Thomas Lekanger datagutt

Config for opencode plugin: opencode-openai-codex-auth

For those who might be having edge case behavior, or oddity with start/restart of opencode not retaining last used model properly, or "changing to a different model name" it's likely because of incorrect recommended setup in the opencode.json config file documented in the plugin repo.

You might try the config below, where model id is the key in the models object rather than user-friendly name.

This solved the odd behavior for me with launching opencode and /models slash command - it also provides shorter model names and easier search for all models with "oauth".

Configuration Settings - Implementation Plan

This document serves as a comprehensive development guide for implementing configurable settings in the opencode-openai-codex-auth plugin. It outlines the configuration settings that will be supported for all GPT-5 family models when accessed through ChatGPT OAuth (subscription-based) authentication.

Supported Models

This plugin provides access to the following models via ChatGPT Plus/Pro subscription:

gpt-5-codex - Optimized for coding tasks with built-in code-aware reasoning
gpt-5 - General-purpose reasoning model for complex tasks

Note

Hi, everyone. I've been putting in a lot of work on this over the last few ~~weeks~~ months (sob) and i'm currently underemployed! If you'd like to hire me to do CMS-based work (i focus on Craft and ExpressionEngine but i do some WordPress work as well), please reach out! Alternatively, if you'd like to chip in toward bills & groceries, that's a big help right now!

Updates (Most Recent First)

13 February 2025
8 February 2025
7 February 2025
6 February 2025
23 January 2025

The Rabbit R1 uses a few custom APIs to talk to The Cloud™. Almost nothing happens on-device, and all the AI magic happens on servers.

Consequently, you don't really need the physical device.

TLS Client Fingerprinting

In lieu of an authentication scheme, Rabbit's servers attempt to verify device authenticity by checking the TLS client's JA3 fingerprint, presumably enforced by AWS WAF.

If your TLS client doesn't match an expected fingerprint, you'll get HTTP 403 errors. This fingerprint works:

TC358743 Radxa Zero 3W Notes

Audio

tc358743-audio.dts overlay allows audio to be captured. I2S audio is a 48kHz sampling rate at 32 bit/sample.

Audio Formats

According to gstreamer, the following caps are supported. This seems to indicate that up to 8-channel audio (likely 7.1) capture is supported by the tc35874x driver. I haven't tested more than stereo, and haven't made sure it isn't just mono.

Important: This does not apply to Twitch's Enhanced Broadcasting program, but I have been involved with it for feedback. It should work decently enough.

Ultrawide Streaming Notes

When I am speaking on "ultrawide", I am usually referring to the common aspect ratio stated as "21:9".

I argue there is a case for content creation at 21:9 resolutions. Primarily,

Smartphones are a very common viewing device, and are ever-increasing in lengthier aspect ratios. Many creators already use 18:9 instead of 16:9 for

	POST / HTTP/1.1
	Host: localhost
	User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/142.0.0.0 Safari/537.36
	Next-Action: x
	Content-Type: multipart/form-data; boundary=----WebKitFormBoundaryx8jO2oVc6SWP3Sad
	Content-Length: 459

	------WebKitFormBoundaryx8jO2oVc6SWP3Sad
	Content-Disposition: form-data; name="0"

	#!/bin/bash

	####################################
	#
	# This script is designed for use with the official Belabox images on the supported Rockchip RK3588 boards
	# in combination with the SpotPear 4G/5G M.2 modem hats:
	# https://spotpear.com/index.php/shop/Raspberry-Pi-M.2-4G-5G-GSM-GPRS-EDGE.html
	#
	# The Belabox image, at least on the Orange Pi 5 Plus, defaults available GPIO pins to IN with a pullup.
	# Physical pins 15 and 40 tie to modem POWER and RESET pins with these hats and the defaults will keep

	import { LexicalComposer } from '@lexical/react/LexicalComposer';
	import { RichTextPlugin } from '@lexical/react/LexicalRichTextPlugin';
	import { ContentEditable } from '@lexical/react/LexicalContentEditable';
	import { HistoryPlugin } from '@lexical/react/LexicalHistoryPlugin';
	import { AutoFocusPlugin } from '@lexical/react/LexicalAutoFocusPlugin';
	import { HashtagPlugin } from '@lexical/react/LexicalHashtagPlugin';
	import LexicalErrorBoundary from '@lexical/react/LexicalErrorBoundary';
	import TreeViewPlugin from './plugins/TreeViewPlugin';
	import ToolbarPlugin from './plugins/ToolbarPlugin';
	import { HeadingNode, QuoteNode } from '@lexical/rich-text';

	"workbench.editor.customLabels.patterns": {
	"/routes//+page.svelte": "${dirname(1)}/${dirname}",
	"/routes//+page.server.ts": "/${dirname} [server]",
	"/app//page.tsx": "${dirname}.${extname}",
	"/app//layout.tsx": "${dirname}/layout.${extname}"
	}