Use Claude Sonnet 4.6 as the default integration test model - #2200
Merged
JasonYeMSFT (JasonYeMSFT) merged 2 commits intoMay 11, 2026
Merged
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
Updates the integration test default model from Claude Sonnet 4.5 to 4.6 to reflect current usage telemetry.
Changes:
- Switches the agent runner’s default model string to
claude-sonnet-4.6 - Updates workflow input model options from 4.5 to 4.6
- Updates the issue template reference to the new default model
Show a summary per file
| File | Description |
|---|---|
| tests/utils/agent-runner.ts | Changes the default session/usage model to Sonnet 4.6 via a shared constant |
| .github/workflows/test-azure-deploy.yml | Updates workflow dispatch model choices to 4.6 variants |
| .github/workflows/test-all-integration.yml | Updates workflow dispatch model choices to 4.6 variants |
| .github/skills/analyze-test-run/references/issue-template.md | Updates the documented default model to Sonnet 4.6 |
Copilot's findings
- Files reviewed: 4/4 changed files
- Comments generated: 4
Jon Gallant (jongio)
approved these changes
May 8, 2026
Jon Gallant (jongio)
left a comment
Jon Gallant (jongio)
left a comment
Collaborator
There was a problem hiding this comment.
Clean config change. Const extraction in agent-runner.ts removes the duplication correctly, workflow options and issue template are consistent. Telemetry justification is solid.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Telemetry of our VS Code extension indicates the usage of Sonnet 4.6 has far exceeded the usage of Sonnet 4.5. This PR upgrades the default model of integration tests to Sonnet 4.6.
Here are the exact percentage of model usage from last week.
5/4/2026, 12:00:00 AM Auto 25.425742574257427
5/4/2026, 12:00:00 AM ClaudeHaiku45 6.178217821782178
5/4/2026, 12:00:00 AM ClaudeOpus46 8.158415841584159
5/4/2026, 12:00:00 AM ClaudeSonnet45 5.02970297029703
5/4/2026, 12:00:00 AM ClaudeSonnet46 24.91089108910891
5/4/2026, 12:00:00 AM GPT41 6.574257425742575
Checklist
cd tests && npm test)npm run test:skills:integration -- <skill>)USE FOR/DO NOT USE FOR/PREFER OVERclauses: confirmed no routing regressions for competing skillsRelated Issues