mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-10 13:31:38 +00:00
4f008b6412
Address all 5 review points against actual delegate_task behavior: - child toolsets are subject to delegate restrictions (leaf strips delegate_task/clarify/memory/send_message/execute_code), not 'full' - durable work has lighter options than kanban (cron one-shot, managed background terminal) for simpler cases - unique per-run /tmp/wf_<name>_<uuid> dir + freshness/count check so a stale interrupted run isn't read as success - note that one delegate_task batch is capped by delegation.max_concurrent_children; large fan-out needs bounded waves - delegate_task exposes no per-task model/profile field (per-task keys are goal/context/toolsets/role); model/profile-scoped runs go via delegation config, cron, kanban, or separate process |
||
|---|---|---|
| .. | ||
| apple | ||
| autonomous-ai-agents | ||
| computer-use | ||
| creative | ||
| data-science | ||
| dogfood | ||
| github | ||
| index-cache | ||
| media | ||
| mlops | ||
| note-taking | ||
| productivity | ||
| research | ||
| smart-home | ||
| social-media | ||
| software-development | ||
| yuanbao | ||