Feat/agent eval showcase - #108
Merged
Merged
Conversation
Add the complete jcode Agent autonomous-execution evaluation suite: - Round-table discussion artifact (roundtable/) - ACP headless harness (harness/) with isolated-HOME orchestration (suite/) - 65-run prior evaluation report (report/report.html, analysis/) - 6 new frontend test cases and deterministic oracles (suite/testcases.json, verify.py) - 18-run frontend batch results: 17/18 passed (94%), clean end_turns - Self-contained showcase landing page (showcase/index.html) displaying the prior report metrics, the 6 discovered defects, and the 6 generated frontend projects as live iframes with per-project model/runtime/token metadata. All generated frontend projects render offline with no external CDN assets. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> 🤖 Generated with [Claude Code](https://claude.com/claude-code)
…frames Redesign the agent-eval landing experience after open-design.ai: - Add agent-eval/site/ with shared CSS/JS, nav, and six pages: index, showcase, report, findings, roundtable, docs. - Apply warm cream background (#f6f3ec), serif display type, pill buttons, white cards, numbered sections, and generous whitespace. - Convert existing docs (README, report, findings, roundtable) into the new site pages while preserving the original report in an iframe. - Embed the 6 generated frontend projects in the showcase as full-width 780px-tall iframes (responsive down to 460px on mobile) so they are actually usable, not thumbnails. - Mirror generated project files under site/projects/ for self-contained browsing, and redirect the old showcase/index.html to the new site. - Update README to point users at site/index.html as the entry point. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> 🤖 Generated with [Claude Code](https://claude.com/claude-code)
- Add 津ICP备13004281号-4 to the footer of every site page. - Fix a malformed li tag in site/roundtable.html. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> 🤖 Generated with [Claude Code](https://claude.com/claude-code)
- Rewrite site/index.html as a product marketing page for jcode (AI coding companion) - Add hero terminal mockup, feature grid, desktop download section, CLI section - Link to GitHub and actual docs/docs/ (copied from repo docs/_site with /jcode/ → /docs/ rewrite) - Rebuild showcase.html with per-demo Maximize modal and Open-in-new-window links - Remove eval/report/test pages from the site nav (report, findings, roundtable, docs.html) - Add Chinese ICP footer to all pages Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> 🤖 Generated with [Claude Code](https://claude.com/claude-code)
Replaces agent-eval/site with site/ — a Vite + React + TypeScript SPA: - Notion-help-style docs rendered straight from docs/*.md (front-matter nav tree, kramdown/liquid cleanup, sidebar + breadcrumbs + scrollspy TOC + search) - Dedicated /desktop page with a live interactive replica of the desktop app and a Remotion-player demo; dedicated /cli page with a frame-driven TUI demo - Showcase index + per-project pages (site header for back-nav, provenance, full-screen iframes) - Four new multi-round challenges implemented end-to-end by the jcode agent itself over ACP (driver: agent-eval/showcase/challenge_round.py): Neon Metropolis (three.js city, 6 rounds), NeuraLab (WebGPU CNN, 7 rounds), Jui UI kit (3 rounds), Circuit Defense (canvas TD game, 3 rounds) - Self-hosted fonts, zero external requests, ICP footer on every page Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
|
Warning Review limit reached
Next review available in: 45 minutes Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: ⛔ Files ignored due to path filters (19)
📒 Files selected for processing (120)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
cnjack
added a commit
that referenced
this pull request
Jul 12, 2026
* feat(eval): frontend showcase + unattended agent evaluation artifacts Add the complete jcode Agent autonomous-execution evaluation suite: - Round-table discussion artifact (roundtable/) - ACP headless harness (harness/) with isolated-HOME orchestration (suite/) - 65-run prior evaluation report (report/report.html, analysis/) - 6 new frontend test cases and deterministic oracles (suite/testcases.json, verify.py) - 18-run frontend batch results: 17/18 passed (94%), clean end_turns - Self-contained showcase landing page (showcase/index.html) displaying the prior report metrics, the 6 discovered defects, and the 6 generated frontend projects as live iframes with per-project model/runtime/token metadata. All generated frontend projects render offline with no external CDN assets. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> 🤖 Generated with [Claude Code](https://claude.com/claude-code) * feat(eval/site): redesign showcase as warm-cream website with large iframes Redesign the agent-eval landing experience after open-design.ai: - Add agent-eval/site/ with shared CSS/JS, nav, and six pages: index, showcase, report, findings, roundtable, docs. - Apply warm cream background (#f6f3ec), serif display type, pill buttons, white cards, numbered sections, and generous whitespace. - Convert existing docs (README, report, findings, roundtable) into the new site pages while preserving the original report in an iframe. - Embed the 6 generated frontend projects in the showcase as full-width 780px-tall iframes (responsive down to 460px on mobile) so they are actually usable, not thumbnails. - Mirror generated project files under site/projects/ for self-contained browsing, and redirect the old showcase/index.html to the new site. - Update README to point users at site/index.html as the entry point. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> 🤖 Generated with [Claude Code](https://claude.com/claude-code) * feat(eval/site): add Chinese ICP footer and fix roundtable typo - Add 津ICP备13004281号-4 to the footer of every site page. - Fix a malformed li tag in site/roundtable.html. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> 🤖 Generated with [Claude Code](https://claude.com/claude-code) * feat(site): product landing page, maximize showcase, real docs - Rewrite site/index.html as a product marketing page for jcode (AI coding companion) - Add hero terminal mockup, feature grid, desktop download section, CLI section - Link to GitHub and actual docs/docs/ (copied from repo docs/_site with /jcode/ → /docs/ rewrite) - Rebuild showcase.html with per-demo Maximize modal and Open-in-new-window links - Remove eval/report/test pages from the site nav (report, findings, roundtable, docs.html) - Add Chinese ICP footer to all pages Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> 🤖 Generated with [Claude Code](https://claude.com/claude-code) * feat(site): standalone React site with agent-built showcase challenges Replaces agent-eval/site with site/ — a Vite + React + TypeScript SPA: - Notion-help-style docs rendered straight from docs/*.md (front-matter nav tree, kramdown/liquid cleanup, sidebar + breadcrumbs + scrollspy TOC + search) - Dedicated /desktop page with a live interactive replica of the desktop app and a Remotion-player demo; dedicated /cli page with a frame-driven TUI demo - Showcase index + per-project pages (site header for back-nav, provenance, full-screen iframes) - Four new multi-round challenges implemented end-to-end by the jcode agent itself over ACP (driver: agent-eval/showcase/challenge_round.py): Neon Metropolis (three.js city, 6 rounds), NeuraLab (WebGPU CNN, 7 rounds), Jui UI kit (3 rounds), Circuit Defense (canvas TD game, 3 rounds) - Self-hosted fonts, zero external requests, ICP footer on every page Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Claude Fable 5 <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.
No description provided.