Files
OpenJarvis/tests/tools/test_knowledge_sql.py
T
23f04264f9 fix(knowledge_sql): match write keywords on word boundaries (allow valid SELECTs) (#640)
* fix(knowledge_sql): match write keywords on word boundaries

The read-only guard rejected a query if any of DROP/DELETE/INSERT/UPDATE/
ALTER/CREATE/ATTACH appeared as a bare substring of the uppercased text. That
wrongly blocks valid SELECTs whose column/alias/literal merely contains one --
e.g. "deleted_at" (DELETE), "created_at" (CREATE), "updated_content" (UPDATE).
The knowledge_chunks table actually has deleted_at/created_at columns and the
store's own retrieval filters on "WHERE deleted_at IS NULL", so realistic
read queries were refused. Match on word boundaries with a compiled regex,
mirroring the sibling tool db_query.py. Add a regression test.

* fix(knowledge_sql): ignore string literals in keyword scan, broaden error handling

- Strip single-quoted literals before the forbidden-keyword scan so
  SELECTs whose data merely mentions a write keyword (e.g. LIKE
  '%delete%') are not rejected.
- Catch sqlite3.Error instead of only OperationalError so multi-
  statement strings return a failed ToolResult instead of raising.
- Document created_at/deleted_at in the tool's schema description.

---------

Co-authored-by: Elliot Slusky <elliot@slusky.com>
2026-07-16 16:36:31 -07:00

126 lines
4.1 KiB
Python

"""Tests for KnowledgeSQLTool."""
from __future__ import annotations
from pathlib import Path
import pytest
from openjarvis.connectors.store import KnowledgeStore
from openjarvis.core.registry import ToolRegistry
@pytest.fixture()
def store(tmp_path: Path) -> KnowledgeStore:
ks = KnowledgeStore(str(tmp_path / "test.db"))
ks.store("Hello from Alice", source="imessage", author="Alice", doc_type="message")
ks.store(
"Hello from Alice again", source="imessage", author="Alice", doc_type="message"
)
ks.store("Meeting notes Q1", source="granola", author="Bob", doc_type="document")
ks.store("Email about Spain trip", source="gmail", author="Carol", doc_type="email")
return ks
def test_select_count(store: KnowledgeStore) -> None:
from openjarvis.tools.knowledge_sql import KnowledgeSQLTool
tool = KnowledgeSQLTool(store=store)
result = tool.execute(query="SELECT COUNT(*) as total FROM knowledge_chunks")
assert result.success
assert "4" in result.content
def test_group_by_author(store: KnowledgeStore) -> None:
from openjarvis.tools.knowledge_sql import KnowledgeSQLTool
tool = KnowledgeSQLTool(store=store)
result = tool.execute(
query=(
"SELECT author, COUNT(*) as n "
"FROM knowledge_chunks "
"GROUP BY author ORDER BY n DESC"
)
)
assert result.success
assert "Alice" in result.content
assert "2" in result.content
def test_rejects_non_select(store: KnowledgeStore) -> None:
from openjarvis.tools.knowledge_sql import KnowledgeSQLTool
tool = KnowledgeSQLTool(store=store)
result = tool.execute(query="DELETE FROM knowledge_chunks")
assert not result.success
assert "read-only" in result.content.lower() or "SELECT" in result.content
def test_rejects_drop(store: KnowledgeStore) -> None:
from openjarvis.tools.knowledge_sql import KnowledgeSQLTool
tool = KnowledgeSQLTool(store=store)
result = tool.execute(query="DROP TABLE knowledge_chunks")
assert not result.success
def test_allows_select_with_keyword_substring(store: KnowledgeStore) -> None:
"""A read-only SELECT must not be rejected because a column/alias merely
contains a write keyword as a substring (e.g. 'created' -> CREATE)."""
from openjarvis.tools.knowledge_sql import KnowledgeSQLTool
tool = KnowledgeSQLTool(store=store)
result = tool.execute(
query="SELECT author AS created_author FROM knowledge_chunks"
)
assert result.success, result.content
assert "Alice" in result.content
def test_allows_keyword_inside_string_literal(store: KnowledgeStore) -> None:
"""A write keyword appearing only inside a string literal must not be
treated as a forbidden statement."""
from openjarvis.tools.knowledge_sql import KnowledgeSQLTool
tool = KnowledgeSQLTool(store=store)
result = tool.execute(
query="SELECT content FROM knowledge_chunks WHERE content LIKE '%delete%'"
)
assert result.success, result.content
def test_rejects_multi_statement(store: KnowledgeStore) -> None:
"""Multi-statement strings fail with a ToolResult, not an exception."""
from openjarvis.tools.knowledge_sql import KnowledgeSQLTool
tool = KnowledgeSQLTool(store=store)
result = tool.execute(query="SELECT 1; VACUUM")
assert not result.success
assert "error" in result.content.lower()
def test_handles_bad_sql(store: KnowledgeStore) -> None:
from openjarvis.tools.knowledge_sql import KnowledgeSQLTool
tool = KnowledgeSQLTool(store=store)
result = tool.execute(query="SELECT * FROM nonexistent_table")
assert not result.success
def test_filter_by_source(store: KnowledgeStore) -> None:
from openjarvis.tools.knowledge_sql import KnowledgeSQLTool
tool = KnowledgeSQLTool(store=store)
result = tool.execute(
query="SELECT title, author FROM knowledge_chunks WHERE source = 'gmail'"
)
assert result.success
assert "Carol" in result.content
def test_registered() -> None:
from openjarvis.tools.knowledge_sql import KnowledgeSQLTool
ToolRegistry.register_value("knowledge_sql", KnowledgeSQLTool)
assert ToolRegistry.contains("knowledge_sql")