fix(evidence): isolate vectors by workspace

This commit is contained in:
2026-07-12 05:50:59 +02:00
parent 24f6a5daa6
commit 05accc1443
13 changed files with 163 additions and 66 deletions
+17 -9
View File
@@ -273,16 +273,18 @@ class PgVectorStore:
filter_params.append(collection_kinds)
if metadata_filter is not None:
if collection != "evidence" or set(metadata_filter) != {
"vector_generation", "document_ids"
"vector_generation", "document_ids", "workspace_id"
}:
raise VectorStoreError("Unsupported vector metadata filter")
generation = metadata_filter["vector_generation"]
document_ids = metadata_filter["document_ids"]
if not isinstance(generation, str) or not isinstance(document_ids, list):
workspace_id = metadata_filter["workspace_id"]
if not isinstance(generation, str) or not isinstance(document_ids, list) or not isinstance(workspace_id, str):
raise VectorStoreError("Invalid vector metadata filter")
clauses.append(sql.SQL("metadata->>'vector_generation' = %s"))
clauses.append(sql.SQL("metadata->>'document_id' = ANY(%s)"))
filter_params.extend((generation, document_ids))
clauses.append(sql.SQL("metadata->>'workspace_id' = %s"))
filter_params.extend((generation, document_ids, workspace_id))
where = (
sql.SQL(" WHERE ") + sql.SQL(" AND ").join(clauses)
if clauses else sql.SQL("")
@@ -404,9 +406,11 @@ class PgVectorStore:
raw.close()
return len(records)
def delete_generation(self, collection: str, generation: str) -> int:
def delete_generation(self, collection: str, generation: str, workspace_id: str) -> int:
if collection != "evidence" or re.fullmatch(r"gen:[0-9a-f]{32}", generation) is None:
raise VectorStoreError("Only exact Evidence generations may be deleted")
if re.fullmatch(r"[a-z][a-z0-9_-]{0,63}", workspace_id) is None:
raise VectorStoreError("Invalid Evidence workspace namespace")
raw = None
try:
raw = self._require_writer().raw_connection()
@@ -414,9 +418,10 @@ class PgVectorStore:
cursor.execute(
sql.SQL(
"DELETE FROM {} WHERE kind = 'evidence' "
"AND metadata->>'vector_generation' = %s"
"AND metadata->>'vector_generation' = %s "
"AND metadata->>'workspace_id' = %s"
).format(_collection(self._schema, collection)),
(generation,),
(generation, workspace_id),
)
count = cursor.rowcount
raw.commit()
@@ -429,9 +434,11 @@ class PgVectorStore:
if raw is not None:
raw.close()
def list_evidence_generations(self, collection: str) -> list[str]:
def list_evidence_generations(self, collection: str, workspace_id: str) -> list[str]:
if collection != "evidence":
raise VectorStoreError("Only exact Evidence generations may be listed")
if re.fullmatch(r"[a-z][a-z0-9_-]{0,63}", workspace_id) is None:
raise VectorStoreError("Invalid Evidence workspace namespace")
raw = None
try:
raw = self._require_writer().raw_connection()
@@ -440,8 +447,9 @@ class PgVectorStore:
sql.SQL(
"SELECT DISTINCT metadata->>'vector_generation' FROM {} "
"WHERE kind = 'evidence' AND metadata->>'vector_generation' "
"~ '^gen:[0-9a-f]{{32}}$' ORDER BY 1"
).format(_collection(self._schema, collection))
"~ '^gen:[0-9a-f]{{32}}$' AND metadata->>'workspace_id' = %s ORDER BY 1"
).format(_collection(self._schema, collection)),
(workspace_id,),
)
return [row[0] for row in cursor.fetchall()]
except Exception as exc: