feat: AkashChat API skill/model added

[sekmet]

AkashChat Skill/Model Integration

Description

This PR introduces a new skill: skills/akashchat, which enables conversational AI with the Meta-Llama-3-3-70B-Instruct model via the AkashChat API.
It also adds support for image generation using the AkashGen model. The integration includes a configurable skill for generating images from text prompts, with support for advanced parameters such as negative prompt, sampler, scheduler, and preferred GPU selection.

Key changes:

• Agent model: Meta-Llama-3-3-70B-Instruct.
• Added skills/akashchat directory with:
  • akashgen_image_generation.py: Implements the AkashGen image generation skill with full async polling and parameter support.
  • base.py, __init__.py, and schema.json for modular skill integration.
• Updated configuration and agent model selection to support AkashChat.
• Updated .env and example.env to include AKASH_CHAT_API_KEY.

Notes

• To use AkashChat, you need to generate an API key from AkashChat.
• More details about AkashChat can be found in the AkashChat documentation.

Type of Change

• Bugfix
• New Feature
• Improvement
• Documentation Update

Checklist

• I have read the contributing guidelines.
• I have added tests to cover my changes.
• All new and existing tests passed.

[hyacinthus]

skills.akashchat.akashgen_image_generation - ERROR - HTTP error during AkashGen image generation: Server error '500 Internal Server Error' for url 'https://gen.akash.network/api/generate'

'error_message': 'validation error: 1 validation error for AkashGenImageGenerationInput\npreferred_gpu\n Input should be a valid list [type=list_type, input_value='["gpu1", "gpu2"]', input_type=str]\n For further information visit https://errors.pydantic.dev/2.10/v/list_type'

The LLM passed the tests, but the skill hasn't been tested by you and won't run properly. In _arun, you should declare optional params as Optional; otherwise, the AI will always fill in something, and it will often be incorrect.

By the way, run sh lint.sh before you commit.

[hyacinthus]

Please include screenshots of your skill testing and paste them here, similar to this pull request.

#434

[hyacinthus]

If you don't have time for self-testing, we will soon have a tool to assist with testing skills, and at that time, a decision on whether to merge will be made based on the results.

[taiyangc]

To expedite the review process, please join https://discord.com/invite/crestal, open a support ticket to apply for an intentkit dev role. We have a discussion channel there for you to join up with the rest of the developers.

[bluntbrain]

Hi @sekmet
thanks for your contribution!

this PR can be reviewed and merged, as soon as these above mentioned conflicts are resolved.

also I think you'd need to make some changes, to make this work, as some files have moved, in the main branch, if possible please do add screenshots of the skill working, thanks!

cc @hyacinthus @taiyangc