retoor
f996336afb
The suite ran with -x, so a run stopped at the first failure and finding N failures cost N full runs. Move -rf into the pytest addopts so every run lists each failure, and add the triage targets test-fast (unit + api, no browser), test-failed (--last-failed), test-first-failure (the old -x), test-slowest and test-cache-clean. A stale .pytest_cache holding node ids from deleted files made --last-failed select everything; make clean and test-cache-clean drop it. Fix the fifteen failures this surfaced. DeepSearch crawling raised AttributeError in its finally block on every run: async_playwright().__aenter__() returns a Playwright, which has no __aexit__. Use start()/stop() at both call sites. Update the tests left behind by changed signatures: VectorStore is async now, fetch_page takes a browser, _summary_payload takes dom_evidence, and the messages/notifications page compounds take a user_uid. Close four real flakes that fail-fast had been hiding, all of them late in the run. Harvest assertions pinned crop.reward_coins while is_golden pays five times on about five percent of harvests, so they now assert through realizable_harvest_coins with the observed golden flag. Market saturation fixtures assumed a single active farm and landed two tiers milder once the api and e2e tiers had created farms, so they scale by active_farms(). The primary-administrator container test raced the one second cross-worker cache version window and now waits for the server to agree. The isslop tools test matched the collapsed nav dropdown link instead of the tools grid card. Stop burning ninety seconds waiting out server-side display caches: DEVPLACE_RANKING_TTL and DEVPLACE_MARKET_SATURATION_TTL follow the existing sitemap and home cache precedent and are zero for the suite, taking the leaderboard test from 60.6s to 4.4s and the saturation test from 30.1s to under a second. 2881 passed, 1 skipped in 15:13.
95 lines
3.0 KiB
Python
95 lines
3.0 KiB
Python
# retoor <retoor@molodetz.nl>
|
|
|
|
from devplacepy.services.deepsearch.embeddings import local_embed
|
|
from devplacepy.services.deepsearch.store import Chunk, VectorStore
|
|
from tests.conftest import run_async
|
|
|
|
|
|
def _chunks():
|
|
texts = [
|
|
"The transistor was invented at Bell Labs in nineteen forty seven.",
|
|
"Silicon is the primary semiconductor material used in chips.",
|
|
"Quantum tunnelling limits how small a transistor can become.",
|
|
]
|
|
chunks = [
|
|
Chunk(uid=f"c{i}", text=text, url=f"https://s{i}.example", title=f"Source {i}")
|
|
for i, text in enumerate(texts)
|
|
]
|
|
return chunks
|
|
|
|
|
|
def test_add_and_count():
|
|
store = VectorStore("ds_store_test_count")
|
|
try:
|
|
chunks = _chunks()
|
|
vectors = local_embed([c.text for c in chunks]).vectors
|
|
run_async(store.add(chunks, vectors))
|
|
assert run_async(store.count()) == 3
|
|
finally:
|
|
store.drop()
|
|
|
|
|
|
def test_hybrid_search_returns_relevant_chunk():
|
|
store = VectorStore("ds_store_test_hybrid")
|
|
try:
|
|
chunks = _chunks()
|
|
vectors = local_embed([c.text for c in chunks]).vectors
|
|
run_async(store.add(chunks, vectors))
|
|
query = "where was the transistor invented"
|
|
query_vector = local_embed([query]).vectors[0]
|
|
results = run_async(store.hybrid_search(query, query_vector, top_k=2))
|
|
assert results
|
|
assert any("transistor" in r.text.lower() for r in results)
|
|
finally:
|
|
store.drop()
|
|
|
|
|
|
def test_keyword_scores_rank_match_higher():
|
|
store = VectorStore("ds_store_test_keyword")
|
|
chunks = _chunks()
|
|
scores = store.keyword_scores("silicon semiconductor", chunks)
|
|
assert scores
|
|
best = max(scores, key=scores.get)
|
|
assert "silicon" in next(c.text for c in chunks if c.uid == best).lower()
|
|
|
|
|
|
def test_dims_reflects_embedding_width():
|
|
store = VectorStore("ds_store_test_dims")
|
|
try:
|
|
chunks = _chunks()
|
|
vectors = local_embed([c.text for c in chunks]).vectors
|
|
run_async(store.add(chunks, vectors))
|
|
assert store.dims == len(vectors[0])
|
|
finally:
|
|
store.drop()
|
|
|
|
|
|
def test_coverage_analytics_empty_collection():
|
|
store = VectorStore("ds_store_test_cov_empty")
|
|
try:
|
|
analytics = run_async(store.coverage_analytics())
|
|
assert analytics == {
|
|
"chunks": 0,
|
|
"domains": 0,
|
|
"sources": 0,
|
|
"avg_chunk_chars": 0,
|
|
}
|
|
finally:
|
|
store.drop()
|
|
|
|
|
|
def test_coverage_analytics_counts_chunks_and_sources():
|
|
store = VectorStore("ds_store_test_cov")
|
|
try:
|
|
chunks = _chunks()
|
|
for index, chunk in enumerate(chunks):
|
|
chunk.source = "httpx" if index == 0 else "playwright"
|
|
vectors = local_embed([c.text for c in chunks]).vectors
|
|
run_async(store.add(chunks, vectors))
|
|
analytics = run_async(store.coverage_analytics())
|
|
assert analytics["chunks"] == 3
|
|
assert analytics["sources"] == 2
|
|
assert analytics["avg_chunk_chars"] > 0
|
|
finally:
|
|
store.drop()
|