Chameth.com - posts like break-everything-fuzz-testing, escaping-spotify-the-hard-way but not debugging-beyond-the-debugger, 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		41/100
Midnight Inscription		72/100
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 2:17 1:52
🏆️ New PB 2km 5:34 4:13
🏆️ New PB 5km 14:51 12:32
🏆️ New PB 10km 36:00 27:21
🏆️ New PB 20km 1:43:33 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 5:56 6:02
🏆️ New PB 1km 7:35 7:36
🏆️ New PB 1 mile 12:28 12:16
🏆️ New PB 2km 15:35 15:16
🏆️ New PB 3km 24:32 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…

Monthly Meanderings: March 2026

2026-04-01T00:00:00Z

Since last month’s update I’ve been unpleasantly reminded that I’m middle aged, through the medium of a dodgy knee. There’s nothing quite like not being able to stand up without groaning to underscore that you’re not young any more. The ongoing game of “will this seemingly mundane activity make my knee go funny again?” is a delight to play, too. I’m great at it.

Website updates

Two new blog posts this month: the longest way to represent a date is a short thought experiment on absurd date formats, and modern CSS is fun goes through some neat new CSS features I’ve used recently for this site.

I did some design tweaks this month: headers now have a blue background behind them¹, and a lot of components have been redesigned to have a consistent style. You can see that component in action in the new “now playing” widget I’ve added:

VersaEmerge — Redesign Me Fixed at Zero Scrobbled 2h 41m ago

Instead of each component defining its own styles (which were mostly copied and pasted), there’s now a single class that handles the drop shadow, border, background colour, and the optional title. It also applies a consistent format to elements that are clickable: they use the blue accent colour for their borders, and have a glow effect shown on hover.

The now playing widget is part of a larger bit of work I did on importing some music stats. I’m pulling in the data from my Navidrome instance. A new music page shows my most listened albums and artists. Navidrome doesn’t store a complete play history, just the last play and the count, so I can’t do “what I listened to last month” stats until next month.

Other projects

Other than a minor bug-fix update to contempt, my Dockerfile templating/updating tool, I’ve not done much on my other open source projects. I’ve got a bit more work to do finish migrating all my repositories from GitHub to my private Forgejo instance. I’ve also been thinking about mirroring my public repositories to Codeberg so there’s a non-GitHub way to access them.

Entertainment

I apparently only watched a single film in March:

The Substance

2026-03-18

I really didn’t get on with this. It’s too long for what it is, and over-the-top in a way that just didn’t work for me.

Demi Moore and Margaret Qualley were great, but nothing else really was. The cinematography and sound design were too affected, the plot was pretty shallow and obvious, most of the body horror fell into the uncanny CGI valley for me.

It’s not completely without merit: there were around 40 minutes in the middle where I was really into it, but that’s not really enough given it’s closing in on a 2.5 hour runtime.

There’s something to be said for the message it’s presenting about women in Hollywood, too, but it was very heavy handed. Dennis Quaid’s character is even called Harvey; it’s not so much a subtle nod as a sledgehammer to the face.

Instead of films, I’ve been watching a bunch of TV. After devouring The Pitt last month, I struggled to find something to fill the hole it left. I settled on catching up on Chicago Fire and Chicago P.D.. They’re both mostly about getting things done without personal drama becoming the primary focus. They’re not quite as grounded as The Pitt, but at least they’ve not completely gone off the deep end like 9-1-1 where the first responders end up in space somehow?

I’ve also watched the first two episodes of SNL UK. I didn’t have very high expectations, and it gave me a pleasant surprise. Both episodes so far have some hilarious sketches, and are obviously written by British comics with the typical darker, more sardonic humour that separates us from the USA.

Last but not least, board games! I spent a weekend at a tabletop/LAN event with friends, so got to physically play some games for a change. I also kept up with some turn-based games on Board Game Arena, as usual.

6 plays
4 plays
4 plays
4 plays
3 plays
3 plays
3 plays
2 plays
2 plays
2 plays
2 plays
2 plays
1 play

Around the web

Warranty Void if Regenerated

Some really cool speculative fiction about a future where all software is written by LLMs, and the social effects that may have. Unfortunately the story itself is written with an LLM, and that becomes painfully obvious about a third of the way in. By that point I was already hooked, though.

