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:
Tianyi Cui
2026-08-02 12:29:02 +08:00
parent 98ccbade7e
commit 5da2ac5835

View File

@@ -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
*/