feat: improve eval workflow and add skills sync (#87)#103
Merged
Conversation
- Add sync-skills scripts (bash + PowerShell) and CI test to enforce single source of truth for skills between src/agentops/templates/skills/ and plugins/agentops/skills/ (closes #87) - Add cross-platform subprocess pattern in agentops-eval and agentops-dataset skills (shutil.which + shell detection) - Genericize auth carrythrough: AGENT_AUTH_HEADER/AGENT_AUTH_TOKEN env vars in callable_adapter.py template and agentops-eval skill - Add azd environment validation step in agentops-eval and agentops-config skills - Add optional unit test generation question and guidance section in agentops-eval skill - Enhance smoke test diagnostics with empty response, format mismatch, UUID prefix, and HTML error detection - Update CONTRIBUTING.md with skills single-source-of-truth rule - Sync plugins/agentops/skills/ from canonical src/ templates
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Generalizable eval workflow improvements based on real-world RAG evaluation testing, plus implementation of #87 (single source of truth for skills).
Changes
Phase 1 — Single Source of Truth for Skills (closes #87)
scripts/sync-skills.shandscripts/sync-skills.ps1to copy skills fromsrc/agentops/templates/skills/toplugins/agentops/skills/tests/unit/test_skills_sync.py— CI test that fails if the two directories divergeCONTRIBUTING.mdwith single-source-of-truth rule and sync instructionsPhase 2 — Cross-Platform Subprocess Pattern
agentops-evalandagentops-datasetskills withshutil.which()+shell=(sys.platform == "win32")pattern for subprocess callsPhase 3 — Generic Auth Carrythrough
AGENT_AUTH_HEADER/AGENT_AUTH_TOKENenv varscallable_adapter.pytemplate to conditionally apply auth headersPhase 4 — azd Environment Validation
agentops-evalandagentops-configskillsazd env list, resource group existence, stale environment warningsPhase 5 — Optional Unit Test Generation
agentops-evalStep 1 offering unit test generationPhase 6 — Enhanced Smoke Test Diagnostics
Test Results