# Unified infra CI pipeline — detects changed stacks and applies only those.
# Platform stacks and app stacks handled in one pipeline with proper ordering.
#
# Optimizations over the previous split pipeline:
# - Custom CI image (no apk/wget per step)
# - Shallow clone (depth=2 for git diff HEAD~1)
# - TF_PLUGIN_CACHE_DIR (shared provider cache)
# - Serial apply with Vault advisory locks (prevents user/CI race conditions)
# - Step consolidation (2 steps instead of 4)
# - Changed-stacks-only detection (skips no-op applies)
# - Global-file fallback (modules/config changes trigger full apply)
# - Lock-aware: skips stacks locked by users instead of failing

when:
  event: push
  branch: master

clone:
  git:
    image: woodpeckerci/plugin-git
    settings:
      partial: false
      depth: 2
      attempts: 5
      backoff: 10s

steps:
  # Audit feed for the allow-then-audit contribution model: any master push by
  # a NON-admin author is surfaced in Slack (Viktor's own pushes are not).
  # Runs before apply and never blocks it. Note: [ci skip] commits never reach
  # this step (Woodpecker skips the whole pipeline) — hence the rule that
  # non-admins must not use [ci skip].
  - name: notify-nonadmin-push
    image: curlimages/curl
    environment:
      SLACK_WEBHOOK:
        from_secret: slack_webhook
    commands:
      - |
        case "$CI_COMMIT_AUTHOR" in
          viktor|ViktorBarzin|wizard) echo "admin push — no notify"; exit 0 ;;
        esac
        SUBJECT=$(echo "$CI_COMMIT_MESSAGE" | head -1 | tr -d '"\\')
        curl -s -X POST -H 'Content-type: application/json' \
          --data "{\"text\":\"📝 infra master push by *$CI_COMMIT_AUTHOR*: $SUBJECT\n$CI_REPO_URL/commit/$CI_COMMIT_SHA\"}" \
          "$SLACK_WEBHOOK" || true

  - name: apply
    image: ghcr.io/viktorbarzin/infra-ci:latest
    pull: true
    backend_options:
      kubernetes:
        resources:
          requests:
            memory: 3Gi
          limits:
            memory: 6Gi
    environment:
      SLACK_WEBHOOK:
        from_secret: slack_webhook
      # Each `- |` command runs in a fresh shell, so we can't rely on an
      # `export VAULT_ADDR=...` in the auth command persisting — pin it at
      # step level. VAULT_TOKEN is still per-command; we persist it to
      # ~/.vault-token (auto-read by `vault` CLI) so downstream commands
      # don't need explicit token propagation.
      VAULT_ADDR: http://vault-active.vault.svc.cluster.local:8200
    commands:
      # ── Forge guard: apply ONLY on the canonical Forgejo forge ──
      # infra is registered in Woodpecker on BOTH the Forgejo canonical repo and
      # the legacy GitHub mirror, and BOTH fire this push pipeline. Without this
      # guard both run `terragrunt apply` on every push and race each other for
      # the per-stack PG state lock — the dominant cause of the "Error acquiring
      # the state lock" failures + push-supersede "killed" runs. The GitHub-mirror
      # registration keeps running the CRONS (drift-detection, renew-tls, …) — only
      # its duplicate push-apply no-ops here. Fail-open: an unknown forge (neither
      # env var set) still applies, preserving prior behaviour.
      - |
        if echo "${CI_REPO_URL:-}${CI_FORGE_URL:-}" | grep -qi 'github\.com'; then
          echo "[forge-guard] GitHub-mirror push — apply runs only on the Forgejo canonical repo (avoids double-apply + state-lock races). Skipping."
          exit 0
        fi

      # ── Skip CI commits ──
      - |
        if echo "$CI_COMMIT_MESSAGE" | grep -q '\[CI SKIP\]\|\[ci skip\]'; then
          echo "Commit has [CI SKIP], exiting"
          exit 0
        fi

      # ── git-crypt unlock ──
      - |
        SA_TOKEN=$(cat /var/run/secrets/kubernetes.io/serviceaccount/token)
        curl -sk "https://10.0.20.100:6443/api/v1/namespaces/woodpecker/configmaps/git-crypt-key" \
          -H "Authorization:Bearer $SA_TOKEN" | jq -r .data.key | base64 -d > /tmp/key
        git-crypt unlock /tmp/key && rm /tmp/key