My 2-step process for AI-free blogging

Speaking of LLM-generated text, this short piece by Manuel Moreale made me laugh. I’m by no means anti-LLM, but I really hate people publishing the output like it’s their own work. It breaks the social assumption that the writer put more effort in than the reader, and makes me wonder how much is hallucinated.

25 Years of Eggs

An interesting applied use of coding agents. I’m a sucker for personal statistics. I have no explicit desire to keep my receipts, or generate graphs of my egg consumption, but seeing the graphs makes me question that. The journey to get there is a great read, too.

I made a one-page notebook

The clever paper folding is interesting, but I really like some of the small touches on the page. There’s a nice little “in reply to” callout providing context at the top of the page, you can click to rotate the image further down, and there’s a details element containing a textual version of it. It has that great ‘small web’ vibe of someone who really cares about what they’re doing.

Workers who love ‘synergizing paradigms’ might be bad at their jobs

I haven’t read the full paper, but the summary given by the article is equal parts interesting and amusing. They developed a “Corporate Bullshit Receptivity Scale”, what more is there to say?

It’s meant to resemble painter’s tape, but I’m not sure quite how well it works. ↩︎

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? ↩︎

Escaping Spotify the hard way

2025-07-25T00:00:00Z

I realised my media consumption was too close to this for comfort.

For the longest time I used Spotify for all my music needs. And I listen to a lot of music: sometimes actively, but mostly passively as background noise. I cancelled my premium subscription last December, and stopped using the service entirely. Why? There’s a bunch of reasons.

Let’s talk about the money first. Spotify launched at £9.99/month, and stayed that way for over a decade. Then in 2023 it went up to £10.99/month. That’s probably fair: the economy was in the toilet, and they haven’t changed their price in so long. Then in 2024 they upped it again to £11.99/month. Hmm. The service they were providing me didn’t improve in that time. I didn’t want audiobooks in my music player, I didn’t want an AI DJ that spouted inane comments at me. Paying them more money to do things I didn’t want seemed silly, and the money that actually goes to the artists is both so small and gets split in such a convoluted way that it’s not worth even thinking about.

My bigger concern was how uninvolved I became in choosing what to listen to. I leaned hard on their algorithmic playlists like “Discover Weekly” instead of manually curating playlists. But they ended up developing this weird feedback loop where it kept playing a country band¹ that I didn’t particularly like, but also didn’t dislike enough to skip. That acted as positive reinforcement, and they kept coming up everywhere. There were definitely ways to solve that by changing how I used Spotify, but the realisation that I was basically just consuming whatever was fed to me made me want to try something completely different. So I decided to go back to buying music instead. Which is where things got… complicated.

Getting some MP3s will be easy, right?

I figured with the money I was no longer giving to Spotify, I could just buy an album or two a month and slowly build up a nice music collection. I already had some music kicking around from before the streaming era, so there would at least be some variety in my listening while I got started. Where to buy music from, though?

Amazon used to do DRM-free music, but as far as I can tell it all got folded up into their own streaming service. Some smaller bands are on Bandcamp, but you won’t be able to grab Taylor Swift’s latest album from there. Qobuz have a good catalogue, but some of the stuff is pricey². It’d be cheaper to buy CDs and rip them like it was 1998 again.

I finally stumbled across an unlikely answer: the iTunes store³. This is still somehow separate from the behemoth of Apple Music, and if you fire up the iTunes software you can indeed buy reasonably priced, DRM free music. For comparison, 1989 (Taylor’s Version)⁴ is £12.89 (plus delivery) on CD from Taylor’s official website, £16.79 in CD quality from Qobuz, and £12.99 from iTunes.

Now, I use Linux, so using iTunes isn’t exactly easy. I ended up running a virtual machine with Windows on it. Every time I wanted to buy an album, I’d boot the VM, open iTunes, search for the album, press the buy button, enter my password, wait for it to download, copy all the files to a shared drive, and then back on Linux copy those files into my music directory. Smooth, right? But it worked. Earlier in the year I switched computers, though, and didn’t want to bother with the VM rigamarole. Spoiler alert: I didn’t make things any simpler.

