e-volv

CI playbook

IncidentResponse

Treats CI failures on protected branches as potential incidents and starts the response.

When CI fails on a protected branch (main/master/develop/production), treats it as a potential production incident: reads the failure logs, investigates the cause in the code, assesses severity, and opens an incident ticket with a triage summary. Distinguishes transient infrastructure flakes (which it may retry once) from real breakage. Requires a connected ticket provider (Jira/Linear/ClickUp); degrades to an execution-log report if none.

Identifier
incident-response
Version
1.0.0
Steps
3
Triggers
1
  • incident
  • ci
  • reliability
  • on-call
  • automated

When it runs

CI resultci_workflow.completed
Settle delay
30s after the event

Only when all hold

  • ciWorkflow.conclusion equals failure
  • ciWorkflow.branch in main, master, develop, production, release
  • 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.

  1. 01
    CI Failed on Protected Branchtrigger

    The event that starts the run.

  2. 02
    Clone Failing Branchgit.clone

    Shallow-clones the repository at the right ref.

  3. 03
    Triage & Open Incidentagent.run

    One agent works the task with its toolkit.

The agent

Incident Responder

Base type
Senior Developer
Temperature
0.2
Max iterations
35
Tools
9

Tickets · 3

  • list_ticketsList Tickets · read
  • create_ticketCreate Ticket · write
  • add_comment_to_ticketAdd Comment to Ticket · write

CI/CD · 2

  • get_ci_run_logsGet CI Run Logs · read
  • retry_ci_workflowRetry CI Workflow · admin

Filesystem · 2

  • read_fileRead File · read
  • list_dirList Directory · read

Code search · 1

  • code_searchCode Search · read

Status · 1

  • update_statusUpdate Status · write