From 63daf33b485cd60ecc1c0378862cfa0cec377570 Mon Sep 17 00:00:00 2001
From: Leonardo Grigorio <48296347+leonardogrig@users.noreply.github.com>
Date: Thu, 2 Apr 2026 13:47:59 -0300
Subject: [PATCH] docs: add Firecrawl section to README

---
 README.md | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/README.md b/README.md
index 0a8e0d2a..cdfd9142 100644
--- a/README.md
+++ b/README.md
@@ -123,6 +123,27 @@ Best if you want local inference on Apple Silicon with Atomic Chat. See [Advance
 
 ---
 
+## Web Search and Fetch
+
+By default, `WebSearch` is disabled for all non-Anthropic providers. The native search backend requires either the Anthropic API or the Codex responses endpoint, so users on GPT-4o, DeepSeek, Gemini, Ollama, and other OpenAI-compatible providers get no web search at all.
+
+`WebFetch` works but uses basic HTTP plus HTML-to-markdown conversion. That fails on JavaScript-rendered pages (React, Next.js, Vue SPAs) and sites that block plain HTTP requests.
+
+Set a [Firecrawl](https://firecrawl.dev) API key to fix both:
+
+```bash
+export FIRECRAWL_API_KEY=your-key-here
+```
+
+With this set:
+
+- `WebSearch` is enabled for all providers and routes through Firecrawl's search API
+- `WebFetch` uses Firecrawl's scrape endpoint instead of raw HTTP, handling JS-rendered pages correctly
+
+Free tier at [firecrawl.dev](https://firecrawl.dev) includes 500 credits. The key is optional — if not set, both tools fall back to their original behavior.
+
+---
+
 ## How It Works
 
 The shim (`src/services/api/openaiShim.ts`) sits between Claude Code and the LLM API: