AItention

Modifiche

Che cosa è cambiato in ogni versione

Lo stesso testo che legge nella finestra di aggiornamento dell'applicazione — qui per intero e senza installare nulla. La più recente in alto. La versione corrente, con la sua somma di controllo, sta nella pagina di download.

Le note esistono in tedesco e in inglese; le altre quattro versioni linguistiche di questa pagina mostrano il testo inglese.

1.21.1

Stages now expand in the strip as well

In 1.21.0, every click in the bottom strip opened GitLab — including a click on a stage. In the pipeline window, the jobs expanded instead. Two views, two answers to the same gesture.

Now both behave the same: clicking a stage shows its jobs, clicking anything else in the row opens the pipeline in GitLab.

1.21.0

Click pipelines — and expand their stages

Clicking a row in the pipeline strip opens it in GitLab. Not a small arrow at the edge, but the whole row: if you see a running pipeline and want to know what it is doing, you aim at what you are reading. The icon appears as soon as your pointer is over the row.

And stages now have an inside. In the pipeline window, a click on check, test or build expands that stage's jobs — with their names and their own status, the way GitLab shows them. They are fetched when you expand: asking for every pipeline up front would be twenty requests per project and cycle for something nobody opened.

Only addresses belonging to your instance are opened. A pipeline's address comes from your GitLab instance's answer — it is a claim, not a fact. AItention opens it only if it points via https:// at exactly the host name you entered. Anything else stays a display.

1.20.2

The strip now shows your projects, not just your branches

Running pipelines were missing whenever no session sat on their branch. If you work on a branch that has not been pushed yet, while three pipelines are running in the same project on main and on your colleagues' branches, the strip stayed empty. It asked per branch; the question “what am I waiting for?” is per project.

AItention now asks, for every project one of your sessions sits in, about the whole project — plus the pushed branches of your sessions, with separate limits so that one cannot crowd out the other. The session row stays strict: only what belongs to its own branch appears there. Showing someone else's pipeline as “yours” would be a false statement, not a caveat.

Nothing changes for notifications: a failed run still reports only for the state you pushed.

1.20.1

Running pipelines no longer vanish with the session

If you are waiting on a pipeline, you are usually waiting after the session has finished. That is exactly when AItention stopped asking: the query was tied to the session's state rather than to the working copy — once it ended, the project and its running pipeline were gone from the display. It now keeps asking as long as a session sits in the working copy, dormant ones included (for up to twelve branches; whatever is being worked on comes first).

“Faded” now means “stale”, not “you are behind”

A pipeline running on a commit other than the one you pushed used to be shown faded — which made the most interesting pipeline the quietest one. It is the one being waited on. Only a finished pipeline that does not belong to your state stays faded: a completed answer about something else. The caveat does not disappear — the tooltip still names the commit, now with the fitting sentence (“Running on a different state”).

Notifications stay strict: a failed run on a foreign commit still reports nothing.

1.20.0

Your machine's load — a second strip at the bottom

A session that is making no progress looks exactly like one that is computing. If the machine sits at 99 %, nobody is waiting on Claude — and that is what the new strip below the list shows: the load across all cores, and expanded, a history over 12 or 24 hours plus the three programs consuming the most right now, with icon and share.

It sits below the pipeline strip, stacked, and each of the two expands on its own — in the main window and in the menu bar panel, with one state for both places. The history is recorded as it happens: one point per minute, 24 hours, and per minute the name of the largest consumer. It is still there after restarting the app.

The measurement comes from the system kernel — number, name and consumed processor time per process. Not the command line, which can contain credentials, and not the path, which would reveal what you are working on. None of it leaves your machine. The figures are for the whole machine; Activity Monitor counts per core and therefore shows higher values for the same situation — the tooltip says both. Processes of other users do not reveal their times: the total load includes them, the program list does not. Can be switched off under “Application” → “Processor”.

Two usage fixes

Two accounts became four after a week. Accounts with no reported name are told apart by the reset time of their weekly window — but that moves on every week, and at the reset an account split in two. They are now told apart by the cycle, not the date. This would have hit everyone a week after first running 1.16.0.

“No readings in the last five hours” while the account was running. The history chart read only the file Claude Desktop writes; if you work in Claude Code, that file stops carrying fresh numbers at some point. They now come from both sources. And the pipeline strip's collapse arrow is finally a button — it used to look like one without being one.

1.19.0

Pipelines in the main window now — with their stages

At the bottom of the window, where usage sits at the top: a strip showing what is still open. Collapsed, one line with the pipeline you have been waiting on longest; expanded, the list, and below it — separated by a seam — the most recently finished ones. The same strip is in the menu bar panel, with one state for both rather than two.

What is new is what a pipeline contains: its stages — check, test, build, deploy — as a row of coloured dots, each with its own status. A stage only counts as failed once nothing in it is still running: while a job can still save it, its dot keeps breathing. Alongside that, the session's application icon, the start time, and a sentence instead of a bare number — “Running for 6 min”, “Took 4 min”, “Waiting 6 min for approval”.

