shape:
{
"awaiting_human_block": "--- AWAITING_HUMAN ...",
"chunk_id": "<uuid>",
"questions": [
{
"id": "<uuid>",
"priority": 0.9,
"text": "Which workflow does this relate to ...?",
"type": "scope"
}
],
"state": "awaiting_human"
}
See also
assess_context, record_human_answer, resume_context, extract_candidate_claims.