This release fixes issues for SREs watching stability and regressions.
Published 1d
AI Agents & Assistants
✓ No known CVEs patched
✓ No known CVEs patched in this version
Topics
agents
ai
ai-agents
application
chatbots
chatgpt
+7 more
genai
llm
long-term-memory
memory
memory-management
python
state-management
Summary
AI summaryFixed multiple vector store filter handling bugs and LLM response format issues.
Full changelog
Bug Fixes:
- Vector Stores: Apply every operator in a Cassandra compound field filter (e.g.
{ age: { gte: 10, lte: 20 } }) instead of stopping after the first, so the remaining bounds are no longer silently ignored (#6511) - Vector Stores: Stop the Chroma where-clause translator from dropping filter conditions. Same-field ranges (
gte+lte), multi-field conditions inside$or, and negatedcontains/icontainsunder$noteach collapsed to a single clause or vanished, widening the search instead of narrowing it (#6521) - Vector Stores: Skip
"*"wildcard filter values in Milvus instead of matching them literally, so a filter like{ user_id: "*" }no longer returns zero memories (#6508) - Vector Stores: Read
textLemmatizedfor BM25 keyword search on Milvus, OpenSearch, and MongoDB, matching the field the memory layer actually writes, so hybrid search on those backends no longer loses the keyword signal (#6497) - LLMs: Forward
responseFormatto Gemini'sresponseMimeTypeingenerateResponse(), so requestingjson_objectreturns JSON instead of free-form text (#6468) - LLMs: Find the Anthropic text block by type instead of indexing
content[0], so a thinking-enabled model whosethinkingblock comes first no longer throwsUnexpected response type from Anthropic API(#6506)
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
Related context
Related tools
Beta — feedback welcome: [email protected]