      # ── Vault auth ──
      - |
        SA_TOKEN=$(cat /var/run/secrets/kubernetes.io/serviceaccount/token)
        VAULT_TOKEN=$(curl -s -X POST "$VAULT_ADDR/v1/auth/kubernetes/login" \
          -d "{\"role\":\"ci\",\"jwt\":\"$SA_TOKEN\"}" | jq -r .auth.client_token)
        if [ -z "$VAULT_TOKEN" ] || [ "$VAULT_TOKEN" = "null" ]; then
          echo "ERROR: Vault K8s auth failed (role=ci, ns=woodpecker)" >&2
          exit 1
        fi
        # Persist for downstream `- |` blocks (each runs in a fresh shell,
        # so exporting VAULT_TOKEN wouldn't help). `vault`, `scripts/tg`,
        # and `scripts/state-sync` all fall through to ~/.vault-token when
        # the env var is unset.
        umask 077; printf '%s' "$VAULT_TOKEN" > "$HOME/.vault-token"

      # ── Generate kubeconfig from projected SA token ──
      # terragrunt.hcl injects `-var kube_config_path=<repo>/config` for every
      # terraform invocation, so we need a kubeconfig file at that path. The
      # `default` SA in the woodpecker namespace is cluster-admin (via the
      # `woodpecker-default` ClusterRoleBinding), so the projected token is
      # sufficient to apply any stack. Using `tokenFile` (not an inline token)
      # so the provider re-reads it if kubelet rotates the projected token
      # mid-pipeline.
      - |
        cat > config <<'EOF'
        apiVersion: v1
        kind: Config
        clusters:
          - name: kubernetes
            cluster:
              server: https://10.0.20.100:6443
              certificate-authority: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        contexts:
          - name: ci
            context:
              cluster: kubernetes
              user: ci
        current-context: ci
        users:
          - name: ci
            user:
              tokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
        EOF
        chmod 600 config
        # Sanity check: kubeconfig works
        kubectl --kubeconfig=config get ns kube-system -o name >/dev/null

      # ── Detect changed stacks ──
      - |
        PLATFORM_STACKS="dbaas authentik crowdsec monitoring nvidia mailserver cloudflared kyverno metallb redis traefik technitium headscale rbac k8s-portal vaultwarden reverse-proxy metrics-server vpa nfs-csi iscsi-csi cnpg sealed-secrets uptime-kuma wireguard xray infra-maintenance platform vault reloader descheduler external-secrets"

        # Ensure we have enough history for diff (clone may be shallow)
        if ! git rev-parse HEAD~1 >/dev/null 2>&1; then
          echo "WARNING: HEAD~1 not available (shallow clone?) — fetching more history"
          git fetch --deepen=1 origin master 2>/dev/null || true
        fi

        # Diff base: prefer the push's true before-state (CI_PREV_COMMIT_SHA).
        # HEAD~1 is WRONG for merge commits — it is the first parent (the
        # feature-branch side), so the diff shows the OTHER lineage's files
        # and silently skips the stacks this push actually changed
        # (bit ci-pipeline-health on 2026-06-12, pipeline 128).
        DIFF_BASE="HEAD~1"
        if [ -n "${CI_PREV_COMMIT_SHA:-}" ] && [ "$CI_PREV_COMMIT_SHA" != "$CI_COMMIT_SHA" ]; then
          git cat-file -e "$CI_PREV_COMMIT_SHA^{commit}" 2>/dev/null || git fetch --depth=50 origin master 2>/dev/null || true
          # Restarted pipelines after master moved produce REVERSE diffs
          # (CI_PREV ahead of the checked-out HEAD re-applied stale trees and
          # reverted a sibling apply on 2026-06-12, pipeline 148). Only use
          # CI_PREV when it is an ancestor of HEAD.
          if git cat-file -e "$CI_PREV_COMMIT_SHA^{commit}" 2>/dev/null \
             && git merge-base --is-ancestor "$CI_PREV_COMMIT_SHA" HEAD 2>/dev/null; then
            DIFF_BASE="$CI_PREV_COMMIT_SHA"
          fi
        fi
        echo "Diff base: $DIFF_BASE"

        # If still no parent, apply all platform stacks as a safe fallback
        if ! git rev-parse HEAD~1 >/dev/null 2>&1; then
          echo "Cannot determine changed files — applying ALL platform stacks"
          echo "$PLATFORM_STACKS" | tr ' ' '\n' > .platform_apply
          > .app_apply
        else
          # Check if global files changed (triggers full platform apply)
          GLOBAL_CHANGED=$(git diff --name-only "$DIFF_BASE" HEAD | grep -E '^(modules/|config\.tfvars|terragrunt\.hcl)' || true)

          if [ -n "$GLOBAL_CHANGED" ]; then
            echo "Global files changed — applying ALL platform stacks"
            echo "$PLATFORM_STACKS" | tr ' ' '\n' > .platform_apply
          else
            # Detect platform stacks that changed
            git diff --name-only "$DIFF_BASE" HEAD | grep '^stacks/' | cut -d/ -f2 | sort -u > .all_changed
            > .platform_apply
            while read -r stack; do
              if echo "$PLATFORM_STACKS" | grep -qw "$stack"; then
                echo "$stack" >> .platform_apply
              fi
            done < .all_changed
          fi