Filter by project, and a tidier panel

If you work across several projects, you can filter the strip down to one — the filter applies in both the window and the panel, and survives a restart. And the panel has room again: the buttons at the bottom are now icons with tooltips, the same ones as in the window's toolbar. Before, four labels crowded 380 points and pushed the content past the edge.

All of this appears only once you have entered an instance under “GitLab pipelines” and stored a token. It is off as shipped, and then the app is as it was.

1.18.0

The pipeline now speaks up by itself

Until now you had to look. When a pipeline fails, AItention tells you — as a notification, with a number on the Dock icon, and, if you have entered a forwarding address, there as well. Mute silences the notification but not the forwarding: wanting quiet is not the same as wanting your automation stopped.

Once, not on every poll — and only for the state you pushed. A pipeline on a different commit wakes nobody; it says nothing about your working copy. Starting the app stays quiet too: whatever had already failed before AItention looked shows up red in the list, but it does not knock after the fact. A notification about an event you cannot date would be worse than none.

The menu bar panel scrolls — and has two tabs

Long lists used to be cut off. The panel showed five waiting sessions and four working ones; the sixth was missing — and that is often exactly the one you are looking for. It scrolls now, and the caps are gone.

There is also a second tab with the pipelines per project and, below it, a strip for whatever is still open: collapsed, one line with the oldest; expanded, up to four, and then that scrolls too. And wherever a bare number used to stand, there is now a sentence: “Running for 6 min”, “Took 4 min”, “Waiting 6 min for approval”.

1.17.0

You now see how the pipeline stands for your state

Waiting for a GitLab pipeline often means waiting a while — and the list only showed that the session was busy. AItention now shows the pipeline's status on the row of the session it belongs to: running, passed, failed, waiting for approval. For a running pipeline the tooltip names the job currently in progress; for a finished one, how long it took.

The match is made through the state you pushed, not through the project name. For that AItention reads the remote, the checked-out branch and the two commit ids from your working copy. If the pipeline ran on a different commit than the pushed one, it is shown faded and names that commit; and a branch you have not pushed yet gets none shown at all. A figure that belongs to another state says nothing about this one.

And every run of a project in one window

The marker on the row answers one question: how your own state is doing. The new “Pipelines” window answers the other — what is running in the project at all, including branches nobody here is working on. The branches one of your sessions is on are highlighted.

This is off as shipped, and it stays off until you set it up. Under “GitLab pipelines” you enter your instance and store an access token with the read_api scope; the token is kept in your keychain and is never displayed. What then goes out is exactly two items: the project path and the branch name. No prompts, no file names, nothing from a commit. The query is made once per branch — twelve sessions in the same project are one request. The full list is in the “About” window under “Data sources”.

1.16.0

The usage figures are now current

The percentages could be hours old without saying so. Measured on 06/10/2026: the display read 86 % while 93 % had in fact been used — the source the figure came from was more than three hours old, later ten.

AItention now reads the figures where Claude Code passes them on with every prompt: in the status line. That costs no network access and no password, and it is set up together with the hooks — you do not need to find a switch. If you already have a status line of your own, AItention leaves it alone and shows you the line you can append.

If you work with several accounts, you now see them apart. Until now the same account occasionally appeared twice — once with the right figure, once with one from the day before. AItention now groups the figures by the moment an account's weekly window resets; that moment differs per account and stays fixed for a week. Where an account cannot be established, its bar stays unnamed rather than carrying the wrong name.

What AItention reads is unchanged: plan fields, the usage figures the provider reports itself, and the organisation identifier that assigns the figures to the right bar — no address, no name, no user identifier. The full list is in the About window under “Data sources”.

1.15.1

Kleinere Berichtigungen

Der Verlauf zeichnete aus einem einzelnen Messwert eine unsichtbare Linie und sah damit kaputt aus, wo nichts kaputt war — ein Verlauf braucht zwei Werte, und das steht jetzt dort. Und wenn ein Konto keine Zahlen hat, nennt der Satz daneben beide Wege, auf denen es welche bekommt.

With several accounts the figures appeared under the wrong name

If you run Claude Code with two accounts through the same configuration location — say one in the Claude desktop app and one in your editor — you could, since 1.15.0, see one account's usage under the other account's name. AItention reads which account a session belongs to from that session's own record; it is not stored at a fixed position there, and in almost every running session it was therefore not found. AItention then fell back to the configuration file — which both instances share.

The identifier is now found reliably, and where it cannot be established, nothing is shown at all. A figure under the wrong name is worse than no figure.

Usage is also there from the start now: the status line through which Claude Code reports usage is set up together with the status hooks, in the same step you confirm anyway. If you already have a status line of your own, it is left untouched.

And two smaller corrections: a trend drew an invisible line from a single reading and so looked broken where nothing was — a trend needs two readings, and it now says so. And when an account has no figures, the sentence beside it names both ways of getting some.

1.15.0

Several Claude accounts, several live bars

If you work with more than one Claude account, you have so far seen figures for only one of them. The reason was not AItention: the file the percentages came from is no longer written by newer versions of the Claude desktop app, and the remaining source covers exactly the account Claude Code is signed in to.

