archipelago
7ba3109b6d
git-subtree-dir: aiui git-subtree-mainline:0c4826f8ccgit-subtree-split:e30ac1d106
1.6 KiB
name, description, allowed-tools
| name | description | allowed-tools |
|---|---|---|
| trace | End-to-end trace of a query through prompt, extraction, tabs, and rendering | Bash(*), Read, Glob, Grep, Agent |
Trace how a specific user query flows through the entire AIUI pipeline. The user will provide a sample query (e.g., "best nostr apps", "recommend some films", "bitcoin news").
Trace each stage:
-
Query classifiers: Run the query through each classifier in
contentFiltering.ts:isNewsQuery(),isMusicQuery(),isBookQuery(),isTVQuery(),isImageQuery(),isPlaceQuery(),isRecipeQuery(),isCodeQuery(),isNostrQuery(),isAppQuery(),isWebsitesQuery()- Report which ones return true
-
Preferred tab: What does
preferredFirstTab()return for this query? -
System prompt: What would
buildSystemPrompt()include? ReaduseAI.tsand trace all dynamic sections. -
Expected AI response: Based on the system prompt instructions, what tags would the AI likely use? Construct a realistic sample response.
-
Extraction: Run the sample response through each extraction function and report what gets found:
extractAllFilms(),extractAllSongs(),extractAllPodcasts(),extractAllBooks(),extractAllTVSeries(),extractAllImages(),extractAllPlaces(),extractApps(),extractCodeBlocks(),extractRecipes()
-
Tab filtering: What tabs would
filterTabsByContext()return? In what order? -
Rendering: Which grid component would render? Trace through ContentPanel.vue and/or ContentGridView.vue.
-
Report: Complete flow diagram showing: Query -> Classifiers -> Prompt -> Expected Response -> Extraction -> Tabs -> Grid