Add 3 new SiliconFlow models (GLM-4.7, GLM-4.6V, DeepSeek-V3.2)

[qychen2001]

Summary

Added 3 new SiliconFlow models to the provider database:

• zai-org/GLM-4.7 - Zhipu's new flagship model with 355B total parameters and 32B activated parameters. Supports reasoning and tool calling. Context: 205K tokens.
• zai-org/GLM-4.6V - Vision-language model with 335B total parameters. Supports image input, reasoning, and tool calling. Context: 131K tokens.
• deepseek-ai/DeepSeek-V3.2 - 671B parameter model featuring DeepSeek Sparse Attention (DSA) for faster long-context inference. Supports reasoning, structured output, and tool calling. Context: 164K tokens.

Changes

• Added model configurations for 3 new SiliconFlow models
• Context lengths are rounded to the nearest thousand following the existing convention (e.g., 204_800 → 205_000)
• All models use the standard TOML format with underscore-separated numbers
• Verified with bun validate

[Copilot]

Pull request overview

This PR adds three new SiliconFlow models to the provider database: GLM-4.7, GLM-4.6V, and DeepSeek-V3.2. The models are added with full configuration including capabilities, pricing, context limits, and modality support.

• Added GLM-4.7 (355B parameters, 205K context) with reasoning and tool calling support
• Added GLM-4.6V (335B parameters, 131K context) as a vision-language model with image input support
• Added DeepSeek-V3.2 (671B parameters, 164K context) with structured output capability

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 4 comments.

File	Description
providers/siliconflow/models/zai-org/GLM-4.7.toml	Adds configuration for Zhipu's GLM-4.7 flagship model with text input/output modalities
providers/siliconflow/models/zai-org/GLM-4.6V.toml	Adds configuration for GLM-4.6V vision-language model supporting text and image inputs
providers/siliconflow/models/deepseek-ai/DeepSeek-V3.2.toml	Adds configuration for DeepSeek-V3.2 with enhanced sparse attention and structured output support

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

The family name should use dots instead of dashes to match the existing naming convention. GLM-4.5 uses "glm-4.5" and GLM-4.6 uses "glm-4.6", so this should be "glm-4.7" instead of "glm-4-7".

Suggested change

	family = "glm-4-7"
	family = "glm-4.7"

[Copilot]

The family name should use dots instead of dashes to match the existing naming convention. GLM-4.5V uses "glm-4.5v", so this should be "glm-4.6v" instead of "glm-4-6v".

Suggested change

	family = "glm-4-6v"
	family = "glm-4.6v"

[Copilot]

The array formatting is inconsistent with the project standard. Arrays should have spaces after commas. This should be ["text", "image"] instead of ["text","image"].

Suggested change

	input = ["text","image"]
	input = ["text", "image"]

[Copilot]

The family name should be "deepseek-v3" to match the existing pattern. Other DeepSeek V3 variants (DeepSeek-V3, DeepSeek-V3.1, DeepSeek-V3.1-Terminus, DeepSeek-V3.2-Exp) all use "deepseek-v3" as the family name, regardless of their minor version differences.

Suggested change

	family = "deepseek-v3-2"
	family = "deepseek-v3"

[rekram1-node]

/oc can you update siliconflow cn too? believe we use symlinks

[opencode-agent]

Perfect! I've successfully updated the SiliconFlow CN provider with the 3 new models by creating symlinks to the corresponding models in the main SiliconFlow provider.

Summary

✅ Completed: Added 3 new SiliconFlow CN models via symlinks:

1. GLM-4.7.toml - Symlinked to ../../../siliconflow/models/zai-org/GLM-4.7.toml
2. GLM-4.6V.toml - Symlinked to ../../../siliconflow/models/zai-org/GLM-4.6V.toml
3. DeepSeek-V3.2.toml - Symlinked to ../../../siliconflow/models/deepseek-ai/DeepSeek-V3.2.toml

The SiliconFlow CN provider uses symlinks to reference models from the main SiliconFlow provider, which is exactly how I've implemented the updates. All changes have been validated successfully with bun validate showing no errors.

The symlinks are now in place at:

• providers/siliconflow-cn/models/zai-org/GLM-4.6V.toml ➜ ../../../siliconflow/models/zai-org/GLM-4.6V.toml
• providers/siliconflow-cn/models/zai-org/GLM-4.7.toml ➜ ../../../siliconflow/models/zai-org/GLM-4.7.toml
• providers/siliconflow-cn/models/deepseek-ai/DeepSeek-V3.2.toml ➜ ../../../siliconflow/models/deepseek-ai/DeepSeek-V3.2.toml

opencode session  |  github run

[opencode-agent]

User opencode-agent[bot] does not have write permissions

github run

[qychen2001]

/oc can you update siliconflow cn too? believe we use symlinks

siliconflow cn has some unique models, and I will further update them after this PR is accepted; some may not be directly symlinked.

[opencode-agent]

User qychen2001 does not have write permissions

github run

[rekram1-node]

ah okay good cal we can revert that then

[qychen2001]

The newly added models can all be symlinked, so I feel like there's no need to delete them, but SiliconFlow has some unique models, like gpt oss, which are not available in CN. CN also has some models that are not in SiliconFlow. I'm not sure how to best handle these differences.