-
Notifications
You must be signed in to change notification settings - Fork 0
[PAT-5148] extend to have option for codex action #28
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
Closed
+133
−7
Closed
Changes from all commits
Commits
Show all changes
14 commits
Select commit
Hold shift + click to select a range
b52ccf2
extend to have option for codex action
ltang-wise 3b1cc38
update brancht o use v1test release
ltang-wise dbcd47f
use main again
ltang-wise d31dbba
use v1.4
ltang-wise c739f57
use main again
ltang-wise 1a270e8
use v1.4-test
ltang-wise fb2e064
test no container
ltang-wise 58ad09f
add safety-strategy: "unsafe"
ltang-wise a521112
test with container and new safety strategy
ltang-wise 4e3e44a
revert back to no container
ltang-wise 431429c
add eu openai URL
ltang-wise 12ea81d
add mcp__github__update_pull_request
moulougeta ddc473e
update prompt for pr and model
moulougeta d861b7e
add more allowed tools and display claude exec output
moulougeta File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -48,22 +48,93 @@ on: | |
| description: "LLM model to use for general purpose tasks" | ||
| required: false | ||
| type: string | ||
| codex_model: | ||
| description: "OpenAI model to use for Codex agent" | ||
| required: false | ||
| type: string | ||
| default: "o3" | ||
|
|
||
| jobs: | ||
| run-ci-ai-agent: | ||
| detect-agent: | ||
| if: | | ||
| inputs.event_name == 'issues' || | ||
| inputs.event_name == 'issue_comment' || | ||
| inputs.event_name == 'pull_request' || | ||
| inputs.event_name == 'pull_request_review_comment' || | ||
| inputs.event_name == 'pull_request_review' | ||
| runs-on: gha-production-medium | ||
| outputs: | ||
| agent: ${{ steps.parse.outputs.agent }} | ||
| codex_prompt: ${{ steps.parse.outputs.codex_prompt }} | ||
| steps: | ||
| - name: Parse agent from comment | ||
| id: parse | ||
| shell: bash | ||
| env: | ||
| EVENT_PAYLOAD: ${{ inputs.event_payload }} | ||
| run: | | ||
| comment=$(echo "$EVENT_PAYLOAD" | jq -r '.comment.body // .review.body // .issue.body // ""') | ||
|
|
||
| if echo "$comment" | grep -q '/codex-'; then | ||
| echo "agent=codex" >> $GITHUB_OUTPUT | ||
| # Extract the command after /codex- (e.g., "review-pr" from "/codex-review-pr") | ||
| codex_cmd=$(echo "$comment" | grep -oE '/codex-[^ ]+' | head -1 | sed 's|/codex-||') | ||
|
||
| # Extract any additional context after the command on the same line or following lines | ||
| full_prompt=$(echo "$comment" | sed -n '/\/codex-/,$p' | sed '1s|.*/codex-[^ ]*||') | ||
|
||
| echo "codex_prompt=${codex_cmd}${full_prompt}" >> $GITHUB_OUTPUT | ||
| else | ||
| echo "agent=claude" >> $GITHUB_OUTPUT | ||
| echo "codex_prompt=" >> $GITHUB_OUTPUT | ||
| fi | ||
|
|
||
| run-claude-agent: | ||
| needs: detect-agent | ||
| if: needs.detect-agent.outputs.agent == 'claude' | ||
| runs-on: gha-production-medium | ||
| container: ci-images-release.arti.tw.ee/actions_java_17_and_21 | ||
| permissions: | ||
| contents: write | ||
| pull-requests: write | ||
| issues: write | ||
| id-token: write | ||
| actions: read | ||
| env: | ||
| PR_PROMPT: | | ||
| REPO: ${{ github.repository }} | ||
| PR NUMBER: ${{ github.event.pull_request.number }} | ||
|
|
||
| Perform a comprehensive code review with the following focus areas: | ||
|
|
||
| 1. **Code Quality** | ||
| - Clean code principles and best practices | ||
| - Proper error handling and edge cases | ||
| - Code readability and maintainability | ||
|
|
||
| 2. **Security** | ||
| - Check for potential security vulnerabilities | ||
| - Validate input sanitization | ||
| - Review authentication/authorization logic | ||
|
|
||
| 3. **Performance** | ||
| - Identify potential performance bottlenecks | ||
| - Review database queries for efficiency | ||
| - Check for memory leaks or resource issues | ||
|
|
||
| 4. **Testing** | ||
| - Verify adequate test coverage | ||
| - Review test quality and edge cases | ||
| - Check for missing test scenarios | ||
|
|
||
| 5. **Documentation** | ||
