Add agentic documentation for OpenShift enhancements#1992
Open
Prashanth684 wants to merge 2 commits into
Open
Conversation
Introduce ai-docs/ with structured documentation covering platform concepts, operator patterns, engineering practices, and development workflows. Includes AGENTS.md navigation index and knowledge graph for AI agent navigation. generating using the /platform-docs skill here: openshift-eng/ai-helpers#437
Contributor
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: The full list of commands accepted by this bot can be found here. DetailsNeeds approval from an approver in each of these files:Approvers can indicate their approval by writing |
4 tasks
Adds evaluation framework to test AI agent usage of CLAUDE.md and ./ai-docs/ documentation using promptfoo and Claude Agent SDK. Test Scenarios (6 total): 1. Navigation (2 tests): - Finding enhancement process documentation - Finding operator pattern documentation 2. Enhancement Authoring (1 test): - Designing fictional "ClusterPowerScheduler" enhancement from scratch - Tests agent applies patterns without copying existing enhancements 3. Anti-Pattern (3 tests) - What docs PREVENT: - Rejects v1 API from start → Requires v1alpha1 graduation - Rejects custom ClusterOperator conditions → Requires Available/Progressing/Degraded - Rejects breaking field rename → Requires deprecation process Key Design: Agents are NOT told to read documentation. They must naturally discover CLAUDE.md exists and follow navigation guidance. Tests verify agents read and apply repo-specific rules by checking "Documentation Used" section in responses. Usage: make eval # Run all 6 tests (~30-60 min) make eval-navigation # Run navigation tests only make eval-anti-pattern # Run anti-pattern tests only make eval-view # View results in web UI make eval-clean # Clear cache Prerequisites: - Node.js 22.22.0+ or 20.20.0+ - Set ANTHROPIC_VERTEX_PROJECT_ID or ANTHROPIC_API_KEY Files: - promptfooconfig.yaml: Test definitions (6 scenarios) - test/eval/run-eval.sh: Runner script (uses npx) - test/eval/README.md: Complete documentation
Contributor
|
@Prashanth684: all tests passed! Full PR test history. Your PR dashboard. DetailsInstructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository. I understand the commands that are listed here. |
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.
Introduce ai-docs/ with structured documentation covering platform concepts, operator patterns, engineering practices, and development workflows. Includes AGENTS.md navigation index and knowledge graph for AI agent navigation.
generating using the /platform-docs skill here: openshift-eng/ai-helpers#437