bd6c0678d8
Some checks failed
Tests / Declarative: Post Actions failed: 2, passed: 142
Both demos went quiet for up to a minute between the build turning red and the monitor reacting, because Ariadne's tick is on cron. The scripts now run that tick immediately over the pod's own loopback - nothing exposed outside the cluster - and print what it saw, so the pause becomes a visible step rather than dead air. Falls back to silence rather than failure: if the request does not land the scheduler still picks the build up within the minute, which is exactly the old behaviour. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
103 lines
3.9 KiB
Bash
Executable File
103 lines
3.9 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Drive and narrate the Hermes automated-triage demo.
|
|
#
|
|
# This is the autonomous loop: a build fails, Ariadne diagnoses it through
|
|
# Hermes, authorizes a predefined repair, performs it, and rebuilds green
|
|
# without a human touching anything.
|
|
#
|
|
# hermes_triage_demo.sh monitor # follow the Test Automation Diagram live
|
|
# hermes_triage_demo.sh reset # restore the demo to its pre-run state
|
|
# hermes_triage_demo.sh preflight # confirm the lab is ready to demo
|
|
# hermes_triage_demo.sh run # arm the failure and narrate the loop
|
|
# hermes_triage_demo.sh status # current incident/alert state, no changes
|
|
#
|
|
# The code-proposal demo is a separate script: hermes_code_demo.sh. They prove
|
|
# different halves of the diagram and reset different things, so they are kept
|
|
# apart rather than behind one command.
|
|
#
|
|
# FIRST RUN: copy hermes_demo.env.example to hermes_demo.env in this directory
|
|
# and fill it in. That file is git-ignored precisely so it can hold real
|
|
# tokens; this script sources it automatically.
|
|
#
|
|
# Needs kubectl access to the cluster as well. Nothing here mutates the cluster
|
|
# directly: the demo only asks Jenkins to run a parameterized build.
|
|
set -euo pipefail
|
|
|
|
# shellcheck source=scripts/ops/hermes_demo_lib.sh
|
|
. "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/hermes_demo_lib.sh"
|
|
|
|
# The fixture is a ConfigMap the demo job reads. Resetting it is the whole
|
|
# blast radius of this script: no repository is touched, because the triage
|
|
# loop repairs infrastructure rather than source.
|
|
cmd_reset() {
|
|
say "Reset — restoring the triage demo to its pre-run state"
|
|
note "fixture -> healthy"
|
|
if kubectl -n "$DEMO_NS" patch cm hermes-triage-demo-fixture \
|
|
--type merge -p '{"data":{"state":"healthy"}}' >/dev/null 2>&1; then
|
|
note " fixture: $(kubectl -n "$DEMO_NS" get cm hermes-triage-demo-fixture -o jsonpath='{.data.state}')"
|
|
else
|
|
note " fixture patch failed (is the demo namespace present?)"
|
|
fi
|
|
say "Ready"
|
|
note "no repository was touched; this demo repairs infrastructure, not source"
|
|
note "run 'preflight' next, then 'run'"
|
|
}
|
|
|
|
cmd_preflight() {
|
|
require_jenkins
|
|
say "Preflight — triage demo"
|
|
note "fixture state: $(kubectl -n "$DEMO_NS" get cm hermes-triage-demo-fixture -o jsonpath='{.data.state}' 2>/dev/null || echo MISSING)"
|
|
shared_preflight
|
|
}
|
|
|
|
cmd_status() {
|
|
shared_status
|
|
say "Demo namespace"
|
|
kubectl -n "$DEMO_NS" get jobs --no-headers 2>/dev/null | sed 's/^/ /'
|
|
}
|
|
|
|
cmd_run() {
|
|
require_jenkins
|
|
local start_num next_num
|
|
start_num="$(last_build_number "$FIXTURE_JOB")"
|
|
next_num=$((start_num + 1))
|
|
say "Arming the demo failure (SEED_FAILURE=true) -> build #$next_num"
|
|
note "HTTP $(jenkins_post "/job/$FIXTURE_JOB/buildWithParameters?SEED_FAILURE=true")"
|
|
note "Only manual step. Everything after this is automatic."
|
|
|
|
say "Waiting for the seeded build to fail"
|
|
note "result: $(wait_for_build "$FIXTURE_JOB" "$next_num")"
|
|
|
|
say "Asking Ariadne to look now rather than on its next minute"
|
|
note "\$ POST /api/internal/hermes/autotriage/run"
|
|
note "$(poke_ariadne)"
|
|
|
|
say "Ariadne detects, gathers evidence, asks Hermes, authorizes, repairs"
|
|
note "the repair is a single in-process ConfigMap patch, so watch the fixture"
|
|
for _ in $(seq 1 40); do
|
|
sleep 10
|
|
if [ "$(kubectl -n "$DEMO_NS" get cm hermes-triage-demo-fixture -o jsonpath='{.data.state}' 2>/dev/null)" = "healthy" ]; then
|
|
note "fixture patched back to healthy"
|
|
break
|
|
fi
|
|
done
|
|
ariadne_ticks 400 4
|
|
|
|
say "Ariadne triggers one rebuild with seeding disabled"
|
|
note "result: $(wait_for_build "$FIXTURE_JOB" $((next_num + 1)))"
|
|
|
|
say "Resolution"
|
|
sleep 45
|
|
ariadne_ticks 200 3
|
|
note "fixture state: $(kubectl -n "$DEMO_NS" get cm hermes-triage-demo-fixture -o jsonpath='{.data.state}')"
|
|
}
|
|
|
|
case "${1:-}" in
|
|
run|fixture) cmd_run ;;
|
|
status) cmd_status ;;
|
|
preflight) cmd_preflight ;;
|
|
reset) cmd_reset ;;
|
|
monitor) run_monitor "$FIXTURE_JOB" ;;
|
|
*) sed -n '2,17p' "$0" | sed 's/^# \{0,1\}//' ; exit 1 ;;
|
|
esac
|