docs(agent): refresh restructure references - #1628
Merged
Merged
Conversation
Deploying agentv with
|
| Latest commit: |
2ebe333
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://b0930936.agentv.pages.dev |
| Branch Preview URL: | https://agent-docs-authoring.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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Future workers now see the current restructure contract in the places they are most likely to follow:
CONCEPTS.md,.agentsrouting guidance, ADR status notes, README result layout, and the AI-facing screenshot skill.This updates the active guidance to use
.internal/index.jsonl,summary.json,result.json,grading.json,metrics.json,sample-N/,workspace.scope: suite|attempt,workspace.reposbefore extensions,scriptgraders,llm-rubricfor free-form rubric judging, andg-evalfor structured or multi-criteria rubric judging. ADR-0011 and ADR-0012 now explicitly point to ADR-0017 for the current output layout instead of leaving rootindex.jsonl,run-N,timing_path, ortiming.jsoneasy to misread as current.Stale-Hit Classification
The focused scan still finds intentional hits in three categories:
.internal/index.jsonlin README,CONCEPTS.md,.agents/conventions.md,.agents/verification.md, ADR-0017, and the screenshot skill.llm-graderregistry plumbing and ADR-0017 text explaining the timing-to-metrics merge.No remaining agent-facing guidance directs workers to use root
index.jsonl, target-levelgrader_target,workspace.hooks,run-N,attempt-N,timing_path,timing.json,code-grader, orgrading.json.assertions[]as the current contract.Verification
bun installbun run lintgit diff --checkCONCEPTS.md,AGENTS.md,.agents,docs/adr,docs/solutions,plugins, andREADME.mdFull tests were not run because this is a Markdown/reference-only change with no runtime code changes.
Post-Deploy Monitoring & Validation
No additional operational monitoring required. This is a docs and agent-reference update only; review validation should focus on whether the PR text matches the implemented contract and whether CI docs/lint checks pass.
Related
Related: av-si4s