Skip to content

Updated smoke copilot to use latest gateway#719

Merged
lpcox merged 1 commit intomainfrom
lpcox/update-aw
Feb 5, 2026
Merged

Updated smoke copilot to use latest gateway#719
lpcox merged 1 commit intomainfrom
lpcox/update-aw

Conversation

@lpcox
Copy link
Collaborator

@lpcox lpcox commented Feb 5, 2026

No description provided.

Copilot AI review requested due to automatic review settings February 5, 2026 18:38
@lpcox lpcox merged commit 28fb640 into main Feb 5, 2026
3 checks passed
@lpcox lpcox deleted the lpcox/update-aw branch February 5, 2026 18:39
Copy link
Contributor

Copilot AI left a 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 smoke-copilot workflow to use the latest tag for the gh-aw-mcpg Docker gateway image instead of a pinned version (v0.0.99). The change affects both the image download step and the Docker command configuration.

Changes:

  • Updated gh-aw-mcpg Docker image reference from v0.0.99 to latest in two locations within the smoke-copilot workflow
Comments suppressed due to low confidence (1)

.github/workflows/smoke-copilot.lock.yml:210

  • Using the latest tag for Docker images in CI/CD workflows introduces non-deterministic behavior and potential instability. The workflow is currently pinning most other Docker images to specific versions (e.g., agent-act:0.13.4, squid:0.13.4, github-mcp-server:v0.30.3), but this change pins gh-aw-mcpg to latest while other workflows in the repository continue to use pinned versions like v0.0.98 or v0.0.99.

This creates several issues:

  1. Reproducibility: The workflow behavior can change unexpectedly when a new version is published
  2. Debugging difficulty: If issues arise, it's harder to identify which version caused the problem
  3. Inconsistency: Other workflows (smoke-codex, daily-compliance-checker, etc.) still use pinned versions like v0.0.98, creating version drift across the repository
  4. Rollback complexity: If the latest version has issues, there's no easy way to roll back to a known good version

Consider pinning to a specific version (e.g., the current latest version number) instead of using the latest tag, consistent with the versioning approach for other Docker images in this workflow and across the repository.

        run: bash /opt/gh-aw/actions/download_docker_images.sh alpine:latest ghcr.io/github/gh-aw-firewall/agent-act:0.13.4 ghcr.io/github/gh-aw-firewall/squid:0.13.4 ghcr.io/github/gh-aw-mcpg:latest ghcr.io/github/github-mcp-server:v0.30.3 ghcr.io/github/serena-mcp-server:latest mcr.microsoft.com/playwright/mcp node:lts-alpine

