Chameth.com - posts like coming-around-on-llms, simple-backups-restic-hetzner but not debugging-beyond-the-debugger, migrating-from-github-to-forgejo, why-you-should-be-using-https

Monthly Meanderings: August 2026

2026-09-01T00:00:00Z

Another month, another edition of “What’s Chris been up to?”. Fun fact: I very nearly published this post with a “[intro]” placeholder here instead of this paragraph, despite proofreading it multiple times. “Yep, that’s where the intro will go, all good”. Now instead we have this weirdly meta introduction.

Website updates and other projects

A few website updates this month, and one of them neatly addresses the “other projects” bit too. First, I’ve added a new fitness page which has some stats and information about my cycling and running. I’ve also added some fitness-related widgets to support that page and these monthly summaries, and a new music one you can see a bit further down.

I’ve also added what I think is quite a fun new feature: a post feed builder that lets you build RSS feeds containing only posts that are semantically similar (or dissimilar) to other posts. So if you want to only hear about my fitness journey you can pin a few of those posts, or if you want to exclude posts that talk about LLMs you can exclude a few of those. It’s basically super-charged fuzzy tags, but it means I don’t have to actually tag things.

I blogged about building a family of single-user services which is where most of my coding energy went this month. Those projects were almost entirely authored by LLMs, and I’m not hating the process. The models have got a lot better at coding, and I enjoyed getting to focus on the bigger picture aspects rather than getting bogged down in details. Rest assured, all the writing on my website is still 100% me. I am the load-bearing seam, here.

Entertainment

Back in March I said ‘I can’t do “what I listened to last month” stats until next month’, and then for the next four months completely forgot about it. Well, not any more! Now I come equipped with some stats about my monthly music habits:

	Album	Artist	Unique tracks played	Total tracks played
1	Fallen	Evanescence	8	40
2	Love, Drugs & Misery	Eva Under Fire	12	32
3	NEON VOID	Sumo Cyco	6	23
4	The Strange Case of…	Halestorm	11	21
5	Coming in Hot	DIAMANTE	9	20
6	Everest	Halestorm	7	20
7	Glory Days	Little Mix	5	20
8	From Zero	Linkin Park	9	19
9	KPop Demon Hunters (Soundtrack from the Netflix Film)	KPop Demon Hunters Cast	7	19
10	No Need to Argue	The Cranberries	6	19

I suspect I won’t show this every month, as it’s probably going to be quite same-y. I, shockingly, tend to play music that I like more than that which I don’t. I’ll usually either put on my “favourites” playlist, or my “daily mix” playlist which biases higher-rated tracks over lower ones. So effectively this just becomes a noisy view over how highly I’ve rated the tracks in an album. Maybe I can control for that, but then I’m not sure what it’d actually be showing… “Here are all the albums I played this month that I don’t usually play because I don’t like them as much as the other albums I’m not showing any more”? It’s a bit wordy. Back to the drawing board with that idea, I think.

I was away for a few weeks this month, including a few days at a small LAN event. Being at a computer gaming event meant that we, naturally, played some board games. Apparently I hit an h-index of 23 from these plays. That’s 23 games I’ve played at least 23 times each. I’ve been at 22 since December last year: obviously the higher the number goes, the harder it is to reach. I also go on and off games (and the whole hobby at times), which doesn’t help on that front. Anyway, here’s ~~Wonderwall~~ the plays for this month:

6 plays
3 plays
3 plays
1 play
1 play

No films this month, but my World of Warcraft habit has picked back up with the launch of the new season. They’ve made Mistweaver Monk, my previous specialisation, a lot less fun to play, so I’m focusing on one of my many alts: a Restoration Shaman:

Level 90

Female Dwarf

Restoration Shaman

309 average item level

Hirameth-Terenas

Professions

Midnight Blacksmithing		42/100
Midnight Inscription		74/100
Midnight Fishing		35/300

Mythic+

Altar of Fangs	+10	23:10	329
Den of Nalorakk	+10	27:36	325
Kings' Rest	+12	28:57	370
Murder Row	+12	28:37	371
Ruby Life Pools	+11	24:28	340
Temple of Sethraliss	+10	30:57	321
The Blinding Vale	+10	24:38	327
Voidscar Arena	+10	22:37	329
Total M+ rating	2711

View on blizzard.com View on raider.io

I don’t quite like it as much as Mistweaver in season 1, but it’s a lot nicer than Mistweaver in season 2. You can actually make health bars move when you press your healing buttons, rather than ignoring half of them because they’re not worth using.

Fitness

My running kick is still going. I’ve “officially” finished the couch-to-5k programme I was doing, and I actually hit 5k on the last day of the programme. I didn’t actually mean to do that: I was saving the 5k run for this week, but by the time I noticed I’d run “too far” it was close enough that I just kept going. I have an actual 5k race coming up this month, which is exciting. Once that’s over I’m planning to work my way up to 10k. I’ve added a few widgets to keep track of some stats:

activities

6h 5m

total time

103.6km

total distance

42.3km

longest distance

🏆️ New PB 1km 2:16 1:52
🏆️ New PB 2km 5:36 4:13
🏆️ New PB 5km 14:44 12:32
🏆️ New PB 10km 36:13 27:21
🏆️ New PB 20km 1:43:43 1:13:24
🏆️ New PB 30km no previous 1:54:25
🏆️ New PB 40km no previous 2:55:52

activities

6h 16m

total time

43.1km

total distance

5km

longest distance

🏆️ New PB 800m 6:20 6:02
🏆️ New PB 1km 7:44 7:36
🏆️ New PB 1 mile 12:43 12:16
🏆️ New PB 2km 15:48 15:16
🏆️ New PB 3km 24:38 23:05
🏆️ New PB 5km no previous 38:40

As well as the running, I did a couple of long (for me) cycle rides, clocking in at around 40 km. It’s a fun loop, but both times I did it I started flagging towards the end. The second time I made sure to eat and drink plenty along the way, and my legs still raised objections about halfway round. My next goal is 50 km which would let me get to the next town over and back but the route has a lot more elevation to go with its increased length, so it’s probably going to be quite a bit more taxing. I’m not sure when I’ll attempt that, as the weather is starting to turn. I was previously bemused when people mentioned “cycling seasons” and switching to indoor trainers. Then I wanted to go out when it was raining, and suddenly I understood. Running in the rain: surprisingly pleasant; cycling in the rain: no thank you.

