feat(providers): add siliconflow-cn as a built-in model provider

[wu21-web]

Description

This pull request is a follow-up of #772 , adds a siliconflow-cn for chinese users at the sametime.

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

none yet

[github-actions]

✅ OpenCodeReview: Review complete: 0 finding(s) across 1 selected item(s).

[lizhengfeng101]

Same feedback as on #772 — the Models list here is identical, so the same concern applies to this preset.

Several entries look like previous-generation models rather than what a new user would want as a first choice:

• deepseek-ai/DeepSeek-V3 and deepseek-ai/DeepSeek-R1 are superseded by the V3.2/V4 line already in the same list.
• Qwen/Qwen3-32B and Qwen/Qwen3-14B are both older and quite small for this workload — review runs depend heavily on reliable tool calling and long-context handling, and small models tend to degrade there.
• baidu/ERNIE-4.5-300B-A47B also looks like an older generation.

These presets are exactly what people pick from the provider TUI without thinking twice, so the defaults carry a lot of weight. Could you re-verify the list and confirm:

1. Every model id still resolves on the CN endpoint (https://api.siliconflow.cn/v1) — the region split with feat(providers): add siliconflow (GLOBAL) to built-in providers #772 means the two lists should not be assumed identical unless you have checked both.
2. Each listed model supports the streaming + tool-calling behaviour the review loop needs.
3. The list reflects the current generation, and older/smaller entries are either dropped or intentionally kept (a one-line rationale in the PR description would help if intentional).

One process note: this PR and #772 both edit the same expected slice in TestListProviders_Order, so whichever lands first will leave the other with a conflict. It may be simpler to fold both presets into a single PR, or to confirm the model list once and apply the same result to both.

A shorter list of models you have actually run a review with is more valuable than a longer list that is partly stale. Thanks!

[wu21-web]

I will notify you when a merged conflict is resolved.

[wu21-web]

Model changes have been synced to this pull request.