fix(gitea-mcp): set command so args don't replace the image CMD

docker.gitea.com/gitea-mcp-server has CMD ["/app/gitea-mcp"] and no ENTRYPOINT, so a Pod with only args runs "-t" as the executable: the container failed with 'exec: "-t": executable file not found in $PATH' and crash-looped.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

.woodpecker/alert-monitor.yml

@@ -101,7 +101,7 @@ steps:
         bash scripts/ci/make-diag-kubeconfig.sh
 
   - name: alert-triage-agent
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.289
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.296
     environment:
       CLAUDE_CODE_OAUTH_TOKEN:
         from_secret: claude_code_oauth_token

.woodpecker/build-ci-images.yml

@@ -408,3 +408,28 @@ steps:
           --dockerfile Containerfile \
           --destination gitea.renner.uno/gitea_admin/bird:$TAG \
           --destination gitea.renner.uno/gitea_admin/bird:latest
+
+  # Orchestrator for the monthly backup-verify CronJob (velero ns).
+  - name: build-backup-verify
+    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.19-debug@sha256:7795cec509a50a71378cc2c365f55c555ee3a05834d8eb1cd2552df5e66d44d8
+    directory: ci/images/backup-verify
+    depends_on: []
+    when:
+      - event: deployment
+      - event: push
+        path: ["ci/images/backup-verify/**", ".woodpecker/build-ci-images.yml"]
+    environment:
+      GITEA_USER: gitea_admin
+      GITEA_TOKEN:
+        from_secret: ci_images_token
+    commands:
+      - mkdir -p /kaniko/.docker
+      - AUTH=$(printf '%s:%s' "$GITEA_USER" "$GITEA_TOKEN" | base64 | tr -d '\n')
+      - printf '{"auths":{"gitea.renner.uno":{"auth":"%s"}}}' "$AUTH" > /kaniko/.docker/config.json
+      - TAG=$(date +%Y-%m-%d)
+      - |
+        /kaniko/executor \
+          --context . \
+          --dockerfile Containerfile \
+          --destination gitea.renner.uno/gitea_admin/ci-backup-verify:$TAG \
+          --destination gitea.renner.uno/gitea_admin/ci-backup-verify:latest

.woodpecker/ci-scripts-test.yml

@@ -35,18 +35,24 @@ when:
 steps:
   - name: model-selection-tests
     depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.289
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.296
     commands:
       - sh scripts/ci/test-model-selection.sh
 
   - name: promtool-rules-guard-tests
     depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.289
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.296
     commands:
       - sh scripts/ci/test-promtool-rules.sh
 
   - name: yaml-citations-guard-tests
     depends_on: []
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.289
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.296
     commands:
       - sh scripts/ci/test-yaml-citations.sh
+
+  - name: backup-verify-tests
+    depends_on: []
+    image: gitea.renner.uno/gitea_admin/ci-backup-verify:2026-10-10
+    commands:
+      - bash kubernetes/infrastructure/velero/backup-verify/tests/run.sh

.woodpecker/deploy-edge-mqtt-bridge.yml

@@ -0,0 +1,36 @@
+when:
+  # Deploy only on master (merge) + manual — never auto-deploy from a branch.
+  - event: push
+    branch: master
+    path:
+      - "ansible/roles/mqtt-bridge/**"
+      - "ansible/plays/edge-mqtt-bridge.yml"
+      - "ansible/inventory/group_vars/edge_host/**"
+      - ".woodpecker/deploy-edge-mqtt-bridge.yml"
+  - event: deployment
+    evaluate: 'CI_PIPELINE_DEPLOY_TARGET == "deploy-edge-mqtt-bridge"'
+
+timeout: 30
+
+steps:
+  - name: deploy-edge-mqtt-bridge
+    image: gitea.renner.uno/gitea_admin/ci-ansible:2026-04-29
+    environment:
+      ANSIBLE_FORCE_COLOR: "true"
+      ANSIBLE_HOST_KEY_CHECKING: "false"
+      ANSIBLE_ROLES_PATH: "../roles:./roles"
+      SSH_PRIVATE_KEY:
+        from_secret: ssh_private_key
+      VAULT_PASS:
+        from_secret: vault_pass
+    commands:
+      - mkdir -p ~/.ssh
+      - echo "$SSH_PRIVATE_KEY" | base64 -d > ~/.ssh/id_ed25519
+      - chmod 600 ~/.ssh/id_ed25519
+      - printf "Host *\n\tStrictHostKeyChecking no\n\tUserKnownHostsFile /dev/null\n" > ~/.ssh/config
+      - cd ansible
+      - echo "$VAULT_PASS" > .vault_pass && chmod 600 .vault_pass
+      - export ANSIBLE_VAULT_PASSWORD_FILE=.vault_pass
+      # Local MQTT bridge on the edge hosts only (REN-1307); restarts only the
+      # local mosquitto on edge-1, never the cluster broker.
+      - ansible-playbook -i inventory/ plays/edge-mqtt-bridge.yml -v

.woodpecker/e2e.yml

@@ -26,7 +26,7 @@ steps:
     # fetch-models.sh response mapping. No cluster, no secrets, no network — the
     # ci-claude image just provides sh + jq. Keeps the flag-injection regression
     # test from rotting (it exercises the exact injection shapes).
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.289
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.296
     commands:
       - sh scripts/ci/test-model-selection.sh
 

.woodpecker/issue-fix.yml

@@ -62,7 +62,7 @@ steps:
       - bash scripts/ci/make-diag-kubeconfig.sh
 
   - name: issue-fix-agent
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.289
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.296
     environment:
       CLAUDE_CODE_OAUTH_TOKEN:
         from_secret: claude_code_oauth_token

.woodpecker/pr-review.yml

@@ -1,301 +1,41 @@
-# PR review bot — event-driven. Woodpecker fires this on `pull_request` (which
-# covers BOTH "PR opened" and "new commits pushed to an open PR"), so a review
-# is produced the moment a PR appears or is updated — no polling, no cron.
+# PR review bot — per-repo STUB. All logic lives centrally in
+# k.renner/homelab: ci/agents/pr-review/run.sh (plus prompt.md,
+# settings.json and scripts/ci/). This file is deployed byte-identical into every
+# reviewed repo (k.renner/homelab, shelly-manager, authentik-samba-bridge,
+# homeassistant) and holds NO logic, so the copies cannot drift apart: change the
+# review in homelab and every repo picks it up on its next PR event. Only edit this
+# stub if the trigger, the image or the secrets change — then change all copies in
+# one go.
 #
-# This file is deployed UNCHANGED into every repo the fleet wants reviewed
-# (k.renner/homelab, shelly-manager, authentik-samba-bridge, homeassistant).
-# Woodpecker events are per-repo, so each repo triggers a review of ITS OWN PR
-# only; the triggering PR is identified from the CI event (CI_REPO +
-# CI_COMMIT_PULL_REQUEST) instead of the old hourly cross-repo discovery loop.
-# Because it runs on the PR event, Woodpecker's built-in clone hands the step
-# THIS repo already checked out at the PR head — so, unlike the old cron model,
-# there is no manual clone of the target repo (the source of an earlier token
-# leak); the agents read the checkout in the workspace directly.
+# Triggers on pull_request: PR opened AND new commits pushed to an open PR.
+# Approves only when the review found nothing red/yellow (see run.sh); humans merge.
 #
-# Prompts: the two agent prompts live once, in k.renner/homelab under
-# ci/agents/pr-review/. The homelab checkout already has them; the other repos
-# don't, so the step falls back to a shallow clone of public homelab@master.
-# One source of truth for the review rubric across all repos.
+# The central code is cloned from public homelab@master on every run, never taken
+# from the PR checkout, so a PR cannot alter the rubric or helper scripts it is
+# reviewed with.
 #
-# Model selection: no model id — and no model family — is baked into this file.
-# scripts/ci/fetch-models.sh pulls the LIVE catalog (Anthropic /v1/models, via
-# CLAUDE_CODE_OAUTH_TOKEN), and a triage agent reads the PR diff + stats and
-# picks whichever currently-available model best fits the review, judged on the
-# catalog's own capability metadata. A model released tomorrow is eligible the
-# day it appears. The shell validates the pick against the catalog snapshot taken
-# BEFORE the triage runs; if the fetch fails, the pick is rejected, or the review
-# is complex/security-sensitive (where the injectable pick is deliberately
-# ignored), it leaves the model unset and the review runs on the CLI's default
-# model. A wrong-way miss only over/under-spends one review.
+# Image: ci-claude:latest — the refresh pipeline keeps it on current Claude Code,
+# and a pinned tag would be the one thing in this file that diverges per repo.
 #
-# Posture: posted as a Gitea PR review, event COMMENT normally or
-# REQUEST_CHANGES on a serious defect. It NEVER approves — a bot must not
-# satisfy branch protection. Humans still merge.
+# Secrets (both must be granted the pull_request event):
+#   claude_code_oauth_token -> CLAUDE_CODE_OAUTH_TOKEN
+#   review_bot_token        -> REVIEW_TOKEN (review-bot PAT, write:repository)
 #
-# Dedup (guards pipeline retries/restarts, not cron re-runs anymore): the PR is
-# skipped when review-bot already left a review carrying the marker
-# "<!-- pr-review:sha=<head_sha> -->" for the PR's CURRENT head commit. A pushed
-# commit changes the head sha and fires a fresh pull_request event -> fresh
-# review.
-#
-# Tokens:
-#   CLAUDE_CODE_OAUTH_TOKEN (claude_code_oauth_token) — Claude subscription
-#     OAuth, how the `claude` CLI authenticates (same as the other agents).
-#   REVIEW_TOKEN (review_bot_token) — a dedicated `review-bot` Gitea account's
-#     PAT, scope write:repository. Reads the PR + diff and POSTs the review, all
-#     over the Gitea API (ephemeral curl Authorization headers — the token is
-#     never written to disk; the repo is NOT cloned). review-bot must be a
-#     collaborator (read) on every reviewed repo.
-#   Both secrets MUST be granted the `pull_request` event, or Woodpecker will
-#     withhold them from this pipeline. Because homelab is PUBLIC, it is also set
-#     to require approval for forked-PR pipelines, so an untrusted fork cannot
-#     rewrite this file to exfiltrate the tokens.
-#
-# Triggering: pull_request only — automatic on PR open + push-to-open-PR. To
-# re-review a PR, push a commit (the new head sha clears the dedup marker below
-# and earns a fresh review). There is deliberately no on-demand trigger for a
-# specific PR: Woodpecker exposes injected variables to YAML substitution and
-# `when` filters, NOT to a step's shell environment, so a PR=<n> re-review would
-# silently no-op (the step would find no PR number and exit green).
-# (Note: keep literal dollar-brace out of THIS file entirely, even in comments —
-# Woodpecker runs its variable substitution over the whole YAML text, comments
-# included, and an unparseable one errors the pipeline before any step runs.)
+# (Note: keep literal dollar-brace out of THIS file, even in comments — Woodpecker
+# runs its variable substitution over the whole YAML text.)
 when:
   - event: pull_request
 
 steps:
   - name: pr-review-agent
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.289
+    image: gitea.renner.uno/gitea_admin/ci-claude:latest
+    pull: true
     environment:
       CLAUDE_CODE_OAUTH_TOKEN:
         from_secret: claude_code_oauth_token
       REVIEW_TOKEN:
         from_secret: review_bot_token
     commands:
-      - |
-        # ---- Resolve the single triggering PR --------------------------------
-        # Woodpecker hands us the repo (CI_REPO, canonical owner/repo) and the PR
-        # number (CI_COMMIT_PULL_REQUEST, a pull_request-event built-in). Build
-        # /tmp/pr-review/worklist.jsonl with 0 or 1 entries; an empty file makes
-        # the next block a no-op (the agent never starts).
-        set -eu
-        API="https://gitea.renner.uno/api/v1"
-        AUTH="Authorization: token $$REVIEW_TOKEN"
-        SLUG="$$CI_REPO"
-        NUM="$${CI_COMMIT_PULL_REQUEST:-}"
-        REVIEW_BOT_LOGIN="review-bot"
-        mkdir -p /tmp/pr-review
-        : > /tmp/pr-review/worklist.jsonl
-
-        if [ -z "$$NUM" ]; then
-          echo "No PR number in CI env (event=$${CI_PIPELINE_EVENT:-?}) — nothing to review."
-          exit 0
-        fi
-        echo "Triggered for $$SLUG#$$NUM (event $${CI_PIPELINE_EVENT:-?})."
-
-        if ! curl -sf -H "$$AUTH" "$$API/repos/$$SLUG/pulls/$$NUM" > /tmp/pr-review/pr.json; then
-          echo "Cannot fetch $$SLUG#$$NUM (review-bot not a collaborator / PR gone?) — skipping."
-          exit 0
-        fi
-        STATE=$$(jq -r '.state'        /tmp/pr-review/pr.json)
-        DRAFT=$$(jq -r '.draft // false' /tmp/pr-review/pr.json)
-        TITLE=$$(jq -r '.title'        /tmp/pr-review/pr.json)
-        HEAD=$$(jq -r '.head.sha'      /tmp/pr-review/pr.json)
-        SHORT=$$(printf '%s' "$$HEAD" | cut -c1-8)
-
-        # Skip closed/merged, drafts, and WIP-titled PRs — not ready for review.
-        case "$$STATE" in open) ;; *) echo "#$$NUM is $$STATE — skip."; exit 0;; esac
-        case "$$DRAFT" in true) echo "#$$NUM draft — skip."; exit 0;; esac
-        case "$$TITLE" in [Ww][Ii][Pp]:*|[Ww][Ii][Pp]\ *) echo "#$$NUM WIP — skip."; exit 0;; esac
-
-        # Dedup: already reviewed at THIS head sha? (guards re-runs / restarts)
-        REVIEWED=$$(curl -sf -H "$$AUTH" "$$API/repos/$$SLUG/pulls/$$NUM/reviews?limit=50" \
-          | jq -r --arg u "$$REVIEW_BOT_LOGIN" --arg m "pr-review:sha=$$HEAD" \
-              '[.[] | select(.user.login == $$u) | select(.body | contains($$m))] | length' \
-          || echo 0)
-        if [ "$${REVIEWED:-0}" -gt 0 ]; then
-          echo "#$$NUM already reviewed at $$SHORT — skip."
-          exit 0
-        fi
-
-        jq -c --arg slug "$$SLUG" \
-          '{slug: $$slug, number: .number, head: .head.sha, base: .base.sha,
-            title: .title, author: .user.login}' \
-          /tmp/pr-review/pr.json >> /tmp/pr-review/worklist.jsonl
-        echo "#$$NUM enqueued (head $$SHORT)."
-      - |
-        # ---- Clone, pick model, review, post ---------------------------------
-        set -eu
-        [ -s /tmp/pr-review/worklist.jsonl ] || { echo "Nothing to review."; exit 0; }
-        API="https://gitea.renner.uno/api/v1"
-        AUTH="Authorization: token $$REVIEW_TOKEN"
-        WS="$$PWD"                     # workspace = this repo, checked out at the PR head by Woodpecker
-        MAX_DIFF_LINES=20000
-
-        # Agent prompts: use the local homelab checkout if present, else clone
-        # public homelab@master for them (one source of truth for the rubric).
-        PROMPTS="$$WS/ci/agents/pr-review"
-        HOMELAB="$$WS"                 # repo root holding ci/ AND scripts/ci/
-        # NB: for a homelab PR, HOMELAB is the PR head checkout, so the
-        # fetch-models.sh run below executes branch-supplied shell. It is wrapped
-        # in `env -u REVIEW_TOKEN`, so the only credential it can see is
-        # CLAUDE_CODE_OAUTH_TOKEN. This is not a new exposure regardless: on
-        # pull_request Woodpecker already takes .woodpecker/*.yml itself from the
-        # PR branch, so a branch can run arbitrary commands in this step anyway.
-        if [ ! -f "$$PROMPTS/prompt.md" ]; then
-          rm -rf /tmp/pr-review/homelab
-          git clone --quiet --depth 1 https://gitea.renner.uno/k.renner/homelab \
-            /tmp/pr-review/homelab
-          PROMPTS=/tmp/pr-review/homelab/ci/agents/pr-review
-          HOMELAB=/tmp/pr-review/homelab
-        fi
-        echo "Using prompts from $$PROMPTS"
-
-        gitea_post() {                 # method url datafile ; echoes+checks HTTP
-          code=$$(curl -s -o /tmp/pr-review/resp.json -w '%{http_code}' \
-            -X "$$1" -H "$$AUTH" -H "Content-Type: application/json" \
-            --data @"$$3" "$$2")
-          echo "$$1 $$2 -> HTTP $$code"
-          if [ "$$code" -lt 200 ] || [ "$$code" -ge 300 ]; then
-            echo "Gitea API error body:"; cat /tmp/pr-review/resp.json; echo; return 1
-          fi
-        }
-
-        while IFS= read -r ITEM; do
-          SLUG=$$(printf '%s' "$$ITEM"  | jq -r '.slug')
-          NUM=$$(printf '%s' "$$ITEM"   | jq -r '.number')
-          HEAD=$$(printf '%s' "$$ITEM"  | jq -r '.head')
-          TITLE=$$(printf '%s' "$$ITEM" | jq -r '.title')
-          SHORT=$$(printf '%s' "$$HEAD" | cut -c1-8)
-          echo "=== Reviewing $$SLUG#$$NUM ($$SHORT) ==="
-          D="/tmp/pr-review/$$NUM"
-          rm -rf "$$D"; mkdir -p "$$D"
-
-          # PR metadata + unified diff (authenticated; private repos need it).
-          curl -sf -H "$$AUTH" "$$API/repos/$$SLUG/pulls/$$NUM" > "$$D/pr.json"
-          curl -sf -H "$$AUTH" "$$API/repos/$$SLUG/pulls/$$NUM.diff" > "$$D/diff.full.patch" \
-            || { echo "Could not fetch diff for $$SLUG#$$NUM — skipping."; continue; }
-          FILES=$$(grep -c '^diff --git ' "$$D/diff.full.patch" || true)
-          ADDED=$$(grep -c '^+[^+]' "$$D/diff.full.patch" || true)
-          DELETED=$$(grep -c '^-[^-]' "$$D/diff.full.patch" || true)
-          TOTAL=$$(wc -l < "$$D/diff.full.patch")
-          if [ "$$TOTAL" -gt "$$MAX_DIFF_LINES" ]; then
-            head -n "$$MAX_DIFF_LINES" "$$D/diff.full.patch" > "$$D/diff.patch"
-            printf '\n... [diff truncated at %s of %s lines] ...\n' \
-              "$$MAX_DIFF_LINES" "$$TOTAL" >> "$$D/diff.patch"
-          else
-            cp "$$D/diff.full.patch" "$$D/diff.patch"
-          fi
-          printf 'repo: %s\nPR: #%s\nfiles_changed: %s\nlines_added: %s\nlines_deleted: %s\ndiff_total_lines: %s\n' \
-            "$$SLUG" "$$NUM" "$$FILES" "$$ADDED" "$$DELETED" "$$TOTAL" > "$$D/stats.txt"
-
-          # Cheaper inputs for the TRIAGE agent (which now runs on a capable
-          # default model): the COMPLETE changed-file list, plus a diff capped far
-          # smaller than the review's. Triage only gauges size/shape/sensitivity,
-          # so it never needs the full (up to 20k-line) review diff — this keeps
-          # "triage is cheap" true now that its model is no longer pinned to Haiku.
-          grep '^diff --git ' "$$D/diff.full.patch" | sed 's|^diff --git a/||; s| b/.*$$||' \
-            | sort -u > "$$D/files.txt"
-          head -n 4000 "$$D/diff.patch" > "$$D/diff.triage.patch"
-
-          # No manual clone of the target repo: this runs on a pull_request
-          # event, so Woodpecker's built-in clone already checked THIS repo out
-          # at the PR head in $$WS — the agents (which cd into $$WS) read it
-          # directly for context. The old cron model had to clone each target
-          # repo by hand (its workspace was homelab@master), and that clone
-          # embedded REVIEW_TOKEN in the URL, persisting a write-scoped PAT in
-          # work/target/.git/config — readable by the review agent whose report
-          # is posted publicly. Per-repo pull_request triggering makes the manual
-          # clone redundant AND keeps the token off disk (it now lives only in
-          # the ephemeral curl Authorization headers used for the API calls).
-
-          # Inputs the agents read live at ./.pr-review (symlink into $$D).
-          rm -f "$$WS/.pr-review"; ln -s "$$D" "$$WS/.pr-review"
-
-          # --- Triage: an agent picks the model from the LIVE catalog, so no
-          #     model id and no model family is baked into this file.
-          #     fetch-models.sh asks the Anthropic /v1/models list (via the same
-          #     CLAUDE_CODE_OAUTH_TOKEN) and we hand the triage the result at
-          #     ./.pr-review/models.txt. If the fetch fails the file is empty and
-          #     MODEL stays empty below, so the review runs on the CLI default.
-          if MODELS_TABLE=$$(env -u REVIEW_TOKEN sh "$$HOMELAB/scripts/ci/fetch-models.sh" --table); then
-            printf '%s\n' "$$MODELS_TABLE" > "$$D/models.txt"
-            echo "Live model catalog ($$(wc -l < "$$D/models.txt") models) written for triage."
-          else
-            : > "$$D/models.txt"
-            echo "Model catalog fetch failed — triage/review will use the CLI default model."
-          fi
-          # env -u REVIEW_TOKEN: the agents never call Gitea (the shell does, via
-          # $$AUTH), so the write:repository PAT must not sit in the agent's env
-          # where a prompt-injected diff could read /proc/self/environ. Defence in
-          # depth alongside the settings.json Read-sandbox. Triage itself runs on
-          # the CLI default model (no --model) — we don't name a family even to
-          # bootstrap the pick.
-          cat "$$PROMPTS/triage-prompt.md" | env -u REVIEW_TOKEN claude \
-            --permission-mode acceptEdits \
-            --allowedTools "Read,Glob,Grep,Write" \
-            --settings "$$PROMPTS/settings.json" \
-            -p || echo "(triage agent exited non-zero)"
-          # Use the triage's pick only if it is a currently-available id;
-          # otherwise (hallucinated id, or empty catalog) leave MODEL empty so
-          # the review runs on the CLI default — a run never dies on selection.
-          MODEL=$$(jq -r '.model // empty' "$$D/triage.json" 2>/dev/null || true)
-          CPLX=$$(jq -r '.complexity // "unknown"' "$$D/triage.json" 2>/dev/null || echo unknown)
-          # triage.json is UNTRUSTED (the triage reads the attacker-controlled
-          # diff and its Write is not path-scoped). valid-model.sh is the single,
-          # unit-tested gate (scripts/ci/test-model-selection.sh): it echoes the id
-          # only if it is a safe [A-Za-z0-9._-] token present in the catalog, else
-          # nothing — so a value like "claude-x\n--dangerously-skip-permissions"
-          # can never reach the unquoted --model expansion below. Empty -> default.
-          # CRITICAL: validate against $$MODELS_TABLE — the catalog captured in a
-          # shell variable BEFORE the triage ran — NOT the on-disk ./.pr-review/
-          # models.txt, which the triage's unscoped Write could overwrite to smuggle
-          # an attacker-chosen token past the membership check (the triage reads the
-          # file, but only $$MODELS_TABLE is trusted). This mirrors pick-model.sh,
-          # which validates its pick against its in-memory table for the same reason.
-          # env -u REVIEW_TOKEN: like fetch-models.sh above, this runs a script from
-          # $$HOMELAB (branch-supplied for a homelab PR) — it must not see the PAT.
-          # `|| true`: keep the "a run never dies on selection" invariant even if
-          # the script is absent (e.g. a PR that moves scripts/ci/).
-          MODEL=$$(printf '%s\n' "$$MODELS_TABLE" | env -u REVIEW_TOKEN sh "$$HOMELAB/scripts/ci/valid-model.sh" "$$MODEL" || true)
-          [ -n "$$MODEL" ] || echo "Triage model rejected or not in live catalog — using the CLI default model."
-          # Defence in depth: for a complex / security-sensitive review, do NOT
-          # trust the triage's pick (it read the attacker-controlled diff and could
-          # be injected into naming the weakest catalog entry to get a shallow
-          # review). Fall back to the CLI default — the strongest configured model.
-          if [ "$$CPLX" = complex ] && [ -n "$$MODEL" ]; then
-            echo "complex review — ignoring triage pick '$$MODEL', using the CLI default (strongest) model."
-            MODEL=
-          fi
-          if [ -n "$$MODEL" ]; then echo "Triage: complexity=$$CPLX -> model=$$MODEL"; else echo "Triage: complexity=$$CPLX -> CLI default model"; fi
-
-          # --- Review with the chosen model ---
-          ( cd "$$WS" && cat "$$PROMPTS/prompt.md" | env -u REVIEW_TOKEN claude $${MODEL:+--model $$MODEL} \
-              --permission-mode acceptEdits \
-              --allowedTools "Read,Glob,Grep,Write" \
-              --settings "$$PROMPTS/settings.json" \
-              -p ) || echo "(review agent exited non-zero)"
-
-          if [ ! -s "$$D/report.md" ]; then
-            echo "Agent wrote no report for $$SLUG#$$NUM — skipping post."
-            continue
-          fi
-          EVENT=$$(jq -r '.event // "COMMENT"' "$$D/verdict.json" 2>/dev/null || echo COMMENT)
-          case "$$EVENT" in REQUEST_CHANGES|COMMENT) ;; *) EVENT=COMMENT;; esac   # never APPROVE
-
-          # Assemble the review body: header + report + marker footer.
-          {
-            printf '🤖 **Automated review** — model `%s` (complexity: %s), commit `%s`.\n\n' \
-              "$${MODEL:-CLI default}" "$$CPLX" "$${HEAD}"
-            printf '> Advisory review by the `review-bot` pipeline. It never approves; a human merges. Push new commits to get a fresh review.\n\n---\n\n'
-            cat "$$D/report.md"
-            printf '\n\n<!-- pr-review:sha=%s -->\n' "$$HEAD"
-          } > "$$D/body.md"
-          jq -n --rawfile b "$$D/body.md" --arg e "$$EVENT" --arg c "$$HEAD" \
-            '{body: $$b, event: $$e, commit_id: $$c}' > "$$D/review.json"
-          gitea_post POST "$$API/repos/$$SLUG/pulls/$$NUM/reviews" "$$D/review.json" \
-            && echo "Posted $$EVENT review on $$SLUG#$$NUM." \
-            || echo "FAILED to post review on $$SLUG#$$NUM (continuing)."
-          rm -f "$$WS/.pr-review"
-        done < /tmp/pr-review/worklist.jsonl
-        echo "PR review run complete."
+      - rm -rf /tmp/pr-review-central
+      - git clone --quiet --depth 1 https://gitea.renner.uno/k.renner/homelab /tmp/pr-review-central
+      - sh /tmp/pr-review-central/ci/agents/pr-review/run.sh

.woodpecker/security-scan.yml

@@ -70,7 +70,7 @@ steps:
     # this step is skipped — otherwise we'd fork-bomb PRs.
     when:
       - branch: master
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.289
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.296
     environment:
       CLAUDE_CODE_OAUTH_TOKEN:
         from_secret: claude_code_oauth_token

.woodpecker/update-audit.yml

@@ -30,7 +30,7 @@ when:
 
 steps:
   - name: update-audit-agent
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.289
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.296
     environment:
       CLAUDE_CODE_OAUTH_TOKEN:
         from_secret: claude_code_oauth_token

.woodpecker/wiki-maintenance.yml

@@ -17,7 +17,7 @@ when:
 
 steps:
   - name: checkout-notes
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.289
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.296
     pull: true
     environment:
       WIKI_BOT_TOKEN:
@@ -54,7 +54,7 @@ steps:
       - bash scripts/ci/make-diag-kubeconfig.sh
 
   - name: distill
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.289
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.296
     pull: true
     environment:
       CLAUDE_CODE_OAUTH_TOKEN:
@@ -89,14 +89,14 @@ steps:
           -p
 