Around the web

Hacker News In Uncompromised Detail

When I first read the title my gut reaction was “I know everything I need to know about Hacker News, right?”. The title is accurate though. There’s so much interesting stuff, presented really cleanly. It’s a good read.

A proposal for new Netflix content rating icons

Another dry sounding title, another fun article. It starts with a treatise on rating systems and ends with a lovely satirical list of rating ideas.

Find Git commits by commit message text

I like to think I’m relatively well versed in how to use Git. I can do an interactive rebase and everything! This tip from Ham was new to me, though, and is incredibly useful.

Novice Marathon Training Plan

Hal Higdon has a whole bunch of training plans. He literally wrote the book on marathon training. I’ll hopefully be following this plan next year, assuming I manage the 5k, 10k and half-marathon training! This would be the perfect plan for someone who’s run a half marathon a while ago, and is tempted to join me in my “marathon before I’m 40” goal…

Building a family of single-user services

2026-08-27T00:00:00Z

Last month I made and wrote about a personal service to track my workouts and record personal bests. Since then, things have escalated. I now have eight different services running in the same “family”:

Name	Purpose
Collegiate Room	Simple weather overview for my current location
German Mall	LLM broker for use by other services
Gloss White	Weight tracking
Olive Crosses	Central service hub
Pompei Band	Workout and personal best tracking
Speed Carp	Spaced repetition system
Tiger Island	Reading history and library tracking
Typical Horse	Location history and analytics

The names are all anagrams of something related to their function. Finding those anagrams brings me an unreasonable amount of joy. Unscrambling them is an exercise left to the reader. On top of those eight, I currently have four other service ideas sat in my todo list. It’s going to be a big family.

A postmortem on the previous hodge-podge

Most of this functionality isn’t new to me. When I started out playing around with LLMs, I created a “personal data aggregator” that just kept getting things bolted on. I said at the time:

My biggest just-for-me project is a web app that I started to help me aggregate film recommendations. It’s since morphed into a general personal data aggregation service: it deals with data from GitHub, Todoist, Letterboxd, TMDB, Healthkit, and others. It also lets me make re-orderable lists, store recipes, and more. Parts of this could definitely be open sourced, and I might carve them out at some point, but it’s mostly a glorious hodge-podge of things specific to me. Having all these services in one place lets me make quick and dirty automations, for example: when I create a Todoist note on my phone or watch, I often forget to set the due date, so it doesn’t show up in the “Today” view. It was literally a few lines of code to plumb things together so any inbox task without a due date gets set to today automatically.

In a twist that nobody could see coming, it turns out that a “glorious hodge-podge” is actually quite hard to maintain and very annoying to work with. It didn’t help that it had a fairly extensive Svelte frontend and I really am not a fan of JavaScript. I ended up using it less and less just because it wasn’t fun to use or work on, and I didn’t want to waste the limited LLM tokens on doing massive refactors or reworks.

I’ve got almost two decades of professional software development experience under my belt, so you’d think I would have learnt the lessons on how to write maintainable software. Hell, my CV even mentions that as something I’m particularly good at. So what went wrong?

There were a few factors. One of the obvious things to blame is that it was written mostly with LLMs. Most of that blame isn’t very honest, though. In the year or so since, LLMs have definitely got better at writing good code; but I was manually reviewing all the code at the time, and telling it quite carefully what to implement and how to do it. So the buck really stops with me.

I think it’s actually more because it was my first larger project using LLMs. It’s a bit like learning a new programming language. I don’t think the first sizable project I’ve written in any language has ever been any good. You can read and learn as much as you want, but you need to actually run into some problems headfirst to get a grip on how the language works. Or at least I do. LLM coding agents are basically the same deal.

What the LLMs actually did was mask several problems. The architecture wasn’t right for how the service developed. It started out as a single-purpose app and gradually got things bolted on, without any major changes. Everything ended up in horizontal slices: a massive database layer with every query used by every part of the app, a massive HTTP layer, and so on. Working on a single feature became a tap dance all over the source tree. This sort of friction is normally quite apparent when you’re writing code by hand, and at some point it hurts enough that you throw in the towel and do some refactoring. But the LLM will happily plod on without exposing that pain, so the project needed a more active kind of architecture management that it just didn’t get.

The other problem they covered up was how brittle and unmaintainable the JavaScript frontend was. I’m not even sure how I ended up with a Svelte frontend in hindsight. It’s my preferred framework, but I still only reach for it as a last resort when there’s no other way to avoid using one. It seems like there were lots of ways to avoid it here, but I seem to have… well… avoided them. Anyway, each feature got its own slew of Svelte components, without much thought to reusability, shared patterns, or anything sensible. Some of them were just thin wrappers around data supplied by Go, others had vast swathes of logic in them, with no real rhyme or reason as to which way that would fall. It’s the same issue as before: a human would look at it, say “WTF?” and suggest tidying it up; instead, the LLM just gets on with what you tell it to do.

There’s also a big non-LLM factor: one of the primary reasons all of this unrelated functionality got tossed into the same app was that I’d previously worked on a few projects with a microservice architecture and really didn’t like it. My conclusion was they only really worked in large environments where you can dedicate people or teams to working on all the boilerplate that happens from maintaining lots of interconnected projects. Dumping everything and the kitchen sink into one badly architected monolith was, perhaps, not the best rebound from that.

