feat(notion-search): add query expansion via Claude Haiku

Generates up to 5 query variants (synonyms + cross-language KR↔EN) so
later Notion API search can union over them. Permissive failure modes:
LLM error or non-JSON response falls back to [original] with stderr
warning. Dedupes and caps variants.

4 tests: variants list, dedup+cap, JSON-parse fallback, exception
fallback. 12 passing total.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-04-28 07:47:20 +09:00
parent 6bb8e6ab3c
commit fffbab201d
2 changed files with 123 additions and 0 deletions

View File

@@ -122,6 +122,47 @@ def test_cache_handles_corrupted_file():
_assert(result is None, "corrupted cache file returns None")
def test_expand_query_returns_variants_with_original_first():
"""LLM mock returns variants; expansion includes original verbatim as first item."""
import notion_search
fake_llm = lambda prompt, **kw: '["AI agents", "multi-agent systems", "autonomous LLMs"]'
variants = notion_search.expand_query("AI agents", llm_caller=fake_llm)
_assert(variants[0] == "AI agents", "original query is first variant")
_assert(len(variants) >= 2, "at least 2 variants returned")
_assert("multi-agent systems" in variants, "LLM-suggested variant included")
def test_expand_query_dedupes_and_caps():
"""Duplicates removed; total ≤ max_variants."""
import notion_search
fake_llm = lambda prompt, **kw: '["AI", "AI", "agents", "agents", "systems", "tools", "models"]'
variants = notion_search.expand_query("AI", llm_caller=fake_llm, max_variants=3)
_assert(len(variants) <= 3, "capped at max_variants=3")
_assert(len(variants) == len(set(variants)), "no duplicates in result")
def test_expand_query_falls_back_on_invalid_json():
"""LLM returns prose instead of JSON → fall back to [original]."""
import notion_search
fake_llm = lambda prompt, **kw: "I'm sorry, I can't help with that."
variants = notion_search.expand_query("AI agents", llm_caller=fake_llm)
_assert(variants == ["AI agents"], "non-JSON response falls back to original only")
def test_expand_query_falls_back_on_llm_exception():
"""LLM raises → fall back to [original]."""
import notion_search
def boom(prompt, **kw):
raise RuntimeError("API error")
variants = notion_search.expand_query("AI agents", llm_caller=boom)
_assert(variants == ["AI agents"], "LLM exception falls back to original only")
def run_all():
tests = [
test_call_claude_dispatches_to_sdk_when_available,
@@ -132,6 +173,10 @@ def run_all():
test_cache_miss_on_different_candidates,
test_cache_miss_after_ttl_expires,
test_cache_handles_corrupted_file,
test_expand_query_returns_variants_with_original_first,
test_expand_query_dedupes_and_caps,
test_expand_query_falls_back_on_invalid_json,
test_expand_query_falls_back_on_llm_exception,
]
for t in tests:
print(f"\n{t.__name__}")