   - name: audit
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.289
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.296
     pull: true
     commands:
       # Findings are report lines in output/, not a pipeline failure.
       - python3 -B notes/bin/wiki_audit.py --vault "$$PWD/notes"
 
   - name: consolidate
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.289
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.296
     pull: true
     environment:
       CLAUDE_CODE_OAUTH_TOKEN:
@@ -145,7 +145,7 @@ steps:
         exit $$rc
 
   - name: push-notes
-    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.289
+    image: gitea.renner.uno/gitea_admin/ci-claude:2.1.296
     pull: true
     environment:
       WIKI_BOT_TOKEN:

README.md

@@ -58,7 +58,8 @@ target `build-agent-runtime`), versions bumped by Renovate. Both also
 carry `claude-agent-acp` for the ACP engine, pinned and patched like
 Paperclip ships it, SDK override included
 (`ci/images/agent-runtime-common/`); bump it by hand
-together with Paperclip. All tools are on the default `PATH`.
+together with Paperclip. All tools are on the default `PATH`. Both add
+`tzdata` (the base has no zoneinfo); the default zone stays UTC.
 
 | Image | `imageRegistry` | Adds |
 |---|---|---|

ansible/docs/edge-host.md

@@ -62,7 +62,6 @@ inventory change.
 |---|---|---|
 | Innomaker USB2CAN (Vitocal/VX3 + E380) | `heating_can` | `plays/install-heating-can.yml` |
 | Nabu Casa ZWA-2 Z-Wave radio | `zwave_gateway` | `plays/install-zwave-gateway.yml` |
-| FTDI serial power-meter head | `power_meter` | `plays/install-power-meter.yml` |
 
 Add the host to the matching group, then run that playbook. They depend on
 the base play having run: all three need the local MQTT bridge, and two of
@@ -87,7 +86,6 @@ kubectl -n home-assistant get secret zwave-js-session -o jsonpath='{.data.sessio
 
 ```yaml
 # vault.yml
-vault_edge_sml2mqtt_mqtt_password: "..."
 vault_edge_open3e_mqtt_password: "..."
 vault_edge_zwavejs_session_secret: "..."
 vault_edge_loki_password: "..."   # dedicated edge-1 Loki push cred (see "Logging & eMMC")
@@ -238,6 +236,21 @@ cluster-side change was needed**: one authenticates as the `open3e` user
 out). The local broker is `allow_anonymous` on loopback — the trust boundary
 is the host; nothing off-host can reach it.
 
+**Bridge credential (REN-1307).** The two vault-password bridges are being
+replaced by one bridge as the register account `edge-1`
+(`kubernetes/apps/home-assistant/mqtt-accounts.yaml`). Its password is pushed
+by mqtt-account-controller to `edge-mqtt-cred` (`:8443`, the controller's
+esp32 API over HTTPS). That endpoint accepts only a client certificate from
+the MQTT CA with CN `mqtt-account-controller`; edge-1 holds the public CA and
+its own server key, nothing else. On a push it writes
+`/etc/mosquitto/bridge.d/edge-1.conf`, deletes `bridge.d/legacy.conf` and
+restarts the local mosquitto. The controller sets a new password whenever the
+bridge reports "not connected" (also after a reinstall), so no play run is
+needed for a rotation. `.woodpecker/deploy-edge-mqtt-bridge.yml` runs
+`plays/edge-mqtt-bridge.yml` on merge. Diagnosis: `journalctl -u
+edge-mqtt-cred`, and `mosquitto_sub -t '$SYS/broker/connection/edge-1/state'`
+(retained `1` = connected).
+
 **eMMC:** the local broker writes **nothing** to flash — `persistence false`
 (retained/queued messages in RAM) and `log_dest stdout` (to the volatile
 journal → Loki). Do not add persistence or log-file settings to

ansible/inventory/group_vars/edge_host/vars.yml

@@ -2,7 +2,6 @@
 # Secret indirection — real values live in vault.yml (ansible-vault) next
 # to this file; see docs/edge-host.md for how to populate it from
 # the cluster secrets.
-edge_sml2mqtt_mqtt_password: "{{ vault_edge_sml2mqtt_mqtt_password }}"
 edge_open3e_mqtt_password: "{{ vault_edge_open3e_mqtt_password }}"
 edge_zwavejs_session_secret: "{{ vault_edge_zwavejs_session_secret }}"
 # Loki push credential (dedicated 'edge-1' user, Traefik basic-auth on the
@@ -39,8 +38,8 @@ chrony_hwtimestamp: false
 
 # --- Local MQTT contract -------------------------------------------------
 # Shared between the broker and its clients, so it belongs to the inventory
-# rather than to either side's role. mqtt-bridge listens here; heating-can and
-# power-meter-sml publish here; and the bridge authenticates to the cluster
+# rather than to either side's role. mqtt-bridge listens here; heating-can
+# publishes here; and the bridge authenticates to the cluster
 # broker AS the open3e user, so it needs that identity too.
 #
 # Keeping these in one role's defaults only worked while a single play loaded

ansible/inventory/pve_hosts.yml

@@ -41,13 +41,9 @@ edge-1.iot.renner.uno
 [heating_can]
 edge-1.iot.renner.uno
 
-[power_meter]
-edge-1.iot.renner.uno
-
 [edge_host:children]
 zwave_gateway
 heating_can
-power_meter
 
 # NTP servers. edge-1 was added here so the role would survive the PVE hosts
 # being retired for bare-metal Talos, which cannot run chrony or keepalived

ansible/plays/edge-mqtt-bridge.yml

@@ -0,0 +1,33 @@
+---
+# Local MQTT bridge and its credential receiver only (REN-1307). Run by
+# .woodpecker/deploy-edge-mqtt-bridge.yml on merge, so a change to this role
+# reaches edge-1 without a play run by hand. The full base play
+# (install-edge-host.yml) carries the same role.
+- name: Converge the edge MQTT bridge
+  hosts: edge_host
+  become: true
+
+  # The SML power-meter reader (sml2mqtt) is retired for good: owner decision
+  # 2026-09-19, grid data comes from the E380 on the CAN bus. Its role and
+  # play are gone; this removes the leftover compose project from edge-1 on
+  # the next pipeline run. Idempotent: a no-op once the directory is gone.
+  pre_tasks:
+    - name: Check for the retired sml2mqtt compose project
+      ansible.builtin.stat:
+        path: /opt/edge-host/sml2mqtt/docker-compose.yml
+      register: edge_sml2mqtt_compose
+
+    - name: Stop the retired sml2mqtt container
+      ansible.builtin.command:
+        cmd: docker compose down --remove-orphans
+        chdir: /opt/edge-host/sml2mqtt
+      when: edge_sml2mqtt_compose.stat.exists
+      changed_when: true
+
+    - name: Remove the retired sml2mqtt directory
+      ansible.builtin.file:
+        path: /opt/edge-host/sml2mqtt
+        state: absent
+
+  roles:
+    - mqtt-bridge

ansible/plays/install-edge-host.yml

@@ -9,7 +9,6 @@
 #
 #   plays/install-zwave-gateway.yml   [zwave_gateway]   ZWA-2 radio
 #   plays/install-heating-can.yml     [heating_can]     Innomaker USB2CAN
-#   plays/install-power-meter.yml     [power_meter]     FTDI meter head
 #
 # Splitting the roles without splitting the plays would have kept the coupling:
 # one play applying every role to one group is the monolith again, a layer up.

ansible/plays/install-power-meter.yml

@@ -1,14 +0,0 @@
----
-# Power-meter reader (sml2mqtt) for hosts with the FTDI serial meter head
-# attached.
-#
-# Targets [power_meter]: membership means the meter head is physically present.
-#
-# Requires the base play (plays/install-edge-host.yml) to have run: it needs
-# docker and publishes to the local MQTT bridge.
-- name: Install power-meter reader
-  hosts: power_meter
-  become: true
-
-  roles:
-    - power-meter-sml

ansible/roles/mqtt-bridge/defaults/main.yml

@@ -10,3 +10,14 @@
 edge_mqtt_cluster_host: mqtt.renner.uno
 edge_mqtt_cluster_tls_port: 8883
 edge_mqtt_bridge_cafile: /etc/ssl/certs/ca-certificates.crt
+
+# --- Bridge credential from mqtt-account-controller (REN-1307) ------------
+# The cluster account the bridge logs in as (register entry in
+# kubernetes/apps/home-assistant/mqtt-accounts.yaml). The controller pushes
+# its password to edge-mqtt-cred and rotates it when the bridge reports
+# "not connected"; there is no copy in ansible-vault.
+edge_mqtt_bridge_account: edge-1
+# HTTPS port of edge-mqtt-cred (esp32 device API, mTLS). Only a client
+# certificate from the MQTT CA with this CN is accepted.
+edge_mqtt_cred_port: 8443
+edge_mqtt_cred_allowed_cn: mqtt-account-controller

ansible/roles/mqtt-bridge/files/edge-mqtt-cred.py

@@ -0,0 +1,141 @@
+#!/usr/bin/env python3
+# Managed by ansible (roles/mqtt-bridge). Receives the cluster bridge password
+# from mqtt-account-controller (REN-1307) so no plaintext copy lives in
+# ansible-vault and no play run is needed to rotate it.
+#
+# Speaks the controller's esp32 device API over HTTPS:
+#   GET /api/status   -> {"mqtt": {"connected": bool}}
+#   PUT /api/settings <- {"mqtt": {"user": "...", "pass": "..."}}
+# A client certificate from the MQTT CA with CN mqtt-account-controller is
+# required; nothing else may call it. The server key is generated on this
+# host and never leaves it (the controller pins it on first contact).
+#
+# PUT writes the bridge file (template + credentials), removes the legacy
+# vault-password bridges and restarts the local mosquitto. The password is
+# kept only in that 0640 root:mosquitto file.
+import grp
+import json
+import os
+import socket
+import ssl
+import subprocess
+import sys
+import tempfile
+import threading
+from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
+
+CONF = json.load(open(sys.argv[1]))
+WRITE = threading.Lock()
+
+
+def connected():
+    try:
+        out = subprocess.run(
+            ["mosquitto_sub", "-h", "127.0.0.1", "-p", str(CONF["local_port"]),
+             "-t", CONF["state_topic"], "-C", "1", "-W", "3"],
+            capture_output=True, text=True, timeout=10).stdout
+    except (OSError, subprocess.TimeoutExpired):
+        return False
+    return out.strip() == "1"
+
+
+def write_bridge(user, password):
+    with open(CONF["template"]) as f:
+        body = f.read()
+    body += f"remote_username {user}\nremote_password {password}\n"
+    d = os.path.dirname(CONF["bridge_file"])
+    fd, tmp = tempfile.mkstemp(dir=d, prefix=".edge-mqtt-cred.")
+    with os.fdopen(fd, "w") as f:
+        f.write(body)
+    os.chown(tmp, 0, grp.getgrnam("mosquitto").gr_gid)
+    os.chmod(tmp, 0o640)
+    os.replace(tmp, CONF["bridge_file"])
+    for legacy in CONF["legacy_files"]:
+        if os.path.exists(legacy):
+            os.remove(legacy)
+    subprocess.run(["systemctl", "restart", "mosquitto"], check=True, timeout=60)
+
+
+def valid(s):
+    # Controller passwords are random URL-safe tokens; anything with
+    # whitespace or a control character would break the config line.
+    return isinstance(s, str) and 0 < len(s) <= 256 and s.isprintable() and not any(c.isspace() for c in s)
+
+
+class Handler(BaseHTTPRequestHandler):
+    def authorized(self):
+        cert = self.connection.getpeercert() or {}
+        cns = [v for rdn in cert.get("subject", ()) for k, v in rdn if k == "commonName"]
+        if cns != [CONF["allowed_cn"]]:
+            self.send_error(403)
+            return False
+        return True
+
+    def reply(self, code, obj=None):
+        data = b"" if obj is None else json.dumps(obj).encode()
+        self.send_response(code)
+        if data:
+            self.send_header("Content-Type", "application/json")
+        self.send_header("Content-Length", str(len(data)))
+        self.end_headers()
+        self.wfile.write(data)
+
+    def do_GET(self):
+        if not self.authorized():
+            return
+        if self.path != "/api/status":
+            return self.send_error(404)
+        self.reply(200, {"mqtt": {"connected": connected()}})
+
+    def do_PUT(self):
+        if not self.authorized():
+            return
+        if self.path != "/api/settings":
+            return self.send_error(404)
+        try:
+            n = int(self.headers.get("Content-Length", "0"))
+            if not 0 < n <= 4096:
+                raise ValueError("body size")
+            m = json.loads(self.rfile.read(n))["mqtt"]
+            user, password = m["user"], m["pass"]
+        except (ValueError, KeyError, TypeError):
+            return self.send_error(400)
+        if user != CONF["user"] or not valid(password):
+            return self.send_error(400)
+        with WRITE:
+            write_bridge(user, password)
+        self.log_message("bridge credentials for %s replaced, mosquitto restarted", user)
+        self.reply(204)
+
+    def log_message(self, fmt, *args):
+        sys.stderr.write("%s %s\n" % (self.address_string(), fmt % args))
+
+
+class Server(ThreadingHTTPServer):
+    address_family = socket.AF_INET6
+
+    def server_bind(self):
+        self.socket.setsockopt(socket.IPPROTO_IPV6, socket.IPV6_V6ONLY, 0)
+        super().server_bind()
+
+    def get_request(self):
+        # The TLS handshake runs in the request thread, with a timeout, so a
+        # stalled peer cannot block the accept loop.
+        sock, addr = self.socket.accept()
+        sock.settimeout(10)
+        return self.ctx.wrap_socket(sock, server_side=True, do_handshake_on_connect=False), addr
+
+
+def main():
+    ctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
+    ctx.minimum_version = ssl.TLSVersion.TLSv1_2
+    ctx.load_cert_chain(CONF["cert"], CONF["key"])
+    ctx.load_verify_locations(CONF["ca"])
+    ctx.verify_mode = ssl.CERT_REQUIRED
+    srv = Server(("::", CONF["port"]), Handler)
+    srv.ctx = ctx
+    srv.serve_forever()
+
+
+if __name__ == "__main__":
+    main()

ansible/roles/mqtt-bridge/files/mqtt-ca.crt

@@ -0,0 +1,10 @@
+-----BEGIN CERTIFICATE-----
+MIIBdTCCARygAwIBAgIUN8ne4k4Wif9O83GDyKiBP0Ma7EIwCgYIKoZIzj0EAwIw
+GTEXMBUGA1UEAxMOUmVubmVyIE1RVFQgQ0EwHhcNMjYxMDA2MTUzMDE1WhcNMzYx
+MDAzMTUzMDE1WjAZMRcwFQYDVQQDEw5SZW5uZXIgTVFUVCBDQTBZMBMGByqGSM49
+AgEGCCqGSM49AwEHA0IABOZhZF2JDoyvVg2oIXSbJAuAWDcoG22RxPA4oMKRMA/b
+XzIY566D2k6cVnWqbil9s/q4O2mj+Epo7plBw8NwuOOjQjBAMA4GA1UdDwEB/wQE
+AwICpDAPBgNVHRMBAf8EBTADAQH/MB0GA1UdDgQWBBQcqSDDiLZzhrvqq9f16Y08
+CO7QfzAKBggqhkjOPQQDAgNHADBEAiBFkxd9pXnqIcjReEcOTvCBZ3HxKu2jNQGL
+/le7gunTGgIgZapWAcu4awa+wmZcR/z2luOjD2GhIT15um14Z+sstJk=
+-----END CERTIFICATE-----

ansible/roles/mqtt-bridge/handlers/main.yml

@@ -5,3 +5,9 @@
   ansible.builtin.service:
     name: mosquitto
     state: restarted
+
+- name: Restart edge-mqtt-cred
+  ansible.builtin.systemd:
+    name: edge-mqtt-cred
+    state: restarted
+    daemon_reload: true

ansible/roles/mqtt-bridge/tasks/main.yml

@@ -11,13 +11,39 @@
     name: mosquitto
     state: present
 
-- name: Deploy local mosquitto bridge config
+- name: Create the bridge directory
+  ansible.builtin.file:
+    path: /etc/mosquitto/bridge.d
+    state: directory
+    owner: root
+    group: mosquitto
+    mode: "0750"
+
+- name: Check for the controller-managed bridge file
+  ansible.builtin.stat:
+    path: "/etc/mosquitto/bridge.d/{{ edge_mqtt_bridge_account }}.conf"
+  register: edge_mqtt_bridge_managed
+
+# Until mqtt-account-controller has pushed the first password, keep the
+# vault-password bridges so the cluster never loses edge-1's data. Once the
+# managed file exists, never render them again (edge-mqtt-cred removed them).
+- name: Deploy legacy vault-password bridges
+  ansible.builtin.template:
+    src: edge-mqtt-bridge-legacy.conf.j2
+    dest: /etc/mosquitto/bridge.d/legacy.conf
+    owner: root
+    group: mosquitto
+    mode: "0640"   # carries the legacy cluster bridge credentials
+  when: not edge_mqtt_bridge_managed.stat.exists
+  notify: Restart mosquitto
+
+- name: Deploy local mosquitto config
   ansible.builtin.template:
     src: edge-mqtt-bridge.conf.j2
     dest: /etc/mosquitto/mosquitto.conf
     owner: root
     group: mosquitto
-    mode: "0640"   # carries the cluster bridge credentials
+    mode: "0640"
   notify: Restart mosquitto
 
 - name: Enable local mosquitto bridge
@@ -25,3 +51,59 @@
     name: mosquitto
     enabled: true
     state: started
+
+# --- edge-mqtt-cred (REN-1307): receives the bridge password from
+# mqtt-account-controller. edge-1 holds only the public MQTT CA and its own
+# server key, generated here and never copied off the host.
+- name: Create edge-mqtt-cred config directory
+  ansible.builtin.file:
+    path: /etc/edge-mqtt-cred
+    state: directory
+    owner: root
+    group: root
+    mode: "0700"
+
+- name: Generate edge-mqtt-cred server key and certificate
+  ansible.builtin.command:
+    cmd: >-
+      openssl req -x509 -newkey ec -pkeyopt ec_paramgen_curve:prime256v1
+      -nodes -days 36500 -subj "/CN={{ inventory_hostname }}"
+      -keyout /etc/edge-mqtt-cred/tls.key -out /etc/edge-mqtt-cred/tls.crt
+    creates: /etc/edge-mqtt-cred/tls.key
+  notify: Restart edge-mqtt-cred
+
+- name: Deploy edge-mqtt-cred files
+  ansible.builtin.copy:
+    src: "{{ item.src }}"
+    dest: "{{ item.dest }}"
+    owner: root
+    group: root
+    mode: "{{ item.mode }}"
+  loop:
+    - {src: edge-mqtt-cred.py, dest: /usr/local/sbin/edge-mqtt-cred, mode: "0755"}
+    # Public CA of the cluster's MQTT client certificates
+    # (kubernetes/infrastructure/post-crds/mqtt-ca.yaml), valid until 2036-10-03.
+    - {src: mqtt-ca.crt, dest: /etc/edge-mqtt-cred/mqtt-ca.crt, mode: "0644"}
+  notify: Restart edge-mqtt-cred
+
+- name: Deploy edge-mqtt-cred config and bridge template
+  ansible.builtin.template:
+    src: "{{ item.src }}"
+    dest: "{{ item.dest }}"
+    owner: root
+    group: root
+    mode: "{{ item.mode }}"
+  loop:
+    - {src: edge-mqtt-cred.json.j2, dest: /etc/edge-mqtt-cred/config.json, mode: "0600"}
+    # Read only on the controller's next push: a change here reaches the
+    # running bridge when the password is next set.
+    - {src: edge-1-bridge.conf.in.j2, dest: /etc/edge-mqtt-cred/bridge.conf.in, mode: "0600"}
+    - {src: edge-mqtt-cred.service.j2, dest: /etc/systemd/system/edge-mqtt-cred.service, mode: "0644"}
+  notify: Restart edge-mqtt-cred
+
+- name: Enable edge-mqtt-cred
+  ansible.builtin.systemd:
+    name: edge-mqtt-cred
+    enabled: true
+    state: started
+    daemon_reload: true

ansible/roles/mqtt-bridge/templates/edge-1-bridge.conf.in.j2

@@ -0,0 +1,21 @@
+# Managed by roles/mqtt-bridge (REN-1307). edge-mqtt-cred appends
+# remote_username/remote_password to this and writes the result to
+# /etc/mosquitto/bridge.d/{{ edge_mqtt_bridge_account }}.conf. One bridge for
+# open3e, as the register account `{{ edge_mqtt_bridge_account }}`
+# (ACL readwrite open3e/#). sml2mqtt is retired (SML reader, 2026-09-19).
+connection {{ edge_mqtt_bridge_account }}
+address {{ edge_mqtt_cluster_host }}:{{ edge_mqtt_cluster_tls_port }}
+bridge_cafile {{ edge_mqtt_bridge_cafile }}
+bridge_insecure false
+remote_clientid edge1-bridge
+cleansession false
+try_private true
+restart_timeout 5 30
+queue_qos0_messages true
+# The bridge state goes to the LOCAL broker only (retained 1/0); edge-mqtt-cred
+# reads it to answer the controller's "connected?".
+notifications true
+notifications_local_only true
+notification_topic $SYS/broker/connection/{{ edge_mqtt_bridge_account }}/state
+topic open3e/# out 0
+topic open3e/cmnd in 0

ansible/roles/mqtt-bridge/templates/edge-mqtt-bridge-legacy.conf.j2

@@ -0,0 +1,21 @@
+# Managed by roles/mqtt-bridge. Legacy vault-password bridges, rendered only
+# while /etc/mosquitto/bridge.d/{{ edge_mqtt_bridge_account }}.conf does not
+# exist; edge-mqtt-cred deletes this file on the controller's first push
+# (REN-1307). Remove with the vault keys once edge-1 is on the register account.
+# --- Bridge 1: open3e datapoints + command topic, as the cluster `open3e`
+# user (its ACL is `readwrite open3e/#`, which covers publishing datapoints
+# and subscribing to open3e/cmnd). e3oncan also publishes under open3e/#.
+connection edge1-open3e
+address {{ edge_mqtt_cluster_host }}:{{ edge_mqtt_cluster_tls_port }}
+bridge_cafile {{ edge_mqtt_bridge_cafile }}
+bridge_insecure false
+remote_username {{ edge_open3e_mqtt_user }}
+remote_password {{ edge_open3e_mqtt_password }}
+remote_clientid edge1-bridge-open3e
+cleansession false
+try_private true
+notifications false
+restart_timeout 5 30
+queue_qos0_messages true
+topic open3e/# out 0
+topic open3e/cmnd in 0

ansible/roles/mqtt-bridge/templates/edge-mqtt-bridge.conf.j2

@@ -22,36 +22,9 @@ log_type notice
 listener 1883 127.0.0.1
 allow_anonymous true
 
-# --- Bridge 1: open3e datapoints + command topic, as the cluster `open3e`
-# user (its ACL is `readwrite open3e/#`, which covers publishing datapoints
-# and subscribing to open3e/cmnd). e3oncan also publishes under open3e/#.
-connection edge1-open3e
-address {{ edge_mqtt_cluster_host }}:{{ edge_mqtt_cluster_tls_port }}
-bridge_cafile {{ edge_mqtt_bridge_cafile }}
-bridge_insecure false
-remote_username {{ edge_open3e_mqtt_user }}
-remote_password {{ edge_open3e_mqtt_password }}
-remote_clientid edge1-bridge-open3e
-cleansession false
-try_private true
-notifications false
-restart_timeout 5 30
-queue_qos0_messages true
-topic open3e/# out 0
-topic open3e/cmnd in 0
-
-# --- Bridge 2: power-meter topics, as the cluster `sml2mqtt` user (ACL
-# `write sml2mqtt/#`). Publish-only, so no `in` topics.
-connection edge1-sml2mqtt
-address {{ edge_mqtt_cluster_host }}:{{ edge_mqtt_cluster_tls_port }}
-bridge_cafile {{ edge_mqtt_bridge_cafile }}
-bridge_insecure false
-remote_username sml2mqtt
-remote_password {{ edge_sml2mqtt_mqtt_password }}
-remote_clientid edge1-bridge-sml2mqtt
-cleansession false
-try_private true
-notifications false
-restart_timeout 5 30
-queue_qos0_messages true
-topic sml2mqtt/# out 0
+# --- Bridges to the cluster broker (REN-1307). bridge.d holds either
+# {{ edge_mqtt_bridge_account }}.conf, written by edge-mqtt-cred with the password
+# mqtt-account-controller pushed, or, until that first push, legacy.conf with
+# the two vault-password bridges. edge-mqtt-cred deletes legacy.conf when it
+# writes the new file.
+include_dir /etc/mosquitto/bridge.d

ansible/roles/mqtt-bridge/templates/edge-mqtt-cred.json.j2

@@ -0,0 +1,13 @@
+{{ {
+  "port": edge_mqtt_cred_port,
+  "allowed_cn": edge_mqtt_cred_allowed_cn,
+  "user": edge_mqtt_bridge_account,
+  "cert": "/etc/edge-mqtt-cred/tls.crt",
+  "key": "/etc/edge-mqtt-cred/tls.key",
+  "ca": "/etc/edge-mqtt-cred/mqtt-ca.crt",
+  "template": "/etc/edge-mqtt-cred/bridge.conf.in",
+  "bridge_file": "/etc/mosquitto/bridge.d/" ~ edge_mqtt_bridge_account ~ ".conf",
+  "legacy_files": ["/etc/mosquitto/bridge.d/legacy.conf"],
+  "local_port": edge_mqtt_port,
+  "state_topic": "$SYS/broker/connection/" ~ edge_mqtt_bridge_account ~ "/state",
+} | to_nice_json }}

ansible/roles/mqtt-bridge/templates/edge-mqtt-cred.service.j2

@@ -0,0 +1,19 @@
+# Managed by roles/mqtt-bridge (REN-1307). See /usr/local/sbin/edge-mqtt-cred.
+[Unit]
+Description=Receives the MQTT bridge credential from mqtt-account-controller
+After=network-online.target mosquitto.service
+Wants=network-online.target
+
+[Service]
+ExecStart=/usr/bin/python3 /usr/local/sbin/edge-mqtt-cred /etc/edge-mqtt-cred/config.json
+Restart=always
+RestartSec=5
+# Root only to write the bridge file and restart mosquitto.
+ProtectSystem=strict
+ReadWritePaths=/etc/mosquitto/bridge.d
+ProtectHome=true
+PrivateTmp=true
+NoNewPrivileges=true
+
+[Install]
+WantedBy=multi-user.target

ansible/roles/power-meter-sml/defaults/main.yml

@@ -1,23 +0,0 @@
----
-# Power-meter reader: sml2mqtt against the FTDI serial meter head.
-
-# Service root. Kept per-role so the role is usable on its own.
-edge_base_dir: /opt/edge-host
-
-# Own compose project directory. Unchanged from the path used under the
-# previous shared project.
-sml_base_dir: "{{ edge_base_dir }}/sml2mqtt"
-
-# The compose file that used to hold both this service and zwave-js. Removed
-# once, so the fixed container_name is released for the new projects.
-edge_legacy_compose: "{{ edge_base_dir }}/docker-compose.yml"
-
-# Stable by-id symlink -- see the zwave-gateway role.
-edge_stromzaehler_device: /dev/serial/by-id/usb-FTDI_FT230X_Basic_UART_DK0E1GP5-if00-port0
-
-# Hand-pinned on purpose: critical meter bridge, deliberately excluded from
-# image automation.
-edge_sml2mqtt_image: spacemanspiff2007/sml2mqtt:3.6.0
-
-# Secret from inventory/group_vars/edge_host/vault.yml:
-#   edge_sml2mqtt_mqtt_password

ansible/roles/power-meter-sml/handlers/main.yml

@@ -1,6 +0,0 @@
----
-- name: Restart sml2mqtt
-  ansible.builtin.command:
-    cmd: docker compose up -d --force-recreate
-    chdir: "{{ sml_base_dir }}"
-  changed_when: true

ansible/roles/power-meter-sml/tasks/main.yml

@@ -1,55 +0,0 @@
----
-# Power-meter reader: sml2mqtt against the FTDI serial meter head.
-#
-# Its own compose project. It shared a compose file with the Z-Wave gateway,
-# which meant a change to either recreated both -- two unrelated services bound
-# to different USB devices. Data paths are unchanged.
-
-- name: Create sml2mqtt directory
-  ansible.builtin.file:
-    path: "{{ sml_base_dir }}"
-    state: directory
-    mode: "0755"
-
-# sml2mqtt reads only a config file and has no env override for the password,
-# so the rendered config carries it -- 0600, root-owned, same trust boundary as
-# the k8s init-container approach it replaced.
-- name: Deploy sml2mqtt config
-  ansible.builtin.template:
-    src: sml2mqtt-config.yml.j2
-    dest: "{{ sml_base_dir }}/config.yml"
-    mode: "0600"
-  notify: Restart sml2mqtt
-
-- name: Deploy sml2mqtt compose project
-  ansible.builtin.template:
-    src: docker-compose.yml.j2
-    dest: "{{ sml_base_dir }}/docker-compose.yml"
-    mode: "0644"
-  notify: Restart sml2mqtt
-
-- name: Pull sml2mqtt image
-  ansible.builtin.command:
-    cmd: docker compose pull
-    chdir: "{{ sml_base_dir }}"
-  changed_when: false
-
-# Tolerates a missing USB device, as for the Z-Wave gateway.
-- name: Start sml2mqtt
-  ansible.builtin.command:
-    cmd: docker compose up -d
-    chdir: "{{ sml_base_dir }}"
-  register: sml_compose_up
-  failed_when: >-
-    sml_compose_up.rc != 0
-    and 'error gathering device information' not in sml_compose_up.stderr
-  changed_when: >-
-    'Started' in sml_compose_up.stderr or 'Created' in sml_compose_up.stderr
-    or 'Started' in sml_compose_up.stdout or 'Creating' in sml_compose_up.stdout
-
-- name: Warn if sml2mqtt is waiting for its USB device
-  ansible.builtin.debug:
-    msg: >-
-      sml2mqtt could not start -- the FTDI meter head is not present:
-      {{ sml_compose_up.stderr_lines | select('search', 'device') | list }}
-  when: sml_compose_up.rc != 0

ansible/roles/power-meter-sml/templates/docker-compose.yml.j2

@@ -1,21 +0,0 @@
-# Managed by ansible (roles/power-meter-sml).
-#
-# Its own compose project -- see the role tasks for why it no longer shares a
-# file with the Z-Wave gateway.
-#
-# Outbound-only (serial in, MQTT out). Host networking sidesteps the docker
-# NAT66 gap: the broker LB is IPv6-first and bridge-network v6 SYNs leave
-# unmasqueraded and die. The host stack reaches it fine (open3e proves it
-# continuously).
-services:
-  sml2mqtt:
-    image: {{ edge_sml2mqtt_image }}
-    container_name: sml2mqtt
-    restart: unless-stopped
-    network_mode: host
-    # Serial exclusivity: this is the ONLY reader of the meter port --
-    # HA's edl21 integration stays disabled.
-    devices:
-      - "{{ edge_stromzaehler_device }}:/dev/stromzaehler"
-    volumes:
-      - ./config.yml:/sml2mqtt/config.yml:ro

ansible/roles/power-meter-sml/templates/sml2mqtt-config.yml.j2

@@ -1,32 +0,0 @@
-# Managed by ansible (roles/power-meter-sml). Ported 1:1 from the k8s ConfigMap
-# sml2mqtt-config; only host and password delivery differ (broker is now
-# reached via its LoadBalancer hostname, password rendered by ansible
-# instead of an init container).
-logging:
-  level: INFO
-  file: stdout        # 'stdout' -> docker logs (NOT '' — that opens the dir)
-
-mqtt:
-  connection:
-    identifier: sml2mqtt-meter
-    host: {{ edge_mqtt_host }}
-    port: {{ edge_mqtt_port }}
-    user: sml2mqtt
-    password: {{ edge_sml2mqtt_mqtt_password }}
-  topic prefix: sml2mqtt
-  defaults:
-    qos: 0
-    retain: false
-  last will:
-    topic: status
-
-general:
-  Wh in kWh: false      # keep raw Wh to match edl21 history — HA long-term
-                        # stats continue with zero unit discontinuity
-  republish after: 120  # re-emit unchanged values every 120 s
-
-inputs:
-  - type: serial
-    url: /dev/stromzaehler   # FTDI FT230X, mapped by docker compose
-    timeout: 3
-    # 9600 8N1 are sml2mqtt defaults for SML/EDL21 — no override needed.

ci/agents/pr-review/prompt.md

@@ -54,16 +54,35 @@ Look for, in priority order:
 
 Ground every finding in a specific location: `path:line` (or a hunk) from the
 diff or the checkout. **Do not invent** bugs, file paths, or behavior you have
-not confirmed by reading the code. The whole repo is on disk in your working
-directory, so verify: if a judgement depends on a caller, the rest of a
-function, or config elsewhere, open it. If after checking you still cannot
-confirm a suspicion, say so explicitly and give the one check that would settle
-it — do not state a hypothesis as fact. A concern you could have checked by
-reading the checkout but did not is a weakness in your review.
+not confirmed.
+
+**Verify every claim yourself before you write it down. Never hand the
+verification to the author.** "I could not find X", "X may not exist", "this is
+unverified" is not a finding — it is unfinished work. For each suspicion:
+
+1. Check the checkout: callers, the rest of the function, config elsewhere,
+   existing uses of the same construct, the repo's `CLAUDE.md`/`README`.
+   Shallow read-only clones of the other fleet repos that are publicly
+   readable (at least `homelab`) are under `./.pr-review/context/<name>/` —
+   look there when the change depends on how a sibling repo does something.
+   A repo missing there simply was not readable; do not treat that as a finding.
+2. If it depends on an external API, syntax, device behavior or product
+   version (a Home Assistant trigger/action, a Shelly generation, a Kubernetes
+   field, a library call), read the authoritative documentation or source with
+   WebFetch/WebSearch (official docs, the project's own repo or README). Your
+   training data is NOT evidence: this repo targets current releases that may
+   postdate it, and "I have not seen this syntax" says nothing about whether
+   it exists.
+3. Only after both: state what you found, with the source (`path:line` or URL).
+
+If after a real attempt you still cannot settle it, list it under
+"Unverified" with what you checked and why that was not enough. An unverified
+suspicion is never Blocking.
 
 Distinguish severity honestly. A blocking issue is a concrete defect — a bug
-that will misbehave, a security hole, or a breaking change — that you can point
-at. Style preferences and optional improvements are not blocking.
+that will misbehave, a security hole, or a breaking change — that you
+**verified** and can point at. Style preferences, optional improvements and
+anything unverified are not blocking.
 
 ## Output
 
@@ -84,6 +103,11 @@ Structure it as:
 why it is wrong. Omit this whole section if there are none — and say so in the
 Summary.>
 
+## ⚪ Unverified
+
+<Suspicions you could not settle after checking the checkout and the docs, each
+with what you checked. Omit if none.>
+
 ## 🟡 Suggestions
 
 <Non-blocking improvements worth considering, each anchored to a location.>
@@ -110,17 +134,21 @@ even if the PR added one; refer to it by location and flag it as blocking.
 
 ```json
 {
-  "event": "COMMENT | REQUEST_CHANGES",
+  "event": "APPROVE | COMMENT | REQUEST_CHANGES",
   "headline": "<short one-line summary of the outcome>"
 }
 ```
 
 - Use **`REQUEST_CHANGES`** only when your report lists at least one real
   **Blocking** issue.
-- Use **`COMMENT`** otherwise (including when you have only suggestions/nits, or
-  the PR looks good).
-- You cannot approve — there is no APPROVE option, by design. A clean PR gets a
-  `COMMENT` review saying so.
+- Use **`APPROVE`** when the report has no 🔴 Blocking, no 🟡 Suggestions and no
+  ⚪ Unverified section — i.e. you checked the change and found nothing to
+  raise. Nits (🟢) alone do not prevent it.
+- Use **`COMMENT`** otherwise.
+- The pipeline sets the final review event from the sections present in your
+  report, so keep the section headings exactly as above and omit a section
+  entirely when it is empty. Do not add a 🟡/🔴/⚪ heading unless you have a
+  finding under it.
 
 If `pr.json` or `diff.patch` is missing or empty, write a `report.md` stating
 you had no diff to review and a `verdict.json` with `event: "COMMENT"`, then

ci/agents/pr-review/run.sh

@@ -0,0 +1,191 @@
+#!/bin/sh
+# PR review bot — the ONE implementation, run by every reviewed repo's
+# .woodpecker/pr-review.yml stub (k.renner/homelab, shelly-manager,
+# authentik-samba-bridge, homeassistant). Edit it here only; the stubs hold no
+# logic. Design notes (event-driven trigger, dedup marker, tokens, model
+# selection, posture) are in the stub and in prompt.md.
+#
+# ---- Resolve the single triggering PR --------------------------------
+# Woodpecker hands us the repo (CI_REPO, canonical owner/repo) and the PR
+# number (CI_COMMIT_PULL_REQUEST, a pull_request-event built-in). Build
+# /tmp/pr-review/worklist.jsonl with 0 or 1 entries; an empty file makes
+# the next block a no-op (the agent never starts).
+set -eu
+API="https://gitea.renner.uno/api/v1"
+AUTH="Authorization: token $REVIEW_TOKEN"
+SLUG="$CI_REPO"
+NUM="${CI_COMMIT_PULL_REQUEST:-}"
+REVIEW_BOT_LOGIN="review-bot"
+mkdir -p /tmp/pr-review
+: > /tmp/pr-review/worklist.jsonl
+
+if [ -z "$NUM" ]; then
+  echo "No PR number in CI env (event=${CI_PIPELINE_EVENT:-?}) — nothing to review."
+  exit 0
+fi
+echo "Triggered for $SLUG#$NUM (event ${CI_PIPELINE_EVENT:-?})."
+
+if ! curl -sf -H "$AUTH" "$API/repos/$SLUG/pulls/$NUM" > /tmp/pr-review/pr.json; then
+  echo "Cannot fetch $SLUG#$NUM (review-bot not a collaborator / PR gone?) — skipping."
+  exit 0
+fi
+STATE=$(jq -r '.state'        /tmp/pr-review/pr.json)
+DRAFT=$(jq -r '.draft // false' /tmp/pr-review/pr.json)
+TITLE=$(jq -r '.title'        /tmp/pr-review/pr.json)
+HEAD=$(jq -r '.head.sha'      /tmp/pr-review/pr.json)
+SHORT=$(printf '%s' "$HEAD" | cut -c1-8)
+
+# Skip closed/merged, drafts, and WIP-titled PRs — not ready for review.
+case "$STATE" in open) ;; *) echo "#$NUM is $STATE — skip."; exit 0;; esac
+case "$DRAFT" in true) echo "#$NUM draft — skip."; exit 0;; esac
+case "$TITLE" in [Ww][Ii][Pp]:*|[Ww][Ii][Pp]\ *) echo "#$NUM WIP — skip."; exit 0;; esac
+
+# Dedup: already reviewed at THIS head sha? (guards re-runs / restarts)
+REVIEWED=$(curl -sf -H "$AUTH" "$API/repos/$SLUG/pulls/$NUM/reviews?limit=50" \
+  | jq -r --arg u "$REVIEW_BOT_LOGIN" --arg m "pr-review:sha=$HEAD" \
+      '[.[] | select(.user.login == $u) | select(.body | contains($m))] | length' \
+  || echo 0)
+if [ "${REVIEWED:-0}" -gt 0 ]; then
+  echo "#$NUM already reviewed at $SHORT — skip."
+  exit 0
+fi
+
+jq -c --arg slug "$SLUG" \
+  '{slug: $slug, number: .number, head: .head.sha, base: .base.sha,
+    title: .title, author: .user.login}' \
+  /tmp/pr-review/pr.json >> /tmp/pr-review/worklist.jsonl
+echo "#$NUM enqueued (head $SHORT)."
+# ---- Clone, pick model, review, post ---------------------------------
+set -eu
+[ -s /tmp/pr-review/worklist.jsonl ] || { echo "Nothing to review."; exit 0; }
+API="https://gitea.renner.uno/api/v1"
+AUTH="Authorization: token $REVIEW_TOKEN"
+WS="$PWD"                     # workspace = this repo, checked out at the PR head by Woodpecker
+MAX_DIFF_LINES=20000
+
+# This script, the prompts and scripts/ci/ all come from the homelab@master
+# clone the per-repo stub made (see .woodpecker/pr-review.yml) — never from the
+# PR checkout, so a PR cannot change the rubric or the helper scripts it is
+# reviewed with.
+PROMPTS="$(cd "$(dirname "$0")" && pwd)"
+HOMELAB="$(cd "$PROMPTS/../../.." && pwd)"   # repo root holding ci/ AND scripts/ci/
+echo "Using prompts from $PROMPTS"
+
+gitea_post() {                 # method url datafile ; echoes+checks HTTP
+  code=$(curl -s -o /tmp/pr-review/resp.json -w '%{http_code}' \
+    -X "$1" -H "$AUTH" -H "Content-Type: application/json" \
+    --data @"$3" "$2")
+  echo "$1 $2 -> HTTP $code"
+  if [ "$code" -lt 200 ] || [ "$code" -ge 300 ]; then
+    echo "Gitea API error body:"; cat /tmp/pr-review/resp.json; echo; return 1
+  fi
+}
+
+while IFS= read -r ITEM; do
+  SLUG=$(printf '%s' "$ITEM"  | jq -r '.slug')
+  NUM=$(printf '%s' "$ITEM"   | jq -r '.number')
+  HEAD=$(printf '%s' "$ITEM"  | jq -r '.head')
+  TITLE=$(printf '%s' "$ITEM" | jq -r '.title')
+  SHORT=$(printf '%s' "$HEAD" | cut -c1-8)
+  echo "=== Reviewing $SLUG#$NUM ($SHORT) ==="
+  D="/tmp/pr-review/$NUM"
+  rm -rf "$D"; mkdir -p "$D"
+
+  # PR metadata + unified diff (authenticated; private repos need it).
+  curl -sf -H "$AUTH" "$API/repos/$SLUG/pulls/$NUM" > "$D/pr.json"
+  curl -sf -H "$AUTH" "$API/repos/$SLUG/pulls/$NUM.diff" > "$D/diff.full.patch" \
+    || { echo "Could not fetch diff for $SLUG#$NUM — skipping."; continue; }
+  FILES=$(grep -c '^diff --git ' "$D/diff.full.patch" || true)
+  ADDED=$(grep -c '^+[^+]' "$D/diff.full.patch" || true)
+  DELETED=$(grep -c '^-[^-]' "$D/diff.full.patch" || true)
+  TOTAL=$(wc -l < "$D/diff.full.patch")
+  if [ "$TOTAL" -gt "$MAX_DIFF_LINES" ]; then
+    head -n "$MAX_DIFF_LINES" "$D/diff.full.patch" > "$D/diff.patch"
+    printf '\n... [diff truncated at %s of %s lines] ...\n' \
+      "$MAX_DIFF_LINES" "$TOTAL" >> "$D/diff.patch"
+  else
+    cp "$D/diff.full.patch" "$D/diff.patch"
+  fi
+  printf 'repo: %s\nPR: #%s\nfiles_changed: %s\nlines_added: %s\nlines_deleted: %s\ndiff_total_lines: %s\n' \
+    "$SLUG" "$NUM" "$FILES" "$ADDED" "$DELETED" "$TOTAL" > "$D/stats.txt"
+
+  # No manual clone of the target repo: this runs on a pull_request
+  # event, so Woodpecker's built-in clone already checked THIS repo out
+  # at the PR head in $WS — the agents (which cd into $WS) read it
+  # directly for context. The old cron model had to clone each target
+  # repo by hand (its workspace was homelab@master), and that clone
+  # embedded REVIEW_TOKEN in the URL, persisting a write-scoped PAT in
+  # work/target/.git/config — readable by the review agent whose report
+  # is posted publicly. Per-repo pull_request triggering makes the manual
+  # clone redundant AND keeps the token off disk (it now lives only in
+  # the ephemeral curl Authorization headers used for the API calls).
+
+  # Inputs the agents read live at ./.pr-review (symlink into $D).
+  rm -f "$WS/.pr-review"; ln -s "$D" "$WS/.pr-review"
+
+  # Cross-repo context for the review agent: shallow, UNAUTHENTICATED clones of
+  # the other fleet repos at ./.pr-review/context/<name> (a change here often
+  # depends on how a sibling repo does it). No credential is involved, so only
+  # publicly readable repos come through; a repo that needs auth fails fast
+  # (GIT_TERMINAL_PROMPT=0) and is skipped, never fatal.
+  CTX="$D/context"; mkdir -p "$CTX"
+  for REPO in k.renner/homelab k.renner/homeassistant konairius/shelly-manager k.renner/authentik-samba-bridge; do
+    [ "$REPO" = "$SLUG" ] && continue
+    GIT_TERMINAL_PROMPT=0 git clone --quiet --depth 1 "https://gitea.renner.uno/$REPO" "$CTX/${REPO#*/}" 2>/dev/null \
+      || echo "No public context clone of $REPO (skipped)."
+  done
+
+  # --- Model: always the most capable CURRENT one, from the live catalog. ---
+  # No model id, no family name and no complexity triage is baked in here: a
+  # triage that downgrades "trivial" PRs to a small model is exactly what made
+  # reviews shallow, and reviews are rare enough that the strongest model is the
+  # right default. pick-model.sh reads the live catalog (Anthropic /v1/models via
+  # CLAUDE_CODE_OAUTH_TOKEN), prefers the newest of comparable models, validates
+  # its pick against that catalog and echoes nothing on any failure — then the
+  # review runs on the CLI's own default model. A model released tomorrow is
+  # eligible the day the API lists it. REVIEW_TOKEN is stripped: the picker never
+  # needs the write-scoped PAT.
+  MODEL=$(env -u REVIEW_TOKEN sh "$HOMELAB/scripts/ci/pick-model.sh" \
+    "careful, high-stakes code review of a pull request: verify claims against the code and external documentation, find real defects, avoid false positives; always pick the most capable and newest model available, regardless of PR size" || true)
+  if [ -n "$MODEL" ]; then echo "Review model: $MODEL"; else echo "Review model: CLI default (catalog/picker unavailable)"; fi
+
+  # --- Review with the chosen model ---
+  ( cd "$WS" && cat "$PROMPTS/prompt.md" | env -u REVIEW_TOKEN claude ${MODEL:+--model $MODEL} \
+      --permission-mode acceptEdits \
+      --allowedTools "Read,Glob,Grep,Write,WebFetch,WebSearch" \
+      --settings "$PROMPTS/settings.json" \
+      -p ) || echo "(review agent exited non-zero)"
+
+  if [ ! -s "$D/report.md" ]; then
+    echo "Agent wrote no report for $SLUG#$NUM — skipping post."
+    continue
+  fi
+  # Review event, derived from the report's own severity sections (not trusted
+  # from verdict.json): any red (Blocking) -> REQUEST_CHANGES; no red, yellow
+  # (Suggestions) or Unverified section on a non-empty diff -> APPROVE; else
+  # COMMENT. An empty diff or a report that names no section never approves.
+  if grep -q '^## 🔴' "$D/report.md"; then
+    EVENT=REQUEST_CHANGES
+  elif [ "$TOTAL" -gt 0 ] && ! grep -q -e '^## 🟡' -e '^## ⚪' "$D/report.md" \
+       && grep -q '^## Recommendation' "$D/report.md"; then
+    EVENT=APPROVE
+  else
+    EVENT=COMMENT
+  fi
+
+  # Assemble the review body: header + report + marker footer.
+  {
+    printf '🤖 **Automated review** — model `%s`, commit `%s`.\n\n' \
+      "${MODEL:-CLI default}" "${HEAD}"
+    printf '> Automated review by the `review-bot` pipeline: it approves only when it found nothing red or yellow, and a human still merges. Push new commits to get a fresh review.\n\n---\n\n'
+    cat "$D/report.md"
+    printf '\n\n<!-- pr-review:sha=%s -->\n' "$HEAD"
+  } > "$D/body.md"
+  jq -n --rawfile b "$D/body.md" --arg e "$EVENT" --arg c "$HEAD" \
+    '{body: $b, event: $e, commit_id: $c}' > "$D/review.json"
+  gitea_post POST "$API/repos/$SLUG/pulls/$NUM/reviews" "$D/review.json" \
+    && echo "Posted $EVENT review on $SLUG#$NUM." \
+    || echo "FAILED to post review on $SLUG#$NUM (continuing)."
+  rm -f "$WS/.pr-review"
+done < /tmp/pr-review/worklist.jsonl
+echo "PR review run complete."

ci/images/agent-runtime-go/Containerfile

@@ -30,6 +30,15 @@ RUN ln -s /usr/local/go/bin/go /usr/local/bin/go \
     && ln -s /usr/local/go/bin/gofmt /usr/local/bin/gofmt
 USER 1000:1000
 
+# Time zones (REN-1196): the base has no /usr/share/zoneinfo, so
+# TZ=Europe/Berlin silently prints UTC and Python ZoneInfo() raises. The
+# default zone stays UTC; agents set TZ where they need local time.
+USER root
+RUN apt-get update \
+    && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends tzdata \
+    && rm -rf /var/lib/apt/lists/*
+USER 1000:1000
+
 # ACP server the Paperclip ACP engine starts in the pod (REN-302). Version and
 # patch match what Paperclip ships: packages/adapters/claude-local/package.json
 # pins 0.73.0 and applies patches/@agentclientprotocol__claude-agent-acp@0.73.0.patch
@@ -63,6 +72,8 @@ ENV PATH=/usr/local/go/bin:$PATH \
 
 # Base user (1000:1000), entrypoint (tini) and cmd (agent shim) are inherited.
 # The PATH check uses the base image's default PATH, not the ENV above.
-RUN go version && golangci-lint version \
+RUN TZ=Europe/Berlin date +%Z | grep -Eq '^CES?T$' \
+    && python3 -c "from zoneinfo import ZoneInfo; ZoneInfo('Europe/Berlin')" \
+    && go version && golangci-lint version \
     && env -i PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin \
        sh -ec 'for t in go gofmt golangci-lint govulncheck claude-agent-acp; do command -v "$t"; done'

ci/images/agent-runtime-ops/Containerfile

@@ -21,6 +21,16 @@ COPY --from=flux /usr/local/bin/flux /usr/local/bin/flux
 COPY --from=kustomize /app/kustomize /usr/local/bin/kustomize
 COPY --from=helm /usr/bin/helm /usr/local/bin/helm
 
+# Time zones (REN-1196): the base has no /usr/share/zoneinfo, so
+# TZ=Europe/Berlin silently prints UTC and Python ZoneInfo() raises. The
+# default zone stays UTC; agents set TZ where they need local time.
+# jq (REN-1345): the agents' duty lists and the Paperclip skill use it.
+USER root
+RUN apt-get update \
+    && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends tzdata jq \
+    && rm -rf /var/lib/apt/lists/*
+USER 1000:1000
+
 # ACP server the Paperclip ACP engine starts in the pod (REN-302). Version and
 # patch match what Paperclip ships: packages/adapters/claude-local/package.json
 # pins 0.73.0 and applies patches/@agentclientprotocol__claude-agent-acp@0.73.0.patch
@@ -46,6 +56,8 @@ USER 1000:1000
 # write only under $HOME, which the sandbox pod mounts writable. No ENV needed.
 
 # Base user (1000:1000), entrypoint (tini) and cmd (agent shim) are inherited.
-RUN kubectl version --client && flux version --client && kustomize version && helm version \
+RUN TZ=Europe/Berlin date +%Z | grep -Eq '^CES?T$' \
+    && python3 -c "from zoneinfo import ZoneInfo; ZoneInfo('Europe/Berlin')" \
+    && kubectl version --client && flux version --client && kustomize version && helm version && jq --version \
     && env -i PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin \
-       sh -ec 'for t in kubectl flux kustomize helm claude-agent-acp; do command -v "$t"; done'
+       sh -ec 'for t in kubectl flux kustomize helm jq claude-agent-acp; do command -v "$t"; done'

ci/images/backup-verify/Containerfile

@@ -0,0 +1,19 @@
+FROM hetznercloud/cli:v1.69.0@sha256:febb8898949b31a2249384aa9728f2254dfb752ff2f69be709178c4a3285b05f AS hcloud
+
+FROM alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
+
+RUN apk add --no-cache \
+      bash \
+      ca-certificates \
+      curl \
+      jq \
+      kubectl \
+      openssh-client \
+      openssh-keygen \
+      tar
+
+COPY --from=hcloud /ko-app/hcloud /usr/local/bin/hcloud
+
+RUN adduser -D -u 65532 -h /work verify
+
+RUN hcloud version && kubectl version --client && jq --version && ssh -V && ssh-keygen -t ed25519 -N '' -q -f /tmp/k && rm -f /tmp/k /tmp/k.pub

ci/images/netbird-service-sync/controller.py

@@ -1,7 +1,10 @@
 #!/usr/bin/env python3
 """netbird-service-sync: reconcile NetBird reverse-proxy services from Ingresses.
 
-Source of truth: every Ingress carrying the public label (dns.renner.uno/public).
+Source of truth: every Ingress carrying one of the public labels.
+dns.renner.uno/public also takes the host out of the LAN DNS (external-dns-unifi
+skips it); netbird.renner.uno/public publishes on the proxy only and leaves the
+LAN record in place.
 For each host on such an Ingress the NetBird management gets one reverse-proxy
 service in TLS-passthrough mode on :443, targeting Traefik's ClusterIP through a
 subnet resource that covers the cluster's service CIDR. SNI and Host reach
@@ -42,7 +45,7 @@ NETWORK_NAME = os.environ.get("NETWORK_NAME", "k8s public ingress")
 ROUTER_GROUP = os.environ.get("ROUTER_GROUP_NAME", "k8s-ingress-router")
 SOURCE_GROUP = os.environ.get("SOURCE_GROUP_NAME", "All")
 TRAEFIK_NS, TRAEFIK_SVC = os.environ.get("TRAEFIK_SERVICE", "ingress/traefik").split("/", 1)
-PUBLIC_LABEL = os.environ.get("PUBLIC_LABEL", "dns.renner.uno/public")
+PUBLIC_LABELS = os.environ.get("PUBLIC_LABELS", "dns.renner.uno/public,netbird.renner.uno/public").split(",")
 LISTEN_PORT = int(os.environ.get("LISTEN_PORT", "443"))
 INTERVAL = int(os.environ.get("INTERVAL_SECONDS", "60"))
 HTTP_TIMEOUT = 20
@@ -86,10 +89,12 @@ def k8s(path):
 
 
 def desired_hosts():
-    sel = urllib.parse.quote(f"{PUBLIC_LABEL}=true")
-    ingresses = k8s(f"/apis/networking.k8s.io/v1/ingresses?labelSelector={sel}")
+    items = []
+    for label in PUBLIC_LABELS:
+        sel = urllib.parse.quote(f"{label}=true")
+        items += k8s(f"/apis/networking.k8s.io/v1/ingresses?labelSelector={sel}").get("items", [])
     hosts = {}
-    for ing in ingresses.get("items", []):
+    for ing in items:
         ref = f'{ing["metadata"]["namespace"]}/{ing["metadata"]["name"]}'
         for rule in ing.get("spec", {}).get("rules", []):
             host = rule.get("host")

ci/images/paperclip/README.md

@@ -52,6 +52,14 @@ Job (and, on destroy, the pod) reads 404, polling for up to 20 s, below the
 server's 30 s plugin RPC timeout. If that check times out or fails, the hook
 returns no receipt, as before. No upstream PR yet.
 
+Agents in k8s pods cannot read their own secrets (REN-1345): the sandbox
+callback bridge answers `403 Route not allowed` for `/api/agents/me/secrets`,
+although upstream's own Paperclip skill documents those routes for runs.
+`ren-1345-bridge-agent-secrets.patch` adds the five `/api/agents/me` secret
+routes (list, read one value, list/create/withdraw proposals) to the bridge
+allowlist. The server still resolves the agent from the run JWT and checks
+the binding; company-wide secret routes stay denied. No upstream PR yet.
+
 ## Files
 
 - `upstream.env` — pinned commit and the version string stamped into the

ci/images/paperclip/ren-1345-bridge-agent-secrets.patch

@@ -0,0 +1,48 @@
+diff --git a/packages/adapter-utils/src/sandbox-callback-bridge.test.ts b/packages/adapter-utils/src/sandbox-callback-bridge.test.ts
+index 4419bee..d57de8d 100644
+--- a/packages/adapter-utils/src/sandbox-callback-bridge.test.ts
++++ b/packages/adapter-utils/src/sandbox-callback-bridge.test.ts
+@@ -1452,6 +1452,11 @@ describe("sandbox callback bridge", () => {
+       { method: "POST", path: "/api/routines/r-1/triggers" },
+       { method: "PATCH", path: "/api/routine-triggers/t-1" },
+       { method: "DELETE", path: "/api/routine-triggers/t-1" },
++      { method: "GET", path: "/api/agents/me/secrets" },
++      { method: "POST", path: "/api/agents/me/secrets/github_token/value" },
++      { method: "GET", path: "/api/agents/me/secret-proposals" },
++      { method: "POST", path: "/api/agents/me/secret-proposals" },
++      { method: "DELETE", path: "/api/agents/me/secret-proposals/prop-1" },
+     ];
+     for (const request of allowed) {
+       expect(authorizeSandboxCallbackBridgeRequestWithRoutes(request)).toBeNull();
+@@ -1491,6 +1496,11 @@ describe("sandbox callback bridge", () => {
+       { method: "POST", path: "/api/companies/co-1/logo" },
+       { method: "GET", path: "/api/companies/co-1/secrets" },
+       { method: "PATCH", path: "/api/secrets/secret-1" },
++      { method: "GET", path: "/api/agents/agent-1/secrets" },
++      { method: "POST", path: "/api/agents/me/secrets/a/b/value" },
++      { method: "GET", path: "/api/agents/me/secrets/github_token/value" },
++      { method: "GET", path: "/api/companies/co-1/secret-proposals" },
++      { method: "POST", path: "/api/companies/co-1/secret-proposals/prop-1/approve" },
+     ];
+     for (const request of denied) {
+       expect(authorizeSandboxCallbackBridgeRequestWithRoutes(request)).toBe(
+diff --git a/packages/adapter-utils/src/sandbox-callback-bridge.ts b/packages/adapter-utils/src/sandbox-callback-bridge.ts
+index 40776a3..e825197 100644
+--- a/packages/adapter-utils/src/sandbox-callback-bridge.ts
++++ b/packages/adapter-utils/src/sandbox-callback-bridge.ts
+@@ -133,6 +133,15 @@ export const DEFAULT_SANDBOX_CALLBACK_BRIDGE_ROUTE_ALLOWLIST: readonly SandboxCa
+   { method: "POST", path: /^\/api\/agents\/[^/]+\/skills\/sync$/ },
+   { method: "PATCH", path: /^\/api\/agents\/[^/]+\/instructions-path$/ },
+ 
++  // Run-scoped secrets of the calling agent (`/agents/me` only). The server
++  // resolves the agent from the run JWT and checks bindings; values are
++  // registered for run-log redaction. Company-wide secret routes stay denied.
++  { method: "GET", path: /^\/api\/agents\/me\/secrets$/ },
++  { method: "POST", path: /^\/api\/agents\/me\/secrets\/[^/]+\/value$/ },
++  { method: "GET", path: /^\/api\/agents\/me\/secret-proposals$/ },
++  { method: "POST", path: /^\/api\/agents\/me\/secret-proposals$/ },
++  { method: "DELETE", path: /^\/api\/agents\/me\/secret-proposals\/[^/]+$/ },
++
+   // Read-only schema discovery for validated control-plane requests.
+   { method: "GET", path: /^\/api\/openapi\.json$/ },
+ 

docs/superpowers/plans/2026-10-11-gitea-mcp.md

@@ -0,0 +1,443 @@
+# Gitea MCP Server Implementation Plan
+
+> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
+
+**Goal:** Deploy the official Gitea MCP server in-cluster at `https://gitea-mcp.renner.uno/mcp`, published on the NetBird proxy, authenticating every request with the caller's own Gitea PAT and rejecting tokenless requests.
+
+**Architecture:** One stateless Deployment in a new `gitea-mcp` namespace, Flux-managed through its own Kustomization. Traefik Ingress with the proxy-only public label; netbird-service-sync publishes it. gitea-mcp runs in `-oauth` mode purely to get the 401-on-missing-token gate; it talks to Gitea via the in-cluster Service.
+
+**Tech Stack:** Kubernetes manifests, Flux (Kustomization, image automation), Cilium CiliumNetworkPolicy, Traefik Ingress, cert-manager.
+
+**Spec:** `docs/superpowers/specs/2026-10-11-gitea-mcp-design.md`
+
+## Global Constraints
+
+- Image `docker.gitea.com/gitea-mcp-server`, initial tag `1.8.1`, ImagePolicy semver `>=1.8.1`, marker `# {"$imagepolicy": "flux-system:gitea-mcp"}`.
+- Args exactly: `-t http -p 8080 -oauth -oauth-public-url https://gitea-mcp.renner.uno -H http://gitea.gitea.svc.cluster.local:3000`. No `-T`/`GITEA_ACCESS_TOKEN`, no `-d`.
+- Host `gitea-mcp.renner.uno`; Ingress label `netbird.renner.uno/public: "true"` (not `dns.renner.uno/public`); cert issuer `letsencrypt-cluster`; TLS secret `gitea-mcp-tls`.
+- Pod label `app.kubernetes.io/name: gitea-mcp`; namespace `gitea-mcp`; Service `gitea-mcp:8080`.
+- No `world` egress from `gitea-mcp`.
+- Manifest comments: one terse factual line at most; rationale goes in commit/PR text.
+- Commits as claude-bot: `git -c user.name='Claude Bot' -c user.email='claude-bot@renner.uno' commit …`; each git command its own Bash call.
+
+## Review Focus
+
+1. Tokenless `POST /mcp` from the internet → must be 401, never anonymous Gitea data (Task 4 step 4).
+2. Request with an invalid/revoked PAT → 401 `invalid_token` (Task 4 step 5).
+3. Kubelet probes with `Host: <podIP>` → `/healthz` must stay 200 despite the oauth Host check (Task 3 readiness, Task 4 step 2).
+4. LAN client resolving `gitea-mcp.renner.uno` → must reach Traefik VIP directly, not the proxy (Task 4 step 3).
+5. Gitea refusing gitea-mcp's connection (missing CNP half) → MCP calls fail; authenticated `list_my_repos` must succeed (Task 4 step 6).
+
+---
+
+### Task 1: Namespace and network policies
+
+**Files:**
+- Modify: `kubernetes/infrastructure/namespaces/namespaces.yaml` (append after the `gitea` Namespace)
+- Create: `kubernetes/infrastructure/network-policies/gitea-mcp-ns.yaml`
+- Modify: `kubernetes/infrastructure/network-policies/kustomization.yaml` (add entry after `gitea-ns.yaml`)
+- Modify: `kubernetes/apps/gitea/networkpolicy.yaml` (append CNP)
+
+**Interfaces:**
+- Produces: namespace `gitea-mcp`; ingress to pods labelled `app.kubernetes.io/name: gitea-mcp` on 8080 from Traefik; egress from `gitea-mcp` to `gitea` pod :3000; Gitea-side ingress allowance from namespace `gitea-mcp` on :3000.
+
+- [ ] **Step 1: Add the Namespace** — insert after the `name: gitea` Namespace document in `namespaces.yaml`:
+
+```yaml
+---
+# Gitea MCP server. Declared here so it exists before infrastructure-crds applies its CNPs.
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: gitea-mcp
+```
+
+- [ ] **Step 2: Create `gitea-mcp-ns.yaml`**
+
+```yaml
+---
+# Baseline policy for the `gitea-mcp` namespace.
+apiVersion: cilium.io/v2
+kind: CiliumNetworkPolicy
+metadata:
+  name: default-deny
+  namespace: gitea-mcp
+spec:
+  endpointSelector: {}