AItention can now read the figures where Claude Code already passes them on: in the status line. Claude Code continuously hands a status-line command how full the two rate-limit windows are — per running instance, and therefore per account. You can set this up with a button in Settings under “Application”. It costs no network access and no password; AItention only reads along with what Claude reports itself. If you already have a status line of your own, AItention leaves it alone and shows you the line you can append instead.

And if you run Claude Code with its own configuration location — for a second account, say — enter that location in the same settings. AItention reads the plan and the reported usage there.

Neither source changes what AItention reads: plan fields, the reported usage figures and the organisation identifier that assigns the figures to the right bar — no address, no name, no user identifier. The full list is unchanged in the About window under “Data sources”.

1.14.1

Quota bars now appear with multiple accounts too

Since 1.14.0 AItention reads usage where Claude records it itself. If you use more than one Claude account, you could not see those figures yet: the strip at the top of the main window decided from the history file whether there was anything to show — and when that file stood still, it said “not measured” even though the new values were already there.

Each bar now decides from the value it actually shows. If it is current, it is drawn; if it is old, it is dimmed with the time it was measured beside it. Only where nothing current exists at all does a sentence replace the number — a zero that looks like a measurement is worse than an honest gap.

A second account stays without a figure as long as Claude does not report its usage. AItention does not read which account a report belongs to — so it does not attribute it to one it cannot vouch for.

And with several accounts the figure now lands on the right bar. Until now AItention assigned the reported values to whichever account was measured last — a guess that is wrong as soon as the Claude desktop app is signed in to a different account than Claude Code. AItention therefore now reads the identifier of the organisation the values belong to. What is read from the configuration file is stated, as before, in Settings and in the About window under “Data sources”: the plan fields, the reported usage figures and that organisation identifier — no address, no name, no user identifier. The identifier only assigns; it is never displayed and never sent.

1.14.0

Quota now reads what Claude itself reports

Until now AItention derived both quota windows from Claude Desktop's history file. That worked while the file was being written — and it is not always: after a change of subscription it simply stops, and the bars went empty even though Claude itself still showed figures.

AItention therefore also reads usage where Claude records it itself. That brings three things: the bars stay filled when the history file goes quiet; the reset time of both windows is now stated exactly instead of estimated — for the weekly window the estimate was once several days off; and if you work on credit beyond your plan, the plan section shows how much of it this month has used, in your account's own currency.

What AItention reads is stated in Settings under “Application”. From the configuration file it takes only the plan fields and the usage figures the provider itself reports — no address and no identifier. Nothing has been loosened there: the same file contains both, and what was not read before is still not read.

If a figure stops being updated it is marked as stale and carries the time it was measured — as everywhere in AItention. A number without a date is not an answer.

1.13.6

The menu bar view is legible again

The menu bar popover carried the same details as the main window — rate, time remaining, forecast and window end. At 380 points wide that wrapped across several lines.

It now shows only the label, the bar and the percentage. Everything else is unchanged in the main window and the usage window, where there is room for it. The switches for paging and for the trend remain in both places.

1.13.5

The weekly window: the time remaining is right again

The display read “5 days left” while the quota was due to reset in three — a day and a half off.

The reason. AItention detects a reset by the value dropping from a noticeable height to almost nothing. Until now every such drop counted, and the most recent one was used. But a single month produced five of them, and three had other causes — a switch to paid credit, a second subscription.

Now the rhythm decides. A drop only counts as a reset if there is a second one a week apart. If there is none, the display shows nothing rather than a figure that is demonstrably wrong.

There is a price, and it belongs here: after a fresh install it takes until the second observed weekly boundary before a day count appears again. We prefer a missing figure to a false one.

1.13.4

No figure where nothing was measured

A second subscription used to show “0 %” — which reads like a measurement. In truth nothing had been measured at all.

The reason lies with the source. Claude Desktop only records usage for the account it is currently signed in to. A second subscription appears there only once you sign in with it — until then there is simply nothing to show.

Instead of a zero you now get the fact: “Not measured since … — Claude Desktop only measures the account it is signed in to.” In the trend, curves without data points are dropped from the legend rather than sitting there as an entry with no line.

With a single subscription nothing changes.

1.13.3

Page through your accounts instead of “Combined”

The “Combined” heading is gone again. It promised a summary and showed the figures of a single account — a label that was simply wrong.

Each set of bars now carries the name of the account it belongs to, and you page through them with ← and →. ↓ lays all accounts out underneath each other, ↑ takes it back. The trend has arrows of its own, so you can hold one account's curve beside another's bars.

And an empty chart now says why it is empty. The curve covers the last five hours; an account idle for days has no point in it. Previously you saw bare axes, which looked as though something had broken.

With a single subscription nothing changes: no heading, no arrows.

1.13.2

The strip in the main window now expands

Two levels, both remembered: one click on the people icon shows your accounts separately, one click on the chart icon puts the trend underneath. Wherever you leave the switches, they stay — including in the menu bar popover, which shows the same strip.

Collapsed it reads “Combined”, with the figures of the account you are currently working with. Not a sum of the percentages — 8 % on one subscription and 40 % on another are shares of two different quotas; adding them would produce a number that means nothing.

