feat: make the catalog easy for AI agents to use - #8
Merged
Conversation
Add a Copy button to the "How to use" modal that yields the guide as Markdown, plus agent-discovery surfaces so the catalog is usable without scraping HTML. - Copy button copies the usage guide as Markdown (clipboard + execCommand fallback) - /llms.txt and /llms-full.txt generated from the YAML catalog at build time - WebMCP tools on navigator.modelContext: search, model params, providers, parameters, usage guide - Structured data: WebSite + SearchAction + Dataset alongside the ItemList - /?q= deep-links search; robots.txt + sitemap point at the new files; CORS on the .txt files - Fix dev watcher: scope dotfile-ignore to basename so a checkout under ~/.paseo no longer disables it; poll by default
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
💭 Why
People are pasting the "How to use" guide into coding agents, and agents that hit the site had to scrape HTML. This gives them first-class ways to read the catalog.
✨ What changed
/llms.txtand/llms-full.txtgenerated from the YAML catalog at build time, served in dev too.navigator.modelContext: search_models, get_model_parameters, list_providers, list_parameters, get_usage_guide./?q=deep-links the search (backs the SearchAction); robots.txt and sitemap point at the new files; CORS on the.txtfiles..paseoancestor dir and silently disabled the whole watch. Scoped it to the basename and poll by default.👤 For users
The "How to use" modal has a Copy button that yields paste-ready Markdown. Agents can read
/llms.txt,/llms-full.txt, or call the in-page WebMCP tools instead of scraping.📝 Notes
Adds tests/llms.test.ts. Build writes both
.txtfiles into dist/. Set CHOKIDAR_USEPOLLING=false for native FS events on a normal local disk.