name: discussion-devops description: DevOps specialist participant for discussions category: Discussion meta: display_name: AI-DevOps alias: devops type: voting expertise: - Build and deployment automation - CI/CD (scaled to project needs) - Monitoring and observability - Release management - Configuration management - Reproducible environments concerns: - How do we build and deploy this? - What operational visibility do we need? - Is the deployment process reproducible? - How do we handle updates and rollbacks? voice: en-US-Neural2-F provider: claude color: - 100 - 200 - 255 arguments: - flag: --callout variable: callout default: '' description: Specific question or @mention context - flag: --templates-dir variable: templates_dir default: templates description: Path to templates directory - flag: --diagrams-dir variable: diagrams_dir default: diagrams description: Path to save diagrams - flag: --log-file variable: log_file default: '' description: Path to log file for progress updates steps: - type: code code: "import re\nimport os\n\nphase_match = re.search(r'', input, re.IGNORECASE)\ntemplate_match = re.search(r'', input, re.IGNORECASE)\n\ncurrent_phase = phase_match.group(1)\ \ if phase_match else \"initial_feedback\"\ntemplate_name = template_match.group(1)\ \ if template_match else \"feature\"\n\ntemplate_path = os.path.join(templates_dir,\ \ template_name + \".yaml\")\nphase_goal = \"Provide DevOps feedback\"\nphase_instructions\ \ = \"Review the proposal for deployment and infrastructure concerns.\"\n\nif\ \ os.path.exists(template_path):\n import yaml\n with open(template_path,\ \ 'r') as f:\n template = yaml.safe_load(f)\n phases = template.get(\"\ phases\", {})\n phase_info = phases.get(current_phase, {})\n phase_goal\ \ = phase_info.get(\"goal\", phase_goal)\n phase_instructions = phase_info.get(\"\ instructions\", phase_instructions)\n\nphase_context = \"Current Phase: \" + current_phase\ \ + \"\\n\"\nphase_context += \"Phase Goal: \" + phase_goal + \"\\n\"\nphase_context\ \ += \"Phase Instructions:\\n\" + phase_instructions\n" output_var: phase_context, current_phase - type: code code: "import re\nimport os\n\ntitle_match = re.search(r'', input)\ndiscussion_name = \"discussion\"\nif title_match:\n discussion_name\ \ = title_match.group(1).strip().lower()\n discussion_name = re.sub(r'[^a-z0-9]+',\ \ '-', discussion_name)\n\nos.makedirs(diagrams_dir, exist_ok=True)\n\nexisting\ \ = []\nif os.path.exists(diagrams_dir):\n for f in os.listdir(diagrams_dir):\n\ \ if f.startswith(discussion_name):\n existing.append(f)\n\n\ next_num = len(existing) + 1\ndiagram_path = diagrams_dir + \"/\" + discussion_name\ \ + \"_devops_\" + str(next_num) + \".puml\"\n" output_var: diagram_path - type: code code: "import sys\nimport datetime as dt\ntimestamp = dt.datetime.now().strftime(\"\ %H:%M:%S\")\nfor msg in [f\"Phase: {current_phase}\", \"Calling AI provider...\"\ ]:\n line = f\"[{timestamp}] [devops] {msg}\"\n print(line, file=sys.stderr)\n\ \ sys.stderr.flush()\n if log_file:\n with open(log_file, 'a') as\ \ f:\n f.write(line + \"\\n\")\n f.flush()\n" output_var: _progress1 - type: prompt prompt: "You are AI-DevOps (also known as Devon), a DevOps specialist who ensures\n\ reliable builds, deployments, and operational excellence.\n\n\ ## FIRST: Understand the Deployment Context\n\ DevOps concerns scale with the project:\n\ - **Cloud service**: Containers, orchestration, scaling, multi-region\n\ - **Single server**: Simple deployment scripts, systemd, backups\n\ - **Desktop app**: Build pipelines, installers, auto-updates, distribution\n\ - **CLI tool**: Package managers, release artifacts, installation scripts\n\ - **Library**: CI testing, versioning, package publishing\n\n\ Not every project needs Kubernetes. Match the operations approach to the project scale.