aiworkhub_review_packet
Returns one bounded, read-only packet of persisted review evidence—validation, gate checks, findings, reachability—so a manager can decide a review_ready candidate without extra calls.
Instructions
READ-ONLY: ONE bounded review packet for a review_ready candidate.
Every fact a manager needs to decide a candidate is already persisted -- validation rows with their declared commands and output tails, the quality gate's checks and blockers, the worker MCP gate and its receipt-conformance verdict, required outputs, destructive-diff checks, the effective tier and its per-lens status, the deduped reviewer findings, the reachability observation -- spread across six nested objects on one card. This returns them together, under a measured byte bound.
Measured over all 419 real cards carrying a quality gate: min 1,662 B, p50 6,387 B, p90 8,813 B, max 13,799 B, 0 needing truncation. It replaces per candidate 10 task-scoped calls at p50 (p90 21) and, session-wide, 1,688 hand-written Bash re-derivations (pytest 611, attempt-artifact reads 242, task_queue.sqlite scripts 250, log tails 113, git diff 155) totalling 1.45 MB.
Nothing here is a verdict: every status was decided by the gate that
recorded it, and accepting still runs the whole fold in
aiworkhub_agent_accept_review. The one live computation is
aiworkhub_agent_accept_preview -- itself read-only -- which
aiworkhub_completion_inbox cannot call because it holds no launch
authority, so it is computed here and passed in.
The decision section prefills the argument dicts for
aiworkhub_agent_accept_review, one aiworkhub_manager_review_finding_dispose
per undisposed finding, and aiworkhub_task_reject_review; it
never picks a disposition or a verdict and is never dropped before an
evidence section.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "aiworkhub_review_packet"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| task_id | No | Id of the task card that request belongs to; omit to resolve it from the request's status (the reply's task_id_source says which). Not accepted with request_ids. | |
| max_bytes | No | Byte bound for the packet, default 90000; lowest-priority sections are dropped until it fits and listed under truncation.dropped_sections. With request_ids it is split evenly across the packets. | |
| request_id | No | Id of the review_ready worker request to build the packet for; leave empty when request_ids is given, or pass task_id alone to use that card's current review request (the reply's request_id_source says which). | |
| request_ids | No | Up to 8 review_ready request ids to read in one call instead of request_id; returns {packets, per_packet_max_bytes}, each packet built exactly like a single call with the split budget, and a member that fails carries its own error without failing the batch. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||