Settings as a screen with two tabs, and fields that cost one line

The settings dialog had outgrown a dialog: it scrolled inside itself,
covered the session it is about, and had nowhere to put a second tab. It
is a screen now, drawn over the session like the file explorer so the
session under it stays composed, with the back gesture to leave it. The
second tab is ProviderScreen itself -- the same composable the machines
tab opens -- so a provider's settings have two ways in and one
implementation.

Every text field in the app goes through LabelledField: the label is a
line above the box rather than a thing floating inside it, the hint says
what leaving it blank means, and the padding is one line's worth.
Material's outlined field spends the height of three lines to hold one,
which on a form of a dozen settings is a screen and a half of scrolling.
The value's own text is unchanged -- the framing was what cost.

A session also gets a system prompt, which for llama.cpp is one entry in
the params table and no app change: it rides in front of the conversation
on every request rather than being recorded as the first thing in it, so
changing it takes effect on the next message. ParamKind::Prose is new
because a paragraph in a one-line box shows six words of itself.

PLAN.md

@@ -477,6 +477,18 @@ deliberate and easy to undo by accident:
   only a turn whose model was changed under it. The conversation is read
   *before* the message is announced, which is what makes "everything before
   this message" true rather than a race against the pump.
+- **A session's system prompt is a param like the rest** (2026-09-21,
+  `systemPrompt`): it rides in front of the conversation on every request
+  rather than being recorded as the first thing in it, so changing it takes
+  effect on the next message instead of leaving a transcript that says
+  otherwise. One entry in `LLAMA_PARAMS` and no app change, which is the
+  property that table exists for -- and a new `ParamKind::Prose`, because a
+  paragraph in a one-line box shows six words of itself. Measured while
+  building it: the prompt reaches the model exactly where it should
+  (`/apply-template` puts it first, with the tools preamble after it), but a
+  0.6B with seven tool definitions in front of it will ignore a short
+  instruction that it obeys with no tools. That is the model, not the
+  plumbing.
 - **An interrupt ends the wait, not the work** (2026-09-21, `awaiting`,
   `Cancel`). Everything a llama turn waits on is on the far side of something
   that cannot be told to stop -- a permission nobody has answered, a shell