From e17c46edc14a1e051f859ff4af8481df66db62e6 Mon Sep 17 00:00:00 2001
From: spqrz <spqrz386@gmail.com>
Date: Sun, 12 Apr 2026 11:12:12 +0100
Subject: [PATCH] use html2md on web_fetch (fixes #3)

---
 Cargo.toml             | 1 +
 src/agent/tools/web.rs | 5 ++++-
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/Cargo.toml b/Cargo.toml
index 2c5246f..9186f64 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -20,6 +20,7 @@ edition.workspace = true
 
 [dependencies]
 anyhow = "1"
+html2md = "0.2"
 crossterm = { version = "0.29", features = ["event-stream", "bracketed-paste", "osc52"] }
 clap = { version = "4", features = ["derive"] }
 figment = { version = "0.10", features = ["env"] }
diff --git a/src/agent/tools/web.rs b/src/agent/tools/web.rs
index 7ad7fc9..15d011e 100644
--- a/src/agent/tools/web.rs
+++ b/src/agent/tools/web.rs
@@ -3,6 +3,7 @@ use std::sync::Arc;
 
 use anyhow::{Context, Result};
 use serde::Deserialize;
+use html2md::parse_html;
 
 pub fn tools() -> [super::Tool; 2] {
     [
@@ -42,7 +43,9 @@ async fn web_fetch(args: &serde_json::Value) -> Result<String> {
     let body = response.text().await
         .with_context(|| format!("failed to read body from {}", a.url))?;
 
-    Ok(super::truncate_output(body, 30000))
+    // Convert HTML to Markdown, then truncate
+    let markdown = parse_html(&body);
+    Ok(super::truncate_output(markdown, 30000))
 }
 
 // ── Search ──────────────────────────────────────────────────────