chore(deps): update bedrock-agentcore SDK to 1.1.x (#341)

Update bedrock-agentcore dependency version constraint. Includes compatibility updates for retrieve.py and test fixes.

Fix: Add missing retrieveFilter parameter to retrieve tool spec (#292)

* Fix: Add missing retrieveFilter parameter to retrieve tool spec

* fix: Break long lines in retrieveFilter description to pass linting

pin hatch version (#330)

feat(code-interpreter): add session persistence and reconnection (#308)

---------

Co-authored-by: Sundar Raghavan <[email protected]>

fix(workflow): Allow workflow tasks access results from previous depe…

…ndent tasks (#202)

Co-authored-by: Fox Qin <[email protected]>

feat(a2a_client): Add httpx params to be passed to allow auth with A2A (

#298)

feat: Add automatic session management to Code Interpreter tool (#284)

* feat: Add automatic session management to Code Interpreter tool

- Make session_name parameter optional in all action models
- Implement auto-session mode with _ensure_session() method
- Enable automatic session creation when sessions don't exist
- Update tool description to prioritize common use cases
- Improve developer experience by reducing manual session management

* fix: docstring

* fix: address PE feedback. Improved Isolation Multi-Case Support. Removed large tool description formatting changes from this PR

* fix: address comments on docstrings, comments

* fix: updated import uuid

* fix: integration test issues

---------

Co-authored-by: Sundar Raghavan <[email protected]>

feat(browser): agent core browser use persistent context (#288)

feat(editor): add EDITOR_DISABLE_BACKUP option to skip backup file cr…

…eation (#259)

fix(batch): Return human-readable results for agent display (#273)

- Add dual output format: human-readable text + structured JSON
- Fix misleading 'Tool missing' error messages
- Preserve original tool results while adding batch metadata
- Enable agents to display individual tool results instead of generic success message
- Fix typo: 'Sammple' -> 'Sample' in documentation
- Update tests to match new output format

Resolves issue where agents only showed 'batch call executed successfully'
instead of actual tool results from parallel executions.