Basically, the /models endpoint is public on many openai-compat
providers, so validation was always passing with any string. This likely
broke in 7d14abb9 and cce8edf9.

Validation has been restored for:
- AiHubMix
- Avian
- Cortecs
- HuggingFace
- io.net
- Quiniu Cloud
- Synthetic
- Venice

New validation added:
- Minimax

Cannot be validated yet:
- Chutes
- Neuralwatt

We attempt to refresh tokens in two scenarios:

* Pro-actively, when we expiration date passed before a request
* Reactively, when we try a request but a 401 was returned

The error / event handling that shows a dialog asking the user to
re-authenticate is dependent on code that runs for the second scenario.
This means that the dialog might not show on the first scenario, if
refreshing the token fails.

If refreshing a token fails, continue with the previous token. Let it
fail and the 401 will trigger a re-authorization dialog.

I caught this because I was switching between local vs. prod Hyper a lot.

chore(styles): overhaul style definitions

Scope unavailable tracking to each Manager instance and retry missing server commands after a short backoff so temporary environment changes do not permanently block LSP startup.

MiniMax API keys don't always follow the "sk-" prefix pattern,
so the validation was causing unnecessary errors for valid keys.

Co-authored-by: Andrey Nering <andreynering@users.noreply.github.com>

* Follow-up of #2592

We've been testing this for 2 weeks, and it's working great.
This is a very useful enhancement to reduce token usage, cost, and make
smaller models behave better.

This is particularly significant for local models. These models are tiny,
and with a long enough system prompt they have little context window left
for work.

It's still possible to have the old behavior by setting:

    export CRUSH_SHORT_TOOL_DESCRIPTIONS=0

Some models like Kimi K2.5 and GLM 5 simply don't handle well that many
content. When a big page or JSON API is fetch, it can break Crush
sessions.

We're drastically reducing the truncation size here, to 1/10 of what we
had before. It may look too much at first look, but 100KB it's actually
very reasonable. For example, the entire Task guide, which is
significantly large, is only 61KB:

https://taskfile.dev/docs/guide.md

* fix(lsp): mitigate stale diagnostics

* fix(lsp): log warning when workspace change notification fails

💘 Generated with Crush

Assisted-by: GLM-5.1 via Crush <crush@charm.land>

* test(lsp): add unit tests for diagnostics settling behavior

💘 Generated with Crush

Assisted-by: GLM-5.1 via Crush <crush@charm.land>

* refactor(lsp): remove blocking diagnostic wait from post-edit notifications

💘 Generated with Crush

Assisted-by: GLM-5.1 via Crush <crush@charm.land>

* chore: add async diagnostic waits

* Update internal/agent/tools/diagnostics.go

Co-authored-by: Andrey Nering <andreynering@users.noreply.github.com>

* fix(lsp): stop timer leaks in WaitForDiagnostics

Replace time.After with time.NewTimer + defer Stop() to prevent
unreclaimable timer allocations on early returns.

💘 Generated with Crush

Assisted-by: GLM-5.1 via Crush <crush@charm.land>

---------

Co-authored-by: Andrey Nering <andreynering@users.noreply.github.com>

For example, the GitHub MCP server can fetch diffs. This makes those
diffs render as such, rather than just showing their raw output.