…3518)

### What this PR does

Before this PR:

Users could not select LMStudio or Ollama models when using Claude Code
in Code Tools feature, even though both local services now support
Anthropic API endpoints (`/v1/messages`).

After this PR:

- LMStudio and Ollama providers are now available for selection in
Claude Code tool
- Environment variables are correctly generated using `apiHost`
(respecting user-configured ports)
- Users can configure custom ports and the settings will be properly
passed to Claude Code

Fixes #13487

### Why we need it and why it was done in this way

The following tradeoffs were made:

- For local services (LMStudio, Ollama), we use `apiHost` directly
instead of a separate `anthropicApiHost` because these services share
the same host for both OpenAI and Anthropic APIs, and users often
customize ports
- Added explicit type assertions for readonly array checks to satisfy
TypeScript strict mode

The following alternatives were considered:

- Using static `anthropicApiHost` for Ollama (rejected: doesn't reflect
user port changes)
- Adding `anthropicApiHost` to LMStudio config (rejected: redundant
since it would duplicate `apiHost`)

Links to places where the discussion took place:

- Issue: #13487
- LMStudio docs: https://lmstudio.ai/docs/integrations/claude-code

### Breaking changes

None. This is a pure addition - no existing functionality is affected.

### Special notes for your reviewer

- LMStudio requires starting the server with Anthropic compatibility
mode enabled
- Ollama needs models that support Anthropic format (newer models like
qwen3-coder, glm-4.7)
- Users should use models with >25k context for optimal Claude Code
experience

### Checklist

This checklist is not enforcing, but it's a reminder of items that could
be relevant to every PR.
Approvers are expected to review this list.

- [x] PR: The PR description is expressive enough and will help future
contributors
- [x] Code: [Write code that humans can
understand](https://en.wikiquote.org/wiki/Martin_Fowler#code-for-humans)
and [Keep it simple](https://en.wikipedia.org/wiki/KISS_principle)
- [x] Refactor: You have [left the code cleaner than you found it (Boy
Scout
Rule)](https://learning.oreilly.com/library/view/97-things-every/9780596809515/ch08.html)
- [x] Upgrade: Impact of this change on upgrade flows was considered and
addressed if required
- [x] Documentation: A [user-guide update](https://docs.cherry-ai.com)
was considered and is present (link) or not required. Check this only
when the PR introduces or changes a user-facing feature or behavior.
- [x] Self-review: I have reviewed my own code (e.g., via
[`/gh-pr-review`](/.claude/skills/gh-pr-review/SKILL.md), `gh pr diff`,
or GitHub UI) before requesting review from others

### Release note

```release-note
feat(code-tools): add LMStudio and Ollama support for Claude Code

Users can now select LMStudio and Ollama models in Code Tools when using Claude Code. Both local AI services support Anthropic API endpoints, enabling seamless integration. The implementation correctly handles custom port configurations by using the provider's `apiHost` directly.
```