BlogMore has been bumped to v2.30.0. This release is pretty heavy on new features, but it does also include one small accessibility tweak too. While looking through some of the neutral feedback from PageSpeed Insights I noticed it mentioned that in some cases I had a category and a tag linked on the same page, where the text of the link was the same. That's pretty common on my blog. For many of the categories (especially things like AI, Coding, Emacs, Python, etc.) I'll also have a corresponding tag. The idea is that categories are essentially sub-blogs within the blog, whereas tags characterise a post.
Given that the same text for different purposes doesn't give much context from an accessibility point of view I've added appropriate aria-label attributes to differentiate these links.
Now for the new features.
The first is another "discover other posts" type feature, that might encourage a reader to venture further into a blog. While BlogMore does support backlinks (as was added back in v2.16.0), I have been thinking that a "related posts" feature would be interesting to add. So now it's added. This is enabled with the with_related configuration option (or the --with-related command line switch) and provides control over how many related posts are shown; the default is three.
The rest of the new features are more admin-based and are all commands on the BlogMore command line. The first is the drafts command which simply lists the filename of all the posts that are in a draft state.
The second new command is links
dump. This is a utility command for dumping a CSV list of all the external links that can be found in your posts, along with the filename of the post the link was found in. This could be useful for all sorts of things; for example writing your own external link statistics tool, or perhaps writing your own external link checker.
Talking of external link checkers: I've also added links
check. This is a bit experimental, but is intended to be a simple checker of all the external links, seeing if they're still out there. By default, when run, it'll check every link it finds and, if there's a problem with it, it'll report the issue. There's a --verbose mode as well if you want feedback on all the links that are working.
It seems like every time I think I'm done adding features, something else is either suggested or pops into my head. I feel like I'm near the end of adding stuff now and should be getting back to refining the code.
Despite the fact that I am not, in any way, superstitious, I kind of have this rule: don't make definitive statements about the absolute happening of an event until it happens; it kind of feels like you're tempting the universe to prank you. I don't always follow it, I know it's kind of silly, but it's there and hard to shake. It's normal. It's human.
Sometimes it happens that it looks like I should stick to that rule.
Eleven days back I wrote about how I was aiming to return to streaming thanks to the fact that I'd once again be the proud owner of a full fibre connection. The thing that, in part, prompted me to write about that was the fact that I'd had an email, that morning, from Openreach, to let me know they'd done some work and that fibre was now available at my property.
The email proudly stated:
Hello Dave,
Congratulations, you can now get Full Fibre on the Openreach network at [my home address].
With Full Fibre broadband, you can choose your package based on the download speeds you'll need from 40 Mbps to 1.6 Gbps. Need some help choosing? Then read our blog before ordering to find out what's a good download speed.
We also have the UK's biggest choice of broadband providers, so you can find a package and price to suit you.
After a button that linked to a site for finding a provider, it went on to say:
After you've placed your order with the provider of your choice, we'll arrange a day and time with you for one of our engineers to connect Full Fibre to your property if it isn't there already.
They may need to drill a small hole in your wall, or they may be able to use the same access point as your current line. Either way, they'll take care of everything and leave you with a broadband that's ready to deal with anything the future brings. You can find out more about what's involved in our handy Full Fibre installation video.
I found this whole email mildly amusing because it was obvious that the work they'd done, that made this possible, will have been the result of the call I made to EE back in March to order fibre in the first place, when it became apparent I was finally able to request it.
So, yeah, when Openreach -- the people who do the cables and stuff -- email you to let you know they've as good as hooked your place up, you know it's a safe bet.
Today was the day. This morning, between 08:00 and 13:00, was the window I'd been given for one of their engineers to turn up and do the hole drilling and the box screwing and all the stuff and then this evening I'd be in a position where, once again, I could download the whole Internet and stream utter nonsense in the highest quality (both creating and consuming). I was looking forward to this.
Everyone in the house was.
The time window started, and kept going, and kept going, and eventually it was 13:00 and nobody had turned up and my house had no extra wires or holes and I was on the phone to EE to ask WHERE IS THE GLASS INTERNET PIPE?!?
Long story short: it wasn't turning up. At all. It appears, at some point in the recent past, Openreach simply cancelled the order and nobody thought to tell me. Openreach (the people who sent me the email 11 days ago) didn't think to tell me. That's the same Openreach who sent me the SMS on the 7th of this month to give me the date of the work; apparently they could not send me an SMS to let me know they'd decided against this.
Of course, it's not all on Openreach. It would also seem that EE knew, from their own system, that the order had been cancelled and they too had failed to email me, message me, call me, something, to let me know I'd be wasting my time clearing half my day to receive them and have the work take place.
So: pretty shitty service all round.
