Specifically, we describe the embedded-shell contract, Windows behavior,
permissive shebang fallback, guaranteed CRUSH/AGENT env markers, and
timeout hard-return semantics.

Share CRUSH=1/AGENT=crush/AI_AGENT=crush between the bash tool's Shell
and the hook runner so the two surfaces can't drift.

This in necessary so hook timeouts can now interrupt long-running
filters and large stdin reads for the builtin jq tool.

This is necessary for sharing the builtin shell with hooks.

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.

Descriptions should describe when a skill applies, not how it does its
job. Leaving language like "using go doc", "the jq command-line
processor", etc. in the trigger encourages the model to guess its way
through without reading SKILL.md.

Models frequently skipped viewing a skill's SKILL.md and inferred its
behavior from the description alone; making the load mandatory in
<critical_rules> prevents LLMs from taking that shortcut.