christian/session-mcp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(CF-1314): Content hashing to prevent duplicate embeddings

Browse Source 
SHA-256 hash check before embedding API call eliminates ~60-80% of
redundant embedding requests. Consolidates dual INSERT paths to single
INSERT with nullable embedding column.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Christian Gick
2026-02-18 08:28:11 +02:00
parent 77097ac65f
commit 1f499bd926
6 changed files with 127 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
migrations/033_content_hash_dedup.sql Normal file
View File

@@ -0,0 +1,20 @@
-- CF-1314: Content hashing to prevent duplicate embeddings
-- Adds content_hash column to all embedding tables for dedup before API call
-- Adds source_id columns for future CF-1315 hybrid search
ALTER TABLE project_archives ADD COLUMN IF NOT EXISTS content_hash TEXT;
ALTER TABLE project_archives ADD COLUMN IF NOT EXISTS source_id TEXT;
ALTER TABLE memories ADD COLUMN IF NOT EXISTS content_hash TEXT;
ALTER TABLE memories ADD COLUMN IF NOT EXISTS source_id TEXT;
ALTER TABLE session_notes ADD COLUMN IF NOT EXISTS content_hash TEXT;
ALTER TABLE session_plans ADD COLUMN IF NOT EXISTS content_hash TEXT;
ALTER TABLE sessions ADD COLUMN IF NOT EXISTS content_hash TEXT;
CREATE INDEX IF NOT EXISTS idx_archives_content_hash ON project_archives(content_hash);
CREATE INDEX IF NOT EXISTS idx_memories_content_hash ON memories(content_hash);
CREATE INDEX IF NOT EXISTS idx_session_notes_content_hash ON session_notes(content_hash);
CREATE INDEX IF NOT EXISTS idx_session_plans_content_hash ON session_plans(content_hash);
CREATE INDEX IF NOT EXISTS idx_sessions_content_hash ON sessions(content_hash);
CREATE INDEX IF NOT EXISTS idx_archives_source_id ON project_archives(source_id);
CREATE INDEX IF NOT EXISTS idx_memories_source_id ON memories(source_id);