Fix failing GitHub Actions workflow for Integration: Workflow Misc Part 2#15722
Conversation
|
@copilot keep working |
Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Fixed! The test failure was caused by incorrect expectations - the test assumed Claude and Codex engines don't support LLM gateway, but they actually do (returning port numbers 10000 and 10001 respectively). Updated the test expectations to match the actual implementation. All "Workflow Misc Part 2" tests now pass. Commit: b6c638a |
pelikhan
deleted the
copilot/fix-github-actions-workflow-6d49c693-07d8-47c0-9592-2ab322cc2e76
branch
There was a problem hiding this comment.
Pull request overview
This PR fixes a failing test in the "Integration: Workflow Misc Part 2" GitHub Actions workflow by correcting incorrect test expectations about LLM gateway support for AI engines. The test TestCollectDockerImages_APIProxyForEnginesWithLLMGateway was expecting that Claude and Codex engines would NOT include the api-proxy Docker image, but the actual implementation shows both engines support LLM gateway (returning ports 10000 and 10001 respectively from SupportsLLMGateway()), which triggers inclusion of the api-proxy container.
Changes:
- Updated test expectations for Claude engine to
expectAPIProxy: true(port 10000) - Updated test expectations for Codex engine to
expectAPIProxy: true(port 10001) - Copilot engine expectations remain unchanged at
expectAPIProxy: false(returns -1)
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
* Initial plan * Changes before error encountered Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Refactor temporary ID validation into reusable helper function Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Fix TypeScript strict null check error in create_issue.cjs (#15721) * Initial plan * Fix TypeScript null check error in create_issue.cjs line 488 Wrap temporaryId with String() before passing to normalizeTemporaryId(). TypeScript's strict null checking was complaining that temporaryId could be null even though we checked for error earlier. The String() wrapper satisfies TypeScript's type system while maintaining the same runtime behavior (normalizeTemporaryId already does String() conversion internally). Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> * Fix failing GitHub Actions workflow for Integration: Workflow Misc Part 2 (#15722) * Initial plan * Fix docker_api_proxy_test expectations for LLM gateway support Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com> Co-authored-by: Peli de Halleux <pelikhan@users.noreply.github.com>
Fixed the failing test
TestCollectDockerImages_APIProxyForEnginesWithLLMGatewayin the "Integration: Workflow Misc Part 2" test suite.Root Cause
The test had incorrect expectations about LLM gateway support for AI engines:
SupportsLLMGateway()returning positive port numbers (10000 and 10001 respectively), which triggers the inclusion of the api-proxy imageChanges Made
Updated test expectations in
pkg/workflow/docker_api_proxy_test.goto correctly reflect actual LLM gateway support:expectAPIProxy: true(supports LLM gateway on port 10000)expectAPIProxy: true(supports LLM gateway on port 10001)expectAPIProxy: false(does not support LLM gateway)Testing
make fmtThe fix is minimal and surgical, only correcting the test expectations to match the actual implementation without modifying any production code.
Original prompt
💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.