Skip to content

Upgrade self-healing model to qwen3:8b#8

Open
philmcneely wants to merge 1 commit into
mainfrom
upgrade/self-healing-model
Open

Upgrade self-healing model to qwen3:8b#8
philmcneely wants to merge 1 commit into
mainfrom
upgrade/self-healing-model

Conversation

@philmcneely

Copy link
Copy Markdown
Owner

Summary

  • Default model changed from llama3.1:8b to qwen3:8b (newer, better code analysis, same size class)
  • Override via OLLAMA_MODEL env var for larger models on capable hardware

Test plan

  • Run with AI_HEALING_ENABLED=true against intentionally broken locator
  • Verify healing report generates with confidence score

Newer model with better code analysis for DOM healing. Same size
class so it runs anywhere. For better results on capable hardware,
set OLLAMA_MODEL=qwen3.5:35b-a3b-coding-nvfp4 in local .env.
Copilot AI review requested due to automatic review settings May 14, 2026 01:06
@github-actions

Copy link
Copy Markdown

✅ All smoke tests passed! View report

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Updates the project’s AI self-healing feature to use a newer default Ollama model (qwen3:8b) while preserving the ability to override via OLLAMA_MODEL.

Changes:

  • Switched the default OLLAMA_MODEL in OllamaAIHealingService from llama3.1:8b to qwen3:8b.
  • Updated the documented/default example value for OLLAMA_MODEL in .env.example.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File Description
utils/ai_healing.py Updates the default Ollama model used by the AI healing service and its env var documentation.
.env.example Updates the example/default Ollama model to match the new intended default.

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

Comment thread utils/ai_healing.py

Environment Variables:
OLLAMA_MODEL: Ollama model to use (default: llama3.1:8b)
OLLAMA_MODEL: Ollama model to use (default: qwen3:8b)
Comment thread .env.example
Comment on lines 52 to 54
#OLLAMA local model info - this is the config default for now
OLLAMA_MODEL=llama3.1:8b
OLLAMA_MODEL=qwen3:8b
OLLAMA_HOST=http://localhost:11434
@github-actions

Copy link
Copy Markdown

✅ All chromium login tests passed! View report

@github-actions

Copy link
Copy Markdown

✅ All firefox login tests passed! View report

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants