feat(memos-local-openclaw): add LLM filter toggle for memory search#1464
Open
hijzy wants to merge 2 commits intoMemTensor:openclaw-local-plugin-20260408from
Open
feat(memos-local-openclaw): add LLM filter toggle for memory search#1464hijzy wants to merge 2 commits intoMemTensor:openclaw-local-plugin-20260408from
hijzy wants to merge 2 commits intoMemTensor:openclaw-local-plugin-20260408from
Conversation
Add a new toggle in Settings > General to enable/disable LLM-based relevance filtering for memory_search and auto-recall. The filter is enabled by default (preserving existing behavior) but can be turned off for faster results that skip the summarizer.filterRelevant call. Changes: - types.ts: add recall.llmFilterEnabled config field - config.ts: default llmFilterEnabled to true - html.ts: add toggle UI, i18n (en/zh), loadConfig & saveGeneralConfig - server.ts: merge-save recall config in handleSaveConfig - index.ts: guard filterRelevant calls behind llmFilterEnabled check
Add two new toggles in Settings > General: - Enable Memory Search (memorySearchEnabled): controls whether memory_search tool and auto-recall retrieve memories. When off, the agent responds without any historical context. - Enable Memory Capture (memoryAddEnabled): controls whether new conversations are captured and written to the database. When off, existing memories can still be retrieved but no new ones are stored. Both default to enabled, preserving existing behavior.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
memory_search工具和自动召回均跳过summarizer.filterRelevant调用，直接返回检索引擎候选结果Changes
src/types.tsrecall配置新增llmFilterEnabled?: boolean字段src/config.tsresolveConfig中默认值设为truesrc/viewer/html.tsloadConfig/saveGeneralConfig处理src/viewer/server.tshandleSaveConfig支持合并保存recall配置index.tsmemory_search工具和before_prompt_build自动召回中根据配置跳过 LLM 过滤Test plan