Persisted leader/subagent ownership. Project membership is not wake authority.
Persisted leader/subagent ownership. Project membership is not wake authority.
(cancel env session-id)(cancel env session-id opts)Cancel an owned subagent and its descendants, including queued work. Cancellation is durable.
Cancel an owned subagent and its descendants, including queued work. Cancellation is durable.
(checkpoint! env messages)Capture the last complete model input, before its in-flight tool call. Never copy runtime handles.
Capture the last complete model input, before its in-flight tool call. Never copy runtime handles.
(claim-iteration! env)Reserve one model iteration. A child budget is durable across replies, turns and restarts.
Reserve one model iteration. A child budget is durable across replies, turns and restarts.
(controls? db actor-id target-id)Leaders control their descendants. Subagents control themselves and their direct children.
Leaders control their descendants. Subagents control themselves and their direct children.
(list-agents env)(list-agents env opts)List your managed team: lineage, task, lifecycle, model, usage and pending input. Independent leaders are not children.
List your managed team: lineage, task, lifecycle, model, usage and pending input. Independent leaders are not children.
(require-enabled!)Refuse new managed work before bootstrapping a session or consuming a checkpoint.
Refuse new managed work before bootstrapping a session or consuming a checkpoint.
(restrict-router env router)Apply an inherited allowlist to every request and retry, including automatic fallback.
Apply an inherited allowlist to every request and retry, including automatic fallback.
(route env model)(route env model opts)Choose a provider/model for yourself or an owned child at the next model-call boundary. The shared router is unchanged. Human model locks and inherited allowed_models cannot be bypassed.
Choose a provider/model for yourself or an owned child at the next model-call boundary. The shared router is unchanged. Human model locks and inherited allowed_models cannot be bypassed.
(spawn env task)(spawn env task opts)Spawn a managed subagent with your full current model context and a delegated task. Use a concrete goal, scope and acceptance criteria. Fresh runtime, shared checkout (not isolation). A safe model checkpoint is required. Optional provider/model pair, allowed_models, iteration_budget (default 32, max 200), and retry key. Limits: depth 2, 32 children/task, 8 active. Reusing a key with different inputs fails. Inspect results with council.subagents and Council.
Spawn a managed subagent with your full current model context and a delegated task. Use a concrete goal, scope and acceptance criteria. Fresh runtime, shared checkout (not isolation). A safe model checkpoint is required. Optional provider/model pair, allowed_models, iteration_budget (default 32, max 200), and retry key. Limits: depth 2, 32 children/task, 8 active. Reusing a key with different inputs fails. Inspect results with council.subagents and Council.
(wake-allowed? db author-id recipient-id)Only a managed team can automatically resume a session. A child may return to its leader; siblings must share a task team. Replies cannot bypass this rule.
Only a managed team can automatically resume a session. A child may return to its leader; siblings must share a task team. Replies cannot bypass this rule.
cljdoc builds & hosts documentation for Clojure/Script libraries
| Ctrl+k | Jump to recent docs |
| ← | Move to previous article |
| → | Move to next article |
| Ctrl+/ | Jump to the search field |