Pompei Band and beyond

When I wanted to implement ~~Strava at home~~ my PB tracking app, it seemed fairly natural to build it out as a new service, rather than bolt it on to the slowly decomposing hodge-podge that was giving off a funny smell. Then when I wanted a weather dashboard, why not do it in the same style as Pompei Band? The same serving architecture, the same page layout… I could even come up with a similar weird two-word name!

Then wouldn’t it be nice if the weather dashboard knew where I was, so it could show the local weather? I could just build that functionality in, but it’d also be a good opportunity to carve out the location history feature from my old service and make a new, shinier one. Then basically every time I even thought about going near the old service, I mentally sketched out a replacement service.

Olive Crosses showing links to the other services

At one point I had the thought that it’d be nice if the services could all link to one another, but I didn’t want to have to touch every service whenever I added a new one. So I made a “hub” service, which maintains the One True Catalogue, and provides a bit of JavaScript the others can all embed to add a navigation sidebar.

So after complaining about microservices and JavaScript, it sounds like I have landed on microservices (or at least miniservices) and JavaScript? Sort of yes, but sort of no. Each service is still its own thing and makes sense independent of the others. There are some cross-service dependencies, but they’re very simple and don’t have the same cognitive or boilerplate overhead as a login service that talks to an authentication service that queries a user manager and so on. And as for the JavaScript, it’s almost exclusively used for progressive enhancement and a few limited client-side visual things like maps and graphs. All of the logic lives in Go, which is a lot easier to maintain and test, and all of the pages are simple Go templates.

Having these services built in a way that I actually like has motivated me to play around a lot more with new features:

My workout tracking app pulls photos from my private Immich server that were taken during workouts, and shows them alongside. Now I can see all my obligatory end-of-run selfies in one place.
The location history app can detect trips away from home, and get an LLM to automatically title them. My most recent, very exotic, trip has the title “A fortnight in Milton Keynes and Coventry”. Each trip gets its own little map, and in the future I want to pull in images like with workouts.
My weight tracking app now exports weigh-ins to Garmin, as it doesn’t fully integrate with Apple Health (it will export its own weights, but not import others, like the ones from my Withings scales). Stupid walled gardens, but thankfully I can fix it myself.
My book tracking app automatically cleans up the titles of books from the nonsense provided by Amazon to something more palatable. “Killing Eve: Long Shot: A twist on obsession, betrayal and revenge from Luke Jennings, author of the TV sensation Killing Eve” becomes “Long Shot (Killing Eve #5)”. It does this by passing the title to an LLM with a bunch of rules.
The hub generates me a snippet of Tailscale configuration that defines the minimal grants needed to allow the intra-service dependencies to work.

The LLM integrations were inspired by my friend Shane who recently demonstrated an inventory tracking app he’d made, which used Haiku to process images of boxes and describe the contents. I’ve dabbled with LLM integration before, and always disliked the process of fiddling with the prompts, and debugging when the LLM gave a nonsensical response. So I built German Mall, which makes it a lot easier. It lets me define a “workflow” consisting of a system prompt, initial message, and expected response format. I can browse past runs, tweak the prompt, rerun them to see the change, all without touching the services using them. Quick iteration loops are the best. German Mall also provides markdown documentation for each workflow, so integrating it downstream is simply a case of pointing a coding agent at the right documentation endpoint.

The “tidy book titles” workflow in German Mall

It’s not all fun and games: having a bunch of services all following the same pattern means you need to do cross-cutting maintenance on them now and then. But that’s surprisingly easy with LLMs. I put all the projects in a common folder, and I launch cross-cutting tasks from that folder. Usually I’ll make the change in one project, and then the cross-cutting task is simply “Look at commit XYZ in ./foo, make the same change to the other projects”.

I’ve also ended up with a shared library used by all the projects to cut down on some boilerplate. That’s normally something I’d resist, especially with personal projects, just because the extra overhead of working in a separate project, managing releases of it, and so on, is a bit annoying. But, again, LLMs can do almost all of that grunt work. They effectively reduce the “cost” of maintaining separate services to a negligible level, leaving me to focus on the more fun aspects like coming up with new names.

Thinking more about backups

2025-11-01T00:00:00Z

The Backblaze logo

Almost a year ago I wrote about how I do backups with Restic and Hetzner. That system has been ticking along well ever since, but recently I had some… thoughts. These backups are all well and good if I accidentally delete a file, or a database gets corrupted, or something, but there are two glaring issues:

Firstly, I’m backing up my Hetzner server to Hetzner cloud storage. If something happens to Hetzner — or my Hetzner account — then all my eggs go down with that basket. Obviously Hetzner are a big organisation and aren’t likely to just vanish overnight, but I’m less confident about my account. Could a false abuse report get it suspended? What if the UK passes even more dumb laws and Hetzner decide it’s easier just to not do business with people here? This is the same sort of concern I have about Google accounts: if you have half of your life in Google Drive and Google Mail, what happens if you comment on a YouTube video, get flagged by an AI moderation process, and your account gets suspended? It’s probably not very likely, but these are things my brain likes to dwell on.

Secondly, the credentials to access the backups sit on each machine that is backed up. If someone malicious gained access to the machine, they’d also have access to delete or tamper with all the backups. It feels a little silly that the same attack could take down both the originals and the backups. There’s no way to avoid that with Hetzner’s S3 implementation, as far as I can tell.

Exploring options

I toyed with the idea of making local copies of the backups, but the only way to avoid the same problems would be to keep them offline and do a manual copy every now and then. I didn’t really want to do that, and was concerned that if I did a monthly offline backup then I stood to lose up to a month of data in the worst case.

I then looked around at other S3 providers. Amazon’s glacier offering is tempting due to its very low storage costs, but you pay for that if you ever want to restore anything. There are also lots of weird pricing edge cases around moving data between storage classes, minimum file sizes, and so on. A much better option is Backblaze’s B2 product. Their pricing is much more straight-forward, and they have an interesting feature that’s particularly useful in this case: lifecycle rules. Coupled with the ability to create API keys that don’t have access to delete files (just “hide” them), this allows for what’s effectively an append-only store.