An account that has been idle for days says so. It keeps its row, but dimmed and with the reading's age beside it, rather than showing an old figure that looks current.

With a single subscription nothing changes: no heading, no accounts switch.

1.13.1

Two subscriptions, two sets of bars — and you name them

Since the last release AItention keeps two Claude subscriptions apart. Now you can see both: two sets of bars in the usage window, the account you are currently working with first.

With one subscription nothing changes. A heading above a single bar would be a distinction without a second side.

The heading is also the name field. Click into it and type “Personal” or “Work” — the name stays on this Mac and is never sent anywhere. Without a name the accounts read “This account” and “Other account 1”.

There is a reason you name them yourself: the only name Claude keeps is one we must not show you. It contains your email address, and AItention promises you under “Application” that it reads neither address nor identifier from that file. A name you choose is the better one anyway.

1.13.0

“Done” now really means done

When a session starts subagents — for a code review, say — and its own turn ends, the row used to read DONE while those agents were still running. We measured up to three minutes of the display claiming there was nothing left to do.

It now says the session is waiting for its agents. A question to you still takes precedence: if the session is waiting for an answer, that is what you see.

A session that could not start stands out

If a session fails before it begins — a folder that no longer exists, for instance — the row carries a warning mark and the reason appears in the tooltip. Previously it looked like any other.

Two subscriptions are no longer mixed

If you use two Claude subscriptions, usage and quota were computed from both at once. A single reading from the other account could shift the time window by more than three hours. AItention now uses the account you are actually working with.

The time remaining is more accurate

Until now we inferred your quota reset from the readings. That goes wrong when much time passes between two of them — overnight it was an hour and a half off from what Claude itself showed. Where Claude states the time, we now take it.

And under the hood

The rule about which files AItention reads at all now applies equally everywhere — including places that previously checked only the file name.

1.12.1

A hardening under the hood

This release changes nothing you can see. It sharpens how AItention decides which files it reads at all.

AItention reads the records that Claude Code and Codex write to your disk. Which files count as such records is now decided in one single place in the program instead of six. A planted file that merely poses as a record is turned away just as strictly everywhere — previously three of those places applied a weaker standard.

Exploiting it would have required someone who can already write inside your user folder. We still think it is worth a release: a rule that holds in one place and not in the next is not a rule.

A check in the build now makes sure it stays that way.

1.12.0

Codex sessions can be turned off

In Settings under “Application” you now decide whether AItention shows your Codex sessions. From this release the default is off.

With the switch off, AItention does not even read Codex' files: no session in the list, none in “Previous sessions”, none in a counter and none in a group total. Usage and quota come from Claude either way.

Hidden sessions come back when you carry on

“Stop showing” used to last forever. Anyone who cleared away a dormant session and later resumed it searched in vain — it stayed hidden even though it was running again.

Now the hiding ends as soon as the session runs again. The button does what it promises: tidy up, not hide for good.

Updates no longer get stuck

With a window open — the introduction on first launch, for instance — an update could stall silently: “Ready to install”, one click, and then nothing. Closing the window later did not catch up, and you stayed on the old release without noticing.

This mostly affected people who had just installed AItention. Fixed.

Smaller things

The button in the hook notice responds at once instead of after a few seconds. Usage figures now say when they are old, and stop projecting into the future. And at larger text sizes nothing gets cut off in the switches any more.

1.11.4

A crash when resuming sessions

Resume a session while it is still running and, for a moment, there are two processes for the same session. AItention could not cope with that and quit — without a message, the window was simply gone.

This is fixed. Of two processes for the same session, the one started last now counts — the one you are actually working in.

The same pattern sat in a second place: loading your federations. There, too, a duplicate entry can no longer end the app.

1.11.3

The installer window

The name in the disk image window sat at the top — where the Finder places items that have no fixed position. Anyone who shows hidden files saw the image's helper folders sitting over the lettering. The name is now at the bottom.

Nothing changes in the app itself.

1.11.2

A maintenance release

Nothing changes that you can see. This release tidies up in places you only notice once they are wrong.

Help texts point at the right path

The instructions for removing the status hooks and for running diagnostics named the “Applications” folder by a fixed name. They now read it from the app itself — rename it or keep it elsewhere and you still get the path that applies. The same goes for the note about how hook entries are marked: it now names the marker that is actually written.

Fewer duplicated truths

The address of the update feed sat in four places: once where it is queried, and three times in texts describing it. Now it sits in one place and the texts read it from there. What you see is the same as before — it just cannot drift apart any more.

1.11.1

“Stay awake” now keeps the display awake too

The button used to keep only the Mac from sleeping — the display still went to sleep, and the screen lock followed. From the outside that looks like a switch that does not do what it says, and that is exactly how it was reported to us.

Both now stay awake while the switch is on, so the lock does not kick in either. A closed lid still sleeps; no app can prevent that. As before, the switch is not remembered: it ends when you quit AItention, so nobody keeps their Mac awake all night because they forgot it the day before yesterday.

You can read back what was run

If you entered a program under “Run on state change”, the About window now shows what actually ran: time, state, the command with its arguments — and, more importantly, the reason when one could not start. That is what the list is for: the case of “I entered something and nothing happens”.

