Show expected vs actual worldview content in read eval reports #12
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Add generated_worldview_content field to EvalResult to capture CLI output - Update report to display both expected (predefined) and actual (CLI-generated) worldview content when CLI mode is used - Include generated content in JSON results for analysis - Update agent TASK_INSTRUCTIONS to encode only explicitly stated facts, avoiding supplementary knowledge from training data for token efficiency
- Create evals/common/ for shared code (config, llm_clients) - Create evals/read_eval/ for read evaluation (tests LLM response to context) - Keep evals/write_eval/ for write evaluation (tests document generation) - Update all imports to use new module paths - Remove expected worldview content from report (only show CLI-generated) - Add proper __init__.py exports for all submodules This structure prepares for adding additional evaluation types in the future.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
worldview content when CLI mode is used
avoiding supplementary knowledge from training data for token efficiency