feat(walkthrough): write walkthroughs in the reader's language

A guided explanation is only useful in a language the reader reads, so the
panel header gets a language picker alongside the model one, defaulting to
the interface language. Like the model, it is request state rather than a
setting: the language travels with the read and the generation, and the one
a walkthrough was written in is stored with it, so reopening a review
describes what is there instead of what a fresh one would be.

Only prose is translated. Hunk aliases resolve back to hunk ids and
icon/importance are validated against fixed English values, so a translated
one would be dropped by the normalizer — silently losing an anchor or a
style. Identifiers and paths stay as they appear in the code.

The language is part of the cache key, and a read now asks the cache for the
exact request it was given before falling back to the pointer. Without that
the panel answered a request to switch languages with the text it already
had, leaving the other language unused in the cache.

Alongside it:

- The answer budget is derived from the resolved model instead of a flat 24k.
  That number was the same for a 64k-context model and for one that admits to
  384k output tokens, and on the latter it was the only reason generation
  failed: the model spent the whole allowance reasoning and returned nothing.
  It is now min(96k, max(24k, a quarter of the context)) capped by the
  catalog's output limit, decided once so the input reserve and the request
  cannot drift apart.
- A read no longer offers Cancel. It is a few hundred milliseconds of git with
  nothing to cancel, and the button flickered on every model or language
  change. When the panel is showing a fallback, a banner names what is on
  screen versus what was asked for — only once the read has settled.
- The header keeps one 32px control height and drops its labels below 680px
  instead of squeezing them to two letters and an ellipsis.

Docs and module documentation updated in every locale.

packages/docs/content/docs/walkthrough.mdx

@@ -33,11 +33,19 @@ The picker only offers models that can return structured output, because the wal
 
 Reopening a panel shows the model that produced what you are looking at, so **Regenerate** repeats with the same one unless you change it.
 
+## Choosing the language
+
+Walkthroughs are written in your interface language by default. The language picker in the panel header starts there, and you can pick any other language OpenChamber is translated into for a single review — a guided explanation is only useful in a language you read comfortably.
+
+Only the prose is translated. Identifiers, file paths, and API names stay exactly as they appear in your code, so what a stop names is still what you can search for.
+
+When nothing has been generated yet in the language you picked, the panel keeps showing the walkthrough it has and says so, rather than emptying itself. Press **Generate walkthrough** to get one in the new language.
+
 ## Cost and caching
 
 Nothing generates on its own. Generation only ever starts when you ask, and regeneration is manual too.
 
-Results are cached against the exact content of the diff. Return the working tree to an earlier state and the earlier walkthrough comes back for free, no model call. Switch models and back, and each one's walkthrough is still there.
+Results are cached against the exact content of the diff. Return the working tree to an earlier state and the earlier walkthrough comes back for free, no model call. Language and model are both part of that key, so each combination is kept separately: once a diff has a walkthrough in two languages, switching between them is instant and costs nothing.
 
 Generation runs on the OpenChamber server, not in your browser tab. Reload the page or close the panel and it keeps going; come back and the result is waiting. Pressing **Cancel** is the only thing that stops it.