[hero_books] Adopt the memory service workspace field so book search returns results #139
Labels
No labels
prio_critical
prio_low
type_bug
type_contact
type_issue
type_lead
type_question
type_story
type_task
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
lhumina_code/hero_books#139
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
hero_books talks to the memory service using the older request shape and does not send the now required workspace field on collections.create, collections.scan, and memory.search (and still calls the removed namespace.create). Because the memory service now scopes every collection and query under a workspace, the documents hero_books indexes land in one scope while its searches look in another, so semantic search and book summaries come back empty even when indexing succeeded. The fix is to adopt the workspace model in hero_books: pick a workspace identity (the library or collection name works, one to one), create the workspace, and thread that workspace value through the create, scan, and search calls. The mismatching call sites are in crates/hero_books_lib/src/memory_client/mod.rs. This is the blocker for the end to end book summary flow.