Every one of these said a switch leaves running sessions alone - that they keep
talking to the old provider until restarted. That is wrong, and reassuring in
exactly the wrong direction: a switch breaks them.
The static half of the config does behave as described. Base URL, model ids and
the env block are read once at startup and a running session keeps what it
started with.
The credential is not. It comes from running apiKeyHelper, which Claude Code
re-invokes on a timer - CLAUDE_CODE_API_KEY_HELPER_TTL_MS is present in the
2.1.251 binary - and claude-key-helper.sh answers for whatever state.json says at
that moment. So the switch reaches into a live session through the one part that
was never cached. Into anthropic, the helper returns nothing by design and the
next refresh comes back with no credential; into another provider, it hands over
the new key while the session is still pointed at the old base URL, which
rejects it. Either way the session starts failing calls whenever the TTL happens
to expire, mid-turn as easily as between turns.
One case does survive, and is now stated rather than glossed: switching between
two presets of the same provider that share a keyRef keeps the same key and the
same endpoint, so the session carries on with the model ids it started with.
The claim in "Restarting sessions" predates this work - it came in with the
Windows build - but it is wrong for the same reason and is corrected too.
The session-confirmation card lays out four buttons, which come to roughly
440px of content in a card 332px wide (360 less 14px of padding each side). A
Row has no notion of how wide its parent is and no wrap, so it put them in one
line and the last two ran off the right edge of the popup.
Flow bound to the parent width instead, so the buttons take a second line when
they need one. Applied to every button row rather than just the one that
overflowed - the failure card can show four at once for the same reason, and the
server form's rows would do it at a narrower card or a larger font.
Labels are left as they are: "Switch and restart" says what the button does to
the sessions listed above it, and two tidy rows read better than four terse ones
crammed into a single line.
GLM 5.3 supersedes 5.2, so every reference to the older id follows it: the zai
preset's opus, sonnet and fable tiers, and the fable tier of `default`, which
routes to the same model through OpenRouter.
Also the hardcoded Z.AI entries in both builds' model pickers, which are the one
place a model id is not read from a preset - leaving those would have gone on
offering a superseded model from the menu while the presets used the new one.
haiku stays on glm-4.7: that is the fast/cheap tier, not a 5.x.
A Quickshell plugin for the Omarchy shell (v4's bar is Quickshell, not Waybar).
The icon is the mode; clicking it opens a panel that switches.
State comes from watching health.json rather than polling the CLI, so the widget
costs nothing while idle and a switch made in a terminal shows up in the bar on
its own. state.json is the fallback, because it exists from install onward where
health.json only appears once claude-mode has run.
The marks are the providers' real logos, drawn as vector paths through
QtQuick.Shapes rather than set as font glyphs - three of the four have no Nerd
Font pictograph at all, and paths take the bar's foreground colour and follow
the theme. Claude, OpenRouter and LM Studio from simple-icons, Z.AI from
lobe-icons; trademarks belong to their owners. Zhipu's mark was rejected for
Z.AI: it is a dense lattice that is unreadable below ~40px.
Rendering them at 13px took three fixes. A layer rasterises the Shape at its own
size and then scales the texture, so a 24px buffer minified to 13 resampled two
pixels into one and the Claude burst lost rays; without the layer the scale is a
transform on the geometry and rasterisation happens once, at final resolution.
CurveRenderer replaces the tessellating default. And the size is forced odd,
because a radially symmetric mark puts its vertical and horizontal arms on the
centre line, which is a pixel centre at odd sizes and the seam between two
pixels at even ones, where each arm splits its coverage and greys out. Measured
against a cairo render at the same size, the result is now identical.
Sizing is measured rather than guessed. Every stock glyph in this bar paints
11px of ink; the marks fill their box instead of carrying a font's padding, so
the box is the smaller number. Each mark also carries an optical scale from two
measurements of a 200px render - LM Studio's filled container covers 69% of its
box against ~38% for the others, and Z.AI and OpenRouter are wide-but-short
marks spanning ~84% of the box height.
Choosing a target does not switch immediately. It runs the CLI's own preflight,
and if that refuses, the panel names what is missing and offers the fix - a
terminal for the hidden key prompt, a re-check once a server is up, or the
server form. If sessions are running it lists them by terminal and directory,
marks any mid-request, and asks whether to restart them, close them, or leave
them. The session action is applied strictly after the write, since restarting
first would only bring them back up on the provider just left.
The server form edits an LM Studio preset's base URL and whether it needs an API
key, reachable from the gear on any LM Studio preset row - per row, because two
presets can point at two different machines - and from the failure card. The
shipped local default is untouched unless it is changed.
Four changes to the POSIX build, found while getting it working on Omarchy.
Colour follows the desktop theme. The sixteen ANSI slots carry no guarantee
about relative brightness and monochrome themes exploit that: under Omarchy's
Solitude, slot 36 (headings) resolves to #707070 and slot 31 (FAIL) to #565d60,
which against #cacccc body text on a #101315 ground is 3.8:1 and 2.8:1 where the
body text is 11.6:1. Headings rendered as fine print and errors as the quietest
thing on screen. The palette is now derived from the theme's own colors.toml,
with each role measured against the background it will actually be drawn on and
lifted toward the foreground when it falls short - hue kept where the theme has
any, weight substituted where it does not. Headings go 3.8:1 -> 9.4:1 and FAIL
2.8:1 -> 5.2:1. Falls back to the ANSI slots off Omarchy, with the two roles the
slots get wrong corrected.
health.json was only ever written by a switch, so a fresh install had none at
all and any reader had to guess. It is now refreshed by `status` and seeded at
install, and `claude-mode health` forces it. The installer also copies VERSION,
which cm_version() has always read and nothing ever wrote - every health.json
until now reported 0.0.0.
Preflight, because a switch that cannot work does not fail loudly: it succeeds,
and every session started afterwards breaks in a way that points at Claude Code
rather than at here. Keys, the helper, the preset's provider and the server are
all checked before the write. LM Studio is the sharp case - its token is an
inline placeholder, so nothing about the switch needs the server to exist.
Session control, because Claude Code reads settings.json once at startup: a
switch leaves running sessions on the old provider until they are restarted, and
one mid-request can lose that turn outright. `sessions` lists them, `--stop` and
`--restart` act on them behind a confirmation, `--dry-run` shows the plan.
Sessions are found through /proc/<pid>/exe rather than by process name, which
would sweep up every shell that merely mentions claude - including the one this
runs from. Two exclusions: the calling session, and forks of a session. A busy
session spawns children off its own binary that inherit the same exe, and
without filtering those the count climbed and fell with load - it read 2, 5, 11
and 40 for the same two sessions before the parent check went in.
LM Studio is no longer assumed to be on this machine. `preset url` and
`preset auth` move it to a LAN box, a tunnel or a proxy and turn authentication
on, and the probe distinguishes ok / auth / notfound / refused, because "start
the server" and "your key is wrong" are opposite remedies. It is probed wherever
it lives - a sleeping LAN box is exactly as absent as an empty loopback port -
while remote gateways are not, since those being briefly unreachable is the
network's problem and a missing key never fixes itself.
Source of truth so far has been c:\Users\smoido\projects\cli on the Windows
box, which has no git history of its own. This is that tree copied verbatim over
SSH, minus dist/ - the PowerShell build, the POSIX port under linux/, and the
presets both share.
Recorded as its own commit so that everything after it is a reviewable diff
rather than an undifferentiated first drop.
smoido