:dev-http {3000 {:root "public"
:proxy-url "http://localhost:7000/my-backend-service"}}
03 March 2026
I’ve broken my reverse proxy configuration in shadow-cljs multiple times, so I need a reminder for myself.
I have the server-side api running in a container, and the CLJS is running in shadow-cljs in dev mode.
With a :proxy-url set,
shadow-cljs will forward
any request it can’t match
with a file
in the root
to the other server.
This helps avoid Cross-Site-Request-Forgery failures
in the browser
during development.
:dev-http {3000 {:root "public"
:proxy-url "http://localhost:7000/my-backend-service"}}
The important part is to ensure the URL lacks the trailing slash. With the slash, I see lots of not-found errors from the backend server for everything but the default index.
19 February 2026
The Gemini AI will make some pretty good guesses about how a 3rd-party API may work. It is good at searching the internet, but when APIs have changed across versions, the old and new docs and examples it’ll find can confuse it. In a dynamic language and environment you’ll not spot these errors until runtime.
To combat the ambiguity and to give the AI agent more power to solve its own problems, ask it to add some tests around the code that uses the API. (In my case, the API is the XTDB client API.) Once it has a way to execute the code through tests, it’ll quickly start figuring out where it’s made mistakes and start running its own experiments to observe errors, search for fixes, and applying those fixes around the codebase. I exhibit the same pattern when I’m doing it by hand.
The tests also give you, the human, an easier entry point to evaluate the code the AI generated. If the tests look gnarly, you know to suggest refactorings to improve the architecture and make it easier to test. When the AI has the tests passing, and the test code is easy enough to read, then you can have a closer look at the application code to refine and keep that maintainable too.
09 February 2026
Gemini CLI
is getting even stronger
for Clojure code.
The clojure-mcp
is part of that power:
it’s exploring the code and fixing up syntax
quicker now.
In addition to writing code, it’s been good at listing and implementing optimizations and refactorings to improve the code when asked.
I’d still like to remind you to ask the AI to explain itself. It’s still our responsibility to understand what it’s doing and to question its decisions, just like we would to get the best we can from any other teammate. It’s our opportunity to learn and understand too from a very comprehensive summary of all the internet searches I used to need to do for myself.
19 January 2026
The Lenovo IdeaPad 5 has a CoPilot where it should have
a Control Key.
The key simulates a combination of keys,
so normal ways of mapping the key
(udev/hwdb.d on Debian) do not work.
keyd can hook the key,
though,
and present another virtual keyboard device.
There are inexpensive USB adapters
that allow plugging a CW key or Iambic paddle
into the computer
for use with vBand
or other games.
The adapter presents as a keyboard,
and the paddles show up as additional Left and Right Ctrl keys.
If you are running keyd on the machine,
its default behavior of mapping Right Ctrl to be Left Ctrl
(which I guess lots of people find useful)
will interfere
and cause both sides of the paddle to trigger the same dit or dah.
Fortunately, we can undo this broken behavior to get the key working again.
Create /etc/keyd/default.conf:
[ids] * [main] # copilot key leftshift+leftmeta+f23 = rightcontrol # keep right ctrl as it is. keyd by default remaps it to left ctrl for some reason rightcontrol = rightcontrol
Restart keyd: systemctl restart keyd
After the mappings have been applied,
you can be observe it with evtest.
You’ll also see the key working in vBand.
I wouldn’t have needed keyd if it wasn’t for
needing to remap the useless CoPilot key.