<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
    <channel>
        <title>Codex - Tag - Daily Deep Think</title>
        <link>https://blog.baifan.site/en/tags/codex/</link>
        <description>Codex - Tag - Daily Deep Think</description>
        <generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>blog@baifan.site (ByF)</managingEditor>
            <webMaster>blog@baifan.site (ByF)</webMaster><lastBuildDate>Tue, 31 Mar 2026 14:00:00 &#43;0800</lastBuildDate><atom:link href="https://blog.baifan.site/en/tags/codex/" rel="self" type="application/rss+xml" /><item>
    <title>Codex Keeps Reconnecting? Four Fixes</title>
    <link>https://blog.baifan.site/en/codex-websocket-reconnect-fix/</link>
    <pubDate>Tue, 31 Mar 2026 14:00:00 &#43;0800</pubDate><author>
                    <name>ByF</name>
                </author><guid>https://blog.baifan.site/en/codex-websocket-reconnect-fix/</guid>
    <description><![CDATA[<div class="featured-image">
                <img src="/pictures/posts/codex-websocket-reconnect-solutions.svg" referrerpolicy="no-referrer">
            </div><!-- more -->
<p>Codex talks to the ChatGPT backend over WebSocket by default. If your network path involves Clash, a corporate proxy, cross-border transit, or Cloudflare challenge pages, that long-lived WebSocket gets killed easily — and you end up staring at <code>Reconnecting... 1/5</code> over and over. Turn off WebSocket and switch to plain HTTP streaming requests, and the problem mostly disappears.</p>
<figure><a class="lightgallery" href="/pictures/posts/codex-websocket-reconnect-solutions.svg" title="" data-thumbnail="/pictures/posts/codex-websocket-reconnect-solutions.svg" data-sub-html="<h2>Comparison of the four fixes</h2>"><img  loading="lazy" src='/pictures/posts/codex-websocket-reconnect-solutions.svg'     width="900px"></a><figcaption class="image-caption">Comparison of the four fixes</figcaption>
    </figure>
<h2 id="why-websocket-breaks-behind-proxies" class="headerLink">
    <a href="#why-websocket-breaks-behind-proxies" class="header-mark"></a>Why WebSocket Breaks Behind Proxies</h2><p>The WebSocket protocol starts with an HTTP Upgrade request; only after the server returns 101 does it switch to the long-lived connection. That long-lived connection is exactly where the problem sits — proxy servers, firewalls, and CDN nodes all run timeout policies on idle connections, and Cloudflare&rsquo;s challenge mechanism can inject an interstitial page mid-path. Any link in that chain kills the connection, and the Codex client starts <code>Reconnecting</code>.</p>]]></description>
</item>
<item>
    <title>Multi-Agent Collaboration: Triggers, Topology, and Merging</title>
    <link>https://blog.baifan.site/en/multi-agent-collaboration-engineering/</link>
    <pubDate>Tue, 03 Mar 2026 14:00:00 &#43;0800</pubDate><author>
                    <name>ByF</name>
                </author><guid>https://blog.baifan.site/en/multi-agent-collaboration-engineering/</guid>
    <description><![CDATA[<div class="featured-image">
                <img src="/pictures/posts/multi-agent-collaboration-topology.svg" referrerpolicy="no-referrer">
            </div><p>Conclusion first: multi-agent collaboration is not &ldquo;spinning up a few more model instances.&rdquo; It has to solve task scheduling, context isolation, permission control, state management, and result merging — every one of which is an engineering problem, not a prompt problem.</p>
<!-- more -->
<p>The multi-agent stories on TikTok and Xiaohongshu usually go like this: one agent researches, one agent writes code, one agent runs tests, one agent does review, and the main agent collects results like a project manager. The comments: &ldquo;Whoa, that&rsquo;s insane.&rdquo;</p>]]></description>
</item>
<item>
    <title>A Guide to SSH Remote Development in the Codex App</title>
    <link>https://blog.baifan.site/en/codex-ssh-remote-development-guide/</link>
    <pubDate>Tue, 10 Feb 2026 14:00:00 &#43;0800</pubDate><author>
                    <name>ByF</name>
                </author><guid>https://blog.baifan.site/en/codex-ssh-remote-development-guide/</guid>
    <description><![CDATA[<div class="featured-image">
                <img src="/pictures/note/codex-ssh-remote-featured.svg" referrerpolicy="no-referrer">
            </div><!-- more -->
<blockquote>
  <p><strong>Update note</strong>: This post is based on the Codex App as of May 2026. SSH Remote is still in alpha, and the configuration methods and UI entry points may change with new releases. If anything here has gone stale, refer to the <a href="https://github.com/openai/codex" target="_blank" rel="noopener noreferrer">official documentation</a> for the latest.</p>

</blockquote><p>The Codex App now supports connecting to remote machines over SSH; the feature is currently in alpha.</p>
<p>If you develop on remote servers, train models, or run environments there, this is worth a try. It lets you connect to a remote server directly inside Codex and work in the remote filesystem and shell — no more jumping back and forth between a local terminal, VSCode Remote, SSH, and tmux.</p>]]></description>
</item>
</channel>
</rss>