The list covers the current run of the program and is deliberately not saved — command arguments can contain paths from your projects, and those do not belong in a file that sits around for years.

Fixed

The “Access” section under “About” still said AItention only reads files. Since it became possible to start a program on a state change, that was too narrow. It now says what is true — and that only what you entered and approved individually will run.

1.11.0

AItention can now act, not just watch

When a session changes state, AItention can run a program — “when waiting, then …”. A sound, a message to another tool, a script of your own: you enter the command, confirm it once, done.

This is the first place where AItention runs an outside program, and it is built accordingly. There is no default: without an entry and without your confirmation, nothing runs. The command does not pass through a shell — nothing is substituted, nothing appended. And the confirmation is tied to the exact wording: change the command by a single character and you have to approve it again.

One control for text size and spacing

“Large” now enlarges both. Large text in tight rows looked cramped, so spacing and row heights grow with it.

Send feedback

A button in the status bar opens your mail app with a prepared message. It carries the version and your macOS version — nothing else. No project paths, no session names, no file names. If no mail app is set up, the address goes to the clipboard instead of the click doing nothing.

Sound follows the states you chose

Mute a state and it no longer chimes either.

Still open

At “large” the header can look cramped if you deliberately make the window small: the minimum width does not grow with the text. Four fixes were tried and discarded because none of them worked — better to ship nothing than something that only looks like a fix.

1.10.1

Four places where a number from another file could end the app

The reason for this release is not a new feature. AItention reads files other programs write — transcripts, logs, plan details. In four places a number from those files went into a calculation unchecked, and on a nonsensical value that calculation does not return a wrong result: it halts the program.

Three of the four sit on paths that run on every pass. Because these files are read again and again, a single corrupted number would not have ended the app once — it would have made it permanently unopenable until someone repaired the foreign file by hand. None of them showed up in normal use; they were found by looking for them. All four are reproduced and fixed.

Choose your text size

Small, medium, large — across every window at once. The menu bar symbol deliberately does not follow: the bar dictates the height there.

Finer control over notifications

You now choose which states AItention speaks up for — all eleven are selectable instead of a fixed four. And you can silence individual sessions or whole projects without silencing everything else. The default is unchanged from the previous behaviour.

“Stay awake”

A button next to the mute switch keeps the Mac awake while a session is working. It is deliberately not remembered: a switch that survives a restart keeps the machine awake all night because somebody forgot it the day before yesterday.

Five points from a user’s feedback

When the five-hour window resets. The remaining time was already in the popover; the clock time now sits beside it — 34 min left (18:00). Plus a notification when a reset is actually observed, not at a calculated moment. The third sound for it is set to silent; choose one if you want one.

Your optimal daily usage. Next to the weekly bar you now see where you stand against it: Left for today — 13 % or 15 % over the daily pace.

The menu bar symbol is configurable. Four checkboxes decide what it carries. The width limit is enforced rather than assumed: if not everything fits, the least essential figure drops out instead of the symbol overflowing the bar.

Click a dormant session to resume it. You used to have to copy the command out. One click now does it — including under “Previous sessions”. It works with any terminal that registers as a handler, and needs no automation permissions.

A state of its own: “Waiting for subagents”. Muted green, its own symbol — and the row says what is being waited for. Before, it looked like ordinary work.

The interface explains itself

The small symbols in the list carried their meaning only for those who already knew it. 53 were counted, 29 of them say something — all now have help text. Counting turned up two real gaps: the state symbol on the task list, and a clickable marker that never said anything would open.

The quota breakdown also says whose quota it shows: seven of the breakdowns come from Claude data alone, with no Codex in any of them. Anyone using both could otherwise have read the figure as a combined total.

Fixed

The projection was noise. 2.66 hours extrapolated to a week produced 632 % — a number that looked like a statement. Now an eighth of the window must have passed before one appears at all. And “exhausted 11:47” read like the past; the calendar day now decides.

1.10.0

Costs are where you look now

The choice between quota, tokens and money used to sit in settings. Anyone who did not know it was there never saw an amount. It now sits in the list header, right next to the counters — the grouping control moved into a dropdown to make room.

You can also choose which of the three figures the row shows: what the provider billed, what the same work would have cost through the API, or what every single token would have cost without caching. The usage window shows quota, tokens and money side by side, each with its own checkbox.

The list stays responsive

With many concurrent sessions the window could freeze for seconds. The cause was how the list was built: groups and rows nested inside each other, which made the effort grow disproportionately with every row. The list is flat now; measured, it copies 40 % less while doing more layout work.

Fixed

The token total in the usage window was more than twice what it should have been — one answer is written as several lines in the transcript, and each carried the same usage figure. A corrupted line in a transcript could also terminate the application, and a row could disappear from the list when a project name contained a vertical bar. All three fixed.

Your token figures will get smaller as a result — they had been more than twice as high since 25 August 2026. That is not a regression, it is the correction. The first time you open the usage view, the application rebuilds its usage store once, in the background.

1.9.0

What a session costs — three numbers, not one

Every session now carries its cost. Three times over, because there are three different questions behind it: what your provider actually billed, what the same work would have cost through the API, and what it would have cost without the cache — that is, had you paid for every single token separately. The third number typically runs four to seven times the second. That is exactly its point: this is what the cache saves you.