This works more-or-less out of the box with Restic. Joseph Price has a guide that goes into the setup in a bit more depth. Basically, whenever Restic would delete a file (e.g. during a “forget” or “prune” operation), it instead gets hidden and is only deleted when the B2 lifecycle rules decide it should be. I’ve kept the existing Hetzner S3 backups for now, and just added an extra step to the end of my script: a simple restic copy and a restic forget. B2 actually works out cheaper than the Hetzner storage, as they don’t bill you for a minimum of 1TB storage; my current usage is around $3/month. Not a bad price for some extra peace of mind!

Further Adventures in Music Organisation

2025-09-21T00:00:00Z

I wrote before about how I’d dropped Spotify in favour of locally stored music, but things have advanced a bit since. I had a few issues: Tauon would occasionally manage to lose its database and along with it all my carefully constructed playlists and song ratings¹, and the experience on my phone was not very fun.

I had to manually sync the music by plugging my phone in to the computer, and sometimes it just refused to mount the right partition. I don’t think there’s really a good way to debug an Apple phone not behaving properly when connected to a Linux desktop. Then I started wanting more than one playlist synced², and trying to find a way to make that work just broke me.

I spent a while looking at different ways of hosting the music centrally. Plexamp gets lots of good reviews, and I’ve used Plex a fair bit. I set about spinning up a Plex server, and just could not get it working. The server ran fine, served the web interface, but would neither associate with my account nor run standalone. The docs were contradictory and there was very little useful logging. After a lot of frustration, I stumbled across mentions that Plex block running on Hetzner. I assume that’s the cause of my issues, although I have no way to know for sure. I use Hetzner for all my servers and other hosted services, but Plex have decided I can’t run the self-hosted software that I have a lifetime subscription for there. What the actual fuck?

I could have probably worked around the arbitrary restriction, but I didn’t want to throw more time down the drain. Instead, I set up Navidrome, an open source music server. It supports the Subsonic protocol, which means you can use a whole slew of different clients with it (or even write your own). It also means there’s a nice way to get data in and out of it programmatically, which I recall being a bit of a fight with Plex.

Syncing and organising

All my music lived on my desktop, but now I wanted it on my server. At first I just used rsync to copy everything up. I’d maintain a local “master” copy, and periodically shove the changes to the server³. That quickly got old, so I set up Syncthing to keep the two folders in sync. That worked… for a while.

Concurrently, I was looking at improving the organisation of my music. It was mostly organised by some Go programs I’d thrown together to automate the importing, with no real validation of metadata or anything else. Some albums got split up into multiple folders because the tracks had different artists (and didn’t have an album artist set); some artists ended up with multiple folders with slight spelling or case variations. It was upsetting.

I’d used MusicBrainz Picard before to fix some issues, but I didn’t really like the UI, especially when trying to do bulk actions. The main alternative is beets, which describes itself as “the music geek’s media organiser”, and is entirely command line. I was intrigued.

I started playing around with beets, and quickly noticed a problem. Every time I changed a metadata tag in a music file, Syncthing had to upload the entire file. I was frequently changing tags across the whole library as I got beets set up how I wanted, and Syncthing was handling it by uploading gigabytes of files for every minor change. I was already a bit unhappy with having the content duplicated in two places, so now I was using a command line organiser I figured I could just get rid of my local copy and move everything to the server.

I set up a Docker container for beets, and then wrote some incredibly hacky shell scripts so I could run beet locally on my desktop and it would SSH to the server over Tailscale and exec into the container, passing the arguments along. Then I did one final sync of the music library, got rid of Syncthing, double checked I had a backup and deleted all of my local music.

Bears, Beets, Battlestar Galactica

Beets is amazing. It has a vast array of plugins that can do almost anything you could want with a music library, and the command line workflow works really well for me. It’s very well documented, and all the individual parts are pleasingly simple and easy to understand.

Here’s what it looks like when importing some new music:

Beets importing an album

If it doesn’t get a perfect match then it shows the closest matches, and summarises what’s different about them (missing tracks, different names, etc), and lets you decide what to do. Aside from the metadata matching, it’s doing a lot of things under the hood that aren’t necessarily apparent. It:

Looks up the genre from Last.fm
Analyses all the tracks and writes ReplayGain metadata to them
Fetches album art
Checks all the files to make sure they’re actually playable
Scrubs any existing metadata tags

It also maintains its own database, and you can query against it. The query language is both simple and quite powerful, like the rest of beets. As an example:

$ beet ls artist:"Linkin Park" year:2025 length:2:00..2:30 
Linkin Park - From Zero - Casualty

Almost all the other commands also let you use the query syntax, which makes the whole tool really powerful. Want to delete all country tracks that you added last month? No problem. Redownload all the album art for a certain band? Easy. You can even do smart playlists using the filters.

Actually playing music

With all this organisation, I’ve not actually mentioned one tiny detail: how I actually play music now. Navidrome has a web UI, which is perfectly usable, but I don’t really want my web browser involved as it makes balancing sound levels tricky, and getting media keys working is a pain. Thankfully there are loads of Subsonic clients. I’ve tried several, but eventually settled on Feishin on the desktop. It’s very pretty:

Feishin’s ’now playing’ screen

What attracted me to it, though, was its built-in support for Navidrome’s smart playlists. These aren’t even properly exposed in Navidrome’s web UI yet, but Feishin has a visual editor that lets you create and edit them. I ended up with an identical system to the playlists I had in Tauon: a “blacklist” playlist which are tracks I never want to play, a “favourites” playlist, and then an “everything” playlist which is the entire catalogue minus the blacklist.

On iOS I’ve settled on Arpeggi. It’s not actually on the App Store yet, but available via TestFlight. It’s one of those really nicely polished apps that are obviously a labour of love, not just out to do the minimum possible to get your money. It can cache songs offline, and automatically download entire playlists, and supports all of the standard Subsonic features like rating, reporting plays back to the server, and so on.