Do you guys not have phones?

I tried a lot of things to avoid setting up a Windows VM again. I’m pretty sure I went through most of the 7 stages of grief in the process. I tried to get Apple Music to work, because that was obviously where all their development was focused, but you can’t actually buy music there (at least not on any version I could run on Linux). I tried running iTunes under Wine, but it just wouldn’t work. I looked into third-party clients, but unsurprisingly they didn’t go anywhere near payment flows.

I eventually realised that I have an Apple device in my pocket. After a bit of searching, it turns out there is actually still an iTunes app for iOS⁵. I bought an album⁶ to see if I could exfiltrate it. I connected my phone to the computer, paired it with idevicepair and then mounted the storage using ifuse⁷. Looking around, I could see a bunch of m4a files, and I could play them. Success!

Except… the file names were random hex strings, and they had no metadata. Yuck. I grabbed a copy of MusicBrainz Picard and had it sort out the mess. I stuck with this process for a while, but matching albums in Picard was sometimes a pain. MusicBrainz does a great job of figuring out what the tracks are, but it struggles to tie those back to a single edition of an album. I wasn’t aware how many subtly different versions of albums there were until I had to manually find the one iTunes had given me. Not fun. Eventually I got so fed up with this that I did something about it.

Plists all the way down

Armed with an instance of Claude Code, I set out to see if I could write some Go code to import the files properly. There were plists in the directory with the m4a files, and I know enough to know that they’re where all the juicy metadata lives on iOS. Maybe we can parse them and do something useful?

There’s a nice plist parser written in Go already, so I got Claude to write a program to dump the contents of one of the many plist files in the directory. Inside was all the metadata for one of the tracks. Yay! Just one small problem: there’s no way to link the plist file to the audio file. There’s one plist file that has a real name, though: StorePurchasesInfo.plist. I had Claude translate it to JSON and found that it contained a data field with a bunch of binary data. Huh.

I thought this was probably a dead end, but stuck the base64’d data into CyberChef and fiddled around a bit to get a hexdump of the binary. Six characters jumped out at me: bplist. I went back to Claude and suggested this might be a plist-in-a-plist scenario. Claude then got very confused because it couldn’t understand where the base64 was coming from⁸. After some LLM-induced suffering, I eventually got the contents of the inner-plist, and for each track it had a list of the audio file, the metadata, and the album art. Yay!

With the data figured out, it was fairly simple to get Claude to write code to parse everything and link them together, and after that move the files into their correct place in my library. I also had it take the metadata from the track’s plist file and write it into tags on the m4a so my media player didn’t have to understand Apple nonsense. I looked around for a Go library to do this, but couldn’t find one supporting m4a files, so ended up just shelling out to exiftool.

As a bonus, I made the tool automatically make a temporary directory and use ifuse to mount the phone, then unmount it when it’s finished. So now all I have to do is plug my phone in, and run import-music on the command line⁹. It’s a very nice quality-of-life upgrade that I probably wouldn’t have bothered with if I didn’t have Claude Code to speed the process up¹⁰.

Sometimes I actually play music too

With all this talk about buying and sorting music, I almost forgot about the most important bit: listening! I use Tauon, and it looks like this:

Tauon, showing off a wide range of different music in my library.

I tried a bunch of different music players, but Tauon hits the sweet spot of being simple enough to use but capable enough in the right places. I particularly like the playlist generators. My “Music” playlist just auto-imports all music in my “Music” folder, then I have a “Classical” playlist with a generator of s"Music" g"classical" auto. That makes it use the “Music” playlist as a source, filter on tracks that have “classical” in their genre, and automatically update when the base playlist changes¹¹. The “Disliked” playlist does the same but filters on rating: s"Music" a rat=0.5 auto. That takes all tracks (a) from the Music playlist, then filters it down to only those that have a rating of 0.5 out of 5¹². Finally, the “Normal” playlist imports everything from “Music” that’s not in one of the others. It sounds a bit clunky, but it works well in practice and I like the way it works.

