retoorandClaude Sonnet 5
572e022584
Notifications: a new "thread" type notifies every other commenter on a
post whenever anyone comments on it, disregarding reply hierarchy -
excluding the actor and whoever already got a comment/reply
notification for that same event, so no one is double-notified.
Implemented via a background-deferred fan-out mirroring the existing
mention-notification pattern.
SEO: discussion_forum_posting() now embeds up to 20 of a post's
comments as nested schema.org Comment entities (not just an aggregate
count), and a new /topics hub plus /topics/{topic} pages give the
feed's topic filter real, independently crawlable/indexable URLs -
/feed?topic=X was never indexable since its canonical strips the
query string back to bare /feed. Both are wired end to end (schemas,
Devii actions, docs API, sitemap, locustfile load-test coverage).
Quiz player: the auto-advance to the next question used to hide the
just-answered slide in the same tick as rendering the grade, so on
any multi-question quiz the Correct/Not correct feedback was never
actually visible before the view moved on. Delayed via setTimeout,
with the pending timer cleared on manual navigation and on
disconnect so it can't race or fire on a removed component.
Also includes other local changes already in progress in this
working tree before this session (messaging, push delivery,
deepsearch jobs, game economy, quiz builder) - verified by the full
suite passing (3467 tests) but not authored or individually reviewed
in this session.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VL9Xn57W5UR3HZbbuuzxdK
111 lines
3.6 KiB
Python
111 lines
3.6 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_hybrid_search_results_carry_embedding_vectors():
|
|
store = VectorStore("ds_store_test_embeddings")
|
|
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=3))
|
|
assert results
|
|
assert all(result.embedding for result in results)
|
|
assert all(len(result.embedding) == len(vectors[0]) for result in results)
|
|
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()
|