The prices are derived and verified, not estimated: Claude Code writes its own cost figure at the end of each session, and the table is checked against it. Where no price is documented for a model, AItention shows tokens instead of money — better no number than an invented one. You always see how old the prices are, and you can override them per model.

While a session is still running, the figure reads “at least”. Not every model call lands in the transcript; the running number is a lower bound and is labelled as one until the final figure arrives.

Model and effort at a glance

Every row shows what it is working with: the model, coloured by family, and the effort level as bars beside it. If a session switches mid-run, the row shows the current state and the expanded view the breakdown. In the list you can switch between quota, tokens and money; on a flat rate the quota comes first, with pay-as-you-go the money. Your plan appears under “Application” and in the usage window — and only the plan fields are read from the configuration, no address and no identifier.

Groups: sessions that belong together

When you hand a task from one session to a new one, the data holds no trace of it — no field connects the two. The new “Copy as subtask” button lays that trace: it copies the start command together with the task text, and AItention recognises the new session as soon as it runs. Both then appear under Group — lead session on top, with completed tasks, waiting sessions and the cost of the whole plan in the heading.

You can also combine sessions yourself: ⌘-click several rows and name them. Where the trace is missing, AItention will at most suggest a group — it never assigns one without your click.

Goals, and quiet from self-resuming sessions

If a session has a goal, it takes the place of the tool name, with progress and elapsed time. For Claude Code, which has no goals of its own, you can set one yourself — budget included.

Some sessions resume on their own because a background task finished. With several of those running you used to be buried in notifications. Under “Alerts” there is now a switch: turned on, such a session only reports when it needs an answer or is done. You can also set a cost limit per session — AItention stops nothing, but it knocks in time.

Corrected

The token counts in the usage window were more than twice what they should have been. One reply appears as several lines in the transcript, each carrying the same usage figure; every line was counted. The proportions in the rankings held, the absolute numbers did not. And the usage window claimed the plan was not available locally — which stopped being true once AItention read it.

1.8.2

Settings are a window now

Ten sections in one popover were taller than some screens: on a smaller MacBook the lower half was cut off — licence, updates, language — and nothing scrolled. Settings now open in their own window with four tabs: List, Alerts, Licence, Application. Each tab fits any screen on its own, and where it does not, it scrolls.

Reach them with ⌘, as in any other application, from the gear in the main window, or from the gear in the menu bar panel — the latter also when you run AItention without a Dock icon. Language and the introduction now live under “Application”.

Smaller improvements

The counter labels — WAITING, ACTIVE, DORMANT — looked stretched. They now use normally proportioned letters with a little more spacing. In a narrow window the grouping switch gives way instead of pushing the counters out of the row. And the “Settings …” and “About AItention” menu entries finally do what they promise.

1.8.1

One letter

The compaction hint read “erfahrungsgemäss”. The correct German spelling is “erfahrungsgemäß”. Nothing else about the application changes.

If you are on 1.8.0, there is no reason to update other than this one.

1.8.0

Mute, in one click

A new switch sits left of the grouping control. It turns off notifications and sounds without touching your settings — unmuting restores exactly what you had. Going into a meeting no longer means flipping three switches and guessing afterwards.

The state is visible without opening a window: the menu bar icon carries it. A mute you forget would be worse than none.

What keeps running: the counters, the badge — and forwarding to a configured address. That goes to a machine, not to you; stopping it would mean losing events with nothing to catch them. The note is at the switch and in the settings.

1.7.1

Codex sessions sit under the right application

If you run Codex through OpenAI's application, your sessions used to be filed under "Visual Studio Code" — even when Visual Studio Code was not installed. Codex Desktop ships a VS Code core and reports it as its surface; which program is running is stated elsewhere. AItention now reads that.

Sessions therefore appear under the name of the application they run in, with its icon — in the list, in the "Previous sessions" window and in the grouping by application. Nothing changes for Codex in a terminal or in Visual Studio Code.

1.7.0

"Previous sessions" now includes Codex

Finished Codex sessions appear in the "Previous sessions" window alongside those from Claude Code — with title, project, application and the right command to continue: codex resume rather than claude --resume.

If codex is not on your path, the copied command carries the full path to the program — it still runs.

1.6.1

Fixed: Codex sessions carried Claude's icon

A Codex session calls itself "Codex Desktop" — and was therefore given Claude's name and Claude's icon. It now carries the icon of the application it actually runs in. Also fixed: with two tools present, the fourth grouping tile was cut off.

1.6.0

Codex is included

AItention now also shows Codex sessions: title, project, state, context and output tokens — alongside your Claude Code sessions in the same list. With both running, a fourth grouping by tool appears.

Without touching your Codex setup. Codex keeps a record of its own per session; AItention reads it and changes nothing. Codex states its context window itself — so the compaction warning is read there, not estimated.

Connecting other tools

The file contract AItention draws its information from is now published: aitention.app/schema/status-v1.json. Any tool that can start a program on events may write a status file and then appears in the list — with no change to AItention. Three fields are required.