Tauon in general just seems to work the way I’d expect it to, which is refreshing. You can just start typing anywhere to search for a track, hit enter, and it starts playing. It has keyboard shortcuts for other operations, and standard features like reporting to last.fm and other sites.

Tauon also supports transcoding and copying tracks to a music player or a phone. I use this to sync my main playlist to my phone. I’ll give you a minute to just bask in the glory of the rube goldberg machine I’ve created to move music from my phone, to my computer, and ultimately back to my phone. This does actually serve a purpose, though: it lets me control which tracks are on my phone. I don’t have to deal with excluding genres or tracks I dislike on the phone in addition to the computer. In the future I might opt to just sync a subset of my tracks to keep the storage size down. I’m telling you it makes sense! Stop looking at me like that!

Paying Attention Pays Off

I mentioned one of my aims for getting away from Spotify was to feel less like I was just consuming whatever’s in front of me. The corollary to that is how do you discover new music without an algorithm to feed it to you? I’ve ended up subscribing to a few blogs, paying more attention to music-related news, and being more aware of songs on the radio and from other sources.

When I find a song I like these days, I tend to listen to a few other tracks on the album (via YouTube, normally, as it’s the least friction) and decide if I want to buy it. When I do, I sit down and listen to the whole thing in order. It’s a radically different experience to just hearing a song now and then. There are themes and connections between tracks that you just miss if you listen to songs at random. Of course, you could do that on Spotify, but I don’t think it really lent itself to it.

My favourite example of this is my rediscovery of Linkin Park¹³. I’m of the age where they were around as I was growing up. I knew a couple of their big hits but younger-me wasn’t that into rock¹⁴, so I didn’t pay them much attention. Then I caught Up From the Bottom on the radio, and from there ended up buying and listening to all of From Zero. It’s an amazing album. The Emptiness Machine has become my favourite song: not only is it a great tune, performed well, it’s also a fantastic introduction to a new era for the band and to Emily Armstrong as the new vocalist. The rest of the album then builds on it to show off what they can do.

I’ve since gone back and reconnected with a lot of Linkin Park’s older albums, too. And from there discovered a lot of other rock bands I really like. Could this have happened with Spotify? Maybe, but it seems unlikely. It had me in a country-band-I-can’t-remember filter bubble, it seems pretty unlikely it’d drop some Linkin Park on me out of nowhere. And the passivity that came along with it would have meant that I probably wouldn’t have paid enough attention when I heard it from elsewhere.

Would I recommend that everyone runs out and cancels their Spotify subscriptions? Eh, probably not. If it works for you, that’s fine. Discovering recursive plists is fun for me, but I appreciate it’s not everyone’s cup of tea. What I would recommend is being a bit more deliberate in your choice of music. Don’t just tune in to a random playlist, or let the ‘DJ’ decide what to play. Find something, and actually listen to it. Then recommend it to me. I want more music!

I can’t even remember the name of the band, that’s how much I was into them. ↩︎
And they’re annoyingly deceptive about it. All the prices are “From £x”, where x is the discounted price you’d get if you paid them £15/month. ↩︎
I’d link to it, but… there isn’t a website. That’s not how things were done in the 1990s, silly. ↩︎
I don’t know why I’m so hung up on Taylor Swift in this post. ↩︎
Again, unrelated to the Apple Music app. ↩︎
It probably wasn’t a Taylor Swift album. Maybe. ↩︎
The Arch wiki has a useful page on this (of course). ↩︎
We were translating the plists to JSON, and if you serialise a byte array to JSON in Go it ends up as a base64-encoded string. Claude was then adamant it needed to base64 decode the binary plist. It did not. ↩︎
I just had the sudden realisation that I can probably automate running the import-music tool whenever I plug my phone in using systemd… ↩︎
I feel like I say that a lot lately. ↩︎
I like classical music, but it’s a mood, and I’m often not in that mood. ↩︎
I basically use this to filter out those introduction/bridge tracks on albums that are just talking and not singing. ↩︎
Surprise! My library isn’t actually just Taylor Swift songs. ↩︎
Younger-me was a dumbass, in some ways. ↩︎

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. ↩︎