fix(memory): remove Strands Bidi hooks

[Hweinstock]

Spec

Issue #665: #665

Problem

The Strands session manager imported experimental Bidi hook events that are not available in the current Strands API, breaking standard CLI-generated Strands projects during import.

Solution

Removed direct Bidi event imports and registrations, removed the obsolete Bidi unit test, and replaced inherited sync hook registration with equivalent standard Agent and multi-agent callbacks so no Bidi callback is registered while memory initialization, retrieval, persistence, batching, and synchronization remain unchanged.

Verification

• Unit suite: 181 passed with Strands 1.56.0.
• Dev-account integration suite in us-east-1: 12 passed in 524.16s.
• Ruff and git diff --check: passed.
• Production scan: no Bidi event imports or registrations.
• CLI-style import with Strands 1.56.0: Agent AgentCoreMemorySessionManager.

Reproduce

uv run --python 3.10 --with 'strands-agents==1.56.0' --extra strands-agents \
  pytest tests/bedrock_agentcore/memory/integrations/strands/test_agentcore_memory_session_manager.py -q

BEDROCK_TEST_REGION=us-east-1 uv run --python 3.10 \
  --with 'strands-agents==1.56.0' --extra strands-agents \
  pytest tests_integ/memory/integrations/test_session_manager.py -v

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
⚠️ Please upload report for BASE (main@9f31042). Learn more about missing BASE report.

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #666   +/-   ##
=======================================
  Coverage        ?   89.51%           
=======================================
  Files           ?      123           
  Lines           ?    10704           
  Branches        ?     1677           
=======================================
  Hits            ?     9582           
  Misses          ?      734           
  Partials        ?      388           

Flag	Coverage Δ
unittests	89.51% <100.00%> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[agentcore-devx-automation]

Claude Security Review: no high-confidence findings. (run)