mirror/nanobot
1
0
Fork 0
mirror of https://github.com/HKUDS/nanobot.git synced 2026-09-02 09:15:19 +03:00
Code Issues Packages Projects Releases Wiki Activity

fix: queue concurrent subagents (#5566)

Browse Source 
* fix: queue concurrent subagents

* chore: keep spawn schema concise
This commit is contained in:
chengyongru
2026-08-27 17:53:28 +08:00
committed by GitHub
parent 39de4594d7
commit b9e7c7f6fe
6 changed files with 197 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/configuration.md
+2 -2
View File
@@ -2213,7 +2213,7 @@ The notification gate runs on a built-in system prompt. Advanced users can overr
## Subagent Concurrency
By default, nanobot only allows one spawned subagent at a time. When the limit is reached, the `spawn` tool returns an error so the agent can decide to wait or rearrange its work. This protects local LLM servers from loading multiple KV caches at once. If your provider can handle more parallel work, raise the limit:
By default, nanobot allows four subagents to run at the same time. Additional subagents wait for capacity instead of being rejected. Lower the limit if a local model server cannot hold multiple KV caches, or raise it when the provider can handle more parallel work:
```json
{
@@ -2229,7 +2229,7 @@ The deprecated `agents.defaults.failOnToolError` field is silently ignored when
| Option | Default | Description |
|--------|---------|-------------|
| `agents.defaults.maxConcurrentSubagents` | `1` | Maximum number of spawned subagents that may run at the same time. Attempts to spawn beyond this limit return an error. |
| `agents.defaults.maxConcurrentSubagents` | `4` | Maximum number of subagents that may run at the same time. Additional tasks wait for capacity. |
## Auto Compact