Support multimodal content in Agent Spec LLM events
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 421
- Forks
- 60
- Avg merge
- 9h 30m
- Merged PRs (30d)
- 4
Description
The content attribute of LLM-based events in Agent Spec Tracing is of type string.
We should extend it to make it support also multimodal content and more complex message structures.
Ideally, the same should apply to the prompts and the Message model.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by locating the definitions of LLM-based events, prompts, and the Message model mentioned in the issue. Determine a consistent structure for multimodal and complex message content across those models; done means each supports the agreed representation without limiting content to strings.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100