record_human_answer
- Category: intel
- Access: write
- Audience: advanced (ordinary users do not normally call this directly)
Purpose
Ingests a human answer for a chunk: resolves open questions and reopens the chunk for enrichment. Call it to unblock context waiting on human input.
Arguments
Required: chunk_ref, answer_text.
Optional: question_id.
-
chunk_ref. -
answer_text. Note: Appended to the chunk body, so the source hash changes and the chunk becomes assessable again. -
question_id. Note: Answers one question when given; answers all open questions for the chunk when omitted. Omitted (not null) to answer all.
Result
Object with chunk_id, new_state, previous_state, questions_resolved count, and source_hash_updated flag.
Boundaries
Operates inside the selected profile boundary. Frozen chunks refuse answers.
Lifecycle / side effects
Marks addressed questions answered, appends the answer to the chunk body with a fresh source hash, moves awaiting_human or uncertain chunks back to enrichable, and records resolution provenance, a history event, and a run-history entry. All-or-nothing.
Errors
Missing chunk_ref or answer_text rejected by validation (multi-missing shape when both absent). Unknown chunk returns not-found. Frozen chunks return a cannot-record error payload.
Example
{
"answer_text": "This covers the bridge sync workflow.",
"chunk_ref": "<uuid>"
}
Result shape:
{
"chunk_id": "<uuid>",
"new_state": "enrichable",
"previous_state": "awaiting_human",
"questions_resolved": 2,
"source_hash_updated": true
}
See also
queue_clarification, assess_context, resume_context, extract_candidate_claims.