feat: initial harness spec v1.0.0 + reference template

Adds the normative contract every platform agent must conform to, plus a
working reference template under template/ that ticks every box out of
the box.

Spec is derived from the production agents shipped in
cjot-backstage-az/agents/ on branch sandbox/jonathan:
  - agent-registry, agent-factory, decomposer, discovery-agent,
    golden-path, modernization-factory, modernization-factory-v2,
    policy-transformer, scaffold-agent, support-intake-agent, the-watcher

Contents:
  - SPEC.md          normative contract (13 sections + conformance checklist)
  - CHANGELOG.md     spec versioning (1.0.0)
  - docs/
      registration.md   self-registration with the agent-gateway
      observability.md  OTel logs/metrics/traces wiring
      manifest.md       /.well-known/agent.json schema + AgentSkill
                        serialisation (pydantic vs protobuf)
      kubernetes.md     k8s deployment shape, mandatory cross-refs,
                        per-namespace agents, resource sizing
      deployment.md     .image-version, ACR build, deploy scripts, rollback
      deviations.md     tracked debts against the spec
  - template/
      .env.local.example, .gitignore, .image-version (0.1.0),
      Dockerfile (python:3.12-slim, non-root UID 1001, HEALTHCHECK),
      requirements.txt (harness floor + optional LLM stack),
      app/agent.py (Starlette entry, lifespan + self-registration,
                    defensive _skill_dict for pydantic vs protobuf),
      app/logging_setup.py (canonical OTel log bridge — copy verbatim),
      app/metrics.py (meter + example counter/histogram),
      app/skills.py (AGENT_CONFIG + AgentSkill list),
      k8s/configmap.yaml + deployment.yaml (Deployment + Service,
                                            OTel annotations + 6-var env block,
                                            agents-sa + agents-kv-spc bindings),
      scripts/deploy.sh (auto-bump + az acr build + apply + rollout),
      scripts/full-deploy.sh (preflight + deploy + post-deploy smoke),
      scripts/deploy-local.sh (docker/podman + .env.local)
This commit is contained in:
2026-06-09 15:54:18 +01:00
parent c87dd3fa55
commit e6f10ba8c9
25 changed files with 1933 additions and 1 deletions

74
template/scripts/full-deploy.sh Executable file
View File

@@ -0,0 +1,74 @@
#!/bin/bash
# full-deploy.sh — Preflight checks + build + deploy + post-deploy smoke.
#
# Run this for first-time deploys or after an outage to validate cluster state.
# For routine redeploys, use scripts/deploy.sh.
set -euo pipefail
SCRIPT_DIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
AGENT_DIR=$(cd "${SCRIPT_DIR}/.." && pwd)
APP_NAME="<agent-name>"
NAMESPACE="agents"
SA_NAME="agents-sa"
SPC_NAME="agents-kv-spc"
PORT=8000
fail() { echo "preflight FAIL: $1" >&2; exit 1; }
ok() { echo "preflight OK : $1"; }
# ─── Preflight ──────────────────────────────────────────────────────────
echo "─── Preflight ──────────────────────────────────────────"
command -v kubectl >/dev/null || fail "kubectl not on PATH"
ok "kubectl on PATH"
command -v az >/dev/null || fail "az CLI not on PATH"
ok "az CLI on PATH"
kubectl cluster-info >/dev/null 2>&1 || fail "kubectl can't reach a cluster"
ok "cluster reachable: $(kubectl config current-context)"
kubectl get namespace "${NAMESPACE}" >/dev/null 2>&1 \
|| fail "namespace ${NAMESPACE} missing"
ok "namespace ${NAMESPACE} exists"
kubectl -n "${NAMESPACE}" get serviceaccount "${SA_NAME}" >/dev/null 2>&1 \
|| fail "ServiceAccount ${NAMESPACE}/${SA_NAME} missing"
ok "ServiceAccount ${SA_NAME} exists"
kubectl -n "${NAMESPACE}" get secretproviderclass "${SPC_NAME}" >/dev/null 2>&1 \
|| fail "SecretProviderClass ${NAMESPACE}/${SPC_NAME} missing"
ok "SecretProviderClass ${SPC_NAME} exists"
echo ""
# ─── Build & deploy ─────────────────────────────────────────────────────
echo "─── Build & deploy ─────────────────────────────────────"
"${SCRIPT_DIR}/deploy.sh" "$@"
echo ""
# ─── Post-deploy smoke ──────────────────────────────────────────────────
echo "─── Post-deploy smoke ──────────────────────────────────"
POD=$(kubectl -n "${NAMESPACE}" get pod -l "app=${APP_NAME}" \
-o jsonpath='{.items[0].metadata.name}')
echo "Probing /health on ${POD}..."
kubectl -n "${NAMESPACE}" exec "${POD}" -c "${APP_NAME}" -- \
curl -fs "http://localhost:${PORT}/health" \
| jq -e '.status == "healthy"' >/dev/null \
&& ok "/health returns healthy" \
|| fail "/health did not return healthy"
echo "Probing /.well-known/agent.json on ${POD}..."
kubectl -n "${NAMESPACE}" exec "${POD}" -c "${APP_NAME}" -- \
curl -fs "http://localhost:${PORT}/.well-known/agent.json" \
| jq -e '.name and .version and (.skills | type == "array")' >/dev/null \
&& ok "/.well-known/agent.json valid" \
|| fail "/.well-known/agent.json invalid"
echo ""
echo "Done. ${APP_NAME} is up and conforming to the harness spec."