feat(generate_image)!: update to support current Bedrock models

[mrityunjayshukla]

Description

Enhance generate_image tool to support current Bedrock models

• Replace legacy stability.stable-diffusion-xl-v1 with current models
• Removed steps and style_preset from the request model, as they are no longer required by the new versions of Stability or Amazon text-to-image AI models.
• Added region_name support in tool request
• Add support for different model families (Stability AI and Amazon)
• Implement model validation to check for legacy models
• Add proper error handling for different response formats
• Enhance test coverage

BREAKING CHANGE: This update removes support for legacy models and changes
the request format for different model families. Users will need to update
their model_id parameter to use currently supported models.

Will do a follow up PR to update the documentation.

Related Issues

#75

Documentation PR

Will do a follow up PR to update the documentation.

Type of Change

• Bug fix
• New Tool
• Breaking change
• Other (please describe)

Testing

1. Unit tests, formatter and linters has passed.
2. Generated invocation to various bedrock supported models in scope in different aws regions - generating images using (Amazon Titan V1 and V2, Nova Canvas, SD Ultra, SD Core and SD 3.5).

=== Testing Default Model Selection ===
No model_id provided. Using automatically selected model: amazon.titan-image-generator-v1
✅ SUCCESS - Default model selection worked
Selected model: The generated image has been saved locally to output/a_beautiful_mountain_landscape_with.png. 

=== Getting available models in us-west-2 ===
Found 5 text-to-image models in us-west-2:
- amazon.titan-image-generator-v1
- amazon.titan-image-generator-v2:0
- stability.sd3-5-large-v1:0
- stability.stable-image-core-v1:1
- stability.stable-image-ultra-v1:1

=== Testing each model individually ===
Testing model amazon.titan-image-generator-v1...
✅ SUCCESS - amazon.titan-image-generator-v1 (11.99s)
Testing model amazon.titan-image-generator-v2:0...
✅ SUCCESS - amazon.titan-image-generator-v2:0 (13.12s)
Testing model stability.sd3-5-large-v1:0...
✅ SUCCESS - stability.sd3-5-large-v1:0 (10.02s)
Testing model stability.stable-image-core-v1:1...
✅ SUCCESS - stability.stable-image-core-v1:1 (9.93s)
Testing model stability.stable-image-ultra-v1:1...
✅ SUCCESS - stability.stable-image-ultra-v1:1 (13.89s)

=== Test Summary ===
Total models tested: 6
Successful tests: 6
Failed tests: 0
Results saved to: /Users/mrshukla/Documents/gitworkspace/strands-agents/tools/output/model_tests/test_results.json

=== Testing Default Model Selection in us-east-1 ===
No model_id provided. Using automatically selected model: amazon.titan-image-generator-v1
✅ SUCCESS - Default model selection worked
Selected model: The generated image has been saved locally to output/a_beautiful_mountain_landscape_with_6.png. 

=== Getting available models in us-east-1 ===
Found 3 text-to-image models in us-east-1:
- amazon.titan-image-generator-v1
- amazon.titan-image-generator-v2:0
- amazon.nova-canvas-v1:0

=== Testing each model individually ===
Testing model amazon.titan-image-generator-v1...
✅ SUCCESS - amazon.titan-image-generator-v1 (12.68s)
Testing model amazon.titan-image-generator-v2:0...
✅ SUCCESS - amazon.titan-image-generator-v2:0 (12.75s)
Testing model amazon.nova-canvas-v1:0...
✅ SUCCESS - amazon.nova-canvas-v1:0 (9.6s)

• hatch fmt --linter
• hatch fmt --formatter
• hatch test --all

Checklist

• I have read the CONTRIBUTING document

• I have added tests that prove my fix is effective or my feature works

• I have updated the documentation accordingly

• I have added an appropriate example to the documentation to outline the feature

• My changes generate no new warnings

• Any dependent changes have been merged and published

• By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

[cagataycali]

Looks great to me!

Thanks for investing time to improving the generate_image tool! Approving and leaving team to have a second look! 🚀