fix(skills): default agentv-bench to CLI mode#1537
Merged
Conversation
Entire-Checkpoint: da4bdc81f3ac
Deploying agentv with
|
| Latest commit: |
4ff3d18
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://3f16287d.agentv.pages.dev |
| Branch Preview URL: | https://fix-agentv-bench-cli-default.agentv.pages.dev |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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-benchnow tells agents to run evaluations through the AgentV CLI unless the user explicitly asks for subagent mode. Subagent execution remains documented as an opt-in fallback, but the skill no longer treatsAGENT_EVAL_MODE=subagentas the default path.Validation
bun test apps/cli/test/unit/skills.test.tsbun scripts/marketplace/validate-frontmatter.ts skills-data/agentv-bench/SKILL.md(reported 0 matching files for this path, matching prior behavior)bun --filter agentv buildbun apps/cli/src/cli.ts skills get agentv-bench | rg -n 'default to AgentV CLI mode|Do not readAGENT_EVAL_MODE|Subagent mode.*opt-in fallback|default tosubagent|default to subagent'bun apps/cli/src/cli.ts skills get agentv-bench --ref subagent-pipeline | rg -n 'explicit opt-in fallback|defaults to AgentV CLI mode|AGENT_EVAL_MODE=subagent|the default'