feat(cli): EVAL.yaml → evals.json transpiler (agentv transpile)#606
Merged
feat(cli): EVAL.yaml → evals.json transpiler (agentv transpile)#606
Conversation
Adds a transpiler that converts AgentV EVAL.yaml format to Agent Skills evals.json format for consumption by the skill-creator pipeline. - New core module: eval-yaml-transpiler (transpileEvalYaml, transpileEvalYamlFile, getOutputFilenames) - New CLI command: agentv transpile <input.yaml> [--out-dir dir] [--stdout] - Handles both assertions: (current) and assert: (deprecated alias) - Extracts prompt and files from structured content blocks (type: text/file) - Converts all assertion types to natural language strings - trigger-judge maps to should_trigger bool, not assertions - Root-level assertions distributed to every test - Multi-skill input produces one evals.json per skill - Tests without trigger-judge assigned to dominant skill or _no-skill - 43 unit tests covering all field mappings and edge cases - Example EVAL.yaml and expected evals.json in examples/features/transpile/
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
agentv transpile <input.yaml>CLI command that converts AgentV EVAL.yaml format to Agent Skills evals.jsonshould_trigger, all assert types → natural language, root-level assertion distribution, multi-skill outputexamples/features/transpile/Field mappings implemented
tests[].input[role=user].content[type=text]evals[].prompttests[].input[role=user].content[type=file][].valueevals[].files[]tests[].input_files[]evals[].files[](shorthand)tests[].expected_outputevals[].expected_output(flattened)tests[].assert[type=trigger-judge].should_triggerevals[].should_trigger(omitted if absent)tests[].criteria+ other assert typesevals[].assertions[](NL strings)assert/assertionsassertions[]Risk
Low — new additive feature, no existing behavior changed.
Closes #598