          # Detect app stacks that changed
          > .app_apply
          git diff --name-only "$DIFF_BASE" HEAD | grep '^stacks/' | cut -d/ -f2 | sort -u | while read -r stack; do
            if echo "$PLATFORM_STACKS" | grep -qw "$stack"; then
              continue  # Skip platform stacks
            fi
            if [ ! -f "stacks/$stack/terragrunt.hcl" ]; then
              continue  # Skip non-terragrunt dirs
            fi
            echo "$stack" >> .app_apply
          done
        fi

        PLATFORM_COUNT=$(wc -l < .platform_apply | tr -d ' ')
        APP_COUNT=$(wc -l < .app_apply | tr -d ' ')
        echo "Platform stacks to apply: $PLATFORM_COUNT"
        echo "App stacks to apply: $APP_COUNT"
        cat .platform_apply .app_apply

      # ── Pre-warm provider cache ──
      - |
        if [ -s .platform_apply ] || [ -s .app_apply ]; then
          FIRST_STACK=$(cat .platform_apply .app_apply 2>/dev/null | head -1)
          if [ -n "$FIRST_STACK" ]; then
            echo "Pre-warming provider cache from stacks/$FIRST_STACK..."
            cd "stacks/$FIRST_STACK" && terragrunt init --terragrunt-non-interactive -input=false 2>&1 | tail -3 && cd ../..
          fi
        fi

      # ── Apply platform stacks (serial, with Vault advisory locks) ──
      - |
        FAILED_PLATFORM_STACKS=""
        if [ -s .platform_apply ]; then
          echo "=== Applying platform stacks (serial, locked) ==="
          while read -r stack; do
            # Tier-0 `vault` is human-applied via OIDC; the CI `ci` Vault role
            # lacks Vault-admin perms (sys/mounts + sys/policies/acl), so a CI
            # apply always 403s and fails the pipeline. Kept in PLATFORM_STACKS
            # (so the app-stack detector still excludes it) but skipped here.
            # (2026-06-27 — see docs/architecture/ci-cd.md)
            if [ "$stack" = "vault" ]; then echo "[vault] SKIPPED (Tier-0, human-applied via OIDC)"; continue; fi
            echo "[$stack] Starting apply..."
            ATTEMPT=0
            while :; do
              ATTEMPT=$((ATTEMPT + 1))
              set +e
              OUTPUT=$(cd "stacks/$stack" && ../../scripts/tg apply --non-interactive 2>&1)
              EXIT=$?
              set -e
              if [ $EXIT -eq 0 ]; then
                echo "$OUTPUT" | tail -3; echo "[$stack] OK"; break
              fi
              # Lock contention → SKIP, not fail. Match BOTH the Tier-0 Vault lock
              # ("is locked by", from scripts/tg) AND the Tier-1 PG-backend lock
              # ("Error acquiring the state lock" / "already locked"). The PG case
              # was previously counted as a failure — the #1 source of false reds.
              if echo "$OUTPUT" | grep -qE 'is locked by|Error acquiring the state lock|already locked'; then
                echo "[$stack] SKIPPED (locked by another session/run)"; break
              fi
              # Transient: provider-registry download timeout / Vault 5xx → bounded
              # retry. Deliberately NOT helm atomic-timeouts or config errors
              # (missing arg, invalid index) — those must fail fast, retry can't fix
              # them and can worsen a stuck helm release.
              if [ $ATTEMPT -lt 3 ] && echo "$OUTPUT" | grep -qE 'Failed to install provider|Client\.Timeout exceeded while awaiting headers|error reading from Vault.*Code: 5[0-9][0-9]'; then
                echo "[$stack] transient error (attempt $ATTEMPT/3) — retrying in 15s..."; sleep 15; continue
              fi
              echo "$OUTPUT" | tail -50; echo "[$stack] FAILED (exit $EXIT)"
              FAILED_PLATFORM_STACKS="$FAILED_PLATFORM_STACKS $stack"; break
            done
          done < .platform_apply
        fi
        # Deferred until after app stacks so both lists get a chance to run.
        echo "$FAILED_PLATFORM_STACKS" > .platform_failed

