feat(memory): add force_boundary flag to API to fix bulk import queue stalls#124
Open
GoodDaySolution wants to merge 1 commit intoEverMind-AI:mainfrom
Open
feat(memory): add force_boundary flag to API to fix bulk import queue stalls#124GoodDaySolution wants to merge 1 commit intoEverMind-AI:mainfrom
GoodDaySolution wants to merge 1 commit intoEverMind-AI:mainfrom
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
Third-party clients bulk-importing historical conversation chunks (e.g. Chrome extensions importing scraped chats) frequently observe their messages getting permanently stuck in the
sync_status = -1queue. Because these imports are one-time events, the [ConvMemCellExtractor]'s LLM-based time-gap detection never triggersshould_end = True, causing silent failures (empty groups).Solution
This PR introduces a
force_boundaryboolean flag to the API layer, allowing clients to explicitly signal that an imported batch is complete and should bypass the LLMshould_waitlogic.Changes Included:
force_boundary: bool = Falseto [MemorizeMessageRequest] and [MemorizeRequest] DTOs.force_boundaryparameter down into the MemCell ExtractRequest abstractions.How to Test
/api/v0/memories."force_boundary": true.Note to Maintainers: I have also noted an issue where
/api/v1/routing fails on the live Cloud Gateway, and strict but silent whitelisting on thesourcefield. Please review if those configurations on the API Gateway are intended.