One unexpected benefit of using a central server is that it handles reporting plays to Last.fm and ListenBrainz instead of the clients. I don’t think I’ve ever bothered to configure my mobile clients to do that before, and now it just works automagically. I’m relying on those services more for recommendations and discovery, as that’s something you lose out on when self-hosting.

Making bad decisions about bitrates

With all the moving, copying, and organising, I started thinking about how large the collection was. The songs were all in different formats, depending on when and where I’d picked them up, and I couldn’t tell the difference between them. I did a test and transcoded an MP3 file down to 128kbps, and still couldn’t tell the difference. So armed with that sample size of 1, I transcoded the entire library and saved so much space.

I don’t remember which track I did that first test with, but it must have been a very unlucky pick. I quickly started to notice the distortions caused by the low bitrate. It was particularly bad in any song with a lot of treble, and started to really annoy me. I started a painful process of reimporting things in their original format. Beets came in clutch again, both with the import process (if you import a duplicate album, it asks if you want to replace the original, and shows the format and bitrate of them for comparison), and keeping track of what was left to fix (beet ls bitrate:..128000).

Having started paying more attention to the sound quality, I think I’ve been nibbled on by the audiophile bug. I’ve been trying to get new music in FLAC format where possible. I’m pretty sure I can’t tell the difference between a decent bitrate MP3 and a FLAC, but maybe if I got a better DAC and some nice headphones…? Someone please hide my credit card!

As for the library taking up a lot of space, I now realise it’s a price worth paying. I might need to swap out the server to one with more storage at some point in the future, but it’s generally worth upgrading every few years with rented dedicated servers anyway, as you often get more for the same amount of money. Next upgrade I’ll just make sure there’s an appropriately-sized disk instead of focusing entirely on RAM and CPU.

Writing more code

Naturally, this whole process spawned several side projects. When browsing albums in Navidrome, I was a bit upset that the album art wasn’t all a consistent size. I thought about scripting something to crop them consistently, but then I had a better idea, and jewelcase was born. It takes the album art, crops it down to a consistent size, and then renders it inside a jewel case. It applies some slight effects, like adjusting the colours, rounding the corners, and tweaking the edges so it looks a bit more real. I don’t know why⁴, but every time I see the effect it gives me a little spark of joy.

Album art, before and after jewelcase is applied

The other project is BASS, a tool that uses the Subsonic API to grab information about my music catalogue, and then generates a “Daily Mix” playlist. It uses a system of weights to select tracks semi-randomly, biasing towards favourite tracks, those that haven’t been played much, and a few other criteria. This gives me a nice balance between having my favourites on repeat, and exploring the full library at random.

All the weights in BASS are customisable, so I can tweak it to my heart’s desire, and anyone else can also run it and configure it entirely differently to me if they want to. I can’t imagine I would’ve been able to do that if I were using Plex!

I was running a version from git as the stable release had fun dependency issues on Arch, so it’s possible this wouldn’t be an issue in normal use. I also started backing up the database, but it’s still annoying to have to restore it. ↩︎
A “favourites” playlist for me, and a more “family friendly” playlist for when I’m playing music out loud that has a bit less screaming/swearing/etc. ↩︎
One of the reasons for starting this was being annoyed by the periodic sync to my phone, obviously it makes perfect sense to introduce a new, different periodic sync. ↩︎
Nostalgia? A little bit of OCD? Both? ↩︎

Finding an awkward bug with Claude Code

2025-06-30T00:00:00Z

The many times Claude thought it was right…

I recently encountered a bug in one of my projects that I couldn’t immediately figure out. It was an issue in Centauri, my reverse proxy. After its config was updated, I noticed¹ it stopped serving responses. Looking at the logs, I could see it was obtaining new certificates from Let’s Encrypt for a couple of domains, but I’d designed it so that wouldn’t block requests (or so I thought). After a few minutes of confusion, everything went back to working.

It felt like an issue with locking, but a quick glance didn’t show me anything obvious. I decided to throw the problem at Claude Code and see how it did. With some guidance² it managed to identify the cause, but it was a bit of a journey to get there. I’m going to share the prompts and responses, as it was an interesting process.

The initial prompt

I thought the issue might be quite obvious, and I’d just overlooked it. Centauri isn’t that complex a project, after all. So I gave Claude a fairly minimal prompt to set it off:

> Hello! Please examine this codebase. I have noticed an issue that when a
  certificate is being renewed, the application seems to not serve any other
  requests. I suspect there is a misplaced lock somewhere.
 
  Can you see what's happening? Think very hard.

Claude Code has special hardcoded triggers to engage “thinking” mode, which makes it take more time to think about alternatives. The keywords are: “think”, “think hard”, “think harder”, and “ultrathink”. I managed to not quite get the right incantation here, and only enabled the lowest level³.

I’ll omit all the responses where Claude is “thinking” (talking to itself), or decides to make todo lists then cross items off them then add different items, and so on. Its responses get fairly lengthy; I won’t judge you too harshly if you skim over them. Its first response was blessedly brief:

● I found the issue! Looking at the certificate manager code, I can see the
  problem:

… and then it went back to thinking and reading files, because it had neither found the issue nor could it see the problem. Ho-hum. Some time later it came back with:

● I found the issue! The problem is in certificate/manager.go:53-54:
  
  m.store.LockCertificate(subject, altNames)
  defer m.store.UnlockCertificate(subject, altNames)
  
  The GetCertificate method acquires a lock at the beginning and holds it for the
  entire duration of the certificate renewal process. This includes:
  
  1. Contacting the ACME server
  2. Solving DNS-01 challenges (can take minutes for DNS propagation)
  3. Obtaining the certificate
  4. Getting OCSP staple
  5. Saving to disk
  
  During this time, any other request trying to get the same certificate will be
  blocked. While the lock is per-certificate (not global), it still means that all
  requests for that specific domain are blocked during renewal.
  