1.4.0

Forwarding: state changes to an address of your own

You can store an address in the settings. When a session then enters a state that needs you, a JSON message goes there — the same rule as for the notification. That connects home automation, a chat channel or whatever you like, without any foreign code starting on your machine.

Session name, project folder, application and state are sent — never prompts, replies or paths. With no address entered nothing happens; the field is empty as shipped. Unencrypted (http) only on your own network, otherwise https.

A warning before the context is compacted

As a session approaches compaction, its context figure changes colour. The threshold is not guessed but read from your own transcripts: the context drops sharply at a compaction, and the size just before it is the point in question.

1.3.0

Waiting time: what not looking actually cost

The new „Waiting time“ tab in the usage window answers the question this program exists for: how long did your sessions sit there finished without anyone noticing? Total, average, longest — per day and per project, over seven, thirty or ninety days.

Recording starts with this version: the waiting time is in no file that existed before. Only start, end, state and project are kept — no content.

1.2.1

Noticeably lighter — and the prompt search responds at once

The app redrew the whole list every second, even when nothing in it had changed and even when the window was not visible at all. Both are fixed: with seven running sessions AItention now uses about half as much, and with no visible window almost nothing.

The prompt search ran several times over every entry on each keystroke, which briefly froze the app. It now runs once per pause in typing, on prepared data — roughly twenty times less work.

1.2.0

Consumption: where the quota actually goes

The usage view showed how full the two rate windows are. The new „Consumption“ tab shows what filled them: output, input and cache, bars per day, rankings by project, application and model, over seven, thirty or ninety days. Counted from your own transcripts — none of it leaves the machine.

The short version also appears in the expandable statistics in the main window: seven days, the three figures, and the top five projects and applications.

Prompt search across all sessions

"Where did I do this before?" — the „Previous sessions“ window now searches every prompt you have ever sent, across all projects. The hit leads to its session, with the resume command next to it.

1.1.2

Fixed: the app could freeze

In 1.1.1 the "Previous sessions" view could enter a layout loop: the window recalculated its arrangement endlessly, consumed a whole CPU core and stopped responding. It affected anyone who had opened that window. The cause is fixed, and a check in the build prevents that shape from returning.

If your app froze: it was us, not your machine. We apologise.

1.1.1

Previous sessions are now where you look for them

In 1.1.0 they sat as a tab inside the About window. That is the wrong place: an About window is a reference for the imprint and the data sources, not a working view. They now have a window of their own, reachable from the clock icon in the main window's toolbar and from the menu bar panel.

Plus a way in at the moment you need it: when the list is empty — after a restart, that is — a button there opens them.

1.1.0

Previous sessions — pick up again after a restart

Close an application or restart the machine and you want to continue with claude --resume — but with many sessions you no longer know which was which. The new Previous sessions tab in the help window lists them: grouped by application or project, searchable, over seven days, thirty days or all of them. Each row offers the complete command to copy.

That command now carries the project folder. Claude Code looks for a session below the directory it starts in — without the leading cd the copied command found nothing when run from elsewhere.

Finished sessions are called what they were called

Until now a finished session was labelled with its folder name, so several in the same project read identically one below the other. The title is now taken from the transcript, which outlives the restart — in the ordinary list as well as in the new tab.

1.0.18

What the session last said — right in the row

In the comfortable density the opening words of the last reply now appear at the bottom of the row. When something new arrives, the old text rolls out upwards and the new one rolls in from below. A click still opens the full text.

The movement runs exactly once per new message and then stops. A display that is permanently in motion costs CPU without pause — something we measured elsewhere and learned from.

1.0.17

Usage expands inside the window

Clicking the usage bar used to open a second window that had to be found, moved and closed again — too much effort for a figure you want to catch in passing. The history now expands between the bar and the session list, and collapses just as easily.

The pin in its corner keeps it open, across restarts as well. Without it, expanding is a question of the moment; with it, a setting.

1.0.16

Fixed: automatic checking never ran

The switch “Download and install updates automatically” was on — yet nothing was ever checked. The reason ran deep: the machinery behind it only came into existence when someone opened the settings. Anyone who never did was never offered an update, with nothing to hint at it.

Updating now starts together with the application, and its state is visible in the diagnostic output — what cannot be seen is never checked.

1.0.15

Fixed: crash while reading session data

In rare cases the application could crash while reading session data. The cause was an instrumentation added in version 1.0.10 for troubleshooting: it wrote its results without protection while two read passes ran at the same time. The instrumentation is now guarded, and two passes can no longer overlap — which also avoids duplicated work.

1.0.14

The five-hour window now says how long it still runs

It used to show when the window would be full at the current pace — even when that moment lay beyond the end of the window itself. “Full in 5 h 40” for a window that rolls over in three hours describes a moment that no longer exists. Now it first states how long the running window still counts, and only then, and only if the limit would genuinely be reached before that, the warning follows.

Update window in your language

The update window appeared in English although it ships with 36 languages: the application had not registered German as an available language. Fixed. Its checkbox now also reflects the same setting as the switch in the preferences.

