version: "1.0.0" name: web-search description: How Pi accesses the web — search, fetch URLs/PDFs/YouTube/GitHub, and retrieve current information. Use whenever a task needs facts, docs, current/latest info, news, prices, versions, or content from a specific URL. Routes by the user's phrasing (web search vs extensive web research vs deep research). Backed by the globally-installed pi-web-access package.

Web Search

The pi-web-access package is installed globally. Zero-config via Exa MCP (no API key), with fallback Exa → Perplexity → Gemini.

CRITICAL: always pass workflow: "none"

Every web_search call MUST include workflow: "none". This skips the interactive browser curator popup (David does not want it opening). No exceptions — single query or batched queries, always set workflow: "none".

web_search({ queries: ["query 1", "query 2"], workflow: "none" })

Tools

• web_search — search the web; returns synthesized answers with citations. Can be called many times per turn. Always pass `workflow: "none"`.
• code_search — zero-key Exa code-context. Use for library/API/code lookups instead of generic web_search.
• fetch_content — fetch URL(s) → markdown; handles PDFs, YouTube, GitHub.
• get_search_content — big pages (>30k chars) are truncated in responses but stored in full; call this to pull the rest on demand so they don't blow context.

fetch_content specifics

• GitHub URLs are cloned, not scraped — you get real files + a local path to explore with read/bash (private repos need the gh CLI). Use this for dev work.
• PDFs → auto-extracted to markdown in ~/Downloads/, readable in sections (text-only, no OCR).
• YouTube/video → full raw transcripts + frame extraction. Needs a GEMINI_API_KEY (not zero-config); frame extraction also needs ffmpeg/yt-dlp.

Routing — match the user's phrasing

Always use the web_search tool. These counts are HARD MINIMUMS — count your queries before answering and do not stop short:

• "web search" → at least 2 queries, varied keywords/angles, then synthesize.
• "extensive web research" → at least 4 queries, totally different keywords and angles.
• "deep research" → at least 8 queries, totally different keywords and angles, run across 2–3 successive batches (refine angles after each batch), to learn as much as possible about the topic.

A single batched web_search call counts each query in queries[] toward the total. If your first batch is under the minimum, fire another batch before synthesizing.