  Let me check if there are other places where this might cause blocking:

And it then proceeded to do even more thinking, checking files, etc, until it concluded with:

● I found the root cause! The issue is actually worse than just a
  per-certificate lock. Here's what's happening:
  
  The main blocking issue is in proxy/manager.go:133-144:
   
  func (m *Manager) CheckCertificates() {
      m.lock.RLock()  // ← Acquires read lock on the entire manager
      for i := range m.routes {
          route := m.routes[i]
          // ...
          m.updateCert(route)  // ← This can take MINUTES for ACME renewal!
      }
      m.lock.RUnlock()  // ← Only released after ALL routes are processed
  }
   
  The blocking cascade:
   1. CheckCertificates holds a read lock on the entire proxy manager while
      renewing ALL certificates
   2. Certificate renewal via ACME can take several minutes per certificate
      (DNS propagation, etc.)
   3. Every incoming request calls routeFor (proxy/manager.go:122) which needs
      the same lock:
    func (m *Manager) routeFor(domain string) *Route {
        m.lock.RLock()  // ← BLOCKED until CheckCertificates completes!
        match := m.domains[strings.ToLower(domain)]
        m.lock.RUnlock()
        // ...
    }
  
  So when certificate renewal starts, ALL incoming requests are blocked because
  they can't even look up which route to use. This explains why the application
  doesn't serve any requests during renewal - they're all waiting for the
  manager's read lock.
  
  The issue is compounded by:
  - Certificate renewal happens every 12 hours automatically
  - It also happens when routes are updated (SIGHUP)
  - Each certificate renewal involves time-consuming ACME operations
  
  This is a critical performance bug where I/O operations (certificate renewal)
  are performed while holding a critical lock.

This doesn’t actually follow on from the earlier response, it’s completely flipped onto a different lock being the issue. Amusingly, it’s nearly right here, but it’s highlighting this code for completely the wrong reason.

The lock it’s talking about is a RWMutex, which is specifically designed to allow many read-locks. Everything it’s pointing out are read locks, so they cannot block one another as it described. The response Claude has given sounds very confident, seems appropriately technical, but is in fact complete rubbish. This is one of the big issue with all LLMs at the minute, and it makes me despair at the idea of people “vibe coding” things when they don’t know enough to push back against nonsense like this.

Course correction

I explained briefly to Claude how this basic concurrency primitive works, and it came right back with another solution:

> But that's a RW Mutex. You can hold many read locks concurrently.

● You're absolutely right! I apologize for the confusion. With a RWMutex,
  multiple readers can hold the lock concurrently. Let me trace through this
  more carefully.
  
● Task(Analyze updateCert method)
  ⎿ Done (8 tool uses · 20.0k tokens · 1m 11.9s)
  
● Excellent analysis! You're right about RWMutex allowing concurrent readers.
  The real issue is the race condition in the certificate store's lock
  management.

  Looking at certificate/store.go:82-91:

  func (j *JsonStore) lockFor(subjectName string, altNames []string) *sync.Mutex {
      key := strings.Join(append([]string{subjectName}, altNames...), ";")

      if mu, ok := j.locks[key]; ok {
          return mu
      } else {
          mu = &sync.Mutex{}
          j.locks[key] = mu  // ← Concurrent map write!
          return mu
      }
  }

  This is a classic concurrent map access bug. When multiple requests hit the
  same domain during certificate operations:

  1. Multiple goroutines call lockFor() simultaneously
  2. They read/write to j.locks map without synchronization
  3. Go runtime can:
    - Panic with "concurrent map writes"
    - Corrupt the map structure
    - Block indefinitely if map internals get corrupted

  This explains the blocking behavior - it's not the RWMutex, but rather a race
  condition causing either panics or deadlocks when the map gets corrupted
  during concurrent certificate operations.

  The fix would be to either:
  1. Add a mutex to protect j.locks map access
  2. Use sync.Map instead of a regular map
  3. Pre-initialize all locks at startup

I do appreciate when me stating a basic fact is called out as “excellent analysis”. Definitely doesn’t make me feel like I’m having smoke blown up my ass.

I think the issue it’s describing here is actually a problem⁴, albeit one that’s unlikely to be hit. But it’s definitely not the one we’re looking for. Claude even describes the possible consequences of the bug, and they don’t match what happened at all.

Maybe logs will help?

While Claude was chugging away, I’d been looking into the issue as well. I had logs from when it happened, and figured Claude may be able to glean something from them too. The first thing I’d noticed is that I wasn’t logging when a process finished, so I’d already added that to the code base, hence the note so Claude doesn’t get itself confused:

> That may be an issue, but it's not the one I was looking for. I've found logs
  from the time it happened. Note that a few logs have been added to the
  codebase since (so we can't tell from the logs when ACME or OCSP processes
  *finished*, just when they started). Here are the logs:
  