\n\n\ ## Your Role\n\ - Design build and deployment processes appropriate to scale\n\ - Plan for operational needs (logs, monitoring, updates)\n\ - Ensure reproducible builds and deployments\n\ - Consider disaster recovery proportional to criticality\n\ - Apply DevOps principles at the right scale\n\ - Engage with all aspects of the discussion, not just infrastructure\n\n\ ## Your Perspective\n\ - Automate what's worth automating at this scale\n\ - You can't fix what you can't see - but logging needs match the project\n\ - Deployments should be reversible\n\ - Reproducibility prevents \"works on my machine\"\n\ - Simple is better than complex when simple works\n\n\ ## Context-Aware Operations\n\ **For cloud services**: CI/CD, containers, scaling, observability, IaC\n\ **For single servers**: Deploy scripts, systemd, simple monitoring, backups\n\ **For desktop apps**: Build automation, installers, crash reporting, updates\n\ **For CLI/libraries**: CI testing, release automation, package publishing\n\n## Phase Context\n{phase_context}\n\n## Diagrams\nWhen creating infrastructure\ \ or deployment diagrams, include a reference marker.\nDiagram path to use: {diagram_path}\n\ \nIMPORTANT: When you create a diagram, your comment MUST include:\nDIAGRAM: {diagram_path}\n\ \n## Current Discussion\n{input}\n\n## Your Task\n{callout}\n\nFollow the phase\ \ instructions. Analyze from a DevOps/infrastructure perspective.\n\n## Response\ \ Format\nRespond with valid JSON only. Use \\n for newlines in strings:\n{{\n\ \ \"comment\": \"Your DevOps analysis...\\n\\nDIAGRAM: path/file.puml (if created)\"\ ,\n \"vote\": \"READY\" or \"CHANGES\" or \"REJECT\" or null,\n \"diagram\"\ : \"@startuml\\n...\\n@enduml\"\n}}\n\nVote meanings:\n- READY: Deployment/infrastructure\ \ is solid\n- CHANGES: DevOps improvements needed\n- REJECT: Significant infrastructure\ \ issues\n- null: Comment only, no vote change\n\nIf you have nothing meaningful\ \ to add, respond: {{\"sentinel\": \"NO_RESPONSE\"}}\n" provider: claude output_var: response - type: code code: "import sys\nimport datetime as dt\ntimestamp = dt.datetime.now().strftime(\"\ %H:%M:%S\")\nline = f\"[{timestamp}] [devops] AI response received\"\nprint(line,\ \ file=sys.stderr)\nsys.stderr.flush()\nif log_file:\n with open(log_file,\ \ 'a') as f:\n f.write(line + \"\\n\")\n f.flush()\n" output_var: _progress2 - type: code code: "import re\njson_text = response.strip()\nif json_text.startswith('```'):\n\ \ code_block = re.search(r'```(?:json)?\\s*(\\{.*\\})\\s*```', json_text, re.DOTALL)\n\ \ if code_block:\n json_text = code_block.group(1).strip()\n" output_var: json_text - type: code code: "import json\ntry:\n parsed = json.loads(json_text)\nexcept json.JSONDecodeError\ \ as e:\n fixed = json_text.replace('\\n', '\\\\n')\n try:\n parsed\ \ = json.loads(fixed)\n except json.JSONDecodeError:\n import re\n \ \ comment_match = re.search(r'\"comment\"\\s*:\\s*\"(.*?)\"(?=\\s*[,}])',\ \ json_text, re.DOTALL)\n vote_match = re.search(r'\"vote\"\\s*:\\s*(\"\ ?\\w+\"?|null)', json_text)\n diagram_match = re.search(r'\"diagram\"\\\ s*:\\s*\"(.*?)\"(?=\\s*[,}])', json_text, re.DOTALL)\n parsed = {\n \ \ \"comment\": comment_match.group(1).replace('\\n', ' ') if comment_match\ \ else \"Parse error\",\n \"vote\": vote_match.group(1).strip('\"')\ \ if vote_match else None,\n \"diagram\": diagram_match.group(1) if\ \ diagram_match else None\n }\n if parsed[\"vote\"] == \"null\"\ :\n parsed[\"vote\"] = None\ncomment = parsed.get(\"comment\", \"\"\ )\nvote = parsed.get(\"vote\")\ndiagram_content = parsed.get(\"diagram\")\nhas_diagram\ \ = \"true\" if diagram_content else \"false\"\n" output_var: comment, vote, diagram_content, has_diagram - type: code code: "if has_diagram == \"true\" and diagram_content:\n with open(diagram_path,\ \ 'w') as f:\n f.write(diagram_content)\n saved_diagram = diagram_path\n\ else:\n saved_diagram = \"\"\n" output_var: saved_diagram - type: code code: "import json\nresult = {\"comment\": comment, \"vote\": vote}\nif saved_diagram:\n\ \ result[\"diagram_file\"] = saved_diagram\nfinal_response = json.dumps(result)\n" output_var: final_response output: '{final_response}'