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

echo "::add-mask::${MCP_GATEWAY_API_KEY}"
export GH_AW_ENGINE="copilot"
export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network host -v /var/run/docker.sock:/var/run/docker.sock -e MCP_GATEWAY_PORT -e MCP_GATEWAY_DOMAIN -e MCP_GATEWAY_API_KEY -e DEBUG -e MCP_GATEWAY_LOG_DIR -e GH_AW_MCP_LOG_DIR -e GH_AW_SAFE_OUTPUTS -e GH_AW_SAFE_OUTPUTS_CONFIG_PATH -e GH_AW_SAFE_OUTPUTS_TOOLS_PATH -e GH_AW_ASSETS_BRANCH -e GH_AW_ASSETS_MAX_SIZE_KB -e GH_AW_ASSETS_ALLOWED_EXTS -e DEFAULT_BRANCH -e GITHUB_MCP_SERVER_TOKEN -e GITHUB_MCP_LOCKDOWN -e GITHUB_REPOSITORY -e GITHUB_SERVER_URL -e GITHUB_SHA -e GITHUB_WORKSPACE -e GITHUB_TOKEN -e GITHUB_RUN_ID -e GITHUB_RUN_NUMBER -e GITHUB_RUN_ATTEMPT -e GITHUB_JOB -e GITHUB_ACTION -e GITHUB_EVENT_NAME -e GITHUB_EVENT_PATH -e GITHUB_ACTOR -e GITHUB_ACTOR_ID -e GITHUB_TRIGGERING_ACTOR -e GITHUB_WORKFLOW -e GITHUB_WORKFLOW_REF -e GITHUB_WORKFLOW_SHA -e GITHUB_REF -e GITHUB_REF_NAME -e GITHUB_REF_TYPE -e GITHUB_HEAD_REF -e GITHUB_BASE_REF -e GH_AW_SAFE_INPUTS_PORT -e GH_AW_SAFE_INPUTS_API_KEY -e GH_AW_SAFE_OUTPUTS_PORT -e GH_AW_SAFE_OUTPUTS_API_KEY -e GH_AW_GH_TOKEN -e GH_DEBUG -e GH_TOKEN -e TAVILY_API_KEY -v /opt:/opt:ro -v /tmp:/tmp:rw -v '"${GITHUB_WORKSPACE}"':'"${GITHUB_WORKSPACE}"':rw ghcr.io/github/gh-aw-mcpg:v0.0.99'
export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network host -v /var/run/docker.sock:/var/run/docker.sock -e MCP_GATEWAY_PORT -e MCP_GATEWAY_DOMAIN -e MCP_GATEWAY_API_KEY -e DEBUG -e MCP_GATEWAY_LOG_DIR -e GH_AW_MCP_LOG_DIR -e GH_AW_SAFE_OUTPUTS -e GH_AW_SAFE_OUTPUTS_CONFIG_PATH -e GH_AW_SAFE_OUTPUTS_TOOLS_PATH -e GH_AW_ASSETS_BRANCH -e GH_AW_ASSETS_MAX_SIZE_KB -e GH_AW_ASSETS_ALLOWED_EXTS -e DEFAULT_BRANCH -e GITHUB_MCP_SERVER_TOKEN -e GITHUB_MCP_LOCKDOWN -e GITHUB_REPOSITORY -e GITHUB_SERVER_URL -e GITHUB_SHA -e GITHUB_WORKSPACE -e GITHUB_TOKEN -e GITHUB_RUN_ID -e GITHUB_RUN_NUMBER -e GITHUB_RUN_ATTEMPT -e GITHUB_JOB -e GITHUB_ACTION -e GITHUB_EVENT_NAME -e GITHUB_EVENT_PATH -e GITHUB_ACTOR -e GITHUB_ACTOR_ID -e GITHUB_TRIGGERING_ACTOR -e GITHUB_WORKFLOW -e GITHUB_WORKFLOW_REF -e GITHUB_WORKFLOW_SHA -e GITHUB_REF -e GITHUB_REF_NAME -e GITHUB_REF_TYPE -e GITHUB_HEAD_REF -e GITHUB_BASE_REF -e GH_AW_SAFE_INPUTS_PORT -e GH_AW_SAFE_INPUTS_API_KEY -e GH_AW_SAFE_OUTPUTS_PORT -e GH_AW_SAFE_OUTPUTS_API_KEY -e GH_AW_GH_TOKEN -e GH_DEBUG -e GH_TOKEN -e TAVILY_API_KEY -v /opt:/opt:ro -v /tmp:/tmp:rw -v '"${GITHUB_WORKSPACE}"':'"${GITHUB_WORKSPACE}"':rw ghcr.io/github/gh-aw-mcpg:latest'
Copy link

Copilot AI Feb 5, 2026

Choose a reason for hiding this comment

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

The same concern about using the latest tag applies here in the Docker command. This creates a mismatch risk where the downloaded image at line 210 might not match the version referenced in this Docker command if they're pulled at different times or if caching behaves unexpectedly.

For production stability and consistency with other workflows in the repository, consider using a pinned version tag instead of latest.

Copilot uses AI. Check for mistakes.
@lpcox lpcox restored the lpcox/update-aw branch February 5, 2026 18:55
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.

1 participant