read_blackboard
Retrieve shared blackboard data for a heads-down run to inspect what tasks, teams, and agents are doing; query sections or filters for status, decisions, claims, files, and events.
Instructions
Read the shared blackboard of this heads-down run: what every task, team and agent is doing. section: summary (default), goal, contract, tasks, task (task_id, default yours), interfaces, decisions, leases, claims, files, diffs, checks, escalations, notes, inbox, budget, agents, teams, events (filters: since_seq, limit, task_id, query = event type prefix), blob (ref: a sha256:… ref from an event; redacted, at most 16 KB), or query: fuzzy matching over tasks, teams, paths and interfaces ("is the nav done?").
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"execution_id": "<execution_id>",
"agent_token": "<agent_token>"
},
"name": "read_blackboard"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| ref | No | Blob ref for section blob. | |
| limit | No | Default 50. | |
| query | No | Free text for section query or tasks/files filters; an event type prefix for events. | |
| section | No | Default summary (query when only query is given, blob when only ref is). | |
| task_id | No | A task (task, checks, diffs, escalations and events filter on it). | |
| since_seq | No | events and notes: only after this seq. | |
| agent_token | Yes | The agent token join_execution returned (once). | |
| execution_id | Yes | The heads-down run (exe-…). |