Cache layer for rerank results. Key is SHA256 of query + sorted candidate IDs, so changing the candidate set automatically invalidates. 1-day TTL by default; corrupted cache files are silently dropped. 5 tests cover hit, miss, different-candidates, TTL expiry, corruption. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
146 lines
5.2 KiB
Python
146 lines
5.2 KiB
Python
#!/usr/bin/env python3
|
|
"""Tests for notion_search.py — run with `python3 test_notion_search.py`."""
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
sys.path.insert(0, str(Path(__file__).parent))
|
|
|
|
|
|
def _assert(cond, msg):
|
|
if not cond:
|
|
print(f" ✗ FAIL: {msg}")
|
|
raise SystemExit(1)
|
|
print(f" ✓ {msg}")
|
|
|
|
|
|
def test_call_claude_dispatches_to_sdk_when_available():
|
|
"""When SDK is available and ANTHROPIC_API_KEY is set, use SDK path."""
|
|
import os
|
|
from unittest.mock import patch
|
|
import _search_llm
|
|
|
|
with patch.object(_search_llm, "_have_anthropic_sdk", return_value=True), \
|
|
patch.dict(os.environ, {"ANTHROPIC_API_KEY": "sk-fake"}), \
|
|
patch.object(_search_llm, "_call_via_sdk", return_value="sdk-response") as sdk_mock, \
|
|
patch.object(_search_llm, "_call_via_cli", return_value="cli-response") as cli_mock:
|
|
result = _search_llm.call_claude("hello")
|
|
_assert(result == "sdk-response", "SDK path returned its response")
|
|
_assert(sdk_mock.called, "SDK path was invoked")
|
|
_assert(not cli_mock.called, "CLI path was NOT invoked")
|
|
|
|
|
|
def test_call_claude_falls_back_to_cli_when_no_sdk():
|
|
"""When SDK is missing but CLI is available, use CLI path."""
|
|
from unittest.mock import patch
|
|
import _search_llm
|
|
|
|
with patch.object(_search_llm, "_have_anthropic_sdk", return_value=False), \
|
|
patch.object(_search_llm, "_have_claude_cli", return_value=True), \
|
|
patch.object(_search_llm, "_call_via_cli", return_value="cli-response") as cli_mock:
|
|
result = _search_llm.call_claude("hello")
|
|
_assert(result == "cli-response", "CLI path returned its response")
|
|
_assert(cli_mock.called, "CLI path was invoked")
|
|
|
|
|
|
def test_call_claude_raises_when_neither_available():
|
|
"""Both clients missing → RuntimeError with setup hint."""
|
|
from unittest.mock import patch
|
|
import _search_llm
|
|
|
|
with patch.object(_search_llm, "_have_anthropic_sdk", return_value=False), \
|
|
patch.object(_search_llm, "_have_claude_cli", return_value=False):
|
|
try:
|
|
_search_llm.call_claude("hello")
|
|
_assert(False, "should have raised RuntimeError")
|
|
except RuntimeError as exc:
|
|
_assert("ANTHROPIC_API_KEY" in str(exc) or "claude" in str(exc).lower(),
|
|
"error mentions setup options")
|
|
|
|
|
|
def test_cache_miss_returns_none():
|
|
import tempfile
|
|
from pathlib import Path
|
|
import _search_cache
|
|
|
|
with tempfile.TemporaryDirectory() as tmpdir:
|
|
result = _search_cache.cache_get("query", ["id1", "id2"], cache_dir=Path(tmpdir))
|
|
_assert(result is None, "cache miss returns None")
|
|
|
|
|
|
def test_cache_hit_returns_cached_results():
|
|
import tempfile
|
|
from pathlib import Path
|
|
import _search_cache
|
|
|
|
with tempfile.TemporaryDirectory() as tmpdir:
|
|
cache_dir = Path(tmpdir)
|
|
results = [{"id": "abc", "title": "Test"}]
|
|
_search_cache.cache_put("query", ["id1", "id2"], results, cache_dir=cache_dir)
|
|
hit = _search_cache.cache_get("query", ["id1", "id2"], cache_dir=cache_dir)
|
|
_assert(hit == results, "cache hit returns the stored results")
|
|
|
|
|
|
def test_cache_miss_on_different_candidates():
|
|
import tempfile
|
|
from pathlib import Path
|
|
import _search_cache
|
|
|
|
with tempfile.TemporaryDirectory() as tmpdir:
|
|
cache_dir = Path(tmpdir)
|
|
_search_cache.cache_put("query", ["id1", "id2"], [{"x": 1}], cache_dir=cache_dir)
|
|
miss = _search_cache.cache_get("query", ["id1", "id3"], cache_dir=cache_dir)
|
|
_assert(miss is None, "different candidate set hashes to different key")
|
|
|
|
|
|
def test_cache_miss_after_ttl_expires():
|
|
import tempfile
|
|
from pathlib import Path
|
|
import _search_cache
|
|
|
|
with tempfile.TemporaryDirectory() as tmpdir:
|
|
cache_dir = Path(tmpdir)
|
|
_search_cache.cache_put("query", ["id1"], [{"x": 1}], cache_dir=cache_dir)
|
|
# TTL=0 means immediately expired
|
|
miss = _search_cache.cache_get("query", ["id1"], cache_dir=cache_dir, ttl_seconds=0)
|
|
_assert(miss is None, "expired cache returns None")
|
|
|
|
|
|
def test_cache_handles_corrupted_file():
|
|
import tempfile
|
|
import hashlib
|
|
from pathlib import Path
|
|
import _search_cache
|
|
|
|
with tempfile.TemporaryDirectory() as tmpdir:
|
|
cache_dir = Path(tmpdir)
|
|
cache_dir.mkdir(exist_ok=True)
|
|
# Write garbage to the expected key path
|
|
key = hashlib.sha256("query|id1".encode()).hexdigest()
|
|
(cache_dir / f"{key}.json").write_text("not json {{{")
|
|
result = _search_cache.cache_get("query", ["id1"], cache_dir=cache_dir)
|
|
_assert(result is None, "corrupted cache file returns None")
|
|
|
|
|
|
def run_all():
|
|
tests = [
|
|
test_call_claude_dispatches_to_sdk_when_available,
|
|
test_call_claude_falls_back_to_cli_when_no_sdk,
|
|
test_call_claude_raises_when_neither_available,
|
|
test_cache_miss_returns_none,
|
|
test_cache_hit_returns_cached_results,
|
|
test_cache_miss_on_different_candidates,
|
|
test_cache_miss_after_ttl_expires,
|
|
test_cache_handles_corrupted_file,
|
|
]
|
|
for t in tests:
|
|
print(f"\n{t.__name__}")
|
|
t()
|
|
print("\n" + "=" * 50)
|
|
print(f"✅ All {len(tests)} tests passed")
|
|
print("=" * 50)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
run_all()
|