kent/consciousness
1
0
Fork 1
Code Issues 1 Pull requests 5 Projects Releases Packages Wiki Activity Actions

use html2md on web_fetch (fixes #3)

Browse source
This commit is contained in:
spqrz 2026-04-12 11:12:12 +01:00
parent d5aad5c1a4
commit e17c46edc1
No known key found for this signature in database
2 changed files with 5 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

1
Cargo.toml
View file

@ -20,6 +20,7 @@ edition.workspace = true
[dependencies] [dependencies]
anyhow = "1" anyhow = "1"
html2md = "0.2"
crossterm = { version = "0.29", features = ["event-stream", "bracketed-paste", "osc52"] } crossterm = { version = "0.29", features = ["event-stream", "bracketed-paste", "osc52"] }
clap = { version = "4", features = ["derive"] } clap = { version = "4", features = ["derive"] }
figment = { version = "0.10", features = ["env"] } figment = { version = "0.10", features = ["env"] }

5
src/agent/tools/web.rs
View file

@ -3,6 +3,7 @@ use std::sync::Arc;
use anyhow::{Context, Result}; use anyhow::{Context, Result};
use serde::Deserialize; use serde::Deserialize;
use html2md::parse_html;
pub fn tools() -> [super::Tool; 2] { 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 let body = response.text().await
.with_context(|| format!("failed to read body from {}", a.url))?; .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 ────────────────────────────────────────────────────── // ── Search ──────────────────────────────────────────────────────