Auto-Sync GitHub Issues to Jira: GPT-4o Bug Analysis & Team Alerts

GitHub Webhook → GPT-4o severity & category analysis → Jira ticket creation → parallel Slack/Discord/GitHub notifications

Who

Development teams, open-source maintainers, or DevOps engineers who need automated GitHub bug triage

You get

New GitHub issues trigger AI analysis to create Jira tickets with severity, category, reproduction steps, and time estimates, while posting back to GitHub and alerting Slack/Discord

You need

n8n · webhook · code · openai · github · slack

Steps

1. Configure GitHub Webhook Trigger

   Activate the workflow in n8n and copy the Webhook node URL. Go to GitHub repo Settings → Webhooks → Add webhook, paste the URL, set Content-type to application/json, select Issues events, and save. Test by creating a new issue.

2. Filter Only New Issues

   Add an IF node with condition action = "opened" (via {{$json.action}}). TRUE continues, FALSE stops. Prevents duplicate Jira tickets from edits, labels, or comments.

3. Extract Issue Context

   Use a Code node to run JavaScript extracting issue number, title, description, reporter, labels, URL, repo info, and regex-match mentioned code files (.js/.py/.ts/.jsx/.tsx/.java/.go/.rb/.php/.cpp/.c/.css/.html) from the GitHub payload. Output a structured object for downstream nodes. Node code: ```js const issue = $input.item.json.issue; const repo = $input.item.json.repository; const fileRegex = /`([^`]*\.(js|py|ts|jsx|tsx|java|go|rb|php|cpp|c|css|html))`/g; const mentionedFiles = []; let match; if (issue.body) { while ((match = fileRegex.exec(issue.body)) !== null) { mentionedFiles.push(match[1]); } } return { issueNumber: issue.number, title: issue.title, description: issue.body || "No description provided", reporter: issue.user.login, reporterAvatar: issue.user.avatar_url, labels: issue.labels.map(l => l.name).join(", ") || "none", url: issue.html_url, createdAt: issue.created_at, mentionedFiles: mentionedFiles.join(", ") || "No files mentioned", repositoryName: repo.full_name, repositoryOwner: repo.owner.login, repositoryRepo: repo.name }; ```

4. GPT-4o Bug Analysis

   Use the OpenAI node calling GPT-4o (model: gpt-4o, maxTokens: 1000, temperature: 0.3). Pass the extracted issue title, description, labels, mentioned files, and repository name in the prompt, requiring strict JSON output with severity, category, reproduction steps, root cause, priority, complexity, recommended developer type, and estimated hours.

   Execution prompt · Source text。GPT-4o Bug Analysis node text field

   Copy prompt

   =Analyze this GitHub issue and provide a structured response in valid JSON format:
   
   **Issue Title:** {{$json.title}}
   **Description:** {{$json.description}}
   **Labels:** {{$json.labels}}
   **Mentioned Files:** {{$json.mentionedFiles}}
   **Repository:** {{$json.repositoryName}}
   
   Provide your analysis in this exact JSON structure:
   {
     "bugSeverity": "Critical|High|Medium|Low",
     "category": "Backend|Frontend|Database|API|UI|Performance|Security|Infrastructure",
     "reproductionSteps": "Clear numbered steps to reproduce",
     "potentialRootCause": "Brief technical analysis",
     "suggestedPriority": "P0|P1|P2|P3",
     "estimatedComplexity": "Simple|Medium|Complex",
     "recommendedDeveloper": "backend-dev|frontend-dev|fullstack-dev|devops",
     "estimatedHours": "number between 1-40"
   }
   
   Respond with ONLY the JSON object, no additional text.

5. Parse GPT Response & Map Data

   Use a Code node to parse the GPT-4o JSON response (with fallback defaults on parse failure: Medium/General/P2/Medium/fullstack-dev/8h). Map recommendedDeveloper to actual email addresses, convert suggestedPriority to Jira priorities (P0→Highest, P1→High, P2→Medium, P3→Low), and build the jiraLabels array. ⚠️ You must customize developerMapping emails. Node code: ```js const issueData = $('Extract Issue Context').item.json; const gptResponse = $input.item.json.text; let analysis; try { analysis = JSON.parse(gptResponse); } catch (error) { analysis = { bugSeverity: "Medium", category: "General", reproductionSteps: "See original issue", potentialRootCause: "Requires investigation", suggestedPriority: "P2", estimatedComplexity: "Medium", recommendedDeveloper: "fullstack-dev", estimatedHours: 8 }; } const developerMapping = { "backend-dev": "[email protected]", "frontend-dev": "[email protected]", "fullstack-dev": "[email protected]", "devops": "[email protected]" }; const priorityMapping = { "P0": "Highest", "P1": "High", "P2": "Medium", "P3": "Low" }; return { ...issueData, bugSeverity: analysis.bugSeverity, category: analysis.category, reproductionSteps: analysis.reproductionSteps, potentialRootCause: analysis.potentialRootCause, suggestedPriority: analysis.suggestedPriority, estimatedComplexity: analysis.estimatedComplexity, estimatedHours: analysis.estimatedHours, recommendedDeveloper: analysis.recommendedDeveloper, assignedDeveloper: developerMapping[analysis.recommendedDeveloper] || "[email protected]", jiraLabels: [analysis.category, analysis.bugSeverity], jiraPriority: priorityMapping[analysis.suggestedPriority] || "Medium" }; ```

6. Create Jira Ticket

   Use the Jira node to create a Bug issue. Set project to YOUR_JIRA_PROJECT_KEY, summary format to [GitHub #{issueNumber}] {title}, description includes reporter, GitHub link, original description, and AI analysis summary (severity, category, complexity, estimated hours, mentioned files, reproduction steps, root cause). additionalFields sets labels, assignee, and priority. Replace your-company.atlassian.net with your actual domain.

7. Parallel Notify GitHub/Slack/Discord

   After Jira ticket creation, three branches execute in parallel: 1) GitHub node adds a comment to the original issue with Jira link, AI summary, assigned developer, and estimated time; 2) Slack node sends a rich message to the dev-alerts channel with title, severity, category, priority, assignee, estimated hours, root cause summary, and View in GitHub/Jira buttons; 3) Discord node sends a Markdown alert via webhook. Configure respective credentials and channel/webhook URLs.

8. Return Webhook Response

   Use Respond to Webhook node to return JSON: {"status": "success", "message": "Bug report processed", "jiraTicket": $json.key}. Confirms successful processing, prevents GitHub retries, and logs are visible at GitHub Settings → Webhooks → Recent Deliveries.