When CI fails on a pull request, reads the failure logs, locates the root cause in the PR's diff, and posts inline suggestions plus a summary comment with a proposed fix. Non-blocking — the author decides whether to apply.
- Identifier
fix-ci- Version
- 1.0.1
- Steps
- 3
- Triggers
- 1
- ci
- testing
- diagnostics
- automated
- review
When it runs
ci_workflow.completed- Settle delay
- 30s after the event
Only when all hold
- ciWorkflow.conclusion equals failure
- ciWorkflow.branch not in main, master, develop, production
- actor.username not contains [bot]
The pipeline
The graph below is the one the workflow opens with in the builder — same steps, same layout, drawn on the same canvas. The run playing through it is a simulation; the branches and conditions are real.
- 01CI Workflow Failed
triggerThe event that starts the run.
- 02Clone Repository (failing branch)
git.cloneShallow-clones the repository at the right ref.
- 03Diagnose CI Failure
agent.runOne agent works the task with its toolkit.
The agent
CI Fix Diagnostician
- Base type
- Senior Developer
- Temperature
- 0.2
- Max iterations
- 30
- Tools
- 12
Git provider · 6
list_pull_requestsList Pull Requests · readread_pull_requestRead Pull Request · readget_pull_request_diffGet Pull Request Diff · readadd_pull_request_review_threadAdd PR Review Thread · writeadd_comment_to_pull_requestAdd Comment to Pull Request · writesubmit_reviewSubmit Review · write
CI/CD · 2
list_pr_ci_runsList PR CI Runs · readget_ci_run_logsGet CI Run Logs · read
Filesystem · 2
read_fileRead File · readlist_dirList Directory · read
Code search · 1
code_searchCode Search · read
Status · 1
update_statusUpdate Status · write
Related playbooks
Flaky Test Detector
Runs the test suite five times on the same commit and files a ticket for every non-deterministic test.
Test Coverage Gap Analysis
Finds untested code paths in PRs and turns the gaps into actionable test tickets.
Write Tests on Command
Comment /write-tests on a PR and an agent writes, runs, and pushes tests to the branch.