  {"time":"22:40:53.187887976Z","level":"INFO","msg":"Received signal, updating routes...","signal":1}
  {"time":"22:40:53.19947532Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:40:53.199507942Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:41:09.048465968Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:41:09.048482309Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:41:17.419299795Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:41:17.419325744Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:41:23.238027386Z","level":"INFO","msg":"Received signal, updating routes...","signal":1}
  {"time":"22:41:29.994330646Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:41:29.994353329Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:41:43.658794811Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:41:43.658819548Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:41:57.635325513Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:41:57.635347515Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:42:10.52439779Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:42:10.524417107Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:42:23.159430249Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:42:23.159452171Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:42:36.347407326Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:42:36.347433295Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:42:52.544628775Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:42:52.544653993Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:43:25.409579107Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:43:25.409602842Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:43:43.819479448Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:43:43.819502041Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:43:54.358957563Z","level":"INFO","msg":"Renewing certificate", ...}
  {"time":"22:43:54.358979355Z","level":"INFO","msg":"Starting ACME process to obtain certificate", ...}
  {"time":"22:44:06.180278128Z","level":"INFO","msg":"Renewing certificate", <big list of alt names>}
  {"time":"22:44:06.180302585Z","level":"INFO","msg":"Starting ACME process to obtain certificate", <big list of alt names>}
  {"time":"22:45:03.830331922Z","level":"WARN","msg":"Failed to connect to upstream","error":"context canceled", ...}
  {"time":"22:45:03.830528134Z","level":"WARN","msg":"Failed to connect to upstream","error":"context canceled", ...}
  {"time":"22:45:03.832388931Z","level":"WARN","msg":"Failed to connect to upstream","error":"context canceled", ...}
  {"time":"22:46:10.225854865Z","level":"WARN","msg":"Failed to connect to upstream","error":"context canceled", ...}
  {"time":"22:46:10.488432434Z","level":"WARN","msg":"Failed to connect to upstream","error":"context canceled", ...}
  {"time":"22:46:10.488439397Z","level":"WARN","msg":"Failed to connect to upstream","error":"context canceled", ...}
  {"time":"22:46:30.617614536Z","level":"WARN","msg":"Failed to connect to upstream","error":"context canceled", ...}

I’ve cut down the logs a bit to remove the specific domains, simplify the timestamps, and remove a bunch of other cruft. The key points are there were two SIGHUPs received, and the last certificate before everything started breaking covered 6 different hostnames.

Claude then went through a phase of periodically shouting “Eureka!” then deciding it hadn’t actually found anything yet:

● Now I see it! The key insight is in the timing and the "context canceled"
  errors. Let me trace through what's happening:
  
● Ah, now I see what's happening! Looking at the logs more carefully:

  1. 22:40:53 - First SIGHUP received, routes updated
  2. 22:40:53 to 22:44:06 - Multiple certificates start renewing (14 certificates!)
  3. 22:41:23 - Another SIGHUP received while renewals are still in progress
  4. 22:45:03 onwards - "context canceled" errors start appearing

  The issue is that SetRoutes is being called AGAIN (at 22:41:23) while the
  previous CheckCertificates() goroutine is still running and renewing
  certificates. Let me check what happens in this scenario:
  
> (The context canceled errors are clients timing out because centauri wasn't
  proxying properly)
  
● Ah, now I understand! The "context canceled" errors are from clients timing
  out because Centauri wasn't proxying their requests. This confirms the
  blocking issue.

  Let me check how incoming requests actually get their certificates:
  
● Now I found the real issue! Looking at the timeline and the code:

  1. 22:40:53 - SIGHUP triggers SetRoutes() which:
    - Calls loadCertificate() for each route
    - Sets route.certificate to the existing certificate
    - Starts go m.CheckCertificates() in background
  2. 22:41:23 - Another SIGHUP while certificates are still renewing
    - SetRoutes() is called AGAIN
    - Creates NEW Route objects with route.certificate = nil initially
    - Replaces the old routes in m.routes
    - The old Route objects (with valid certificates) are replaced!

  The critical issue is in proxy/manager.go:42-65:

  func (m *Manager) SetRoutes(newRoutes []*Route, fallback *Route) error {
      // ... validation ...

      for i := range newRoutes {
          route := newRoutes[i]  // These are NEW Route objects!
          // ...
          m.loadCertificate(route)  // Try to load certificate
      }

      m.lock.Lock()
      m.routes = newRoutes  // REPLACES all routes!
      m.lock.Unlock()
  }

  When the second SIGHUP arrives:
  1. New Route objects are created
  2. For domains currently being renewed, GetExistingCertificate might fail or
     return expired certs
  3. These routes get route.certificate = nil and CertificateMissing status
  4. CertificateForClient returns nil for these domains
  5. TLS handshake fails → clients can't connect → "context canceled" errors

  The fix would be to either:
  1. Prevent concurrent CheckCertificates runs
  2. Copy certificates from existing routes before replacing them
  3. Make certificate renewal truly independent of route management

Midway through it had started searching for “context canceled” errors in the codebase, which doesn’t make much sense. That’s what happens when a client gives up waiting, so the corresponding backend request is terminated. You won’t actually find “context canceled” anywhere in Centauri, because it’s a feature of the Go standard library. I gave it a little nudge to try to stop it rabbit holing.

As far as I can tell, what it’s talking about in this response isn’t an issue. I guess it’s possible that there’s a race condition whereby a route would be replaced and end up with an old version of a certificate that was just being renewed, but it wouldn’t cause an issue in practice; it’d just get updated next time the certificates were refreshed.

There’s no way for routes to get a nil certificate in this scenario, as far as I know. But I don’t have the unfounded confidence of an LLM, so I simply said:

> I don't follow why the certificate would be nil?

Attempt the third

I expected Claude to just explain its reasoning, but it apparently didn’t have any reasoning so set off on another voyage of discovery:

● You're right to question that. Let me trace through this more carefully.

● Good point! Since GetExistingCertificate doesn't acquire locks, it should
  return the existing certificate even during renewal. Let me dig deeper:
  
● Now I see a potential race condition! Here's what could happen:

● I found it! There's a critical race condition that explains the blocking:

  The Race Condition

  1. Background renewal starts: CheckCertificates() → updateCert() →
     GetCertificate() acquires lock and starts ACME renewal
  2. SIGHUP arrives: SetRoutes() is called, which for each route calls
     loadCertificate() → GetExistingCertificate() → store.GetCertificate()
  3. The race:
    - store.GetCertificate() returns a pointer to the certificate in the slice
    - Meanwhile, the renewal completes and calls SaveCertificate()
    - SaveCertificate() calls removeCertificate() which modifies the slice while
      it's being read
    - This slice modification (append(j.certificates[:i], j.certificates[i+1:]...))
      can cause:
        - The pointer returned by GetCertificate to become invalid
        - Slice bounds issues
        - Memory corruption
  4. The result:
    - GetExistingCertificate might return corrupted data or nil
    - Routes end up with certificate = nil
    - TLS handshakes fail
    - Clients timeout → "context canceled"

  The Timeline Confirms This

  - 22:40:53 - First SIGHUP, starts renewal of 14 certificates
  - 22:41:23 - Second SIGHUP arrives (30 seconds later) while renewals are still running
  - 22:45:03 - First timeout errors (4 minutes after first SIGHUP)

  The 4-minute delay matches ACME renewal time. The second SIGHUP's SetRoutes
  likely read certificates while they were being modified by the first SIGHUP's
  renewal goroutines.

