feat(llm): add z-ai-coding provider for GLM Coding Plan endpoint

[givingwu]

Z.AI (智谱) subscribers to the GLM Coding Plan must route requests through the dedicated coding endpoint (https://open.bigmodel.cn/api/coding/paas/v4) for them to be billed against the subscription quota. The existing z-ai provider points at the generic pay-as-you-go endpoint (https://open.bigmodel.cn/api/paas/v4), so Coding Plan keys silently drain the wallet balance instead of consuming the plan quota, surfacing as a spurious "1113 余额不足" error even when the plan is barely used.

Add a dedicated z-ai-coding provider following the existing *-tokenplan pattern (dashscope/dashscope-tokenplan, tencent-tokenhub/hy-tokenplan). It reuses Z_AI_API_KEY — the same key authenticates against both endpoints, so selecting this provider is all that's needed to activate the plan. The model list is restricted to the models officially supported by the Coding Plan to avoid selecting a non-plan model that falls back to wallet billing.

• internal/llm/providers.go: register z-ai-coding preset
• extensions/vscode/src/shared/providers.ts: mirror the preset (kept in sync with the Go registry per the file header)
• internal/llm/providers_test.go: update the sorted provider list assertion

Description

Type of Change

• Bug fix (non-breaking change that fixes an issue)
• New feature (non-breaking change that adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)
• Refactoring (no functional changes)
• Documentation update
• CI / Build / Tooling

How Has This Been Tested?

• make test passes locally
• Manual testing (describe below)

Checklist

• My code follows the project's coding style (go fmt, go vet)
• I have performed a self-review of my code
• I have added tests that prove my fix is effective or my feature works
• New and existing unit tests pass locally with my changes
• I have updated the documentation accordingly (if applicable)
• I have signed the CLA

Related Issues

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[github-actions]

✅ OpenCodeReview: No comments generated. Looks good to me.

[lizhengfeng101]

Code Review

Thanks for the contribution — the problem statement is clear and the fix is well-motivated. A few items to address before merge:

1. Remove comments from the TypeScript provider preset

extensions/vscode/src/shared/providers.ts — the preset objects are plain data (JSON-like). The other entries in this array have no comments; this one shouldn't either. Please remove the comment block:

// GLM Coding Plan (智谱编程套餐). Dedicated coding endpoint bills against
// the subscription quota instead of the pay-as-you-go wallet. The same key
// authenticates both endpoints, so Z_AI_API_KEY is reused.

2. Use a dedicated env var instead of reusing Z_AI_API_KEY

The existing tokenplan providers each define their own env var:

Provider	EnvVar
dashscope	DASHSCOPE_API_KEY
dashscope-tokenplan	DASHSCOPE_TOKENPLAN_KEY
tencent-tokenhub	TENCENT_HUNYUAN_KEY
hy-tokenplan	TENCENT_HUNYUAN_TOKENPLAN_KEY

Please follow the same convention — e.g. introduce Z_AI_CODING_API_KEY (or similar) so that users who have both a pay-as-you-go key and a Coding Plan key can configure them independently without collision.

3. Do not modify pages/ for a provider addition

Changes under pages/ (i18n files, DocsPage.tsx) are outside the scope of a provider registration PR. Provider additions should only touch:

• internal/llm/providers.go
• extensions/vscode/src/shared/providers.ts
• internal/llm/providers_test.go

Please revert the pages/ changes. Documentation updates for providers can be handled separately if needed.

4. Confirm: is the model list identical to z-ai on purpose?

The z-ai-coding model list (glm-5.2, glm-5.1, glm-5-turbo, glm-4.7) is exactly the same as the generic z-ai provider. The PR description says the list is "restricted to the models officially supported by the Coding Plan" — does the Coding Plan actually support all four of these models? If the plan only covers a subset, the list should be narrowed accordingly.