Harden telemetry provenance and hybrid retrieval isolation#1
Open
nstranquist wants to merge 1 commit into
Open
Harden telemetry provenance and hybrid retrieval isolation#1nstranquist wants to merge 1 commit into
nstranquist wants to merge 1 commit into
Conversation
nstranquist
marked this pull request as ready for review
July 14, 2026 00:30
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What changed
--sourceisolation in both the mmap flat-vector path and the SQLite hybrid fallback before top-K selectionWhy
The local dogfood audit found three integrity gaps: roughly 33k legacy query rows could not distinguish eval traffic from adoption, the embedding cache contained 21,857 rows for a 17,208-document corpus because stale paths accumulated, and a source-scoped refs eval admitted global Nicos-stack candidates during hybrid retrieval. These changes make each boundary explicit and testable.
User impact
Integrations can label searches without rewriting history; fixture curation no longer silently promotes automated traffic. Embedding refreshes reconcile deleted paths, and source-scoped hybrid searches stay within the requested corpus. The OSS CLI remains local-first; optional provider calls remain opt-in. The Team offer is a recruiting pilot, not a SaaS-launch or revenue claim.
Validation
go build -tags sqlite_fts5 ./...go vet -tags sqlite_fts5 ./...go test -race -tags sqlite_fts5 ./...refs-dissections/*candidates after the fixThis PR is ready for independent review and remains intentionally unmerged.