-
Notifications
You must be signed in to change notification settings - Fork 2.3k
fix: remove qwen3-coder from provider/mcp smoke tests #5551
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
This PR updates the test scripts to remove references to specific AI models that are no longer being tested. The changes remove qwen/qwen3-coder from the OpenRouter provider tests and replace it with gemini-2.5-flash in the MCP test script.
Key changes:
- Removed
qwen/qwen3-coderfrom OpenRouter provider tests intest_providers.sh - Replaced
qwen/qwen3-coderwithgemini-2.5-flashin OpenRouter provider tests intest_mcp.sh
Reviewed Changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| scripts/test_providers.sh | Removed qwen/qwen3-coder from the OpenRouter provider test configuration |
| scripts/test_mcp.sh | Replaced qwen/qwen3-coder with gemini-2.5-flash for OpenRouter provider testing |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
scripts/test_mcp.sh
Outdated
| "anthropic:claude-haiku-4-5-20251001" | ||
| "google:gemini-2.5-flash" | ||
| "openrouter:qwen/qwen3-coder" | ||
| "openrouter:gemini-2.5-flash" |
Copilot
AI
Nov 3, 2025
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The model identifier gemini-2.5-flash appears to be missing the provider prefix. Based on the pattern in line 18 of this file (google/gemini-2.5-flash) and line 18 of test_providers.sh (google/gemini-2.5-flash), OpenRouter model identifiers should include the provider namespace. This should likely be google/gemini-2.5-flash to be consistent with OpenRouter's model naming convention.
| "openrouter:gemini-2.5-flash" | |
| "openrouter:google/gemini-2.5-flash" |
93e6879 to
956d22c
Compare
956d22c to
0cb85b6
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
Copilot reviewed 2 out of 2 changed files in this pull request and generated no new comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
|
@alexhancock are you sure it isn't a regression, as it was I thought reliably working. The aim of these is to catch drift in Goose so fi it adds something that breaks popular models then we have a regression. (I think this is https://openrouter.ai/qwen/qwen3-coder model?) - if it doesn't work for this, we have regressed something in goose. |
* 'main' of github.com:block/goose: (21 commits) Manual compaction counting fix + cli cleanup (#5480) chore(deps): bump prismjs and react-syntax-highlighter in /ui/desktop (#5549) fix: remove qwen3-coder from provider/mcp smoke tests (#5551) fix: do not build unsigned desktop app bundles on every PR in ci. add manual option. (#5550) fix: update Husky prepare script to v9 format (#5522) Fix 404 for responsible coding guide (#5543) fix hermit `text file busy` issues on linux (#5372) Fix image processing (#5544) docs: AI attribution for PRs (#5547) chore(tests/mcp): testing for MCP sampling (#5456) docs: adding HOWTOAI.md (#5533) added configuration content, also added signoff, fix merging issue with another commit by creating a clean branch. removed and closed commits that caused signoff issues. (#5519) Fixes Gemini API parse issue by converting nullable type arrays to single types in tool schemas (#5530) Troubleshooting diagnostics doc (#5526) fix link to Ollama FAQ (#5531) docs: remove speech-mcp (#5514) fix: adds ProviderRetry to openai provider (#5518) docs: extensions directory minor updates (#5466) Docs/json recipe support (#5492) docs: recipe buttons (#5507) ...
* main: (85 commits) improve linux tray icon support (#5425) feat: log rotation (#5561) use app.isPackaged instead of checking for node env development (#5465) disable RPM build-ID generation to prevent package conflicts (#5563) Add Diagnostics Info to Q&A and Bug Report Templates (#5565) fix: improve server error messages to include HTTP status code (#5532) improvement: add useful error message when attempting to use unauthenticated cursor-agent (#5300) fix: unblock acp via databricks (#5562) feat: add --output-format json flag to goose run command (#5525) Sessions required (#5548) feat: add grouped extension loading notification (#5529) we should run this on main and also test open models at least via ope… (#5556) info: print location of sessions.db via goose info (#5557) chore: remove yarn usage from documentation (#5555) cli: adjust default theme to address #1905 (#5552) Manual compaction counting fix + cli cleanup (#5480) chore(deps): bump prismjs and react-syntax-highlighter in /ui/desktop (#5549) fix: remove qwen3-coder from provider/mcp smoke tests (#5551) fix: do not build unsigned desktop app bundles on every PR in ci. add manual option. (#5550) fix: update Husky prepare script to v9 format (#5522) ...
* main: (54 commits) add clippy warning for string_slice (#5422) improve linux tray icon support (#5425) feat: log rotation (#5561) use app.isPackaged instead of checking for node env development (#5465) disable RPM build-ID generation to prevent package conflicts (#5563) Add Diagnostics Info to Q&A and Bug Report Templates (#5565) fix: improve server error messages to include HTTP status code (#5532) improvement: add useful error message when attempting to use unauthenticated cursor-agent (#5300) fix: unblock acp via databricks (#5562) feat: add --output-format json flag to goose run command (#5525) Sessions required (#5548) feat: add grouped extension loading notification (#5529) we should run this on main and also test open models at least via ope… (#5556) info: print location of sessions.db via goose info (#5557) chore: remove yarn usage from documentation (#5555) cli: adjust default theme to address #1905 (#5552) Manual compaction counting fix + cli cleanup (#5480) chore(deps): bump prismjs and react-syntax-highlighter in /ui/desktop (#5549) fix: remove qwen3-coder from provider/mcp smoke tests (#5551) fix: do not build unsigned desktop app bundles on every PR in ci. add manual option. (#5550) ...
Signed-off-by: fbalicchia <[email protected]>
Signed-off-by: Blair Allan <[email protected]>
Noticing the
qwen3-coderoften produces failing test results in test_providers.sh an test_mcp.sh because it doesn't reliably call the tools we expectMost recent example where it simply didn't call the
sampleLLMtool when it is directly told to do so by the test script https://github.com/block/goose/actions/runs/19044249135/job/54389311803?pr=5550