vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 07:30:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs(active-memory): document cacheTtlMs bounds (#65708)

Browse Source 
The Active Memory docs listed cacheTtlMs without noting its bounds. The
zod schema and the plugin manifest cap it at 1000-120000 ms with a
15000 ms default. A user following older "paste this in" snippets with
cacheTtlMs=300000 crashed the gateway on startup with an opaque schema
error before figuring out the real limit.

Document the range and default inline in the tuning-fields table so the
limit is discoverable before boot.

Closes #65708
This commit is contained in:
Intern Dev
2026-04-13 01:42:50 -04:00
committed by Tak Hoffman
parent 189c91eae6
commit 0c449a63c6
1 changed files with 8 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
docs/concepts/active-memory.md
View File

@@ -547,14 +547,14 @@ The most important fields are:
Useful tuning fields:
| Key | Type | Meaning |
| ----------------------------- | -------- | ------------------------------------------------------------- |
| `config.maxSummaryChars` | `number` | Maximum total characters allowed in the active-memory summary |
| `config.recentUserTurns` | `number` | Prior user turns to include when `queryMode` is `recent` |
| `config.recentAssistantTurns` | `number` | Prior assistant turns to include when `queryMode` is `recent` |
| `config.recentUserChars` | `number` | Max chars per recent user turn |
| `config.recentAssistantChars` | `number` | Max chars per recent assistant turn |
| `config.cacheTtlMs` | `number` | Cache reuse for repeated identical queries |
| Key | Type | Meaning |
| ----------------------------- | -------- | ---------------------------------------------------------------------------------- |
| `config.maxSummaryChars` | `number` | Maximum total characters allowed in the active-memory summary |
| `config.recentUserTurns` | `number` | Prior user turns to include when `queryMode` is `recent` |
| `config.recentAssistantTurns` | `number` | Prior assistant turns to include when `queryMode` is `recent` |
| `config.recentUserChars` | `number` | Max chars per recent user turn |
| `config.recentAssistantChars` | `number` | Max chars per recent assistant turn |
| `config.cacheTtlMs` | `number` | Cache reuse for repeated identical queries (range: 1000-120000 ms; default: 15000) |
## Recommended setup