| - Ensure code is properly documented | ||
| - Verify README updates for new features | ||
| - Check API documentation accuracy | ||
|
|
||
| Provide detailed feedback using inline comments for specific issues. | ||
| Use top-level comments for general observations or praise. | ||
| Update the PR description section in the PR body with a concise summary for the human | ||
| reviewer that surfaces security and correctness risks, highlights suspicious diffs, and | ||
| provides a brief change summary. | ||
| steps: | ||
| - name: Checkout repository | ||
| uses: actions/checkout@v5 | ||
|
|
@@ -93,6 +164,7 @@ jobs: | |
| - name: Run AI Agent | ||
| uses: transferwise/claude-code-action@main | ||
| with: | ||
| prompt: ${{ inputs.event_name == 'pull_request' && env.PR_PROMPT || '' }} | ||
| trigger_phrase: "/run-ci-ai-agents" | ||
| use_commit_signing: "true" | ||
| anthropic_bedrock_base_url: ${{ secrets.ANTHROPIC_BEDROCK_BASE_URL }} | ||
|
|
@@ -106,5 +178,59 @@ jobs: | |
| api.github.com | ||
| ${{ secrets.ANTHROPIC_BEDROCK_BASE_URL }} | ||
| claude_args: | | ||
| --allowedTools "mcp__github_inline_comment__create_inline_comment,mcp__github_file_ops__commit_files,mcp__github_file_ops__delete_files" | ||
| --model ${{ inputs.generic_model != '' && inputs.generic_model || vars.ANTHROPIC_DEFAULT_HAIKU_MODEL }} | ||
| --allowedTools "Bash(gh pr comment:*),Bash(gh pr diff:*),Bash(gh pr view:*),mcp__github_inline_comment__create_inline_comment,mcp__github_file_ops__commit_files,mcp__github_file_ops__delete_file,mcp__github__update_pull_request" | ||
| --model ${{ inputs.generic_model != '' && inputs.generic_model || vars.ANTHROPIC_DEFAULT_OPUS_MODEL }} | ||
|
|
||
| - name: Show Claude execution output | ||
| if: always() | ||
| run: | | ||
| cat /__w/_temp/claude-execution-output.json | ||
|
|
||
| run-codex-agent: | ||
| needs: detect-agent | ||
| if: needs.detect-agent.outputs.agent == 'codex' | ||
| runs-on: gha-production-medium | ||
| # container: ci-images-release.arti.tw.ee/actions_java_17_and_21 | ||
| permissions: | ||
| contents: write | ||
| pull-requests: write | ||
| issues: write | ||
| id-token: write | ||
| actions: read | ||
| steps: | ||
| - name: Checkout repository | ||
| uses: actions/checkout@v5 | ||
| with: | ||
| fetch-depth: 1 | ||
|
|
||
| - name: "Add repo as safe directory" | ||
| run: | | ||
| git config --global --add safe.directory "$GITHUB_WORKSPACE" | ||
|
|
||
| - name: Sync caller event context | ||
| shell: bash | ||
| env: | ||
| CALLER_EVENT_PAYLOAD: ${{ inputs.event_payload }} | ||
| run: | | ||
| event_file="$RUNNER_TEMP/original_event.json" | ||
| printf '%s' "$CALLER_EVENT_PAYLOAD" > "$event_file" | ||
| { | ||
| echo "GITHUB_EVENT_PATH=$event_file" | ||
| echo "GITHUB_EVENT_NAME=${{ inputs.event_name }}" | ||
| echo "GITHUB_REPOSITORY=${{ inputs.repository }}" | ||
| echo "GITHUB_REF=${{ inputs.ref }}" | ||
| echo "GITHUB_SHA=${{ inputs.sha }}" | ||
| echo "GITHUB_ACTOR=${{ inputs.actor }}" | ||
| } >> "$GITHUB_ENV" | ||
|
|
||
| - name: Run Codex Agent | ||
| uses: transferwise/codex-action@v1.4-test | ||
| env: | ||
| GITHUB_API_URL: https://eu.api.openai.com | ||
| with: | ||
| prompt: ${{ needs.detect-agent.outputs.codex_prompt }} | ||
| openai-api-key: ${{ secrets.OPENAI_API_KEY }} | ||
| model: ${{ inputs.codex_model }} | ||
| sandbox: "workspace-write" | ||
| allow-users: "*" | ||
| safety-strategy: "unsafe" | ||
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
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.
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 jq expression '.comment.body // .review.body // .issue.body' may not extract the correct content for all event types. For issue_comment events on pull requests, the comment body is correct, but for issues events, you should check both issue.body and issue.title (as done in the trigger condition on line 19). The current implementation doesn't check issue.title, which means /codex- commands in issue titles won't be detected by this parsing logic.