mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
docs(subagent): state that per-activation knobs are not restored on cold resume
The descriptor deliberately snapshots a curated composition field set rather than the merge-extensible `AgentOptions`, and it already names the per-activation exclusions (`outputSchema`). `maxTokens` is the same class of property — it budgets one activation, and on cold resume there is no parent to inherit a limit from, so the resumed activation runs under the deployment defaults. Spell that out in the module contract so the fallback is a documented decision instead of a silent surprise for deployments that set explicit child token limits.
This commit is contained in:
@@ -12,6 +12,10 @@
|
||||
* omits `subagentDepth` — cold resume trusts the persisted header's
|
||||
* `delegationDepth` as the monotone floor — and `outputSchema`, which belongs
|
||||
* to one activation's result contract rather than durable child composition.
|
||||
* Per-activation knobs such as `maxTokens` are omitted for the same reason as
|
||||
* `outputSchema`: they budget one activation and, on cold resume, no parent
|
||||
* exists to inherit them from, so the resumed activation runs under the
|
||||
* deployment defaults rather than restoring a stale budget.
|
||||
*
|
||||
* @module @deepseek-ai/dsh-subagent/descriptor
|
||||
*/
|
||||
|
||||
Reference in New Issue
Block a user