This release adds 1 notable feature for engineering teams evaluating rollout.
Published 8mo
AI Agents & Assistants
✓ No known CVEs patched
✓ No known CVEs patched in this version
Topics
agentic
agentic-ai
agents
ai
anthropic
autonomous-agents
+13 more
bedrock
genai
litellm
llama
llm
machine-learning
mcp
multi-agent-systems
ollama
openai
opentelemetry
python
strands-agents
Summary
AI summaryUpdates fix, feat, and models across a mixed release.
Full changelog
What's Changed
- feat: decouple Strands ContentBlock and BedrockModel by @dbschmigelski in https://github.com/strands-agents/sdk-python/pull/836
- fix: Invoke callback handler for structured_output by @zastrowm in https://github.com/strands-agents/sdk-python/pull/857
- fix: Update prepare to use format instead of test-format by @zastrowm in https://github.com/strands-agents/sdk-python/pull/858
- fix: add explicit permissions to auto-close workflow by @Unshure in https://github.com/strands-agents/sdk-python/pull/893
- fix: make mcp_instrumentation idempotent to prevent recursion errors by @Unshure in https://github.com/strands-agents/sdk-python/pull/892
- fix: Fix github workflow to use fmt instead of hatch run by @Unshure in https://github.com/strands-agents/sdk-python/pull/898
- fix(models): make tool_choice an optional keyword arg instead positional by @dbschmigelski in https://github.com/strands-agents/sdk-python/pull/899
Full Changelog: https://github.com/strands-agents/sdk-python/compare/v1.9.0...v1.9.1
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
About harness-sdk
A model-driven approach to building AI agents in just a few lines of code.
Related context
Related tools
Beta — feedback welcome: [email protected]