The main explanation I've been given is something to do with a "CBT"1, or something related. This means that it's just not possible to deliver fibre to my address. This is after:
I called to check in March
I was told in March it was possible
Openreach checked things out, said more work was needed, did the work
I literally saw them doing the work, with a trench and barriers and everything
I was emailed by Openreach after the work took place to say they'd done the work and I could have fibre
Even today, even right now, if I go on their site and put in my exact address:
Not "no". Not "eventually". Not "soon". Now. It says now.
At this point this is where I have to say, after making a bit of a mess of all of this, EE have done all they can to smooth things over (especially given there's sod all they can actually do about this). They've compensated me for the missed appointment (despite the fact it wasn't technically missed; it had been cancelled and nobody had let me know), left me to hang on to all the new equipment for if/when the fibre does turn up (meaning I'll have a backup router I guess), and have also compensated me for 3 months of my current copper-based broadband by way of an apology.
On top of that they didn't just brush me off with a "sorry, can't do anything about this", they went to bat for me during a 90 minute phone conversation, chasing up more detailed explanations of what the issue was with Openreach, as we talked. While I don't actually have a solution that is anything other than "you'll have to wait", at least now I have something of a better explanation as to what the actual problem is.
So where does this leave me? Here's what I do know:
The issue that stopped my installation is solvable and, in all likelihood, is the sort of thing that will be solved in the next few months (mention being made of a reasonable range of between a 2 to 6 month wait).
Almost every alternative provider I could go to would have the same issue, as they all work over the fibre that Openreach would install.
From what I can see no provider that isn't Openreach-connected is even the least bit interested in providing fibre.
Openreach have promised that the moment they have a solution to the technical problem that stops the installation, they will call me and arrange to kick things off again (or at least, I guess, let me know it's safe to place the order with EE again).
To be clear too: we're not talking about providing a service to a house in the middle of a field in the middle of nowhere, not even a house in some out-of-the-way village. I live in a reasonably large town, far bigger than the village I lived in before where I did have full fibre.
All of which concludes with: I started today excited by the prospect of fast downloads, fast uploads, and returning to talking nonsense on YouTube while being terrible at playing games; I'm finishing the day with no clear path to having fibre, and a wait time that could extend well into the rest of this year, and perhaps even into next.
I hope it won't be that bad, but I am deflated and disappointed.
Also, on the very remote chance that either Sharon or Neil from EE ever stumble on this blog post: thank you for all the effort you went to to get actual answers for me. It's a shame that it needs to be said, but it is rare these days that you call a customer support line at a service or utility company and get people who are willing and able to work in a way that isn't just following a script.
Well, except for the bit right at the end... I'm fine Neil, I don't need to swap mobile provider. ;-)
While it did appear something had changed for the better yesterday evening, things looked different again this morning. Before getting to work, I did a couple of quick changes to BlogMore; this time Antigravity seemed to use up a bit more quota in the same amount of time as I was working last night, but this time the reset window is much bigger.
I'm sure there's a method to this, but at the moment I'm really unclear what it is.
I guess I could ask it...
Yeah, let's do that.
Can you explain your quota cooldown time for me? Sometimes it seems to count down from 1 hour, others 5. Am I not reading this correctly?
You are reading the quota cooldown correctly! The reason the timer fluctuates between 1 hour, 5 hours, or other times is due to how the rolling usage window and compute-based limits work.
1. Rolling 5-Hour Window
Your usage limit is evaluated on a rolling window (typically 5 hours) rather than resetting at a fixed time of day.
If you see a 5-hour cooldown: You likely used a large portion of your compute capacity very recently. You have to wait for that recent window to clear.
If you see a 1-hour cooldown: You are close to the edge of your rolling window. A batch of high-compute requests you made 4 hours ago is about to fall out of the 5-hour window, which will free up capacity for you in 1 hour.
2. Compute-Based Usage (Not Message Count)
Your quota is consumed by compute rather than a flat number of messages. Compute is affected by:
Chat Length: Every time you send a new message, the model re-processes the entire chat history. Longer conversations consume your quota much faster.
Task Complexity: Tasks like code generation, deep thinking, or agentic workflows require more processing power and consume more quota.
Tips to Manage Your Quota:
Start New Chats: For new topics or tasks, start a fresh conversation. This prevents the model from having to re-read long histories and saves significant compute.
Use Clear, Targeted Prompts: Try to combine instructions rather than sending multiple short follow-up messages.
So, I don't think I'm any wiser after that. The explanation for the 1-hour countdown I saw last night has no connection to anything I did yesterday; I wasn't using Antigravity 4 hours earlier when I checked the quota near the end of that session. Guess I need to go and find and RTFM. Just like we used to in the good old days.
