8badb8181a
E2E workflow for incident post-mortems: 1. /post-mortem skill generates structured post-mortem markdown 2. Woodpecker pipeline triggers on docs/post-mortems/*.md changes 3. parse-postmortem-todos.sh extracts safe TODOs (Alert/Config/Monitor) 4. postmortem-todo-resolver agent implements TODOs headlessly 5. Agent updates post-mortem with Follow-up Implementation table Components: - .claude/skills/post-mortem/ — writer skill + template - .claude/agents/postmortem-todo-resolver.md — headless agent - .woodpecker/postmortem-todos.yml — CI pipeline - scripts/parse-postmortem-todos.sh — TODO extractor - cluster-health skill — auto-suggest post-mortem after recovery Safety: only auto-implements Alert/Config/Monitor types. Architecture/Migration/Investigation items are skipped. [ci skip] Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
80 lines
3 KiB
YAML
80 lines
3 KiB
YAML
when:
|
|
event: push
|
|
branch: master
|
|
path:
|
|
include:
|
|
- 'docs/post-mortems/*.md'
|
|
exclude:
|
|
- '.woodpecker/**'
|
|
|
|
steps:
|
|
- name: parse-todos
|
|
image: python:3.12-alpine
|
|
commands:
|
|
- apk add --no-cache jq git openssh-client
|
|
# Find which post-mortem changed
|
|
- PM_FILE=$(git diff HEAD~1 --name-only | grep 'docs/post-mortems/.*\.md' | head -1)
|
|
- |
|
|
if [ -z "$PM_FILE" ]; then
|
|
echo "No post-mortem markdown changes detected"
|
|
echo '{"skip": true}' > /tmp/todos.json
|
|
exit 0
|
|
fi
|
|
- echo "Post-mortem changed: $PM_FILE"
|
|
# Check if there are new TODOs (not just TODO→Done updates)
|
|
- |
|
|
if ! git diff HEAD~1 -- "$PM_FILE" | grep -q '+.*| TODO |'; then
|
|
echo "No new TODOs added (only status updates)"
|
|
echo '{"skip": true}' > /tmp/todos.json
|
|
exit 0
|
|
fi
|
|
# Parse TODOs
|
|
- python3 scripts/parse-postmortem-todos.sh "$PM_FILE" > /tmp/todos.json || bash scripts/parse-postmortem-todos.sh "$PM_FILE" > /tmp/todos.json
|
|
- cat /tmp/todos.json
|
|
- TODO_COUNT=$(jq '.safe_todos' /tmp/todos.json)
|
|
- echo "$TODO_COUNT auto-implementable TODO(s) found"
|
|
- |
|
|
if [ "$TODO_COUNT" -eq 0 ]; then
|
|
echo "No auto-implementable TODOs (all are Architecture/Investigation/Migration type)"
|
|
echo '{"skip": true}' > /tmp/todos.json
|
|
fi
|
|
|
|
- name: implement-todos
|
|
image: alpine
|
|
commands:
|
|
- |
|
|
if [ "$(jq -r '.skip // empty' /tmp/todos.json 2>/dev/null)" = "true" ]; then
|
|
echo "Skipping — no TODOs to implement"
|
|
exit 0
|
|
fi
|
|
- apk add --no-cache openssh-client jq
|
|
- PM_FILE=$(jq -r '.file' /tmp/todos.json)
|
|
- PM_DATE=$(echo "$PM_FILE" | grep -oP '\d{4}-\d{2}-\d{2}')
|
|
- TODOS=$(cat /tmp/todos.json)
|
|
# SSH to DevVM and run Claude Code in headless mode
|
|
- |
|
|
ssh -o StrictHostKeyChecking=no wizard@10.0.10.10 \
|
|
"cd ~/code/infra && git pull && claude -p \
|
|
--agent postmortem-todo-resolver \
|
|
--dangerously-skip-permissions \
|
|
--max-budget-usd 5 \
|
|
'Implement the auto-implementable TODOs from $PM_FILE. Here is the parsed TODO list: $TODOS'"
|
|
secrets:
|
|
- ssh_deploy_key
|
|
|
|
- name: notify-slack
|
|
image: alpine
|
|
commands:
|
|
- apk add --no-cache curl jq
|
|
- |
|
|
PM_FILE=$(jq -r '.file // "unknown"' /tmp/todos.json 2>/dev/null)
|
|
SAFE=$(jq -r '.safe_todos // 0' /tmp/todos.json 2>/dev/null)
|
|
SKIPPED=$(jq -r '.skipped_todos // 0' /tmp/todos.json 2>/dev/null)
|
|
STATUS="${CI_PIPELINE_STATUS:-unknown}"
|
|
curl -sf -X POST "$SLACK_WEBHOOK_URL" \
|
|
-H "Content-Type: application/json" \
|
|
-d "{\"text\": \"*Post-mortem TODO resolver* ($STATUS)\\n• File: \`$PM_FILE\`\\n• Safe TODOs processed: $SAFE\\n• Skipped (needs human): $SKIPPED\\n• Pipeline: ${CI_PIPELINE_URL:-N/A}\"}" || true
|
|
secrets:
|
|
- slack_webhook
|
|
when:
|
|
- status: [success, failure]
|