+  ingress:
+    - fromEndpoints:
+        - matchLabels:
+            "k8s:io.kubernetes.pod.namespace": gitea-mcp
+    - fromEndpoints:
+        - matchLabels:
+            "k8s:io.kubernetes.pod.namespace": monitoring
+    - fromEntities:
+        - host
+        - remote-node
+    - fromEndpoints:
+        - matchExpressions:
+            - key: io.kubernetes.pod.namespace
+              operator: Exists
+      icmps:
+        - fields:
+            - { type: 0,   family: IPv4 }
+            - { type: 3,   family: IPv4 }
+            - { type: 8,   family: IPv4 }
+            - { type: 11,  family: IPv4 }
+            - { type: 12,  family: IPv4 }
+            - { type: 1,   family: IPv6 }
+            - { type: 2,   family: IPv6 }
+            - { type: 3,   family: IPv6 }
+            - { type: 4,   family: IPv6 }
+            - { type: 128, family: IPv6 }
+            - { type: 129, family: IPv6 }
+            - { type: 133, family: IPv6 }
+            - { type: 134, family: IPv6 }
+            - { type: 135, family: IPv6 }
+            - { type: 136, family: IPv6 }
+            - { type: 143, family: IPv6 }
+  egress:
+    - toEndpoints:
+        - matchLabels:
+            "k8s:io.kubernetes.pod.namespace": gitea-mcp
+    - toEndpoints:
+        - matchLabels:
+            "k8s:io.kubernetes.pod.namespace": kube-system
+            k8s-app: kube-dns
+      toPorts:
+        - ports:
+            - port: "53"
+              protocol: UDP
+            - port: "53"
+              protocol: TCP
+    - toEndpoints:
+        - matchLabels:
+            "k8s:io.kubernetes.pod.namespace": gitea
+            app.kubernetes.io/name: gitea
+      toPorts:
+        - ports:
+            - port: "3000"
+              protocol: TCP
+---
+apiVersion: cilium.io/v2
+kind: CiliumNetworkPolicy
+metadata:
+  name: gitea-mcp-allow-traefik
+  namespace: gitea-mcp
+spec:
+  endpointSelector:
+    matchLabels:
+      app.kubernetes.io/name: gitea-mcp
+  ingress:
+    - fromEndpoints:
+        - matchLabels:
+            "k8s:io.kubernetes.pod.namespace": ingress
+            app.kubernetes.io/name: traefik
+      toPorts:
+        - ports:
+            - port: "8080"
+              protocol: TCP
+```
+
+- [ ] **Step 3: Register it** — in `network-policies/kustomization.yaml` add `  - gitea-mcp-ns.yaml` directly after `  - gitea-ns.yaml`.
+
+- [ ] **Step 4: Gitea-side allowance** — append to `kubernetes/apps/gitea/networkpolicy.yaml`:
+
+```yaml
+---
+# gitea-mcp reaches the in-cluster Service; egress half is in network-policies/gitea-mcp-ns.yaml.
+apiVersion: cilium.io/v2
+kind: CiliumNetworkPolicy
+metadata:
+  name: gitea-allow-gitea-mcp
+  namespace: gitea
+spec:
+  endpointSelector:
+    matchLabels:
+      app.kubernetes.io/name: gitea
+  ingress:
+    - fromEndpoints:
+        - matchLabels:
+            "k8s:io.kubernetes.pod.namespace": gitea-mcp
+            app.kubernetes.io/name: gitea-mcp
+      toPorts:
+        - ports:
+            - port: "3000"
+              protocol: TCP
+```
+
+- [ ] **Step 5: Validate builds**
+
+Run each separately:
+`kubectl kustomize kubernetes/infrastructure/namespaces` → output contains `name: gitea-mcp`
+`kubectl kustomize kubernetes/infrastructure/network-policies` → output contains `gitea-mcp-allow-traefik`
+`kubectl kustomize kubernetes/apps/gitea` → output contains `gitea-allow-gitea-mcp`
+
+- [ ] **Step 6: Server-side dry-run of the Gitea-side CNP** (namespace already exists):
+`kubectl apply --dry-run=server -f kubernetes/apps/gitea/networkpolicy.yaml`
+Expected: every CNP `configured (server dry run)` or `unchanged`, `gitea-allow-gitea-mcp created (server dry run)`.
+
+- [ ] **Step 7: Commit**
+
+`git add kubernetes/infrastructure/namespaces/namespaces.yaml kubernetes/infrastructure/network-policies/gitea-mcp-ns.yaml kubernetes/infrastructure/network-policies/kustomization.yaml kubernetes/apps/gitea/networkpolicy.yaml`
+`git -c user.name='Claude Bot' -c user.email='claude-bot@renner.uno' commit -m "feat(gitea-mcp): namespace and network policies" -m "Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>"`
+
+### Task 2: Image automation
+
+**Files:**
+- Create: `kubernetes/infrastructure/image-automation/gitea-mcp.yaml`
+- Modify: `kubernetes/infrastructure/image-automation/kustomization.yaml` (insert `  - gitea-mcp.yaml` alphabetically after `  - gatus.yaml`)
+
+**Interfaces:**
+- Produces: ImagePolicy `flux-system:gitea-mcp`, referenced by the marker in Task 3.
+
+- [ ] **Step 1: Create `gitea-mcp.yaml`**
+
+```yaml
+apiVersion: image.toolkit.fluxcd.io/v1
+kind: ImageRepository
+metadata:
+  name: gitea-mcp
+  namespace: flux-system
+spec:
+  image: docker.gitea.com/gitea-mcp-server
+  interval: 1h
+---
+apiVersion: image.toolkit.fluxcd.io/v1
+kind: ImagePolicy
+metadata:
+  name: gitea-mcp
+  namespace: flux-system
+spec:
+  imageRepositoryRef:
+    name: gitea-mcp
+  policy:
+    semver:
+      range: ">=1.8.1"
+```
+
+- [ ] **Step 2: Register it** in `image-automation/kustomization.yaml` after `  - gatus.yaml`.
+
+- [ ] **Step 3: Validate**
+`kubectl kustomize kubernetes/infrastructure/image-automation` → contains `docker.gitea.com/gitea-mcp-server`
+`kubectl apply --dry-run=server -f kubernetes/infrastructure/image-automation/gitea-mcp.yaml` → both objects `created (server dry run)`.
+
+- [ ] **Step 4: Commit**
+
+`git add kubernetes/infrastructure/image-automation/gitea-mcp.yaml kubernetes/infrastructure/image-automation/kustomization.yaml`
+`git -c user.name='Claude Bot' -c user.email='claude-bot@renner.uno' commit -m "feat(gitea-mcp): track docker.gitea.com/gitea-mcp-server via image automation" -m "Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>"`
+
+### Task 3: App manifests and Flux Kustomization
+
+**Files:**
+- Create: `kubernetes/apps/gitea-mcp/deployment.yaml`, `service.yaml`, `ingress.yaml`, `kustomization.yaml`
+- Create: `kubernetes/clusters/homelab/gitea-mcp.yaml`
+
+**Interfaces:**
+- Consumes: namespace + CNPs (Task 1), ImagePolicy `flux-system:gitea-mcp` (Task 2).
+- Produces: `https://gitea-mcp.renner.uno/mcp` and `/healthz`.
+
+- [ ] **Step 1: `deployment.yaml`**
+
+```yaml
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: gitea-mcp
+  namespace: gitea-mcp
+  labels:
+    app.kubernetes.io/name: gitea-mcp
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: gitea-mcp
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: gitea-mcp
+    spec:
+      securityContext:
+        runAsNonRoot: true
+        runAsUser: 65532
+        runAsGroup: 65532
+        seccompProfile:
+          type: RuntimeDefault
+      containers:
+        - name: gitea-mcp
+          image: docker.gitea.com/gitea-mcp-server:1.8.1 # {"$imagepolicy": "flux-system:gitea-mcp"}
+          args:
+            - -t
+            - http
+            - -p
+            - "8080"
+            # Only for the 401 on tokenless requests; clients send their own Gitea PAT.
+            - -oauth
+            - -oauth-public-url
+            - https://gitea-mcp.renner.uno
+            - -H
+            - http://gitea.gitea.svc.cluster.local:3000
+          securityContext:
+            allowPrivilegeEscalation: false
+            readOnlyRootFilesystem: true
+            capabilities:
+              drop:
+                - ALL
+          ports:
+            - containerPort: 8080
+              name: http
+          volumeMounts:
+            - name: tmp
+              mountPath: /tmp
+          livenessProbe:
+            httpGet:
+              path: /healthz
+              port: http
+            initialDelaySeconds: 5
+            periodSeconds: 30
+          readinessProbe:
+            httpGet:
+              path: /healthz
+              port: http
+            initialDelaySeconds: 2
+            periodSeconds: 10
+          resources:
+            requests:
+              cpu: 10m
+              memory: 32Mi
+            limits:
+              memory: 128Mi
+      volumes:
+        - name: tmp
+          emptyDir:
+            medium: Memory
+            sizeLimit: 16Mi
+```
+
+- [ ] **Step 2: `service.yaml`**
+
+```yaml
+apiVersion: v1
+kind: Service
+metadata:
+  name: gitea-mcp
+  namespace: gitea-mcp
+  labels:
+    app.kubernetes.io/name: gitea-mcp
+spec:
+  type: ClusterIP
+  selector:
+    app.kubernetes.io/name: gitea-mcp
+  ports:
+    - name: http
+      port: 8080
+      targetPort: http
+```
+
+- [ ] **Step 3: `ingress.yaml`**
+
+```yaml
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: gitea-mcp
+  namespace: gitea-mcp
+  labels:
+    app.kubernetes.io/name: gitea-mcp
+    # Published on the NetBird proxy; LAN DNS stays on the Traefik VIP.
+    netbird.renner.uno/public: "true"
+  annotations:
+    cert-manager.io/cluster-issuer: letsencrypt-cluster
+spec:
+  ingressClassName: traefik
+  rules:
+    - host: gitea-mcp.renner.uno
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: gitea-mcp
+                port:
+                  number: 8080
+  tls:
+    - secretName: gitea-mcp-tls
+      hosts:
+        - gitea-mcp.renner.uno
+```
+
+- [ ] **Step 4: `kustomization.yaml`**
+
+```yaml
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - deployment.yaml
+  - service.yaml
+  - ingress.yaml
+```
+
+- [ ] **Step 5: `kubernetes/clusters/homelab/gitea-mcp.yaml`**
+
+```yaml
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: gitea-mcp
+  namespace: flux-system
+spec:
+  interval: 10m
+  retryInterval: 2m
+  timeout: 5m
+  sourceRef:
+    kind: GitRepository
+    name: flux-system
+  path: ./kubernetes/apps/gitea-mcp
+  prune: true
+  wait: true
+  dependsOn:
+    - name: infrastructure
+    - name: infrastructure-crds
+```
+
+- [ ] **Step 6: Validate**
+`kubectl kustomize kubernetes/apps/gitea-mcp` → renders Deployment, Service, Ingress, all in namespace `gitea-mcp`.
+`kubectl apply --dry-run=server -f kubernetes/clusters/homelab/gitea-mcp.yaml` → `created (server dry run)`.
+Confirm `kubernetes/clusters/homelab/` is picked up without a listing file: `ls kubernetes/clusters/homelab/flux-system` and read its `kustomization.yaml`; if it lists files explicitly, add `gitea-mcp.yaml` where `gitea.yaml` is listed.
+
+- [ ] **Step 7: Commit**
+
+`git add kubernetes/apps/gitea-mcp kubernetes/clusters/homelab/gitea-mcp.yaml`
+`git -c user.name='Claude Bot' -c user.email='claude-bot@renner.uno' commit -m "feat(gitea-mcp): deploy the Gitea MCP server at gitea-mcp.renner.uno" -m "Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>"`
+
+### Task 4: PR, rollout and live verification
+
+- [ ] **Step 1: Push and open the PR**
+
+`git -c credential.helper='store --file=/home/krenner/.config/claude-bot/creds' push -u origin feat/gitea-mcp`
+`tea pr create --login claude-bot --repo k.renner/homelab --base master --head feat/gitea-mcp --title "feat(gitea-mcp): in-cluster Gitea MCP server on the NetBird proxy" --description "<summary of spec + verification plan; ends with 🤖 Generated with [Claude Code](https://claude.com/claude-code)>"`
+Wait for `ci-manifests-test` green (`woodpecker` CLI). Owner merges; never self-merge.
+
+- [ ] **Step 2: After merge — rollout**
+`flux get kustomization gitea-mcp` → Ready True. `kubectl -n gitea-mcp get pods` → 1/1 Running, 0 restarts.
+`curl -sS -o /dev/stdout -w "\nHTTP %{http_code}\n" https://gitea-mcp.renner.uno/healthz` → `ok`, HTTP 200.
+
+- [ ] **Step 3: DNS paths**
+`getent ahosts gitea-mcp.renner.uno` from the LAN → Traefik VIP (fd99::86 / 10.2.99.86).
+Public answer: query Cloudflare's authoritative NS directly (UDM intercepts `@1.1.1.1`) → NetBird proxy address. NetBird management lists a reverse-proxy service for `gitea-mcp.renner.uno` (netbird-service-sync logs via `logcli`).
+
+- [ ] **Step 4: Tokenless request is rejected**
+
+```
+curl -sS -i https://gitea-mcp.renner.uno/mcp -H 'Content-Type: application/json' -H 'Accept: application/json, text/event-stream' --data '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"curl","version":"0"}}}'
+```
+Expected: `HTTP/2 401` with `WWW-Authenticate: Bearer resource_metadata=…`.
+
+- [ ] **Step 5: Invalid token is rejected** — same request plus `-H 'Authorization: Bearer invalid'` → 401 with `error="invalid_token"`.
+
+- [ ] **Step 6: Authenticated calls work** — same `initialize` request with `--oauth2-bearer "$(cat /home/krenner/.config/claude-bot/gitea-token)"` → 200 with `serverInfo`. Then `tools/call` `{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"list_my_repos","arguments":{}}}` with the same token → non-empty repo list; `list_my_repos` resolves the caller from the token, so a result proves the PAT was used. If the server demands `Mcp-Protocol-Version`/`Mcp-Method` headers, take the required values from the error and resend.
+
+- [ ] **Step 7: Image policy** — `flux get image policy gitea-mcp` → latest image `docker.gitea.com/gitea-mcp-server:1.8.1` or newer.
+
+- [ ] **Step 8: Wiki** — route through `wiki-ingest` → `wiki-distill`: netbird-service-sync label mechanism (`dns.renner.uno/public` vs `netbird.renner.uno/public`), and gitea-mcp deployment facts (oauth-mode-as-auth-gate, PAT passthrough, `/healthz` outside the Host check).

docs/superpowers/specs/2026-10-10-backup-verify-cloud-vm-design.md

@@ -0,0 +1,180 @@
+# Backup verification on an ephemeral Hetzner Cloud VM — design
+
+Date: 2026-10-10
+Status: draft, awaiting review
+
+## Goal
+
+Replace the monthly Velero `restore-test` with a check that proves every PVC
+backup is readable and complete, **without writing restored data to the
+homelab Ceph OSDs**. The work runs on a throwaway Hetzner Cloud VM next to the
+backup bucket; the cluster only orchestrates.
+
+Full disaster-recovery rehearsals (Velero restores of manifests into a fresh
+cluster) are a later, separate project. This spec only covers data
+verifiability.
+
+## Why
+
+- `restore-test` restores every schedule into the production Ceph pools. On
+  2026-10-01 the immich restore took the fullest OSD from 74% to 95% and Ceph
+  went `OSD_FULL` (REN-451). The test is a large share of the OSD write budget.
+- Its file-count parity compares the restored PVC against the *live* volume.
+  That needs a source-side snapshot probe per StorageClass (it broke for
+  `ceph-filesystem-bulk`, see PR #1224) and volatile-path exclusions.
+- The restore only covers `persistentvolumeclaims`/`persistentvolumes`, so a
+  data-level check loses no coverage that the current test has.
+
+## Decisions
+
+| Topic | Decision |
+|---|---|
+| What is verified | Data only (option A): `kopia snapshot verify --verify-files-percent=100` on the latest Kopia snapshot of every DataUpload of the latest `Completed` backup per schedule, plus a size check against Velero's own `DataUpload.status.progress.totalBytes`. No restore, no Kubernetes on the VM. |
+| Where it runs | Ephemeral Hetzner Cloud VM in `fsn1` (same location as bucket `renner-uno-k8s-velero`). Bucket traffic stays inside Hetzner's eu-central zone. |
+| Orchestrator | In-cluster CronJob `backup-verify` (namespace `velero`), monthly `0 8 1 * *` UTC. It reads Kubernetes, drives the VM via the Hetzner API and SSH, and writes nothing but logs. |
+| Alerting | Exit 1 on any `FAIL` → existing `KubeJobFailed`. Results in the Job log (Loki). |
+| Coverage | All DataUploads, including CNPG volumes (read-only, no cost). Schedules discovered by label `app.kubernetes.io/part-of=homelab-backup`. |
+| SSH source restriction | None. Key-only auth with a per-run key, pinned host key, password auth off, VM lives ~1 h. |
+| Kopia version | CLI pinned to **0.16.0**, the version Velero 1.18.2 vendors (`project-velero/kopia` fork of 0.16.0). sha256 pinned per arch. |
+
+## Architecture
+
+```
+CronJob backup-verify (velero ns)            Hetzner project homelab-backup-verify
+  image ci-backup-verify                       ┌──────────────────────────────┐
+  ├─ 1 sweep stale resources by label ───────▶ │ servers / ssh-keys / firewalls│
+  ├─ 2 build plan from Backups+DataUploads     │   label managed-by=backup-verify
+  ├─ 3 create ssh-key, firewall, server ─────▶ │ VM cx23 (fallback cax11),     │
+  ├─ 4 ssh: run vm-verify.sh, creds on stdin ▶ │ debian-12, fsn1               │
+  │      ◀─ OK/FAIL lines ─────────────────────│  kopia 0.16.0 --readonly ─────┼─▶ S3 renner-uno-k8s-velero
+  ├─ 5 summary, exit code                      └──────────────────────────────┘     kopia/<ns>/
+  └─ 6 trap: delete server, key, firewall
+```
+
+### 1. Sweep
+
+Delete every server, SSH key and firewall in the project labelled
+`managed-by=backup-verify`. `concurrencyPolicy: Forbid` guarantees no other run
+is live, so everything carrying the label is residue.
+
+### 2. Plan
+
+For each Schedule labelled `app.kubernetes.io/part-of=homelab-backup`:
+
+- newest Backup with `status.phase == Completed` for that schedule
+  (`PartiallyFailed` → the schedule is reported `FAIL` without verifying);
+- its DataUploads (`velero.io/backup-name` label): `spec.sourceNamespace`,
+  `spec.sourcePVC`, `status.snapshotID`, `status.progress.totalBytes`,
+  `status.phase` (anything but `Completed` → `FAIL`);
+- a schedule with no DataUploads (e.g. `authentik`) is `SKIP` (nothing to verify).
+
+`ONLY_NAMESPACES` (comma list, optional) limits the plan for test runs.
+An empty plan is `FAIL`.
+
+### 3. VM
+
+- Per-run ed25519 client key → `hcloud ssh-key create`.
+- Per-run ed25519 **host** key, injected via cloud-init `ssh_keys`; the
+  orchestrator writes the matching `known_hosts` entry and connects with
+  `StrictHostKeyChecking=yes`.
+- `hcloud firewall create` + inbound rule `tcp/22` from `0.0.0.0/0, ::/0`.
+- `hcloud server create --type cx23 --image debian-12 --location fsn1`
+  with labels; if `cx23` is not orderable in `fsn1`, retry once with `cax11`
+  (ARM). The chosen arch selects the Kopia download.
+- cloud-init: disable password auth, mount a tmpfs at `/run/verify`,
+  `shutdown -h +240` as a backstop (a halted server is still billed; the next
+  run's sweep deletes it).
+- No credentials in user-data.
+
+### 4. Verify (on the VM, `vm-verify.sh`)
+
+- Download Kopia 0.16.0 release tarball for the arch, check sha256, install.
+- Credentials arrive on SSH stdin (S3 access/secret key, repository password)
+  and live only in `/run/verify` (tmpfs).
+- Per namespace in the plan:
+  - `kopia repository connect s3 --readonly --bucket renner-uno-k8s-velero
+    --prefix kopia/<ns>/ --endpoint fsn1.your-objectstorage.com --region fsn1`,
+    config and cache under `/run/verify`, cache hard limits set small.
+  - `kopia snapshot list --all --json` once; per planned `snapshotID`, find the
+    manifest by `id` and take its root object ID and `TotalFileSize`.
+  - `kopia snapshot verify --directory-id <root> --verify-files-percent=100`.
+  - Emit one line per PVC: `OK|FAIL <ns>/<pvc> snapshot=<id> bytes=<kopia>/<velero> <reason>`.
+  - `kopia repository disconnect`.
+- Size check: Kopia `TotalFileSize` must equal DataUpload `totalBytes` (both
+  come from the same upload; Velero reports `manifest.Stats.TotalFileSize`).
+  `incrementalBytes` is not used (observed negative values).
+
+Unverified details the first test run must confirm before the check is
+trusted: the JSON field names in `snapshot list --json`, that `--directory-id`
+verifies exactly that snapshot, and the exit code of `verify` on error.
+
+### 5. Summary
+
+PASS/FAIL/SKIP counts, the list of failures and skips, wall time, server type
+used. Exit 1 on any `FAIL`.
+
+### 6. Teardown
+
+A `trap` on EXIT and TERM deletes the server, SSH key and firewall by label.
+`activeDeadlineSeconds` 4 h, `terminationGracePeriodSeconds` 120 s (enough for
+the hcloud deletes).
+
+## Security
+
+- **Hetzner Cloud token**: dedicated project `homelab-backup-verify`
+  (Read & Write; tokens cannot be scoped finer, so the project is the
+  boundary) with a budget alert. OpenBao `homelab/infrastructure/hcloud-backup-verify`,
+  key `token`, synced by an ExternalSecret into `velero`.
+- **S3 + repository password**: existing Secrets `cloud-credentials-hetzner`
+  and `velero-repo-credentials` mounted into the pod. Hetzner S3 keys are
+  project-wide and not read-only; mitigated by `--readonly`, tmpfs-only
+  storage on the VM, and the VM's ~1 h lifetime.
+- **RBAC**: ServiceAccount `backup-verify`: `get/list` on `schedules`,
+  `backups`, `datauploads` (`velero.io`). No access to Secrets via the API.
+- **Network**: CiliumNetworkPolicy for the pod: egress to the kube-apiserver,
+  DNS, `api.hetzner.cloud:443` (FQDN), and `tcp/22` to world (VM address is
+  not known in advance).
+
+## Image
+
+`ci/images/backup-verify/Containerfile`: Alpine with `bash`, `kubectl`, `jq`,
+`openssh-client`; `hcloud` copied from `hetznercloud/cli:v1.69.0`. Built by
+`.woodpecker/build-ci-images.yml`, published as
+`gitea.renner.uno/gitea_admin/ci-backup-verify`, with ImageRepository,
+ImagePolicy and setter marker in the first PR.
+
+Scripts `backup-verify.sh` and `vm-verify.sh` in
+`kubernetes/infrastructure/velero/`, packaged into a ConfigMap by
+`configMapGenerator` like `restore-test.sh`.
+
+## Testing
+
+1. `ONLY_NAMESPACES=apps` manual run (`kubectl create job --from=cronjob/backup-verify`):
+   confirms the unverified Kopia details above.
+2. Negative test: a forged `snapshotID` must end `FAIL` with exit 1.
+3. Abort test: delete the Job mid-run; afterwards no labelled resource may
+   remain in the Hetzner project.
+4. Full run: record wall time and cost.
+
+## Rollout
+
+- **PR 1**: image + image automation, scripts, CronJob `backup-verify` with
+  `suspend: true`, RBAC, ExternalSecret, CiliumNetworkPolicy. `restore-test`
+  unchanged. Tests 1–4 run manually after merge.
+- **PR 2** (after tests pass, before 2026-11-01): unsuspend `backup-verify`;
+  remove `restore-test` (CronJob, RBAC, script, its rule in
+  `network-policies/monitoring-ns.yaml`); rewrite the restore-test section of
+  `kubernetes/RECOVERY.md`. The failed `restore-test-29847360` Job goes with
+  the CronJob, clearing the open `KubeJobFailed` (velero) alert.
+- Close PR #1224 as superseded.
+- The `*-snapshot-readonly` StorageClasses stay (the node-agent uses them for
+  backups).
+- After the first green full run: ingest the run facts into the wiki.
+
+## Out of scope
+
+- Disaster-recovery rehearsal (manifests, Velero restore into a fresh
+  cluster) — separate project.
+- CNPG logical restore checks (`RECOVERY.md` "CNPG restore-test").
+- Whether the Velero repository password is still the upstream default
+  `static-passw0rd` — noted for a separate review.

docs/superpowers/specs/2026-10-11-gitea-mcp-design.md

@@ -0,0 +1,127 @@
+# Gitea MCP server — design
+
+Date: 2026-10-11
+Status: draft, awaiting review
+
+## Goal
+
+Run the official Gitea MCP server (`gitea.com/gitea/gitea-mcp`) in the cluster
+and publish it on the NetBird proxy, so MCP clients anywhere (Claude Code on
+the workstation, Paperclip agents, other machines) can use Gitea through MCP
+with their own Gitea personal access token.
+
+## Decisions
+
+| Topic | Decision |
+|---|---|
+| Hosting | In-cluster HTTP service, own namespace `gitea-mcp`, one stateless replica. |
+| Exposure | Public via NetBird proxy, host `gitea-mcp.renner.uno`, label `netbird.renner.uno/public` (proxy-only; the LAN record on the Traefik VIP stays, so LAN clients don't hairpin). |
+| Client auth | Bearer PAT per request (`Authorization: Bearer <pat>` or `token <pat>`). The server holds no token. Every call runs with exactly the caller's Gitea permissions. |
+| Anonymous access | Rejected with 401. Achieved by running with `-oauth`: in that mode a missing token is refused, a present token is passed through unchanged and checked with one `GET /api/v1/user`. No OAuth app or client secret is needed server-side. |
+| Gitea backend | `http://gitea.gitea.svc.cluster.local:3000` (in-cluster Service, no hairpin via the ingress LB). |
+| Image | `docker.gitea.com/gitea-mcp-server`, starting at `1.8.1`, tracked by Flux image automation (semver). |
+| Read-only mode | Off; write tools exposed. Write access is bounded by each caller's token. |
+
+## Why the `-oauth` flag with PATs
+
+Gitea answers anonymous API calls: `GET /api/v1/repos/search` without
+credentials returns `k.renner/homelab`, `konairius/Wiki` and
+`gitea_admin/_cargo-index`. In plain HTTP mode (no `-oauth`, no server token)
+gitea-mcp forwards tokenless requests as an anonymous Gitea client, so the MCP
+endpoint would serve those repos to anyone. Upstream has no "require token"
+flag outside OAuth mode.
+
+With `-oauth -oauth-public-url https://gitea-mcp.renner.uno` (upstream
+`pkg/oauth/oauth.go`):
+
+- `/mcp` without a token → 401 with an RFC 9728 `WWW-Authenticate` challenge.
+- `/mcp` with a token → `TokenRejected` calls Gitea `GET /user` with it; only a
+  401 there rejects. The token is then used as-is for the API calls, so a plain
+  PAT works. There is no JWT/introspection/audience check.
+- The server only publishes `/.well-known/oauth-protected-resource` metadata;
+  config is the public URL and the Gitea URL, nothing else.
+- `/mcp` additionally checks `Host` against the public URL's host (or
+  loopback) and returns 421 otherwise. `/healthz` is outside both checks.
+
+Costs: one extra `/user` call per MCP request. The metadata document advertises
+the in-cluster Gitea URL as authorization server; this only matters for
+OAuth-flow clients (claude.ai connectors), which are out of scope.
+
+## Architecture
+
+```
+client ──HTTPS, Authorization: Bearer <pat>──▶ gitea-mcp.renner.uno
+  ├─ internet: NetBird proxy (TLS passthrough, PROXY v2) ─▶ Traefik
+  └─ LAN:      Traefik VIP (LAN DNS record)                ─▶ Traefik
+Traefik (TLS termination, letsencrypt-cluster cert) ──HTTP :8080──▶ gitea-mcp pod
+gitea-mcp ──HTTP :3000, same token──▶ gitea.gitea.svc (Gitea API)
+```
+
+Traefik forwards `Host` and the `Mcp-*` headers unchanged by default, which the
+Host check and the MCP transport need. `/mcp` is stateless POST only, so no
+sticky sessions or long-lived streams.
+
+## Components
+
+All paths under `kubernetes/`.
+
+- `infrastructure/namespaces/namespaces.yaml` — Namespace `gitea-mcp`.
+- `clusters/homelab/gitea-mcp.yaml` — Flux Kustomization, path
+  `./kubernetes/apps/gitea-mcp`, `prune: true`, `wait: true`, dependsOn
+  `infrastructure`, `infrastructure-crds`.
+- `apps/gitea-mcp/`
+  - `deployment.yaml` — 1 replica; label `app.kubernetes.io/name: gitea-mcp`;
+    args `-t http -p 8080 -oauth -oauth-public-url https://gitea-mcp.renner.uno
+    -H http://gitea.gitea.svc.cluster.local:3000`; no `GITEA_ACCESS_TOKEN`, no
+    `-d` (debug may log tokens via the SDK); pod/container securityContext as in
+    gatus (non-root 65532, drop ALL, no privilege escalation, RuntimeDefault
+    seccomp) plus `readOnlyRootFilesystem: true` with a disk-backed `emptyDir`
+    (`sizeLimit: 2Gi`) at `/tmp` for the app's own rotated log file; liveness/readiness `httpGet /healthz` on `http`;
+    requests `cpu: 10m, memory: 32Mi`, limit `memory: 128Mi`; image line
+    carries the `$imagepolicy` marker.
+  - `service.yaml` — ClusterIP `gitea-mcp`, port 8080 → `http`.
+  - `ingress.yaml` — host `gitea-mcp.renner.uno`, `ingressClassName: traefik`,
+    `cert-manager.io/cluster-issuer: letsencrypt-cluster`, TLS secret
+    `gitea-mcp-tls`, label `netbird.renner.uno/public: "true"`.
+  - `kustomization.yaml`.
+- `infrastructure/network-policies/gitea-mcp-ns.yaml` (+ entry in that
+  directory's `kustomization.yaml`) — default-deny CNP following
+  `gitea-ns.yaml`: ingress from same namespace, `monitoring`, `host`/
+  `remote-node`, ICMP; ingress from Traefik (`ingress` ns,
+  `app.kubernetes.io/name: traefik`) on 8080; egress to kube-dns and to
+  `gitea` ns `app.kubernetes.io/name: gitea` on 3000. No `world` egress.
+- `apps/gitea/networkpolicy.yaml` — new CNP `gitea-allow-gitea-mcp`, modelled on
+  `gitea-allow-flux-rotator`: ingress to Gitea on 3000 from the `gitea-mcp`
+  namespace.
+- `infrastructure/image-automation/gitea-mcp.yaml` (+ kustomization entry) —
+  ImageRepository `docker.gitea.com/gitea-mcp-server`, ImagePolicy semver
+  `>=1.8.1`.
+
+## Error handling
+
+- Invalid/expired token → Gitea `/user` 401 → gitea-mcp returns 401
+  `invalid_token`.
+- Gitea unreachable → upstream's token check fails open (transport errors are
+  not treated as rejection), but the subsequent API call fails, so the client
+  gets a tool error, never data.
+- Pod down → Traefik 503; Flux `wait` surfaces a failed rollout as
+  `FluxResourceNotReady`.
+
+## Verification (after Flux reconciles)
+
+1. `gitea-mcp` Kustomization Ready; pod Ready.
+2. `https://gitea-mcp.renner.uno/healthz` → 200, from the LAN and through the
+   NetBird proxy (public resolution).
+3. `POST /mcp` `initialize` without a token → 401.
+4. `POST /mcp` with the `claude-bot` PAT: `initialize`, then `tools/call`
+   `list_my_repos` → returns repos.
+5. NetBird management lists a reverse-proxy service for
+   `gitea-mcp.renner.uno`.
+6. ImagePolicy `gitea-mcp` resolves `1.8.1` (or newer).
+
+## Out of scope
+
+- Registering the server in Claude Code / other clients.
+- OAuth browser flow for claude.ai connectors (would need a Gitea OAuth2 app
+  and `-H https://gitea.renner.uno`).
+- Read-only mode, tool filtering (`-O`/`-S`).

kubernetes/RECOVERY.md

@@ -165,26 +165,33 @@ permanent recovery.
 
 ---
 
-## Velero restore-test: 80% OSD capacity gate
+## Velero backup verification (backup-verify)
 
-The monthly Velero restore-test restores into the production Ceph pools. Before
-each schedule's restore it projects the restore's raw size (DataUpload
-`totalBytes` x the pool's replication/EC factor, spread over all OSDs) onto
-current OSD usage from Prometheus. If the fullest OSD would go above **80%**
-(`OSD_MAX_PCT` in `restore-test-cronjob.yaml`), that schedule is not restored:
-the Job log shows it as **SKIP** with the projected %, and the summary lists it
-under "Skipped (backup NOT restore-tested)". A SKIP does not fail the Job, so
-read the summary each month. If the projection cannot be made (Prometheus
-down, unsized DataUpload), the schedule is not restored and counts as FAIL.
-Background: REN-441, REN-442.
+Monthly (1st, 08:00 UTC) CronJob `velero/backup-verify`. It creates a throwaway
+Hetzner Cloud VM in fsn1 (project `homelab-backup-verify`) and runs
+`kopia snapshot verify --verify-files-percent=100` read-only against the latest
+snapshot of every DataUpload of each schedule's newest finished backup. Snapshot
+sizes are checked against `DataUpload.status.progress.totalBytes`. Nothing is
+restored into the cluster. A full run takes about an hour (2026-10-10: 39 PVCs,
+~410 GB, 61 min, cx23).
+
+- Results: `kubectl -n velero logs job/<backup-verify-...>`; `FAIL` lines name the
+  backup, PVC, snapshot and cause.
+- A failed run fires `KubeJobFailed` (velero).
+- Manual run: `kubectl -n velero create job bv-manual --from=cronjob/backup-verify`;
+  limit it with env `ONLY_NAMESPACES=apps,gitea`.
+- Every run first deletes everything labelled `managed-by=backup-verify` in the
+  Hetzner project, so a leftover VM is cleaned up by the next run. Do not start a
+  manual run while another one is running: its sweep deletes the other run's VM.
+- This checks data readability, not a full restore. Disaster-recovery rehearsal is separate.
 
 ---
 
 ## CNPG restore-test (verify backups are restorable — non-destructive)
 
-The monthly Velero restore-test (`kubernetes/infrastructure/velero/`) exercises
-PVC restores but **explicitly does not touch CNPG** (barman-cloud is a separate
-code path). Run this drill periodically to prove the CNPG backups are actually
+The monthly Velero backup verification (`kubernetes/infrastructure/velero/`)
+checks the Velero PVC backups but **does not cover CNPG** (barman-cloud is a
+separate code path). Run this drill periodically to prove the CNPG backups are actually
 restorable, **without touching the live clusters**. It restores into a throwaway
 cluster in the *same* namespace (so it can reference the existing namespaced
 `ObjectStore` and creds) and declares the barman plugin with

kubernetes/apps/authentik/blueprints-configmap.yaml

@@ -1591,7 +1591,7 @@ data:
             # return entries instead of short-circuiting. Built from
             # the samba-bridge repo at
             # gitea.renner.uno/k.renner/authentik-samba-bridge .
-            container_image: gitea.renner.uno/k.renner/authentik-samba-bridge-ldap-outpost:2026.5.3-f02b945
+            container_image: gitea.renner.uno/k.renner/authentik-samba-bridge-ldap-outpost:2026.8.3-872f754
             object_naming_template: "ak-outpost-%(name)s"
             kubernetes_namespace: authentik
             kubernetes_replicas: 1
@@ -2189,6 +2189,23 @@ data:
           negate: false
           failure_result: false
 
+      # OpenProject, decommissioned. Application first: Application.provider
+      # is on_delete=PROTECT. Its policy binding cascades with it.
+      - model: authentik_core.application
+        identifiers:
+          slug: openproject
+        state: absent
+
+      - model: authentik_providers_oauth2.oauth2provider
+        identifiers:
+          name: Provider for OpenProject
+        state: absent
+
+      - model: authentik_core.group
+        identifiers:
+          name: OpenProject Users
+        state: absent
+
       # Superseded by the single passkey-webauthn-validation stage above.
       # Their flowstagebindings are FK-CASCADEd away with them; the
       # identification stage's webauthn_stage FK is SET_NULL and is

kubernetes/apps/authentik/helmrelease.yaml

@@ -20,7 +20,7 @@ spec:
       # Pinned to match the samba-bridge fork's app image (server.Dockerfile
       # AUTHENTIK_VERSION). Bump in lockstep with the bridge rebuild — a
       # floating range drifts the chart ahead of the pinned app image.
-      version: "2026.5.3"
+      version: "2026.8.3"
       sourceRef:
         kind: HelmRepository
         name: authentik
@@ -58,7 +58,7 @@ spec:
         # 2. Pinning means the deployed binary is traceable to a
         #    specific repo commit. Bump the tag whenever a new build
         #    is published from gitea.renner.uno/k.renner/authentik-samba-bridge .
-        tag: "2026.5.3-f02b945"
+        tag: "2026.8.3-872f754"
       envFrom:
         # SAMBA_BRIDGE_DOMAIN_SID / _ENABLED_GROUP / _UID_OFFSET
         # consumed by the bridge module at Django app startup. Missing
@@ -100,6 +100,13 @@ spec:
             secretKeyRef:
               name: ldap-outpost-tls
               key: tls.key
+        # 2026.8 honours X-Forwarded-Proto/-Host/-For only from these
+        # networks. Traefik reaches authentik-server (IPv4 single-stack
+        # Service) from a pod IP; same ranges Traefik itself trusts for
+        # forwarded headers. Without them, HTTPS is seen as HTTP and SSO
+        # breaks. Comma-separated, no spaces (authentik list parsing).
+        - name: AUTHENTIK_LISTEN__TRUSTED_PROXY_CIDRS
+          value: "10.244.0.0/16,fd10:244::/48,127.0.0.0/8,::1/128"
 
     authentik:
       log_level: info

kubernetes/apps/gitea-mcp/deployment.yaml

@@ -0,0 +1,75 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: gitea-mcp
+  namespace: gitea-mcp
+  labels:
+    app.kubernetes.io/name: gitea-mcp
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: gitea-mcp
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: gitea-mcp
+    spec:
+      securityContext:
+        runAsNonRoot: true
+        runAsUser: 65532
+        runAsGroup: 65532
+        seccompProfile:
+          type: RuntimeDefault
+      containers:
+        - name: gitea-mcp
+          image: docker.gitea.com/gitea-mcp-server:1.8.1 # {"$imagepolicy": "flux-system:gitea-mcp"}
+          # The image has no ENTRYPOINT; args alone would replace its CMD.
+          command:
+            - /app/gitea-mcp
+          args:
+            - -t
+            - http
+            - -p
+            - "8080"
+            # Only for the 401 on tokenless requests; clients send their own Gitea PAT.
+            - -oauth
+            - -oauth-public-url
+            - https://gitea-mcp.renner.uno
+            - -H
+            - http://gitea.gitea.svc.cluster.local:3000
+          securityContext:
+            allowPrivilegeEscalation: false
+            readOnlyRootFilesystem: true
+            capabilities:
+              drop:
+                - ALL
+          ports:
+            - containerPort: 8080
+              name: http
+          volumeMounts:
+            - name: tmp
+              mountPath: /tmp
+          livenessProbe:
+            httpGet:
+              path: /healthz
+              port: http
+            initialDelaySeconds: 5
+            periodSeconds: 30
+          readinessProbe:
+            httpGet:
+              path: /healthz
+              port: http
+            initialDelaySeconds: 2
+            periodSeconds: 10
+          resources:
+            requests:
+              cpu: 10m
+              memory: 32Mi
+            limits:
+              memory: 128Mi
+      volumes:
+        # Holds the app's own rotated log file (100MB x 11 max); stdout carries the same lines.
+        - name: tmp
+          emptyDir:
+            sizeLimit: 2Gi

kubernetes/apps/gitea-mcp/ingress.yaml

@@ -0,0 +1,28 @@
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: gitea-mcp
+  namespace: gitea-mcp
+  labels:
+    app.kubernetes.io/name: gitea-mcp
+    # Published on the NetBird proxy; LAN DNS stays on the Traefik VIP.
+    netbird.renner.uno/public: "true"
+  annotations:
+    cert-manager.io/cluster-issuer: letsencrypt-cluster
+spec:
+  ingressClassName: traefik
+  rules:
+    - host: gitea-mcp.renner.uno
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: gitea-mcp
+                port:
+                  number: 8080
+  tls:
+    - secretName: gitea-mcp-tls
+      hosts:
+        - gitea-mcp.renner.uno

kubernetes/apps/gitea-mcp/kustomization.yaml

@@ -0,0 +1,6 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - deployment.yaml
+  - service.yaml
+  - ingress.yaml

kubernetes/apps/gitea-mcp/service.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: gitea-mcp
+  namespace: gitea-mcp
+  labels:
+    app.kubernetes.io/name: gitea-mcp
+spec:
+  type: ClusterIP
+  selector:
+    app.kubernetes.io/name: gitea-mcp
+  ports:
+    - name: http
+      port: 8080
+      targetPort: http

kubernetes/apps/gitea/ingress.yaml

@@ -5,6 +5,9 @@ metadata:
   namespace: gitea
   labels:
     app.kubernetes.io/name: gitea
+    # Published on the NetBird proxy; LAN DNS stays on the Traefik VIP so
+    # SSH (gitea-ssh) and node image pulls stay local.
+    netbird.renner.uno/public: "true"
   annotations:
     cert-manager.io/cluster-issuer: letsencrypt-cluster
     # Long-running git fetch/push and container-registry blob uploads:

kubernetes/apps/gitea/kustomization.yaml

@@ -8,7 +8,16 @@ resources:
   - statefulset.yaml
   # The live size of the data volume; see the file (REN-583).
   - pvc.yaml
+  # Before the version upgrade (REN-1367); remove after it.
+  - volumesnapshot-pre-upgrade.yaml
   - service.yaml
   - ingressroute-ssh.yaml
   - ingress.yaml
   - networkpolicy.yaml
+  # Nightly prune of old CI image builds (REN-1203).
+  - package-retention.yaml
+configMapGenerator:
+  - name: gitea-package-retention
+    namespace: gitea
+    files:
+      - package-retention.py

kubernetes/apps/gitea/networkpolicy.yaml

@@ -49,3 +49,46 @@ spec:
         - ports:
             - port: "3000"
               protocol: TCP
+---
+# Package retention CronJob (package-retention.yaml, REN-1203). It lists pods
+# to find the running image tags. The namespace baseline does not open the API
+# server: `kube-apiserver` is its own entity in Cilium (see
+# network-policies/paperclip-renner-ns.yaml); port is the post-DNAT 6443. Its
+# Gitea calls go to the in-cluster Service, which the baseline already allows
+# inside the namespace.
+apiVersion: cilium.io/v2
+kind: CiliumNetworkPolicy
+metadata:
+  name: gitea-package-retention-kube-apiserver
+  namespace: gitea
+spec:
+  endpointSelector:
+    matchLabels:
+      app.kubernetes.io/name: gitea-package-retention
+  egress:
+    - toEntities:
+        - kube-apiserver
+      toPorts:
+        - ports:
+            - port: "6443"
+              protocol: TCP
+---
+# gitea-mcp reaches the in-cluster Service; egress half is in network-policies/gitea-mcp-ns.yaml.
+apiVersion: cilium.io/v2
+kind: CiliumNetworkPolicy
+metadata:
+  name: gitea-allow-gitea-mcp
+  namespace: gitea
+spec:
+  endpointSelector:
+    matchLabels:
+      app.kubernetes.io/name: gitea
+  ingress:
+    - fromEndpoints:
+        - matchLabels:
+            "k8s:io.kubernetes.pod.namespace": gitea-mcp
+            app.kubernetes.io/name: gitea-mcp
+      toPorts:
+        - ports:
+            - port: "3000"
+              protocol: TCP

kubernetes/apps/gitea/package-retention.py

@@ -0,0 +1,162 @@
+"""Prune old CI image builds from Gitea's container registry (REN-1203).
+
+See package-retention.yaml for what is pruned, what is kept, and why.
+Standard library only.
+"""
+import json
+import os
+import re
+import ssl
+import sys
+import urllib.parse
+import urllib.request
+from datetime import datetime
+
+GITEA = os.environ["GITEA_URL"].rstrip("/")
+TOKEN = os.environ["GITEA_TOKEN"]
+REGISTRY_HOST = os.environ["REGISTRY_HOST"]
+OWNERS = os.environ["OWNERS"].split(",")
+KEEP = int(os.environ["KEEP_IMAGES"])
+GROUP_SECONDS = int(os.environ["GROUP_SECONDS"])
+MAX_DELETES = int(os.environ["MAX_DELETES"])
+EXCLUDE = re.compile(os.environ["EXCLUDE_PACKAGES"])
+DRY_RUN = os.environ.get("DRY_RUN", "false") == "true"
+
+# A package is a CI build package if at least one of its tags looks like this.
+BUILD_TAG = re.compile(r"^(build\.[0-9]+|main-[0-9a-f]{7,40})$")
+ALWAYS_KEEP = {"main", "latest"}
+
+SA = "/var/run/secrets/kubernetes.io/serviceaccount"
+
+
+def log(msg):
+    print(msg, flush=True)
+
+
+def gitea(method, path):
+    req = urllib.request.Request(
+        GITEA + path, method=method, headers={"Authorization": "token " + TOKEN}
+    )
+    with urllib.request.urlopen(req, timeout=60) as resp:
+        body = resp.read()
+        return json.loads(body) if body else None
+
+
+def ts(s):
+    # Gitea returns RFC 3339, e.g. 2026-10-07T18:07:32Z or +02:00.
+    return datetime.fromisoformat(s.replace("Z", "+00:00")).timestamp()
+
+
+def running_images():
+    """Tags in use by any pod, per package. Packages referenced by digest only
+    cannot be matched to a tag, so they are returned in `unsafe` and skipped."""
+    ctx = ssl.create_default_context(cafile=SA + "/ca.crt")
+    with open(SA + "/token") as f:
+        sa_token = f.read().strip()
+    req = urllib.request.Request(
+        "https://kubernetes.default.svc/api/v1/pods",
+        headers={"Authorization": "Bearer " + sa_token},
+    )
+    with urllib.request.urlopen(req, timeout=60, context=ctx) as resp:
+        pods = json.load(resp)["items"]
+    in_use, unsafe = {}, set()
+    prefix = REGISTRY_HOST + "/"
+    for pod in pods:
+        spec = pod["spec"]
+        for c in (
+            spec.get("containers", [])
+            + spec.get("initContainers", [])
+            + spec.get("ephemeralContainers", [])
+        ):
+            image = c["image"]
+            if not image.startswith(prefix):
+                continue
+            ref = image[len(prefix):].split("@", 1)[0]
+            repo, _, tag = ref.rpartition(":")
+            if not repo or "/" in tag:
+                unsafe.add(ref)
+                continue
+            in_use.setdefault(repo, set()).add(tag)
+    return in_use, unsafe
+
+
+def list_packages(owner):
+    out, page = [], 1
+    while True:
+        batch = gitea(
+            "GET", f"/api/v1/packages/{owner}?type=container&limit=50&page={page}"
+        )
+        if not batch:
+            return out
+        out.extend(batch)
+        page += 1
+
+
+def plan(versions, protected):
+    """Group tags into images (one push writes all tags of an image within a
+    few seconds) and return the tags of the images to delete."""
+    tags = sorted(
+        (v for v in versions if not v["version"].startswith("sha256:")),
+        key=lambda v: ts(v["created_at"]),
+        reverse=True,
+    )
+    images, last = [], None
+    for v in tags:
+        t = ts(v["created_at"])
+        if last is None or last - t > GROUP_SECONDS:
+            images.append([])
+        images[-1].append(v["version"])
+        last = t
+    delete = []
+    for i, image in enumerate(images):
+        if i < KEEP or set(image) & (ALWAYS_KEEP | protected):
+            continue
+        delete.extend(image)
+    return images, delete
+
+
+def main():
+    in_use, unsafe = running_images()
+    log(f"running tags from {REGISTRY_HOST}: {sum(len(t) for t in in_use.values())}")
+    work = []
+    for owner in OWNERS:
+        by_name = {}
+        for v in list_packages(owner):
+            by_name.setdefault(v["name"], []).append(v)
+        for name, versions in sorted(by_name.items()):
+            full = f"{owner}/{name}"
+            if EXCLUDE.search(full):
+                log(f"skip {full}: excluded")
+                continue
+            if not any(BUILD_TAG.match(v["version"]) for v in versions):
+                continue
+            if full in unsafe:
+                log(f"skip {full}: a pod pins it by digest only")
+                continue
+            protected = in_use.get(full, set())
+            images, delete = plan(versions, protected)
+            log(f"{full}: {len(images)} images, {len(delete)} tags to delete, running {sorted(protected)}")
+            work += [(owner, name, tag) for tag in delete]
+    if len(work) > MAX_DELETES:
+        log(f"abort: {len(work)} deletes exceed MAX_DELETES={MAX_DELETES}; nothing deleted")
+        return 1
+    failed = 0
+    for owner, name, tag in work:
+        if DRY_RUN:
+            log(f"dry-run: would delete {owner}/{name}:{tag}")
+            continue
+        path = "/api/v1/packages/{}/container/{}/{}".format(
+            owner, urllib.parse.quote(name, safe=""), urllib.parse.quote(tag, safe="")
+        )
+        try:
+            gitea("DELETE", path)
+            log(f"deleted {owner}/{name}:{tag}")
+        except Exception as e:  # keep going; report at the end
+            failed += 1
+            log(f"FAILED {owner}/{name}:{tag}: {e}")
+    log(f"done: {len(work) - failed} deleted, {failed} failed, dry_run={DRY_RUN}")
+    return 1 if failed else 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

kubernetes/apps/gitea/package-retention.yaml

@@ -0,0 +1,165 @@
+# Nightly retention for CI image builds in Gitea's container registry (REN-1203).
+#
+# Why: nothing pruned old builds, so the data volume filled up (REN-580, at
+# 40Gi) and was down to 24% free again four days after the grow to 60Gi
+# (REN-1203, about 2.2 GB/day). Gitea 1.21 has no API for per-owner cleanup
+# rules, and the owners are human accounts, so the rules cannot live in Gitea.
+# This job applies the rule Hermes ran by hand in REN-1204.
+#
+# What it prunes, per package of the owners in OWNERS:
+#   - only CI build packages: at least one tag is `build.<n>` or `main-<sha>`.
+#     Date-tagged utility images (alpine-jq, cni-plugins, ...) are not touched.
+#   - one image carries several tags (build.N, short and long sha, sometimes
+#     main/latest). Tags pushed within GROUP_SECONDS are one image, and the job
+#     deletes all tags of an image, because a sha tag left behind keeps the
+#     blobs alive.
+#   - keeps the KEEP_IMAGES newest images, any image tagged main or latest, and
+#     any image whose tag a pod in the cluster runs now. A package that a pod
+#     pins by digest only is skipped as a whole.
+#   - never touches gitea_admin/* (CI base images) or EXCLUDE_PACKAGES. The
+#     agent-runtime images are excluded because Paperclip pins their tag in its
+#     own config, not in a pod that exists between runs.
+#   - aborts without deleting if the plan exceeds MAX_DELETES.
+# Freed blobs are removed by Gitea's own `cleanup_packages` cron (daily).
+#
+# Token: `gitea-hermes-bot-package-retention-token` on hermes-bot (site admin),
+# scope `write:package` only (REN-1204). Admin and repo routes return 403 with
+# it. Hermes owns the account and the token.
+#
+# Kubernetes access: list pods, cluster-wide, to find the running tags. Nothing
+# else.
+#
+# Dry run: set DRY_RUN to "true"; the job then only logs the plan.
+# Stop it: `spec.suspend: true` in git. Revert: delete this file, the
+# configMapGenerator entry and the policy in networkpolicy.yaml. Deleted images
+# cannot be restored; CI rebuilds one from its commit.
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: gitea-package-retention
+  namespace: gitea
+spec:
+  refreshInterval: 1h
+  secretStoreRef:
+    kind: ClusterSecretStore
+    name: openbao
+  target:
+    name: gitea-package-retention
+  data:
+    - secretKey: GITEA_TOKEN
+      remoteRef:
+        key: infrastructure/gitea/hermes-bot
+        property: gitea-hermes-bot-package-retention-token
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: gitea-package-retention
+  namespace: gitea
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: gitea-package-retention
+rules:
+  - apiGroups: [""]
+    resources: ["pods"]
+    verbs: ["list"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: gitea-package-retention
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: gitea-package-retention
+subjects:
+  - kind: ServiceAccount
+    name: gitea-package-retention
+    namespace: gitea
+---
+apiVersion: batch/v1
+kind: CronJob
+metadata:
+  name: gitea-package-retention
+  namespace: gitea
+  labels:
+    app.kubernetes.io/name: gitea-package-retention
+spec:
+  # Quiet hour for CI pushes. Gitea's own daily cleanup_packages cron frees
+  # the blobs afterwards.
+  schedule: "30 22 * * *"
+  timeZone: Etc/UTC
+  concurrencyPolicy: Forbid
+  successfulJobsHistoryLimit: 2
+  failedJobsHistoryLimit: 3
+  startingDeadlineSeconds: 3600
+  jobTemplate:
+    spec:
+      backoffLimit: 0
+      activeDeadlineSeconds: 1800
+      ttlSecondsAfterFinished: 604800
+      template:
+        metadata:
+          labels:
+            app.kubernetes.io/name: gitea-package-retention
+        spec:
+          restartPolicy: Never
+          enableServiceLinks: false
+          serviceAccountName: gitea-package-retention
+          securityContext:
+            runAsNonRoot: true
+            runAsUser: 65534
+            runAsGroup: 65534
+            seccompProfile:
+              type: RuntimeDefault
+          containers:
+            - name: retention
+              image: docker.io/library/python:3.13-alpine@sha256:2d9aefe2fef018a7eb2c13064c89c71929800fd2e5dccdbf52ea5da5bb8d929a
+              command: ["python3", "/app/package-retention.py"]
+              env:
+                # In-cluster Service; the public name hairpins off the ingress
+                # LB from a pod (see networkpolicy.yaml).
+                - name: GITEA_URL
+                  value: http://gitea.gitea.svc:3000
+                - name: REGISTRY_HOST
+                  value: gitea.renner.uno
+                - name: OWNERS
+                  value: k.renner,konairius
+                - name: KEEP_IMAGES
+                  value: "5"
+                # Tags of one push land within seconds; the smallest gap
+                # between two images was 379 s (REN-1204).
+                - name: GROUP_SECONDS
+                  value: "60"
+                - name: MAX_DELETES
+                  value: "300"
+                - name: EXCLUDE_PACKAGES
+                  value: "^konairius/agent-runtime"
+                - name: DRY_RUN
+                  value: "false"
+                - name: PYTHONDONTWRITEBYTECODE
+                  value: "1"
+              envFrom:
+                - secretRef:
+                    name: gitea-package-retention
+              resources:
+                requests:
+                  cpu: 10m
+                  memory: 32Mi
+                limits:
+                  memory: 128Mi
+              securityContext:
+                allowPrivilegeEscalation: false
+                readOnlyRootFilesystem: true
+                capabilities:
+                  drop: ["ALL"]
+              volumeMounts:
+                - name: script
+                  mountPath: /app
+                  readOnly: true
+          volumes:
+            - name: script
+              configMap:
+                name: gitea-package-retention

kubernetes/apps/gitea/statefulset.yaml

@@ -34,10 +34,12 @@ spec:
           # RUN_USER check -> fatal). The migrated /var/lib/gitea/data drops in as-is,
           # but the LXC's /etc/gitea/app.ini is RELOCATED to custom/conf/app.ini
           # (GITEA_APP_INI below) and its RUN_USER must read `git`, not `gitea` —
-          # both handled as explicit steps in MIGRATION-gitea-woodpecker.md. Pinned
-          # to match the LXC for a clean SQLite lift; no imagepolicy marker (an
-          # auto-bump across versions on live SQLite data must never be applied).
-          image: gitea/gitea:1.21.4-rootless@sha256:600f1f1e1d090c763866db16882b5eac5c6a80b7664ee53bec0806c656c0033f
+          # both handled as explicit steps in MIGRATION-gitea-woodpecker.md. No
+          # imagepolicy marker: a minor bump migrates the live SQLite database and
+          # needs a snapshot first (volumesnapshot-pre-upgrade.yaml). 1.21.4 ->
+          # 1.27.3 in REN-1367; the
+          # next step, 28.x, changes the outgoing-request (webhook) host lists.
+          image: gitea/gitea:1.27.3-rootless@sha256:1c17ecaead42eb3b5391553d8708103a4beb0e86edf5b9ebc1eb269c318845f2
           env:
             - name: GITEA_WORK_DIR
               value: /var/lib/gitea
@@ -113,11 +115,23 @@ spec:
             # Nothing here authenticates via query tokens (CI uses webhooks/OAuth).
             - name: GITEA__security__DISABLE_QUERY_AUTH_TOKEN
               value: "true"
+            # Webhook targets Gitea may call; every configured webhook host.
+            - name: GITEA__security__ALLOWED_HOST_LIST
+              value: "ci.renner.uno,paperclip-api.renner.uno,wiki.ai.svc.cluster.local"
           ports:
             - name: http
               containerPort: 3000
             - name: ssh
               containerPort: 2222
+          # The first start on a new minor version runs the database migrations
+          # before the HTTP server listens. Give that up to 15 minutes; without
+          # it the liveness probe kills Gitea in the middle of a migration.
+          startupProbe:
+            httpGet:
+              path: /api/healthz
+              port: http
+            periodSeconds: 10
+            failureThreshold: 90
           readinessProbe:
             httpGet:
               path: /api/healthz

kubernetes/apps/gitea/volumesnapshot-pre-upgrade.yaml

@@ -0,0 +1,30 @@
+---
+# Point-in-time copy of the Gitea data PVC (SQLite DB, repositories, LFS,
+# packages, app.ini), taken before the 1.21.4 -> 1.27.3 upgrade (REN-1367).
+# Merge this first and see the SnapshotReady event in namespace gitea before
+# the image bump: 1.22+ migrates the database, and a migrated database cannot
+# run on 1.21 again. The way back is a restore from this snapshot.
+#
+# Crash-consistent (taken from the live RBD volume), like the velero CSI
+# snapshots; SQLite recovers from its journal on open. The velero
+# `gitea-daily` schedule holds a second, off-cluster copy.
+#
+# Restore (only if the upgrade fails):
+#   1. Revert the image bump PR and set `replicas: 0` on the StatefulSet in git.
+#   2. In git, replace pvc.yaml with a claim `data-gitea-0` that has
+#      `dataSource: {kind: VolumeSnapshot, apiGroup: snapshot.storage.k8s.io,
+#      name: gitea-data-pre-upgrade}` and no volumeName; the old claim must be
+#      deleted first (prune is disabled on it, so this is a cluster-write step).
+#   3. Set `replicas: 1` again; gitea-0 starts 1.21.4 on the restored data.
+#
+# Delete this file once the upgrade has run cleanly; the snapshot goes with it
+# (prune).
+apiVersion: snapshot.storage.k8s.io/v1
+kind: VolumeSnapshot
+metadata:
+  name: gitea-data-pre-upgrade
+  namespace: gitea
+spec:
+  volumeSnapshotClassName: ceph-block-snapclass
+  source:
+    persistentVolumeClaimName: data-gitea-0

kubernetes/apps/home-assistant/deployment.yaml

@@ -95,7 +95,7 @@ spec:
               memory: 32Mi
       containers:
         - name: home-assistant
-          image: ghcr.io/home-assistant/home-assistant:2026.9.4 # {"$imagepolicy": "flux-system:home-assistant"}
+          image: ghcr.io/home-assistant/home-assistant:2026.10.1 # {"$imagepolicy": "flux-system:home-assistant"}
           env:
             - name: TZ
               value: Europe/Berlin
@@ -187,6 +187,55 @@ spec:
               memory: 32Mi
             limits:
               memory: 64Mi
+        # MQTT client certificate for Home Assistant (REN-953). HA keeps
+        # client certificates only as PEMs uploaded into its MQTT config
+        # entry, so a cert-manager renewal (~60 days) could never reach it
+        # without a reconfigure flow and an admin token. Instead HA's config
+        # entry points at 127.0.0.1:11883 (plain, loopback only) and this
+        # sidecar forwards to the broker's mTLS listener :8884 with the
+        # certificate of the register account `home-assistant`. The broker
+        # takes the username from the certificate CN; whatever user/password
+        # HA sends is ignored. --timed-reload picks up a renewed certificate
+        # for new connections without a restart; an open connection stays up
+        # (checked locally with ghostunnel v1.11.3 and mosquitto 2.0.22).
+        #
+        # Probes: liveness only, on the HTTPS status port (process alive). No
+        # readiness probe on purpose: a broker outage must not take HA out of
+        # its Service endpoints.
+        - name: mqtt-tls
+          image: ghostunnel/ghostunnel:v1.11.3@sha256:2599b8a04bae16d70a4209495618dea61b46a00a9a05fcf74da282688ad3517f
+          args:
+            - client
+            - --listen=127.0.0.1:11883
+            - --target=mosquitto.home-assistant.svc.cluster.local:8884
+            - --cert=/mqtt-tls/tls.crt
+            - --key=/mqtt-tls/tls.key
+            - --cacert=/mqtt-tls/ca.crt
+            - --timed-reload=10m
+            - --status=0.0.0.0:16060
+          securityContext:
+            runAsNonRoot: true
+            runAsUser: 65534
+            runAsGroup: 65534
+            allowPrivilegeEscalation: false
+            readOnlyRootFilesystem: true
+            capabilities:
+              drop: [ALL]
+          livenessProbe:
+            tcpSocket:
+              port: 16060
+            periodSeconds: 30
+            failureThreshold: 4
+          volumeMounts:
+            - name: mqtt-tls
+              mountPath: /mqtt-tls
+              readOnly: true
+          resources:
+            requests:
+              cpu: 5m
+              memory: 16Mi
+            limits:
+              memory: 64Mi
         # Browser-based VS Code editing /config in-place. Sidecar (not
         # separate Deployment) because the config PVC is RWO ceph-block.
         # Exposed LAN-only on vscode.home.renner.uno; --auth=none means
@@ -297,6 +346,14 @@ spec:
         - name: proxy-config
           configMap:
             name: ha-proxy-config
+        # Client certificate of the register account home-assistant, issued
+        # by mqtt-account-controller. Not subPath, so renewals land in place.
+        # 0444 because the sidecar runs as 65534; only this pod mounts it.
+        # Not in the Reloader annotation: a renewal must not restart HA.
+        - name: mqtt-tls
+          secret:
+            secretName: mqtt-home-assistant-tls
+            defaultMode: 0444
         # Writable emptyDir for the nginx entrypoint's envsubst output
         # (/etc/nginx/conf.d/default.conf rendered from the .template).
         - name: proxy-conf-d

kubernetes/apps/home-assistant/kustomization.yaml

@@ -16,9 +16,6 @@ resources:
   # probes use the cert account mosquitto-probe, REN-953); removed with its
   # rotator in the REN-802 cleanup step.
   - mosquitto-health-credentials-externalsecret.yaml
-  # open3e-int broker credential: open3e-esp32 gateway on the Vitocal internal
-  # CAN; OpenBao-backed + Class-A rotated.
-  - mosquitto-open3e-int-credentials-externalsecret.yaml
   - mosquitto-config.yaml
   - mosquitto-certificate.yaml
   - mosquitto-service.yaml

kubernetes/apps/home-assistant/mosquitto-bootstrap.yaml

@@ -177,77 +177,6 @@ spec:
             limits:
               memory: 64Mi
 ---
-# Second broker user: `shellies`. Separate Secret (not a second key on
-# mosquitto-credentials) so each credential's lifecycle is independent —
-# rotating one never touches the other, and existing clusters whose
-# mosquitto-credentials was already generated for `homeassistant` only
-# don't end up with a half-populated Secret.
-apiVersion: batch/v1
-kind: Job
-metadata:
-  name: mosquitto-shellies-credentials-bootstrap
-  namespace: home-assistant
-  annotations:
-    # Job pod templates are immutable; force-recreate so image bumps
-    # apply on Flux re-reconcile. Safe: the Job is idempotent (see above).
-    kustomize.toolkit.fluxcd.io/force: enabled
-spec:
-  backoffLimit: 4
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/name: mosquitto-bootstrap
-    spec:
-      serviceAccountName: mosquitto-bootstrap
-      restartPolicy: OnFailure
-      containers:
-        - name: bootstrap
-          image: alpine:3.24@sha256:294b683cb724975bec92580e1e685676bd4b50bda910ddb8c51d4cabeaec77e6
-          command:
-            - sh
-            - -c
-            - |
-              set -eu
-              apk add --no-cache curl jq >/dev/null
-
-              NS=home-assistant
-              NAME=mosquitto-shellies-credentials
-              TOKEN=$(cat /var/run/secrets/kubernetes.io/serviceaccount/token)
-              CA=/var/run/secrets/kubernetes.io/serviceaccount/ca.crt
-              API=https://kubernetes.default.svc
-
-              if curl -fsSL --cacert "$CA" -H "Authorization: Bearer $TOKEN" \
-                   "$API/api/v1/namespaces/$NS/secrets/$NAME" >/dev/null 2>&1; then
-                echo "$NAME already exists; nothing to do."
-                exit 0
-              fi
-
-              PW=$(tr -dc 'A-Za-z0-9' </dev/urandom | head -c 32)
-              PW_B64=$(printf '%s' "$PW" | base64 | tr -d '\n')
-
-              body=$(jq -nc \
-                --arg name "$NAME" \
-                --arg ns "$NS" \
-                --arg pw "$PW_B64" \
-                '{apiVersion: "v1",
-                  kind: "Secret",
-                  metadata: {name: $name, namespace: $ns},
-                  type: "Opaque",
-                  data: {password: $pw}}')
-
-              curl -fsSL --cacert "$CA" -H "Authorization: Bearer $TOKEN" \
-                   -H "Content-Type: application/json" -X POST \
-                   --data "$body" \
-                   "$API/api/v1/namespaces/$NS/secrets" >/dev/null
-
-              echo "generated $NAME"
-          resources:
-            requests:
-              cpu: 10m
-              memory: 32Mi
-            limits:
-              memory: 64Mi
----
 # Fourth broker user: `sml2mqtt` — the power-meter bridge. Publish-only
 # under `sml2mqtt/#` (ACL in mosquitto-deployment.yaml). Own credential so
 # its lifecycle is independent of the others. The sml2mqtt pod reads this
@@ -392,7 +321,7 @@ spec:
 ---
 # Broker user `zigbee2mqtt` — the Zigbee2MQTT bridge (ZHA replacement). Scoped
 # to its own `zigbee2mqtt/#` subtree plus `write homeassistant/#` (so it can
-# publish HA MQTT-discovery configs, exactly like the `shellies` user) and
+# publish HA MQTT-discovery configs) and
 # `read homeassistant/status` (HA's birth/will topic; on `online` Z2M
 # republishes cached device states, NOT discovery configs — ACL and the full
 # reasoning in mosquitto-deployment.yaml). Own credential so its lifecycle is

kubernetes/apps/home-assistant/mosquitto-deployment.yaml

@@ -5,14 +5,6 @@ metadata:
   namespace: home-assistant
   labels:
     app.kubernetes.io/name: mosquitto
-  annotations:
-    # REQUIRED for credential rotation to take effect. The startup shim rebuilds
-    # the password file only on pod start, so without this a rotated Secret sits
-    # inert while the old password stays valid indefinitely.
-    #
-    # Listed per-Secret rather than with the blanket auto annotation, so that
-    # enrolling another broker user is a visible edit to this line.
-    secret.reloader.stakater.com/reload: mosquitto-open3e-int-credentials
 spec:
   replicas: 1
   strategy:
@@ -74,23 +66,14 @@ spec:
               set -eu
               rm -f /mosquitto/auth/passwd
               mosquitto_passwd -c -b /mosquitto/auth/passwd homeassistant "$HA_PASSWORD"
-              mosquitto_passwd -b /mosquitto/auth/passwd shellies "$SHELLY_PASSWORD"
               mosquitto_passwd -b /mosquitto/auth/passwd admin "$ADMIN_PASSWORD"
               mosquitto_passwd -b /mosquitto/auth/passwd sml2mqtt "$SML2MQTT_PASSWORD"
               mosquitto_passwd -b /mosquitto/auth/passwd open3e "$OPEN3E_PASSWORD"
-              mosquitto_passwd -b /mosquitto/auth/passwd open3e-int "$OPEN3E_INT_PASSWORD"
               mosquitto_passwd -b /mosquitto/auth/passwd evcc "$EVCC_PASSWORD"
               mosquitto_passwd -b /mosquitto/auth/passwd zigbee2mqtt "$ZIGBEE2MQTT_PASSWORD"
-              # ACL: HA keeps full access (subscribes to everything); the
-              # shellies user is `readwrite shellies/#` (devices publish state
-              # and subscribe to their command topics) + `write homeassistant/#`
-              # so Shelly Gen2 firmwares can publish HA MQTT-discovery configs.
-              # It is WRITE-only on homeassistant/# on purpose: a publish-only
-              # client never needs to read the whole discovery/state tree, and
-              # denying read removes device-inventory recon for a compromised
-              # Shelly. (Full per-device write scoping isn't expressible with
-              # the flat discovery topic layout; that would need a dynamic-auth
-              # plugin — out of scope.)
+              # ACL: HA keeps full access (subscribes to everything). Shellies
+              # are not legacy users any more: each has its own Dynamic Security
+              # account from mqtt-accounts.yaml (REN-802, REN-1017).
               # `admin` is a workstation/debugging credential — full
               # readwrite, kept on its own credential so its password can
               # be rotated independently of the HA session.
@@ -111,10 +94,6 @@ spec:
               user homeassistant
               topic readwrite #
 
-              user shellies
-              topic readwrite shellies/#
-              topic write homeassistant/#
-
               user admin
               topic readwrite #
 
@@ -124,12 +103,6 @@ spec:
               user open3e
               topic readwrite open3e/#
 
-              # open3e-esp32 gateway on the Vitocal internal CAN: own subtree
-              # under open3e/ so edge-1's listener on open3e/cmnd never sees
-              # its commands.
-              user open3e-int
-              topic readwrite open3e/int/#
-
               user evcc
               topic read open3e/#
               topic readwrite evcc/#
@@ -137,9 +110,8 @@ spec:
 
               # `zigbee2mqtt` is the Zigbee2MQTT bridge (the ZHA replacement).
               # Owns its own `zigbee2mqtt/#` subtree; may WRITE `homeassistant/#`
-              # to publish HA MQTT-discovery configs (write-only there, like the
-              # shellies user, to deny discovery-tree recon from a compromised
-              # bridge); and READs `homeassistant/status`, HA's birth/will topic.
+              # to publish HA MQTT-discovery configs (write-only there, to deny
+              # discovery-tree recon from a compromised bridge); and READs `homeassistant/status`, HA's birth/will topic.
               #
               # That read grant does NOT buy a discovery re-publish: on
               # `online`, Z2M 2.12.1 republishes bridge/state and cached device
@@ -176,11 +148,6 @@ spec:
                 secretKeyRef:
                   name: mosquitto-credentials
                   key: homeassistant-password
-            - name: SHELLY_PASSWORD
-              valueFrom:
-                secretKeyRef:
-                  name: mosquitto-shellies-credentials
-                  key: password
             - name: ADMIN_PASSWORD
               valueFrom:
                 secretKeyRef:
@@ -196,13 +163,6 @@ spec:
                 secretKeyRef:
                   name: mosquitto-open3e-credentials
                   key: password
-            # open3e-int: OpenBao-backed + Class-A rotated (see
-            # mosquitto-open3e-int-credentials-externalsecret.yaml).
-            - name: OPEN3E_INT_PASSWORD
-              valueFrom:
-                secretKeyRef:
-                  name: mosquitto-open3e-int-credentials
-                  key: password
             - name: EVCC_PASSWORD
               valueFrom:
                 secretKeyRef:

kubernetes/apps/home-assistant/mosquitto-open3e-int-credentials-externalsecret.yaml

@@ -1,21 +0,0 @@
-# Projects the mosquitto `open3e-int` broker credential (open3e-esp32 gateway
-# on the Vitocal internal CAN) from OpenBao into the Secret the broker
-# consumes. Rotator: kubernetes/infrastructure/openbao/rotation/mosquitto-open3e-int.yaml.
-#
-# creationPolicy is implicitly Owner: deleting this ExternalSecret deletes the
-# live Secret. Set creationPolicy: Orphan first to detach without destroying.
-apiVersion: external-secrets.io/v1
-kind: ExternalSecret
-metadata:
-  name: mosquitto-open3e-int-credentials
-  namespace: home-assistant
-spec:
-  refreshInterval: 10m
-  secretStoreRef:
-    kind: ClusterSecretStore
-    name: openbao
-  target:
-    name: mosquitto-open3e-int-credentials
-  dataFrom:
-    - extract:
-        key: apps/home-assistant/mosquitto-open3e-int-credentials

kubernetes/apps/home-assistant/mqtt-account-controller.yaml

@@ -85,6 +85,8 @@ subjects:
 #     that creates, because the name is in the request path).
 #   mqtt-<name>-tls: delete on revocation, one entry per cert account
 #     delivered to this namespace. Add the name with the register entry.
+#   mqtt-ha-cert-sync: sha256 of the client certificate last accepted by
+#     Home Assistant's MQTT config entry (HA cert sync, REN-953/REN-1284).
 apiVersion: rbac.authorization.k8s.io/v1
 kind: Role
 metadata:
@@ -95,7 +97,7 @@ metadata:
 rules:
   - apiGroups: [""]
     resources: ["secrets"]
-    resourceNames: ["mqtt-account-hashes", "mqtt-dynsec-seed"]
+    resourceNames: ["mqtt-account-hashes", "mqtt-dynsec-seed", "mqtt-ha-cert-sync"]
     verbs: ["get", "create", "patch"]
   - apiGroups: [""]
     resources: ["secrets"]
@@ -252,7 +254,7 @@ spec:
         - name: controller
           # Woodpecker builds main-<sha> on every merge to main; no sortable
           # tag, so bumps are manual (same as ical-proxy).
-          image: gitea.renner.uno/konairius/mqtt-account-controller:main-982231a@sha256:851dd025a8aea352061ac818f9968e1c4a074c8f33af405efde3424382e77ae1
+          image: gitea.renner.uno/konairius/mqtt-account-controller:main-cb96b1a@sha256:9d9b9e83a9c0f9f567e57edacab11cf4c58e8c0e49e38e8d7b51421cd1242911
           env:
             - name: BROKER_URL
               value: ssl://mosquitto.home-assistant.svc.cluster.local:8884
@@ -263,6 +265,22 @@ spec:
               value: http://shelly-manager-api.home-assistant.svc.cluster.local
             - name: SHELLY_MANAGER_API_KEY_FILE
               value: /etc/shelly-manager/api-key
+            # HA cert sync (REN-953, REN-1284): keeps Home Assistant's MQTT
+            # config entry on mosquitto:8884 with the CA and client
+            # certificate of the register account `home-assistant`. After
+            # each loop the controller compares tls.crt (mounted below) with
+            # the last certificate HA accepted (Secret mqtt-ha-cert-sync) and,
+            # only inside 02:00-05:00 Europe/Berlin, runs HA's reconfigure
+            # flow. HA tests the connection before it saves. Defaults:
+            # broker mosquitto.home-assistant.svc.cluster.local:8884, cert dir
+            # /etc/mqtt-home-assistant-tls. Off while HA_MQTT_ENTRY_ID is unset.
+            - name: HA_MQTT_ENTRY_ID
+              value: 01KRFXD4046FEBWQ0EX0GNE418
+            # HA itself (:8123), not the :8124 XFF proxy; same namespace.
+            - name: HA_URL
+              value: http://home-assistant-bgp.home-assistant.svc.cluster.local:8123
+            - name: HA_TOKEN_FILE
+              value: /etc/ha-token/token
             # Not :8080: several :8080 ingress grants in the home-assistant
             # default-deny apply to every pod in the namespace.
             - name: LISTEN
@@ -293,6 +311,12 @@ spec:
             - name: shelly-manager-key
               mountPath: /etc/shelly-manager
               readOnly: true
+            - name: ha-mqtt-tls
+              mountPath: /etc/mqtt-home-assistant-tls
+              readOnly: true
+            - name: ha-token
+              mountPath: /etc/ha-token
+              readOnly: true
           resources:
             requests:
               cpu: 5m
@@ -315,3 +339,35 @@ spec:
             items:
               - key: api-key
                 path: api-key
+        # Client certificate HA gets (cert-manager renews it in place; not a
+        # subPath mount, so the next loop sees the new file).
+        - name: ha-mqtt-tls
+          secret:
+            secretName: mqtt-home-assistant-tls
+        # HA long-lived token of the service user `MQTT Cert Sync`
+        # (system-admin; config flows need admin). REN-1268.
+        - name: ha-token
+          secret:
+            secretName: mqtt-account-controller-ha-token
+---
+# HA admin token for the HA cert sync (see the Deployment env). Minted by
+# Hermes on a dedicated HA service user, not the owner's account (REN-1268).
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: mqtt-account-controller-ha-token
+  namespace: home-assistant
+  labels:
+    app.kubernetes.io/name: mqtt-account-controller
+spec:
+  refreshInterval: 1h
+  secretStoreRef:
+    kind: ClusterSecretStore
+    name: openbao
+  target:
+    name: mqtt-account-controller-ha-token
+  data:
+    - secretKey: token
+      remoteRef:
+        key: apps/home-assistant/mqtt-cert-sync-token
+        property: token

kubernetes/apps/home-assistant/mqtt-accounts.yaml

@@ -59,11 +59,25 @@
   auth: cert
   deliver: {namespace: paperclip}
   acl: ["read open3e/#", "read zigbee2mqtt/#", "read homeassistant/#"]
+# edge-1's local mosquitto bridge (REN-1307): one bridge for open3e/e3oncan
+# and sml2mqtt, replacing the legacy password users `open3e` and `sml2mqtt`
+# (different name, so it cannot shadow their logins). The controller pushes
+# the password to edge-mqtt-cred on edge-1 (ansible role mqtt-bridge) over
+# HTTPS with its own client certificate, and pins edge-1's self-generated
+# server certificate on first contact (key edge-1.pin in mqtt-account-hashes;
+# delete it after a reinstall of edge-1).
+- name: edge-1
+  auth: password
+  deliver: {esp32: "https://edge-1.iot.renner.uno:8443"}
+  # No sml2mqtt/#: the SML meter reader is retired for good (owner,
+  # 2026-09-19; grid data comes from the E380 on the CAN bus).
+  acl: ["readwrite open3e/#"]
 # Shellies (REN-1017): one password account per device, pushed by the
 # controller through shelly-manager's per-device API. Name shelly-<id> =
-# shelly-manager device id. Same ACL as the legacy user `shellies`, which
-# keeps working until every device has moved. Gen2+ devices reboot once
-# when their password is pushed.
+# shelly-manager device id. ACL as the former shared user `shellies`
+# (removed in REN-1017 step 4). Gen2+ devices reboot once when their password
+# is pushed. A new Shelly needs its entry here first: shelly-manager's MQTT
+# template user no longer exists on the broker.
 - name: shelly-5               # Plus i4, the API test device of REN-929
   auth: password
   deliver: {shelly-manager: 5}
@@ -181,6 +195,10 @@
   auth: password
   deliver: {shelly-manager: 44}  # HiluX DS8 34b7da894604, Toilette (standalone, no mesh)
   acl: ["readwrite shellies/#", "write homeassistant/#"]
+- name: shelly-30
+  auth: password
+  deliver: {shelly-manager: 30}  # Plus 2PM b48a0a226c28 (reachable again, REN-1108)
+  acl: ["readwrite shellies/#", "write homeassistant/#"]
 # Sleeping H&Ts (REN-1107): awake only 8-13 s every 1-2 h, so the
 # controller pushes when the device publishes `online` on its wake topic
 # (shelly-manager topic prefix `shellies/<hostname>`), not in the 2-min loop.

kubernetes/apps/home-assistant/shelly-manager-deployment.yaml

@@ -61,7 +61,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: shelly-manager
-          image: gitea.renner.uno/k.renner/shelly-manager:build.1791385485 # {"$imagepolicy": "flux-system:shelly-manager"}
+          image: gitea.renner.uno/k.renner/shelly-manager:build.1791426752 # {"$imagepolicy": "flux-system:shelly-manager"}
           imagePullPolicy: IfNotPresent
           ports:
             - name: http

kubernetes/apps/immich/machine-learning.yaml

@@ -32,7 +32,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: immich-machine-learning
-          image: ghcr.io/immich-app/immich-machine-learning:v3.2.4 # {"$imagepolicy": "flux-system:immich-machine-learning"}
+          image: ghcr.io/immich-app/immich-machine-learning:v3.3.1 # {"$imagepolicy": "flux-system:immich-machine-learning"}
           ports:
             - name: http
               containerPort: 3003

kubernetes/apps/immich/server.yaml

@@ -87,7 +87,7 @@ spec:
               mountPath: /ca
       containers:
         - name: immich-server
-          image: ghcr.io/immich-app/immich-server:v3.2.4 # {"$imagepolicy": "flux-system:immich-server"}
+          image: ghcr.io/immich-app/immich-server:v3.3.1 # {"$imagepolicy": "flux-system:immich-server"}
           ports:
             - name: http
               containerPort: 3001

kubernetes/apps/monitoring-rules/prometheusrule-ceph.yaml

@@ -15,9 +15,6 @@ spec:
           # Per-check rather than ceph_health_status, so one permanently-active
           # check cannot mask every other Ceph warning.
           #
-          # AUTH_INSECURE_* is excluded: it cannot clear until the nodes run a
-          # kernel supporting aes256k over the CSI mount path (#527).
-          #
           # POOL_NO_REDUNDANCY is in scope. An unreplicated pool makes
           # `ceph osd ok-to-stop` refuse for every OSD, so it reports blocked
           # maintenance and not just data risk — do not exclude it for a pool
@@ -34,20 +31,14 @@ spec:
           # both episodes in the 30d to 2026-08-23 ran ~26h and cleared
           # untouched, the first ~24h after the last stall.
           #
-          # Both began inside the Velero restore-test sweep — a ~5h sustained
-          # restore that outruns the SLC cache on these QLC NVMe. The sweep
-          # runs monthly, 08:00-14:00Z on the 1st.
-          #
-          # Expected for the hardware, but not excludable:
-          # this is also the earliest signal of a genuinely failing drive, and
-          # all three are at 80-87% endurance used (see cephcluster.yaml).
-          expr: ceph_health_detail{name!~"AUTH_INSECURE_.+"} == 1
+          # Not excludable: it is also the earliest signal of a failing drive.
+          expr: ceph_health_detail == 1
           for: 6h
           labels:
             severity: warning
           annotations:
             summary: "Ceph health check {{ $labels.name }} active for 6h"
-            description: "Ceph health check {{ $labels.name }} has been active for six hours. Only AUTH_INSECURE_* is excluded (kernel-blocked, see #527). BLUESTORE_SLOW_OP_ALERT is sticky for 24h after the last stall and clears itself: check whether the stall fell inside the monthly Velero restore-test window (08:00-14:00Z on the 1st), which is expected on these QLC drives — one outside that window, or a repeat on the same OSD, means check that drive (#557). Detail: `kubectl -n rook-ceph exec deploy/rook-ceph-tools -- ceph health detail`."
+            description: "Ceph health check {{ $labels.name }} has been active for six hours. BLUESTORE_SLOW_OP_ALERT stays for 24h after the last stall even when latency is back to normal; find the OSD in the detail output and check that drive's SMART data (#557). Detail: `kubectl -n rook-ceph exec deploy/rook-ceph-tools -- ceph health detail`."
 
         - alert: CephPoolLostRedundancy
           # Names the pool, which POOL_NO_REDUNDANCY does not.

kubernetes/apps/monitoring/helmrelease-alloy-syslog.yaml

@@ -174,18 +174,18 @@ spec:
             forward_to = [loki.process.udm_cef.receiver]
           }
 
-          // CEF parser for UDM SIEM payload. One regex with named groups
-          // for header (vendor|product|product_version|sig_id|name|sev) and
-          // extension (UNIFIhost / UNIFIdeviceName / -Model / -Ip / -Mac /
-          // -Version / msg). Only deviceName may contain spaces — use a
-          // non-greedy match anchored to the literal next-key boundary.
-          // Keep the full raw line as the log content so unparsed senders
-          // (or future CEF format drift) still land queryably.
+          // CEF parser for UDM SIEM payload. The listener also receives the
+          // UDM's plain syslog (log_all_contents), which does not match and
+          // passes through unlabelled. CEF extension keys differ per event
+          // type, so the regex anchors only on the header
+          // (vendor|product|product_version|sig_id|name|sev), UNIFIcategory,
+          // UNIFIhost and the trailing msg. The full raw line stays the log
+          // content.
           loki.process "udm_cef" {
             forward_to = [loki.write.default.receiver]
 
             stage.regex {
-              expression = "CEF:\\d+\\|(?P<vendor>[^|]*)\\|(?P<product>[^|]*)\\|(?P<product_version>[^|]*)\\|(?P<signature_id>[^|]*)\\|(?P<event_name>[^|]*)\\|(?P<cef_severity>[^|]*)\\|UNIFIhost=(?P<unifi_host>\\S+) UNIFIdeviceName=(?P<device_name>.+?) UNIFIdeviceModel=(?P<device_model>\\S+) UNIFIdeviceIp=(?P<device_ip>\\S+) UNIFIdeviceMac=(?P<device_mac>\\S+) UNIFIdeviceVersion=(?P<device_version>\\S+) msg=(?P<msg>.+)$"
+              expression = "CEF:\\d+\\|(?P<vendor>[^|]*)\\|(?P<product>[^|]*)\\|(?P<product_version>[^|]*)\\|(?P<signature_id>[^|]*)\\|(?P<event_name>[^|]*)\\|(?P<cef_severity>[^|]*)\\|UNIFIcategory=(?P<category>.+?) UNIFIhost=(?P<unifi_host>.+?) \\S+=.* msg=(?P<msg>.+)$"
             }
 
             stage.labels {
@@ -194,8 +194,7 @@ spec:
                 product      = "product",
                 signature_id = "signature_id",
                 event_name   = "event_name",
-                device_model = "device_model",
-                host         = "device_name",
+                category     = "category",
               }
             }
           }

kubernetes/apps/music-assistant/deployment.yaml

@@ -55,7 +55,7 @@ spec:
         # stdlib only; Flux keeps the tag in lockstep via the shared image
         # policy) — no extra dependency.
         - name: reconcile-publish-ip
-          image: ghcr.io/music-assistant/server:2.10.5 # {"$imagepolicy": "flux-system:music-assistant"}
+          image: ghcr.io/music-assistant/server:2.10.6 # {"$imagepolicy": "flux-system:music-assistant"}
           command: ["/app/venv/bin/python", "/scripts/reconcile.py"]
           volumeMounts:
             - name: data
@@ -65,7 +65,7 @@ spec:
               readOnly: true
       containers:
         - name: music-assistant
-          image: ghcr.io/music-assistant/server:2.10.5 # {"$imagepolicy": "flux-system:music-assistant"}
+          image: ghcr.io/music-assistant/server:2.10.6 # {"$imagepolicy": "flux-system:music-assistant"}
           env:
             - name: LOG_LEVEL
               value: info

kubernetes/apps/paperclip/agent-kubectl-rbac.yaml

@@ -5,8 +5,9 @@
 # `paperclip-prometheus-read`. Atlas, Iris, Hestia and Argus get exactly what
 # they hold today through that shared account: built-in `view` cluster-wide
 # (no Secrets, no write verb) plus the `monitoring/paperclip-prometheus-read`
-# Role (see prometheus-read-rbac.yaml). Hermes gets only `get` on the five
-# token Secrets below, to issue and rotate the kubeconfigs.
+# Role (see prometheus-read-rbac.yaml). Hermes gets `get` on the five token
+# Secrets below, to issue and rotate the kubeconfigs, plus that Prometheus
+# Role (REN-1345).
 #
 # Token Secrets carry no data in git; kube-controller-manager fills
 # `data.token`. Flux applies server-side and does not own `data`, so it does
@@ -159,7 +160,9 @@ roleRef:
   # Existing Role in prometheus-read-rbac.yaml, unchanged.
   name: paperclip-prometheus-read
 # Subjects live in `paperclip`, the binding in `monitoring`: `namespace:` is
-# load-bearing.
+# load-bearing. agent-hermes is bound here too (REN-1345): its duty list reads
+# Prometheus, and this Role is `get` on three named read-only proxies only.
+# It does not get `view`.
 subjects:
   - kind: ServiceAccount
     name: agent-atlas
@@ -173,6 +176,9 @@ subjects:
   - kind: ServiceAccount
     name: agent-argus
     namespace: paperclip
+  - kind: ServiceAccount
+    name: agent-hermes
+    namespace: paperclip
 ---
 apiVersion: rbac.authorization.k8s.io/v1
 kind: Role

kubernetes/apps/paperclip/paperclip.yaml

@@ -34,7 +34,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: paperclip
-          image: gitea.renner.uno/konairius/paperclip:build.1791297080@sha256:0764e882521410d8ce8ed1359f8a1aa64eaa7746aa909653ef70050c239ca195 # {"$imagepolicy": "flux-system:paperclip"}
+          image: gitea.renner.uno/konairius/paperclip:build.1791487850@sha256:ff81da300e6c35581f34fad61a55da771b0e991d2fb2dcb624a0361263f01a37 # {"$imagepolicy": "flux-system:paperclip"}
           ports:
             - name: http
               containerPort: 3100

kubernetes/apps/paperless/paperless.yaml

@@ -50,11 +50,9 @@ data:
   PAPERLESS_TIKA_ENABLED: "1"
   PAPERLESS_TIKA_ENDPOINT: "http://tika:9998"
   PAPERLESS_TIKA_GOTENBERG_ENDPOINT: "http://gotenberg:3000"
-  # AI suggestions against the cluster's own LLM (kubernetes/apps/llama-server).
-  # Nothing leaves the cluster: both endpoints are ClusterIP Services, so
-  # document text is never sent to a third party and there is no API key to
-  # rotate — llama-server has no authentication, and the ai namespace's network
-  # policy is what restricts who may reach it.
+  # AI suggestions against Mistral AI's hosted API (OpenAI-compatible). Document
+  # text is sent to Mistral. The key is PAPERLESS_AI_LLM_API_KEY, from the
+  # paperless-secrets Secret (OpenBao apps/paperless, field minstral-token).
   #
   # CAVEAT, and it is a real one: paperless reads these from an
   # ApplicationConfiguration row in the database and falls back to the
@@ -63,20 +61,14 @@ data:
   # here — and leave those fields untouched in the UI.
   PAPERLESS_AI_ENABLED: "true"
   PAPERLESS_AI_LLM_BACKEND: "openai-like"
-  PAPERLESS_AI_LLM_ENDPOINT: "http://llama-server.ai.svc.cluster.local:8080/v1"
-  # Must match --alias in kubernetes/apps/llama-server/deployment.yaml. The
-  # server ignores the field on the wire, but paperless sends it and the value
-  # is what appears in its logs.
-  PAPERLESS_AI_LLM_MODEL: "qwen3.6-35b-a3b"
-  # ClusterIP addresses are private, and paperless blocks non-public endpoints
-  # unless this is set. Default is already true; explicit because the whole
-  # integration silently stops working if it ever flips.
+  PAPERLESS_AI_LLM_ENDPOINT: "https://api.mistral.ai/v1"
+  PAPERLESS_AI_LLM_MODEL: "mistral-small-2603"
+  # The embedding endpoint is the in-cluster llama-embed, a ClusterIP address,
+  # and paperless blocks non-public endpoints unless this is set. Default is
+  # already true; explicit because the embedding integration silently stops
+  # working if it ever flips.
   PAPERLESS_AI_LLM_ALLOW_INTERNAL_ENDPOINTS: "true"
-  # Under llama-server's own 16384, leaving room for the response.
   PAPERLESS_AI_LLM_CONTEXT_SIZE: "12288"
-  # The 120s default is too tight at ~11 tok/s: a classification is roughly
-  # 2-4k prompt tokens plus a second round trip for localisation.
-  PAPERLESS_AI_LLM_REQUEST_TIMEOUT: "300"
   # Matched against Django's settings.LANGUAGES, so the region is required —
   # "de" alone does not resolve. Without it the model returns German tags but
   # English document types, which was reproducible against this endpoint.
@@ -86,6 +78,9 @@ data:
   # primarily English archives — the better fit for a German corpus.
   PAPERLESS_AI_LLM_EMBEDDING_BACKEND: "openai-like"
   PAPERLESS_AI_LLM_EMBEDDING_ENDPOINT: "http://llama-embed.ai.svc.cluster.local:8080/v1"
+  # The embedding key falls back to PAPERLESS_AI_LLM_API_KEY when unset, which
+  # would send the Mistral token to llama-embed. llama-embed has no auth.
+  PAPERLESS_AI_LLM_EMBEDDING_API_KEY: "unused"
   # Must match --alias in kubernetes/apps/llama-server/embed.yaml. Changing the
   # embedding model invalidates every stored vector, so a swap means the LLM
   # index has to be rebuilt.
@@ -200,6 +195,11 @@ spec:
                 secretKeyRef:
                   name: paperless-secrets
                   key: secret-key
+            - name: PAPERLESS_AI_LLM_API_KEY
+              valueFrom:
+                secretKeyRef:
+                  name: paperless-secrets
+                  key: minstral-token
             - name: PAPERLESS_DBUSER
               valueFrom:
                 secretKeyRef:

kubernetes/apps/trmnl/terminus.yaml

@@ -134,7 +134,7 @@ spec:
         # is a device-bricking class of risk. Bumps are a reviewed, manual
         # act — see kubernetes/infrastructure/image-automation/README.md.
         - name: terminus
-          image: ghcr.io/usetrmnl/terminus:0.76.0 # {"$imagepolicy": "flux-system:terminus"}
+          image: ghcr.io/usetrmnl/terminus:0.77.0 # {"$imagepolicy": "flux-system:terminus"}
           ports:
             - name: http
               containerPort: 2345
@@ -197,7 +197,7 @@ spec:
             capabilities:
               drop: ["ALL"]
         - name: sidekiq
-          image: ghcr.io/usetrmnl/terminus:0.76.0 # {"$imagepolicy": "flux-system:terminus"}
+          image: ghcr.io/usetrmnl/terminus:0.77.0 # {"$imagepolicy": "flux-system:terminus"}
           command: ["bundle", "exec", "sidekiq", "-r", "./config/sidekiq.rb"]
           envFrom:
             - configMapRef:

kubernetes/apps/woodpecker/agent.yaml

@@ -34,7 +34,7 @@ spec:
           # Image automation, range 3.x (see image-automation/woodpecker.yaml).
           # MUST stay version-matched with woodpecker-server (gRPC parity) — both
           # track the same range/filter so they bump together on each release.
-          image: woodpeckerci/woodpecker-agent:v3.18.1 # {"$imagepolicy": "flux-system:woodpecker-agent"}
+          image: woodpeckerci/woodpecker-agent:v3.19.0 # {"$imagepolicy": "flux-system:woodpecker-agent"}
           env:
             - name: WOODPECKER_SERVER
               value: woodpecker.woodpecker.svc.cluster.local:9000 # in-cluster gRPC, replaces LXC :9000

kubernetes/apps/woodpecker/server.yaml

@@ -40,7 +40,7 @@ spec:
           # minor + patch auto-update within 3.x; only the 4.0 major is held for
           # a reviewed bump. Safe now the DB is postgres (the old sqlite-surprise
           # -bump hazard is gone). Stays in lockstep with the agent.
-          image: woodpeckerci/woodpecker-server:v3.18.1 # {"$imagepolicy": "flux-system:woodpecker-server"}
+          image: woodpeckerci/woodpecker-server:v3.19.0 # {"$imagepolicy": "flux-system:woodpecker-server"}
           env:
             - name: WOODPECKER_HOST
               value: https://ci.renner.uno

kubernetes/clusters/homelab/gitea-mcp.yaml

@@ -0,0 +1,18 @@
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: gitea-mcp
+  namespace: flux-system
+spec:
+  interval: 10m
+  retryInterval: 2m
+  timeout: 5m
+  sourceRef:
+    kind: GitRepository
+    name: flux-system
+  path: ./kubernetes/apps/gitea-mcp
+  prune: true
+  wait: true
+  dependsOn:
+    - name: infrastructure
+    - name: infrastructure-crds

kubernetes/infrastructure/flux-notifications/provider.yaml

@@ -4,7 +4,9 @@ metadata:
   name: alertmanager
   namespace: flux-system
 spec:
-  # The notification controller appends `/api/v2/alerts/` itself, so
-  # spec.address is the bare base URL with trailing slash.
+  # The notification controller POSTs to spec.address verbatim (it does
+  # not append a path), so the address must be the full Alertmanager v2
+  # alerts endpoint. The bare base URL is answered with 405 Method Not
+  # Allowed and every Flux notification is dropped.
   type: alertmanager
-  address: http://kube-prometheus-stack-alertmanager.monitoring.svc.cluster.local:9093/
+  address: http://kube-prometheus-stack-alertmanager.monitoring.svc.cluster.local:9093/api/v2/alerts/

kubernetes/infrastructure/image-automation/backup-verify.yaml

@@ -0,0 +1,23 @@
+apiVersion: image.toolkit.fluxcd.io/v1
+kind: ImageRepository
+metadata:
+  name: backup-verify
+  namespace: flux-system
+spec:
+  image: gitea.renner.uno/gitea_admin/ci-backup-verify
+  interval: 30m
+---
+# build-ci-images.yml tags each build YYYY-MM-DD; newest date wins.
+apiVersion: image.toolkit.fluxcd.io/v1
+kind: ImagePolicy
+metadata:
+  name: backup-verify
+  namespace: flux-system
+spec:
+  imageRepositoryRef:
+    name: backup-verify
+  filterTags:
+    pattern: '^\d{4}-\d{2}-\d{2}$'
+  policy:
+    alphabetical:
+      order: asc

kubernetes/infrastructure/image-automation/gitea-mcp.yaml

@@ -0,0 +1,20 @@
+apiVersion: image.toolkit.fluxcd.io/v1
+kind: ImageRepository
+metadata:
+  name: gitea-mcp
+  namespace: flux-system
+spec:
+  image: docker.gitea.com/gitea-mcp-server
+  interval: 1h
+---
+apiVersion: image.toolkit.fluxcd.io/v1
+kind: ImagePolicy
+metadata:
+  name: gitea-mcp
+  namespace: flux-system
+spec:
+  imageRepositoryRef:
+    name: gitea-mcp
+  policy:
+    semver:
+      range: ">=1.8.1"

kubernetes/infrastructure/image-automation/kustomization.yaml

@@ -3,9 +3,11 @@ kind: Kustomization
 resources:
   - update-automation.yaml
   - audiobookshelf.yaml
+  - backup-verify.yaml
   - ceph.yaml
   - cnpg-barman-plugin.yaml
   - gatus.yaml
+  - gitea-mcp.yaml
   - gotenberg.yaml
   - home-assistant.yaml
   - immich.yaml

kubernetes/infrastructure/namespaces/namespaces.yaml

@@ -198,6 +198,12 @@ kind: Namespace
 metadata:
   name: gitea
 ---
+# Gitea MCP server. Declared here so it exists before infrastructure-crds applies its CNPs.
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: gitea-mcp
+---
 # netbird-service-sync, moving out of `openbao` (issue #876). Declared here like
 # `woodpecker` above, so it exists before infrastructure-crds applies its
 # CiliumNetworkPolicies. No pod-security labels: the cluster default applies.

kubernetes/infrastructure/netbird-service-sync/deployment.yaml

@@ -1,5 +1,6 @@
 # Reconciles NetBird reverse-proxy services from Ingresses that carry
-# dns.renner.uno/public: one TLS-passthrough service per host on :443,
+# dns.renner.uno/public or netbird.renner.uno/public (proxy only, LAN DNS
+# untouched): one TLS-passthrough service per host on :443,
 # targeting Traefik's ClusterIP through a subnet resource over the service
 # CIDR (ci/images/netbird-service-sync/controller.py).
 #
@@ -80,7 +81,7 @@ spec:
           # image directory (branch and master alike) and the registry keeps
           # only the newest manifest per tag, so the digest must come from
           # the MASTER build of the code change.
-          image: gitea.renner.uno/gitea_admin/netbird-service-sync:2026-09-23@sha256:64f6057c508640e1dbc50457dc26e9b2de058a111fd46ca096021d7444b5bbff
+          image: gitea.renner.uno/gitea_admin/netbird-service-sync:2026-10-11@sha256:2e8c5e45cffd515cc93e04dc9fd47403a7910368fc7516e94c78d8f53dcd5272
           securityContext:
             allowPrivilegeEscalation: false
             readOnlyRootFilesystem: true

kubernetes/infrastructure/network-policies/gitea-mcp-ns.yaml

@@ -0,0 +1,82 @@
+---
+# Baseline policy for the `gitea-mcp` namespace.
+apiVersion: cilium.io/v2
+kind: CiliumNetworkPolicy
+metadata:
+  name: default-deny
+  namespace: gitea-mcp
+spec:
+  endpointSelector: {}
+  ingress:
+    - fromEndpoints:
+        - matchLabels:
+            "k8s:io.kubernetes.pod.namespace": gitea-mcp
+    - fromEndpoints:
+        - matchLabels:
+            "k8s:io.kubernetes.pod.namespace": monitoring
+    - fromEntities:
+        - host
+        - remote-node
+    - fromEndpoints:
+        - matchExpressions:
+            - key: io.kubernetes.pod.namespace
+              operator: Exists
+      icmps:
+        - fields:
+            - { type: 0,   family: IPv4 }
+            - { type: 3,   family: IPv4 }
+            - { type: 8,   family: IPv4 }
+            - { type: 11,  family: IPv4 }
+            - { type: 12,  family: IPv4 }
+            - { type: 1,   family: IPv6 }
+            - { type: 2,   family: IPv6 }
+            - { type: 3,   family: IPv6 }
+            - { type: 4,   family: IPv6 }
+            - { type: 128, family: IPv6 }
+            - { type: 129, family: IPv6 }
+            - { type: 133, family: IPv6 }
+            - { type: 134, family: IPv6 }
+            - { type: 135, family: IPv6 }
+            - { type: 136, family: IPv6 }
+            - { type: 143, family: IPv6 }
+  egress:
+    - toEndpoints:
+        - matchLabels:
+            "k8s:io.kubernetes.pod.namespace": gitea-mcp
+    - toEndpoints:
