mortal/TencentDB-Agent-Memory
1
0
Fork 0
mirror of https://github.com/TencentCloud/TencentDB-Agent-Memory synced 2026-07-10 12:34:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(recall): cap injected memory context (#71)

Browse Source 
- Add `recall.maxCharsPerMemory` and `recall.maxTotalRecallChars` with defaults of `0`, which do not alter existing behavior. Users can opt in by setting positive values to cap injected memory context.
- Apply the budget after L1 search and before `<relevant-memories>` injection, preserving score order while truncating oversized entries and dropping overflow.
- Document the new guards in README, README_CN, and `openclaw.plugin.json`.
This commit is contained in:
YOMXXX
2026-05-26 21:19:38 +08:00
committed by GitHub
parent d92cbd3840
commit 1bdcf28c5e
5 changed files with 96 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2
View File
@@ -259,6 +259,8 @@ docker exec -it hermes-memory hermes
| `storeBackend` | `"sqlite"` | Storage backend: `sqlite` |
| `recall.strategy` | `"hybrid"` | Recall strategy: `keyword` / `embedding` / `hybrid` (RRF fusion, recommended) |
| `recall.maxResults` | `5` | Number of items returned per recall |
| `recall.maxCharsPerMemory` | `0` | Max characters injected for one recalled L1 memory; `0` disables this guard |
| `recall.maxTotalRecallChars` | `0` | Total character budget for auto-recalled L1 memories; `0` disables this guard |
| `pipeline.everyNConversations` | `5` | Trigger an L1 memory extraction every N turns |
| `extraction.maxMemoriesPerSession` | `20` | Max memories extracted per L1 pass |
| `persona.triggerEveryN` | `50` | Generate the user persona every N new memories |