  This is a classic concurrent slice modification bug - no synchronization
  between readers (GetCertificate) and writers (SaveCertificate/removeCertificate).

Once again we have a very confident and technical answer that does not explain the symptoms we’re looking for. It’s also mostly rubbish again. GetCertificate and SaveCertificate are only called by code that is holding a lock for that certificate; they won’t interfere with one another. There may, again, be a small concurrency issue if different certificates are handled in parallel, but it’s definitely not the cause of our current problems.⁵

Working through these explanations and debunking them was annoying me at this point. I decided to give it once last chance, and used the “ultrathink” shibboleth:

> So there may be a concurrent modification issue, but that doesn't explain the
  symptoms. If a TLS handshake failed it wouldn't result in the clients timing
  out. Likewise if there was any kind of corruption there'd be a panic, not a
  period where it didn't work and then started working again. Engage ultrathink.

Fourth time lucky

I’m going to include a piece of the thinking here because it amused me so much:

✻ Thinking…

  Oh! I need to think about this differently. Let me trace through what happens
  when a request comes in:

Apparently it takes “ultrathink” to actually work through the problem logically? Amusingly it did actually get there:

● You're absolutely right. Let me think more carefully about this...

● EXACTLY! That's the issue. Looking at the timeline:

  1. 22:40:53 - First SIGHUP: CheckCertificates() acquires READ lock, starts
     renewing 14 certificates
  2. 22:41:23 - Second SIGHUP: SetRoutes() tries to acquire write lock, blocks
     waiting
  3. Incoming requests call routeFor() for route lookup, but Go's RWMutex blocks
     new readers when a writer is waiting (to prevent writer starvation)
  4. 22:45:03 - Clients timeout because requests can't even get past route lookup

  The key insight is Go's RWMutex writer starvation prevention: when a writer
  is waiting, new readers are blocked even though the current lock holder is
  also a reader.

  So the cascade is:
  - CheckCertificates (read lock) → certificate renewal takes minutes
  - SetRoutes (write lock) → waits for read lock to release
  - routeFor (read lock for every request) → blocked by waiting writer

  Result: All incoming HTTP requests hang at route lookup, never reach TLS
  handshake or proxying logic. Clients timeout waiting for any response
  → "context canceled".

  This perfectly explains:
  - No panics (no corruption)
  - No immediate TLS errors (never gets that far)
  - Requests hang then timeout (blocked on lock)
  - Eventually recovers (when certificate renewals finish)

  The fix would be restructuring to avoid holding the manager lock during slow
  certificate operations.

We’re back to the RWMutex again, but this time it’s dropping knowledge on me not the other way around: if there’s a writer waiting, then new readers are blocked. This does indeed perfectly explain the symptoms, and was something I’d overlooked. The write lock is only held briefly to update some struct members to prevent it from blocking the readers, but this behaviour coupled with the long-running read lock ends up doing that anyway.

The fix

After all this work it’s very tempting just to ask Claude to fix it, but I had almost no confidence it’d be able to maintain any of the concurrency requirements given how much it flailed around with bad explanations. But in the interests of science, I asked it to try. Here’s what it came up with:

   // CheckCertificates checks and updates the certificates required for registered routes.
   // It should be called periodically to renew certificates and obtain new OCSP staples.
   func (m *Manager) CheckCertificates() {
+    // Create a snapshot of routes to avoid holding the lock during slow certificate operations
     m.lock.RLock()
+    routes := make([]*Route, len(m.routes))
+    copy(routes, m.routes)
+    provider := m.provider
+    m.lock.RUnlock()

+    // Process certificate renewals without holding the manager lock
-    for i := range m.routes {
+    for i := range routes {
-      route := m.routes[i]
+      route := routes[i]
 
       if provider == nil {
         route.certificateStatus = CertificateNotRequired
       } else {
         m.updateCert(route)
       }
     }
-    m.lock.RUnlock()
   }

   // updateCert updates the certificate for the given route.

That’s about what I expect. It definitely fixes the exact issue described, but it’s a bit… sloppy. Routes are now being updated when the lock isn’t being held, which is a change in semantics. It also doesn’t address the underlying issue that requests can be blocked if there’s a pending writer, and pending writes can be blocked by readers. A better approach would be to allow these operations to happen without blocking, maybe by using an atomic pointer to an immutable slice. I guess I’ve got some coding to do!

As for Claude: while the journey was frustrating, I think trying to figure this out by myself would have been even more so. It’s one of those things where everything looks right to me, and I’d have to go down a fairly long chain of checking my assumptions to find where I’d gone wrong.

There’s definitely a lot of room for improvement in coding LLMs: being able to estimate their own confidence level instead of stating everything as absolute truth would go a long way. I imagine there’s also a lot of benefit of having one LLM vet the responses of another; that’s sort-of how thinking mode works, but it doesn’t seem to go far enough to stop it outputting rubbish. It’ll be interesting to see how they develop in the future, anyway.

read as “I got spammed by a bunch of monitoring notifications” ↩︎
read as “Me repeatedly telling it that it was talking rubbish” ↩︎
If only we had some kind of language model technology that could understand this kind of thing. ↩︎
I sense some fun times with Go’s race detector in my near future ↩︎
The most likely outcome from these concurrency issues is Centauri panicking, which isn’t great but would only interrupt ongoing connections before it restarts and starts serving traffic again. Much less problematic than the “block for five minutes” behaviour I’m trying to fix. ↩︎