1.0.13

One update switch, not two

Checking for updates used to raise a second dialog with its own consent — it did not know about the setting and therefore showed it wrongly. Two switches for one thing means none. Only the one in the settings remains, and it is off by default.

The usage display, larger and colour-coded

Larger type, stronger bars, and the projection is now coloured according to where usage is heading. New for the five-hour window: it has no fixed reset — its values fall continuously as older usage drops out — so instead of a reset date it now shows how long it will last at the current pace.

1.0.12

The usage bar now says where it is heading

Both windows sit one above the other rather than side by side — which makes them comparable and leaves room for what counts: how long the usage still applies, and what it will add up to at the current pace.

The projection uses the average since the last reset, not the pace of the last hour. The difference is substantial: one busy hour extrapolated over five days would produce figures beyond 200 per cent. And when the window will not last, what is shown is not the number but the moment — “exhausted Thu 14:00” says what to do.

1.0.11

Ten times less load

The pulsing dot on a working session was drawn as an endless animation — on every frame the display produces, up to 120 times a second, without pause. On its own it accounted for by far the largest share of CPU use: measured at 37 per cent with, 2 per cent without. The dot still breathes, but in step with the display rather than in an endless loop. It looks the same; it now measures around four per cent.

Time left in the weekly window

Next to the seven-day usage you now see how long it still counts — “5 days left”. Eighty per cent is relaxed if the reset is tomorrow and tight if five days remain. The moment is derived from the history; until a week of it exists, nothing is claimed.

1.0.10

The list only redraws when something changes

The display used to follow along every second so that entries like “waiting for 3 min” stayed current. But seconds are only shown during the first minute — after that the same picture was drawn fifty-nine times over. Each redraw does not end inside the application: it also occupies the system's compositor.

The clock now ticks every second only while seconds are visible somewhere, and every five seconds otherwise. Nothing changes on screen — a great deal changes in load.

1.0.9

Substantially lower load

With many sessions open and a long uptime the application used more CPU than it should — to the point of noticeable sluggishness. Four causes have been removed: language resolution ran for every translated string instead of once; a row's tooltip was built every second for every row although at most one is shown; the mapping from session to application walked the process tree on every pass; and the status files were all re-read every two seconds, including those of long-dormant sessions.

1.0.8

More accurate recording of stalls

The application records when its interface stops responding. Until now that measurement also counted time while the computer was asleep — a night in standby appeared as a series of stalls that never happened. Only waking time is measured now.

The CPU time consumed is also noted. Only both numbers together mean something: whatever burns CPU is stuck in a loop, whatever does not is waiting for something. Nothing changes in day-to-day use — for us it is the difference between a lead and a false alarm.

1.0.7

New state: Scheduled

A session can schedule a wake-up for itself and carry on unaided. Until now that looked like “waiting for you” — making it the one statement in this application you could not rely on. Such sessions now appear as Scheduled in a colour of their own, no longer count towards the badge and raise no notification. The tooltip says when they will speak up again.

What matters is how this is recognised: by the wake-up actually scheduled, not by what a session claims about itself in prose. A question asked and a failed turn are untouched — both need you, whatever arrangement sits beside them.

What was said last

A session's most recent reply now appears in the tooltip of every row, in the compact density too, along with what the session is currently waiting for.

1.0.6

Visible: what a session is waiting for

A session can wait for a condition — a pipeline to finish, an agent to report, a file to fill up. Until now that looked like any other work from the outside. The list now shows such monitors as a marker of their own, with their count; the tooltip names the condition and how long it has been waiting.

The distinction matters more than it sounds: a session waiting on an external condition does not need you — one that has asked a question does.

1.0.5

Fixed: freeze after longer uptime

With many sessions open at once the application could reach a state it never recovered from: the list was recomputed more often than one computation took. It then stopped responding and could only be quit.

The cause has been removed. The grouping of the list is now recomputed only when something has actually changed — the sessions themselves, or your settings for grouping, sorting and filters.

In addition, the application now records stalls even when they do not end by themselves. Previously the most serious case was the one that went unnoticed.

1.0.4

Stability

In rare cases the interface could stop responding for a few seconds after a long uptime. One cause has been removed: the application could create its timers more than once. It now also records such stalls itself, so that any remaining case can be shown rather than guessed at.

Maintenance

After an update the application brings its status helper to the same version by itself. Previously the version installed earlier stayed in place — silently, which meant improvements to it never reached anyone who had already set the application up. The application icon is now generated at the sizes macOS expects.

1.0.2

Provider details in the application

The “About and Help” window has a fourth tab: whoever sells a program has to say who stands behind it — and nobody should have to look up a website for that.

One statement on the “About” page has also been corrected. It read “no network access”. Since the application can look for updates, that is no longer true, and the page now states exactly when it goes online.

1.0.1

Updates

The application can look for new versions by itself. You decide on first launch whether it may; you can change that at any time in the settings and check manually instead. Every archive is verified against a key built into the application.

Only your IP address, the application's own version and the system version are transmitted. No profile of your system configuration is sent, and no logs are kept of these requests.

1.0.0

First release

AItention shows in the menu bar which of your Claude Code sessions is working, waiting, finished, or asking a question.