[BUG] filter_restored_tool_context is incompatible with extended thinking

### Version

`bedrock-agentcore` 1.19.0

### Model

Claude Sonnet 4.6 via Amazon Bedrock, with extended thinking enabled (`{"type": "adaptive", "display": "summarized"}`)

### What happens

Setting `filter_restored_tool_context=True` on `AgentCoreMemoryConfig` makes every request fail once there is history to restore:

```
ValidationException: messages.1.content.6: `thinking` or `redacted_thinking` blocks in
the latest assistant message cannot be modified. These blocks must remain as they were
in the original response.
```

The option is unusable for any agent with extended thinking enabled. Turning the flag off restores normal operation.

### Expected

Either the option works alongside extended thinking, or the incompatibility is documented and the flag rejected at configuration time rather than failing on every request at runtime.

### Context

We hit this while trying to work around https://github.com/strands-agents/harness-sdk/issues/3651, where an interrupted turn leaves a session permanently unusable.

Reproduce the failure with bedrock-agentcore 1.19.0 using AgentCoreMemoryConfig(filter_restored_tool_context=True), restored history, and Claude extended thinking. Trace the configuration and restored-message handling, then verify that the option either works with thinking blocks or is rejected at configuration time with documented guidance.

Written by the indexing model from the issue text.