Add "echo" model for dry run debugging #1155
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Introduce the "echo" model to the GenAI ecosystem, enabling dry runs without LLM calls. This addition enhances debugging capabilities by allowing users to see the expected output without invoking an actual LLM provider.
• ✨ Introduces an "echo" provider that does a dry run by returning messages without calling any external service
• 🦺 Adds a "hidden" property for providers so some can be excluded from CLI prompts or configuration menus
• 📚 Updates documentation and CLI references to include the new "echo" provider and to only show non-hidden providers
• ➿ Improves text rendering by collapsing excessive line breaks
• 🏗 Adds a sample script demonstrating usage with the "echo" provider for debugging and testing