fix: improve GLM model detection patterns for LM Studio and OpenAI-compatible endpoints

[ghost]

This PR attempts to address Issue #11071 where GLM4.5 models via LM Studio or OpenAI-compatible endpoints get stuck repeating file reads.

Problem

The user reported that model names like:

• mlx-community/GLM-4.5-4bit
• GLM-4.5-UD-Q8_K_XL-00001-of-00008.gguf
• glm-4.5

were not being detected as GLM models, causing the optimizations for GLM models to not be applied.

Solution

Created a flexible isGlmModel() utility function that uses a simple regex pattern (/glm/i) to detect GLM anywhere in the model ID, case-insensitively. This handles:

• Standard Z.ai format: glm-4.5, glm-4.6, glm-4.7
• MLX format: mlx-community/GLM-4.5-4bit
• GGUF format: GLM-4.5-UD-Q8_K_XL-00001-of-00008.gguf
• HuggingFace format: THUDM/glm-4-9b-chat
• ChatGLM variants: chatglm-6b, chatglm2-6b

Changes

1. New utility (src/api/providers/utils/glm-model-detection.ts):

   • isGlmModel(modelId) - Detects if a model ID represents a GLM model
   • getGlmModelOptions(modelId) - Returns recommended options for GLM models

2. LmStudioHandler - Now detects GLM models and applies:

   • mergeToolResultText: true - Prevents conversation flow disruption
   • parallel_tool_calls: false - Disabled as GLM may not support it

3. BaseOpenAiCompatibleProvider - Same GLM detection and optimizations

4. Tests - 41 tests covering various GLM model name formats

Feedback and guidance are welcome!

---

Important

Introduces GLM model detection utility and updates handlers to apply GLM-specific options, with tests for various model formats.

• Utility Function (glm-model-detection.ts):
  • isGlmModel(modelId): Detects GLM models using regex /glm/i.
  • getGlmModelOptions(modelId): Returns options for GLM models, disabling parallel_tool_calls and enabling mergeToolResultText.
• Handlers:
  • LmStudioHandler and BaseOpenAiCompatibleProvider now use getGlmModelOptions() to apply GLM-specific options.
• Tests (glm-model-detection.spec.ts):
  • 41 tests added for various GLM model name formats to ensure correct detection and option application.

^{This description was created by for 0016aa0. You can customize this summary. It will automatically update as commits are pushed.}

[ghost]

Rooviewer   See task on Roo Cloud

Review complete. No issues found.

The implementation is clean and follows established patterns in the codebase. The GLM detection uses the existing mergeToolResultText option (already used by DeepSeek and Z.ai) and all 41 tests pass.

_{Mention @roomote in a comment to request specific changes to this pull request or fix all unresolved issues.}