george larson

icon indicating a website link https://georgelarson.me icon indicating an email [email protected]

icon location Experienced technology leader with a diverse background spanning software engineering, infrastructure management, and business process optimization.

Results 3 issues of george larson

fix(write): handle array content from GLM and Qwen models

3 comment

## Problem Some models (GLM 4.6, Qwen 3 Coder 480B) send the write tool's `content` parameter as an array of strings instead of a single string, causing validation errors: ```...

provider: qwen

feat(venice): add additional models to Venice.ai provider

## Summary Expands Venice.ai model selection from 5 to 13 models, providing more options for different use cases. ## Changes - Add Llama 3.1 models (405B, 70B, 8B) - Add...

fix(write): support array content from Venice.ai models

12 comment

Some AI models (e.g., GLM 4.6, Qwen 3 Coder 480B) send tool call content as arrays instead of strings. This causes the write tool to fail with: 'Invalid input: expected...