docs: spec the HTML validation report#72
Merged
Conversation
Specs a self-contained HTML report + machine-readable report.json emitted at the end of every run, summarizing all validation layers and the reviewer with embedded screenshots. Flags the key structural finding: runJudge already computes per-layer detail (Layer 1 findings, Layer 2 command/duration/stderr, reviewer diffs) but collapses it to a summary string, so the report cannot be a pure post-process of today's JudgeResult — widening what survives the run is step 1. Includes the RunReport data model, src/report/ layout, CLI flags, MCP integration, testing approach, and implementation order. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Adds
docs/validation-report.md— the design spec for a self-contained HTML validation report (plus a machine-readablereport.json) emitted at the end of every agent run.Highlights
runJudgealready computes per-layer detail (Layer 1 findings, Layer 2 command/duration/stderrTail, reviewer diffs) but collapses it into a singlesummarystring. The report cannot be a pure post-process of today'sJudgeResult— widening what survives the run is step 1 of implementation.RunReportasreport.json;renderReport(report) → stringis a pure, golden-file-testable function. Self-contained single HTML file by default (base64-embedded screenshots, inlined CSS, no JS framework / no network).RunReportdata model,src/report/layout, report sections (platform×layer matrix, findings tables, screenshot filmstrip, rubric rationales, rename-plan appendix), CLI flags, MCP integration, testing plan, and a 7-step implementation order.Implementation lands in a follow-up PR (step 1: widen
runJudgeto retain per-layer detail).🤖 Generated with Claude Code