      # ── Apply app stacks (serial, with Vault advisory locks) ──
      - |
        FAILED_APP_STACKS=""
        if [ -s .app_apply ]; then
          echo "=== Applying app stacks (serial, locked) ==="
          while read -r stack; do
            echo "[$stack] Starting apply..."
            ATTEMPT=0
            while :; do
              ATTEMPT=$((ATTEMPT + 1))
              set +e
              OUTPUT=$(cd "stacks/$stack" && ../../scripts/tg apply --non-interactive 2>&1)
              EXIT=$?
              set -e
              if [ $EXIT -eq 0 ]; then
                echo "$OUTPUT" | tail -3; echo "[$stack] OK"; break
              fi
              # Lock contention → SKIP, not fail (Tier-0 Vault + Tier-1 PG; see platform loop).
              if echo "$OUTPUT" | grep -qE 'is locked by|Error acquiring the state lock|already locked'; then
                echo "[$stack] SKIPPED (locked by another session/run)"; break
              fi
              # Transient provider-download / Vault 5xx → bounded retry (see platform loop).
              if [ $ATTEMPT -lt 3 ] && echo "$OUTPUT" | grep -qE 'Failed to install provider|Client\.Timeout exceeded while awaiting headers|error reading from Vault.*Code: 5[0-9][0-9]'; then
                echo "[$stack] transient error (attempt $ATTEMPT/3) — retrying in 15s..."; sleep 15; continue
              fi
              echo "$OUTPUT" | tail -50; echo "[$stack] FAILED (exit $EXIT)"
              FAILED_APP_STACKS="$FAILED_APP_STACKS $stack"; break
            done
          done < .app_apply
        fi
        # Fail the step loudly so the pipeline `default` workflow state
        # reflects reality — the service-upgrade agent and CI alert cascade
        # both rely on this (see bd code-e1x). Lock-skipped stacks are NOT
        # counted as failures.
        FAILED_PLATFORM=$(cat .platform_failed 2>/dev/null | tr -d ' ')
        if [ -n "$FAILED_PLATFORM" ] || [ -n "$FAILED_APP_STACKS" ]; then
          echo "=== FAILED STACKS: platform=[$FAILED_PLATFORM ] apps=[$FAILED_APP_STACKS ] ==="
          exit 1
        fi

      # ── Commit and push state changes ──
      - |
        mkdir -p ~/.ssh && ssh-keyscan -H github.com >> ~/.ssh/known_hosts 2>/dev/null
        chmod 400 secrets/deploy_key
        git add stacks/ state/ .woodpecker/ 2>/dev/null || true
        git remote set-url origin git@github.com:ViktorBarzin/infra.git
        git diff --cached --quiet && echo "No changes to commit" && exit 0
        git commit -m "Woodpecker CI deploy [CI SKIP]"
        GIT_SSH_COMMAND='ssh -i ./secrets/deploy_key -o IdentitiesOnly=yes' git fetch origin master
        if ! GIT_SSH_COMMAND='ssh -i ./secrets/deploy_key -o IdentitiesOnly=yes' git rebase origin/master; then
          echo "ERROR: Git rebase failed — state commits could not be pushed"
          echo "Manual intervention required: pull, resolve conflicts, push"
          GIT_SSH_COMMAND='ssh -i ./secrets/deploy_key -o IdentitiesOnly=yes' git rebase --abort || true
          exit 1
        fi
        GIT_SSH_COMMAND='ssh -i ./secrets/deploy_key -o IdentitiesOnly=yes' git push origin master

      # ── Slack notification ──
      - |
        PLATFORM_COUNT=$(wc -l < .platform_apply 2>/dev/null | tr -d ' ')
        APP_COUNT=$(wc -l < .app_apply 2>/dev/null | tr -d ' ')
        curl -s -X POST -H 'Content-type: application/json' \
          --data "{\"channel\":\"general\",\"text\":\"Woodpecker CI: infra pipeline ${CI_PIPELINE_STATUS} (platform:${PLATFORM_COUNT}, apps:${APP_COUNT})\"}" \
          "$SLACK_WEBHOOK" || true

  # Slack on failure (runs even if apply step fails)
  - name: notify-failure
    image: curlimages/curl
    commands:
      - |
        curl -s -X POST -H 'Content-type: application/json' \
          --data "{\"channel\":\"general\",\"text\":\":red_circle: Woodpecker CI: infra pipeline FAILED\"}" \
          "$SLACK_WEBHOOK" || true
    environment:
      SLACK_WEBHOOK:
        from_secret: slack_webhook
    when:
      status: [failure]