Skip to content

Tags: strands-agents/sdk-python

Tags

v1.20.0

Toggle v1.20.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
fix(mcp): close mcp client event loop (#1321)

---------

Co-authored-by: David Padbury <padbury@amazon.com>
Co-authored-by: Dean Schmigelski <dbschmigelski+github@gmail.com>

v1.19.0

Toggle v1.19.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
test(steering): adjust integ test system prompts to reduce flakiness (#…

…1282)

v1.18.0

Toggle v1.18.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
fix: fix integ test for mcp eclicitation_server (#1234)

v1.17.0

Toggle v1.17.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
fix(a2a): base64 decode byte data before placing in ContentBlocks (#1195

)

v1.16.0

Toggle v1.16.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
fix(models): allow setter on system_prompt and system_prompt_content (#…

…1171)

v1.15.0

Toggle v1.15.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
feat(models): add SystemContentBlock support for provider-agnostic ca…

…ching (#1112)

* feat(model): support prompt caching via SystemContentBlock

* fix: concat text blocks for system_prompt

* remove litellm and openai changes for now

* integ tests

* linting

* linting

* fix test

* add test cases

v1.14.0

Toggle v1.14.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Transform invalid tool usages on sending, not on initial detection (#…

…1091)

Per bug #1069, session-managers never persist tool-name changes after we initially persist the message, which means once an agent generates an invalid-tool name, that message history is poisoned  on re-hydration.  To avoid that going forward, do the translation of invalid-tool names on sending to the provider and not on the initial tool_use detection.  The initial tool_use detection is needed to add a tool_response with a proper error message for the LLM, but this will avoid the poisoning issue

---------

Co-authored-by: Mackenzie Zastrow <zastrowm@users.noreply.github.com>

v1.13.0

Toggle v1.13.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
interrupts - decorated tools (#1041)

v1.12.0

Toggle v1.12.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Fix additional_args passing in SageMakerAIModel (#983)

* fix(sagemaker): additional_args dict issue

Fix error where passing an additional_args dict to SageMakerAIModel
would raise an AttributeError because Python dicts have no '__dict__'
attribute.

Fixes #982

* fix(sagemaker): typing for endpoint_config

Fix typing for SageMakerAIModel.endpoint_config which was previously
being treated as an arbitrary dictionary due to init assignment.

* fix(sagemaker): Typing for payload_config

Fix typing for SageMakerAIModel.payload_config, which was previously
being treated as a plain dict due to init assignment.

* test(sagemaker): tests for ep additional_args

Add a test to check for insertion of endpoint config additional_args

* fix(sagemaker): include payload additional_args

Copy SageMakerAIPayloadSchema's additional_args into request payloads
where provided - previously these were being ignored. Includes unit
tests.

v1.11.0

Toggle v1.11.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
fix(litellm): map LiteLLM context-window errors to ContextWindowOverf…

…lowException (#994)