+        - matchLabels:
+            "k8s:io.kubernetes.pod.namespace": kube-system
+            k8s-app: kube-dns
+      toPorts:
+        - ports:
+            - port: "53"
+              protocol: UDP
+            - port: "53"
+              protocol: TCP
+    - toEndpoints:
+        - matchLabels:
+            "k8s:io.kubernetes.pod.namespace": gitea
+            app.kubernetes.io/name: gitea
+      toPorts:
+        - ports:
+            - port: "3000"
+              protocol: TCP
+---
+apiVersion: cilium.io/v2
+kind: CiliumNetworkPolicy
+metadata:
+  name: gitea-mcp-allow-traefik
+  namespace: gitea-mcp
+spec:
+  endpointSelector:
+    matchLabels:
+      app.kubernetes.io/name: gitea-mcp
+  ingress:
+    - fromEndpoints:
+        - matchLabels:
+            "k8s:io.kubernetes.pod.namespace": ingress
+            app.kubernetes.io/name: traefik
+      toPorts:
+        - ports:
+            - port: "8080"
+              protocol: TCP

kubernetes/infrastructure/network-policies/kustomization.yaml

@@ -25,6 +25,7 @@ resources:
   - woodpecker-ci-ns.yaml
   - woodpecker-ns.yaml
   - gitea-ns.yaml
+  - gitea-mcp-ns.yaml
   - netbird-service-sync-ns.yaml
   - trmnl-ns.yaml
   - matrix-ns.yaml

kubernetes/infrastructure/network-policies/monitoring-ns.yaml

@@ -50,17 +50,6 @@ spec:
         - ports:
             - port: "9090"
               protocol: TCP
-    # velero restore-test Job: its capacity gate reads OSD usage from
-    # Prometheus :9090 (restore-test.sh, preflight_capacity). Scoped to the
-    # Job's pod label; the velero namespace has no egress policy.
-    - fromEndpoints:
-        - matchLabels:
-            "k8s:io.kubernetes.pod.namespace": velero
-            app.kubernetes.io/name: restore-test
-      toPorts:
-        - ports:
-            - port: "9090"
-              protocol: TCP
     # Kubelet probes + control-plane (PrometheusRule/ServiceMonitor admission
     # webhooks via kube-prometheus-stack-operator are called by kube-apiserver).
     # Also covers external alloy-syslog traffic — ETP=Cluster on the LB SNATs

kubernetes/infrastructure/network-policies/velero-ns.yaml

@@ -6,7 +6,7 @@ metadata:
 spec:
   endpointSelector: {}
   ingress:
-    # Intra-namespace — velero server ↔ node-agent ↔ restore-test job.
+    # Intra-namespace — velero server ↔ node-agent.
     - fromEndpoints:
         - matchLabels:
             "k8s:io.kubernetes.pod.namespace": velero
@@ -42,3 +42,44 @@ spec:
             - { type: 135, family: IPv6 }
             - { type: 136, family: IPv6 }
             - { type: 143, family: IPv6 }
+---
+# backup-verify CronJob: kube-apiserver, DNS, Hetzner Cloud API, SSH to its VM.
+apiVersion: cilium.io/v2
+kind: CiliumNetworkPolicy
+metadata:
+  name: backup-verify-egress
+  namespace: velero
+spec:
+  endpointSelector:
+    matchLabels:
+      app.kubernetes.io/name: backup-verify
+  egress:
+    - toEntities:
+        - kube-apiserver
+        - host
+        - remote-node
+    - toEndpoints:
+        - matchLabels:
+            "k8s:io.kubernetes.pod.namespace": kube-system
+            k8s-app: kube-dns
+      toPorts:
+        - ports:
+            - port: "53"
+              protocol: UDP
+            - port: "53"
+              protocol: TCP
+          rules:
+            dns:
+              - matchPattern: "*"
+    - toFQDNs:
+        - matchName: "api.hetzner.cloud"
+      toPorts:
+        - ports:
+            - port: "443"
+              protocol: TCP
+    - toEntities:
+        - world
+      toPorts:
+        - ports:
+            - port: "22"
+              protocol: TCP

kubernetes/infrastructure/openbao/policies/rotator-mosquitto-open3e-int.hcl

@@ -1,30 +0,0 @@
-# OpenBao policy: rotator-mosquitto-open3e-int
-#
-# Least-privilege policy for the mosquitto `open3e-int` broker-credential
-# rotation CronJob (kubernetes auth role `rotator-mosquitto-open3e-int`).
-# Per-secret isolation, same template as rotator-mosquitto-health.
-#
-# NOT applied by Flux. Apply ONCE with an admin token:
-#
-#   bao policy write rotator-mosquitto-open3e-int \
-#     kubernetes/infrastructure/openbao/policies/rotator-mosquitto-open3e-int.hcl
-#
-#   bao write auth/kubernetes/role/rotator-mosquitto-open3e-int \
-#     bound_service_account_names=mosquitto-open3e-int-secret-rotator \
-#     bound_service_account_namespaces=openbao \
-#     policies=rotator-mosquitto-open3e-int ttl=15m
-#
-# Do NOT set token_no_default_policy=true (kv-v2 patch preflight needs default).
-#
-# BOOTSTRAP: `random` mode rotates an existing field and never creates one.
-# Seed the path once with a `password` field before the first rotation:
-#
-#   bao kv put -mount=homelab apps/home-assistant/mosquitto-open3e-int-credentials \
-#     password=<generated>
-#
-# The consumer is the open3e-esp32 gateway on the heat pump's internal CAN
-# (NVS key mq_pass); a rotation takes effect on the device only after its
-# MQTT settings are updated (web UI or NVS image).
-path "homelab/data/apps/home-assistant/mosquitto-open3e-int-credentials" {
-  capabilities = ["read", "patch"]
-}

kubernetes/infrastructure/openbao/rotation/kustomization.yaml

@@ -48,7 +48,6 @@ resources:
   - review-bot.yaml
   - claude-oauth.yaml
   - mosquitto-health.yaml
-  - mosquitto-open3e-int.yaml
 # NOT ROTATED, deliberately — recorded here because the whole point of this
 # directory is that unrotated credentials should be a visible choice:
 #

kubernetes/infrastructure/openbao/rotation/mosquitto-open3e-int.yaml

@@ -1,83 +0,0 @@
----
-# Class-A rotation of the mosquitto `open3e-int` broker credential: the
-# open3e-esp32 gateway on the Vitocal internal CAN (ECU 0x6e0). Same
-# rotator -> OpenBao -> ESO -> Reloader chain as mosquitto-health.yaml.
-#
-# The consumer is an embedded device: after a rotation its MQTT password must
-# be updated on the device (web UI Einstellungen, or an NVS image over USB).
-#
-# ON-DEMAND: kubectl -n openbao create job --from=cronjob/mosquitto-open3e-int-secret-rotate mosquitto-open3e-int-secret-rotate-now
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: mosquitto-open3e-int-secret-rotator
-  namespace: openbao
-  labels:
-    app.kubernetes.io/name: mosquitto
-    app.kubernetes.io/component: secret-rotator
----
-apiVersion: batch/v1
-kind: CronJob
-metadata:
-  name: mosquitto-open3e-int-secret-rotate
-  namespace: openbao
-  labels:
-    app.kubernetes.io/name: mosquitto
-    app.kubernetes.io/component: secret-rotator
-spec:
-  # Quarterly, own month offset (paperless: 1,4,7,10; health: 2,5,8,11).
-  schedule: "0 4 1 3,6,9,12 *"
-  # Suspended (REN-802): the ESP32 only gets its password by hand, so a
-  # rotation would take the gateway offline. MQTT credentials move to the
-  # git-defined account register; this rotator is removed in that cleanup.
-  suspend: true
-  timeZone: Europe/Berlin
-  concurrencyPolicy: Forbid
-  successfulJobsHistoryLimit: 2
-  failedJobsHistoryLimit: 5
-  startingDeadlineSeconds: 3600
-  jobTemplate:
-    spec:
-      backoffLimit: 2
-      activeDeadlineSeconds: 300
-      ttlSecondsAfterFinished: 259200 # 3 d
-      template:
-        metadata:
-          labels:
-            app.kubernetes.io/name: mosquitto
-            app.kubernetes.io/component: secret-rotator
-        spec:
-          serviceAccountName: mosquitto-open3e-int-secret-rotator
-          restartPolicy: Never
-          securityContext:
-            runAsNonRoot: true
-            runAsUser: 65534
-            runAsGroup: 65534
-            seccompProfile:
-              type: RuntimeDefault
-          containers:
-            - name: rotate
-              image: gitea.renner.uno/gitea_admin/secret-rotator:2026-07-30
-              args: ["random"]
-              securityContext:
-                allowPrivilegeEscalation: false
-                readOnlyRootFilesystem: true
-                capabilities:
-                  drop: ["ALL"]
-              env:
-                - name: BAO_ADDR
-                  value: http://openbao.openbao.svc.cluster.local:8200
-                - name: BAO_ROLE
-                  value: rotator-mosquitto-open3e-int
-                - name: BAO_PATH
-                  value: homelab/apps/home-assistant/mosquitto-open3e-int-credentials
-                - name: BAO_FIELDS
-                  value: "password"
-                - name: RANDOM_BYTES
-                  value: "32"
-              resources:
-                requests:
-                  cpu: 25m
-                  memory: 16Mi
-                limits:
-                  memory: 48Mi

kubernetes/infrastructure/post-crds/hcloud-backup-verify-externalsecret.yaml

@@ -0,0 +1,15 @@
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: hcloud-backup-verify
+  namespace: velero
+spec:
+  refreshInterval: 1h
+  secretStoreRef:
+    kind: ClusterSecretStore
+    name: openbao
+  target:
+    name: hcloud-backup-verify
+  dataFrom:
+    - extract:
+        key: infrastructure/hcloud-backup-verify

kubernetes/infrastructure/post-crds/kustomization.yaml

@@ -25,6 +25,7 @@ resources:
   - netbird-ingress-externalsecret.yaml
   - velero-externalsecret.yaml
   - velero-hetzner-creds-externalsecret.yaml
+  - hcloud-backup-verify-externalsecret.yaml
   # traefik.io CRDs, same reasoning — installed by the Traefik HelmRelease in
   # infrastructure. Traefik is deliberately absent from that Kustomization's
   # healthChecks, so this KS may dry-run before the chart lands; it retries on

kubernetes/infrastructure/post-crds/openbao-clustersecretstore.yaml

@@ -22,6 +22,7 @@ spec:
         - crowdsec
         - evcc
         - flux-system # flux-system-git-auth: syncs the rotated flux gitea PAT into Flux's git secret
+        - gitea # gitea-package-retention token (apps/gitea/package-retention.yaml, REN-1203)
         - home-assistant
         - immich
         - influxdb

kubernetes/infrastructure/velero/backup-verify-cronjob.yaml

@@ -0,0 +1,74 @@
+apiVersion: batch/v1
+kind: CronJob
+metadata:
+  name: backup-verify
+  namespace: velero
+spec:
+  schedule: "0 8 1 * *"
+  timeZone: Etc/UTC
+  suspend: false
+  concurrencyPolicy: Forbid
+  successfulJobsHistoryLimit: 2
+  failedJobsHistoryLimit: 3
+  startingDeadlineSeconds: 3600
+  jobTemplate:
+    spec:
+      backoffLimit: 0
+      activeDeadlineSeconds: 14400
+      ttlSecondsAfterFinished: 3456000
+      template:
+        metadata:
+          labels:
+            app.kubernetes.io/name: backup-verify
+        spec:
+          serviceAccountName: backup-verify
+          restartPolicy: Never
+          terminationGracePeriodSeconds: 120
+          securityContext:
+            runAsNonRoot: true
+            runAsUser: 65532
+            runAsGroup: 65532
+            seccompProfile:
+              type: RuntimeDefault
+          containers:
+            - name: backup-verify
+              image: gitea.renner.uno/gitea_admin/ci-backup-verify:2026-10-10 # {"$imagepolicy": "flux-system:backup-verify"}
+              command: ["bash", "/script/backup-verify.sh"]
+              env:
+                - name: HOME
+                  value: /work
+              securityContext:
+                allowPrivilegeEscalation: false
+                readOnlyRootFilesystem: true
+                capabilities:
+                  drop: ["ALL"]
+              volumeMounts:
+                - { name: script, mountPath: /script, readOnly: true }
+                - { name: work, mountPath: /work }
+                - { name: hcloud, mountPath: /secrets/hcloud, readOnly: true }
+                - { name: s3, mountPath: /secrets/s3, readOnly: true }
+                - { name: repo, mountPath: /secrets/repo, readOnly: true }
+              resources:
+                requests:
+                  cpu: 20m
+                  memory: 64Mi
+                limits:
+                  memory: 384Mi
+          volumes:
+            - name: script
+              configMap:
+                name: backup-verify-scripts
+                defaultMode: 0755
+            - name: work
+              emptyDir:
+                medium: Memory
+                sizeLimit: 128Mi
+            - name: hcloud
+              secret:
+                secretName: hcloud-backup-verify
+            - name: s3
+              secret:
+                secretName: cloud-credentials-hetzner
+            - name: repo
+              secret:
+                secretName: velero-repo-credentials

kubernetes/infrastructure/velero/backup-verify-rbac.yaml

@@ -0,0 +1,29 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: backup-verify
+  namespace: velero
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: backup-verify
+  namespace: velero
+rules:
+  - apiGroups: ["velero.io"]
+    resources: ["schedules", "backups", "datauploads"]
+    verbs: ["get", "list"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: backup-verify
+  namespace: velero
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: backup-verify
+subjects:
+  - kind: ServiceAccount
+    name: backup-verify
+    namespace: velero

kubernetes/infrastructure/velero/backup-verify/backup-verify.sh

@@ -0,0 +1,180 @@
+#!/usr/bin/env bash
+# Monthly backup verification: plan from Velero, verify on a throwaway
+# Hetzner Cloud VM, summarize, always delete the VM.
+set -euo pipefail
+
+SCRIPT_DIR=${SCRIPT_DIR:-/script}
+WORK=${WORK:-/work}
+LABEL=managed-by=backup-verify
+LOCATION=${LOCATION:-fsn1}
+SERVER_IMAGE=${SERVER_IMAGE:-debian-12}
+SERVER_TYPES=${SERVER_TYPES:-cx23 cax11}
+ONLY_NAMESPACES=${ONLY_NAMESPACES:-}
+SSH_WAIT_S=${SSH_WAIT_S:-600}
+HCLOUD_TOKEN_FILE=${HCLOUD_TOKEN_FILE:-/secrets/hcloud/token}
+S3_CREDENTIALS_FILE=${S3_CREDENTIALS_FILE:-/secrets/s3/cloud}
+REPO_PASSWORD_FILE=${REPO_PASSWORD_FILE:-/secrets/repo/repository-password}
+RUN_ID=${RUN_ID:-$(date +%s)}
+NAME="backup-verify-$RUN_ID"
+SSH_OPTS=()
+VM_ADDR=""
+SERVER_TYPE=none
+START_S=$(date +%s)
+
+log() { printf '[%s] %s\n' "$(date -u +%H:%M:%S)" "$*" >&2; }
+
+delete_kind() {
+  local id
+  for id in $(hcloud "$1" list -l "$LABEL" -o noheader -o columns=id); do
+    log "deleting $1 $id"
+    hcloud "$1" delete "$id" >&2 || log "WARN: could not delete $1 $id"
+  done
+}
+
+sweep() {
+  local kind
+  for kind in server firewall ssh-key; do delete_kind "$kind"; done
+}
+
+build_plan() {
+  local only
+  only=$(jq -cn --arg s "$ONLY_NAMESPACES" '$s | split(",") | map(select(. != ""))')
+  kubectl -n velero get schedules.velero.io -l app.kubernetes.io/part-of=homelab-backup -o json > "$WORK/schedules.json"
+  kubectl -n velero get backups.velero.io -o json > "$WORK/backups.json"
+  kubectl -n velero get datauploads.velero.io -o json > "$WORK/datauploads.json"
+  jq -n --slurpfile s "$WORK/schedules.json" --slurpfile b "$WORK/backups.json" --slurpfile d "$WORK/datauploads.json" \
+     '{schedules: $s[0].items, backups: $b[0].items, datauploads: $d[0].items}' \
+    | jq --argjson only "$only" -f "$SCRIPT_DIR/plan.jq" \
+    | jq --arg f "${FORGE_SNAPSHOT_ID:-}" \
+         'if $f == "" then . else map(if .status == "VERIFY" then .snapshotID = $f else . end) end' \
+    > "$WORK/plan.json"
+  if [ -n "${FORGE_SNAPSHOT_ID:-}" ]; then log "NEGATIVE TEST: every snapshotID replaced by $FORGE_SNAPSHOT_ID"; fi
+  log "plan: $(jq -r 'group_by(.status) | map("\(.[0].status)=\(length)") | join(" ")' "$WORK/plan.json")"
+}
+
+# cloud-config as JSON (a YAML subset), so jq does the escaping.
+render_user_data() {
+  printf '#cloud-config\n'
+  jq -n --rawfile priv "$WORK/host_key" --arg pub "$(cat "$WORK/host_key.pub")" '{
+    ssh_pwauth: false,
+    ssh_deletekeys: true,
+    ssh_genkeytypes: [],
+    ssh_keys: {ed25519_private: $priv, ed25519_public: $pub},
+    packages: ["jq", "curl", "ca-certificates"],
+    runcmd: [
+      "mkdir -p /run/verify && mount -t tmpfs -o size=1500m,mode=0700 tmpfs /run/verify",
+      ["shutdown", "-h", "+240"]
+    ]
+  }'
+}
+
+create_vm() {
+  local type
+  ssh-keygen -q -t ed25519 -N '' -C "$NAME" -f "$WORK/client_key"
+  ssh-keygen -q -t ed25519 -N '' -C "$NAME-host" -f "$WORK/host_key"
+  render_user_data > "$WORK/user-data.yaml"
+  hcloud ssh-key create --name "$NAME" --public-key-from-file "$WORK/client_key.pub" --label "$LABEL" >&2
+  hcloud firewall create --name "$NAME" --label "$LABEL" >&2
+  hcloud firewall add-rule "$NAME" --direction in --protocol tcp --port 22 --source-ips 0.0.0.0/0 --source-ips ::/0 >&2
+  for type in $SERVER_TYPES; do
+    if hcloud server create --name "$NAME" --type "$type" --image "$SERVER_IMAGE" --location "$LOCATION" \
+         --ssh-key "$NAME" --firewall "$NAME" --label "$LABEL" \
+         --user-data-from-file "$WORK/user-data.yaml" -o json > "$WORK/server.json"; then
+      log "server $NAME created (type $type)"
+      SERVER_TYPE=$type
+      return 0
+    fi
+    log "server type $type not available"
+    # A create that timed out may still have left the server behind under $NAME.
+    delete_kind server
+  done
+  return 1
+}
+
+wait_ssh() {
+  local v4 v6 hostkey addr deadline rc
+  v6=$(hcloud server ip -6 "$NAME")
+  v4=$(hcloud server ip "$NAME")
+  hostkey=$(cut -d' ' -f1,2 "$WORK/host_key.pub")
+  printf '%s %s\n%s %s\n' "$v6" "$hostkey" "$v4" "$hostkey" > "$WORK/known_hosts"
+  SSH_OPTS=(-i "$WORK/client_key" -o "UserKnownHostsFile=$WORK/known_hosts" -o StrictHostKeyChecking=yes
+            -o ConnectTimeout=10 -o BatchMode=yes -o ServerAliveInterval=30)
+  deadline=$(( $(date +%s) + SSH_WAIT_S ))
+  while [ "$(date +%s)" -lt "$deadline" ]; do
+    for addr in "$v6" "$v4"; do
+      # Background + wait so a TERM is handled while cloud-init is still running.
+      ssh "${SSH_OPTS[@]}" "root@$addr" 'cloud-init status --wait > /run/cloud-init-wait.log' < /dev/null &
+      if wait $!; then
+        VM_ADDR=$addr
+        log "ssh ready via $addr"
+        return 0
+      else
+        rc=$?
+      fi
+      # 255 is an ssh connection error; anything else is cloud-init itself failing.
+      if [ "$rc" -ne 255 ]; then
+        log "cloud-init failed on $addr (exit $rc):"
+        ssh "${SSH_OPTS[@]}" "root@$addr" 'cloud-init status --long' < /dev/null >&2 || true
+        return 1
+      fi
+    done
+    sleep 10
+  done
+  log "ssh not reachable within ${SSH_WAIT_S}s"
+  return 1
+}
+
+secrets() {
+  awk -F' *= *' '/^aws_access_key_id/ {print "AWS_ACCESS_KEY_ID=" $2} /^aws_secret_access_key/ {print "AWS_SECRET_ACCESS_KEY=" $2}' "$S3_CREDENTIALS_FILE"
+  printf 'KOPIA_PASSWORD=%s\n' "$(cat "$REPO_PASSWORD_FILE")"
+}
+
+push() { ssh "${SSH_OPTS[@]}" "root@$VM_ADDR" "cat > /run/verify/$2" < "$1"; }
+
+run_vm() {
+  jq '[.[] | select(.status == "VERIFY")]' "$WORK/plan.json" > "$WORK/vm-plan.json"
+  if ! { ssh "${SSH_OPTS[@]}" "root@$VM_ADDR" 'mkdir -p /run/verify' < /dev/null \
+         && push "$WORK/vm-plan.json" plan.json \
+         && push "$SCRIPT_DIR/check.jq" check.jq \
+         && push "$SCRIPT_DIR/vm-verify.sh" vm-verify.sh; }; then
+    log "could not stage files on the VM; every VERIFY entry will report no result"
+    return 0
+  fi
+  # Background + wait: bash runs the TERM trap during `wait`, not during a foreground child.
+  ( secrets | ssh "${SSH_OPTS[@]}" "root@$VM_ADDR" 'bash /run/verify/vm-verify.sh /run/verify/plan.json' \
+      | tee "$WORK/vm.out" >&2 ) &
+  wait $! || log "vm-verify exited non-zero"
+}
+
+summarize() {
+  { grep $'^RESULT\t' "$WORK/vm.out" || true; } \
+    | jq -R 'split("\t") | {status: .[1], namespace: .[2], pvc: .[3], snapshotID: .[4], reason: .[5]}' \
+    | jq -s . > "$WORK/results.json"
+  jq -n --slurpfile p "$WORK/plan.json" --slurpfile r "$WORK/results.json" '{plan: $p[0], results: $r[0]}' \
+    | jq -f "$SCRIPT_DIR/summary.jq" > "$WORK/summary.json"
+  jq -r '.entries[] | "\(.status)\t\(.schedule // "-")\t\(.backup // "-")\t\(.namespace // "-")/\(.pvc // "-")\tsnapshot=\(.snapshotID // "-")\t\(.reason // "")"' "$WORK/summary.json"
+  jq -r '"PASS=\(.pass) FAIL=\(.fail) SKIP=\(.skip)"' "$WORK/summary.json"
+  printf 'elapsed=%ss server_type=%s\n' "$(( $(date +%s) - START_S ))" "$SERVER_TYPE"
+  [ "$(jq .fail "$WORK/summary.json")" -eq 0 ]
+}
+
+main() {
+  mkdir -p "$WORK"
+  : > "$WORK/vm.out"
+  HCLOUD_TOKEN=$(cat "$HCLOUD_TOKEN_FILE")
+  export HCLOUD_TOKEN
+  trap sweep EXIT
+  trap 'log "TERM received, tearing down"; exit 143' TERM INT
+  sweep
+  build_plan
+  if [ "$(jq '[.[] | select(.status == "VERIFY")] | length' "$WORK/plan.json")" -gt 0 ]; then
+    if create_vm && wait_ssh; then
+      run_vm
+    else
+      log "VM setup failed; every VERIFY entry will report no result"
+    fi
+  fi
+  summarize
+}
+
+if [ "${BASH_SOURCE[0]}" = "$0" ]; then main "$@"; fi

kubernetes/infrastructure/velero/backup-verify/check.jq

@@ -0,0 +1,21 @@
+# kopia `snapshot list --json` -> verdict per $plan entry (one namespace).
+(map({key: .id, value: .}) | from_entries) as $m
+| [ $plan[] as $e
+    | $m[$e.snapshotID] as $s
+    | if $s == null then
+        $e + {status: "FAIL", reason: "snapshot not in repository"}
+      else
+        ($s.stats.totalSize // $s.rootEntry.summ.size) as $kb
+        | $e + {rootID: ($s.rootEntry.obj // ""), kopiaBytes: $kb}
+        | if ($s.incomplete // "") != "" then
+            . + {status: "FAIL", reason: "snapshot incomplete: \($s.incomplete)"}
+          elif ($s.rootEntry.summ.numFailed // 0) > 0 then
+            . + {status: "FAIL", reason: "\($s.rootEntry.summ.numFailed) entries failed at backup time"}
+          elif .rootID == "" then
+            . + {status: "FAIL", reason: "snapshot has no root object"}
+          elif $kb != $e.totalBytes then
+            . + {status: "FAIL", reason: "size mismatch kopia=\($kb) velero=\($e.totalBytes)"}
+          else
+            . + {status: "VERIFY"}
+          end
+      end ]

kubernetes/infrastructure/velero/backup-verify/plan.jq

@@ -0,0 +1,37 @@
+# Velero objects -> plan entries. Input: {schedules, backups, datauploads}
+# (kubectl .items). $only: namespaces to keep; [] keeps all.
+def finished: . as $p | ["Completed", "PartiallyFailed", "Failed", "FailedValidation"] | index($p) != null;
+
+.backups as $backups
+| .datauploads as $dus
+| [ .schedules | sort_by(.metadata.name)[]
+    | .metadata.name as $s
+    | ([ $backups[]
+         | select(.metadata.labels["velero.io/schedule-name"] == $s)
+         | select((.status.phase // "") | finished) ]
+       | sort_by(.metadata.creationTimestamp) | last) as $b
+    | if $b == null then
+        {schedule: $s, status: "FAIL", reason: "no finished backup"}
+      elif $b.status.phase != "Completed" then
+        {schedule: $s, backup: $b.metadata.name, status: "FAIL",
+         reason: "latest finished backup phase=\($b.status.phase)"}
+      else
+        [ $dus[] | select(.metadata.labels["velero.io/backup-name"] == $b.metadata.name) ] as $mine
+        | if ($mine | length) == 0 then
+            {schedule: $s, backup: $b.metadata.name, status: "SKIP", reason: "no DataUploads"}
+          else
+            $mine | sort_by(.spec.sourceNamespace, .spec.sourcePVC)[]
+            | {schedule: $s, backup: $b.metadata.name,
+               namespace: .spec.sourceNamespace, pvc: .spec.sourcePVC,
+               snapshotID: (.status.snapshotID // ""),
+               totalBytes: (.status.progress.totalBytes // 0)}
+              + if .status.phase != "Completed" then
+                  {status: "FAIL", reason: "DataUpload phase=\(.status.phase)"}
+                elif (.status.snapshotID // "") == "" then
+                  {status: "FAIL", reason: "DataUpload has no snapshotID"}
+                else
+                  {status: "VERIFY"}
+                end
+          end
+      end ]
+| if ($only | length) > 0 then map(select(.namespace as $n | $only | index($n) != null)) else . end

kubernetes/infrastructure/velero/backup-verify/summary.jq

@@ -0,0 +1,15 @@
+# {plan, results} -> {entries, pass, fail, skip}.
+(.results | map({key: "\(.namespace)/\(.pvc)/\(.snapshotID)", value: .}) | from_entries) as $r
+| [ .plan[]
+    | if .status == "VERIFY" then
+        $r["\(.namespace)/\(.pvc)/\(.snapshotID)"] as $x
+        | if $x == null then . + {status: "FAIL", reason: "no result from VM"}
+          else . + {status: $x.status, reason: $x.reason} end
+      else . end ] as $e
+| {entries: $e,
+   pass: ([$e[] | select(.status == "OK")] | length),
+   fail: ([$e[] | select(.status == "FAIL")] | length),
+   skip: ([$e[] | select(.status == "SKIP")] | length)}
+| if (.pass + .fail) == 0 then
+    .fail += 1 | .entries += [{status: "FAIL", reason: "nothing verified"}]
+  else . end