feat(wiki): roll the pod when one of its Secrets changes

All credentials reach the service via envFrom, which is read once at pod
start. Reloader watches the four Secrets and restarts the Deployment on a
change, so a corrected or rotated key takes effect without a manual restart.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

.woodpecker/build-ci-images.yml

@@ -377,37 +377,6 @@ steps:
           --destination gitea.renner.uno/gitea_admin/netbird-service-sync:$TAG \
           --destination gitea.renner.uno/gitea_admin/netbird-service-sync:latest
 
-  # wiki-index: embedding index over the Notes repo's wiki/, fed from Gitea and
-  # queried by ~/Notes/bin/wiki_rank.py. Runtime artifact like netbird-service-sync.
-  - name: build-wiki-index
-    image: registry.gitlab.com/gitlab-ci-utils/container-images/kaniko:v1.25.18-debug
-    directory: ci/images/wiki-index
-    depends_on: []
-    when:
-      - event: deployment
-      - event: push
-        path: ["ci/images/wiki-index/**", ".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=$(date +%Y-%m-%d)
-      # Also a per-commit tag: several builds a day (branch pushes and the
-      # merge) all rewrite the dated tag, and the deployment pin raced them
-      # on 2026-09-20. The commit tag is immutable and needs no digest lookup.
-      - SHORT=$(printf '%s' "$CI_COMMIT_SHA" | cut -c1-8)
-      - |
-        /kaniko/executor \
-          --context . \
-          --dockerfile Containerfile \
-          --destination gitea.renner.uno/gitea_admin/wiki-index:$TAG \
-          --destination gitea.renner.uno/gitea_admin/wiki-index:$TAG-$SHORT \
-          --destination gitea.renner.uno/gitea_admin/wiki-index:latest
-
   # bird: BGP daemon for the pod-network mesh over pod0 (#576). Runtime
   # artifact like heating-can; same registry so the audit tracks it.
   - name: build-bird

.woodpecker/wiki-maintenance.yml

@@ -1,11 +1,13 @@
 # Nightly wiki maintenance for the Notes vault (k.renner/notes), replacing the
-# workstation's wiki-maintenance.timer: distill the raw/ backlog into wiki/
-# (a `claude` run of the wiki-distill agent), then audit wiki/ with the vault's
-# own script (structural checks, no model). The pipeline commits and pushes as
-# Claude Bot; the push webhook then refreshes the wiki-index service.
+# workstation's wiki-maintenance and wiki-consolidate timers: distill the raw/
+# backlog into wiki/ (wiki-distill agent), audit wiki/ with the vault's own
+# script (structural checks, no model), then consolidate (wiki-consolidate
+# agent: verifies a cohort of notes against sources, repos and the live
+# cluster and edits them). The pipeline commits and pushes as Claude Bot; the
+# push webhook then refreshes the wiki service.
 #
-# The agent and its retrieval scripts address the vault as ~/Notes, so the
-# distill step links $HOME/Notes to the checkout instead of rewriting them.
+# The agents address the vault as ~/Notes and the repos as ~/source/<repo>, so
+# each agent step links those into the workspace instead of rewriting them.
 when:
   - event: cron
     cron: wiki-maintenance
@@ -29,6 +31,27 @@ steps:
         git -c http.extraheader="AUTHORIZATION: token $$TOKEN" \
           clone --depth 50 --branch main https://gitea.renner.uno/k.renner/notes.git notes
         echo "raw backlog: $$(ls notes/raw/*.md | grep -v _index.md | wc -l) file(s)"
+        # Full history for the consolidate agent's `git log` checks; the
+        # workspace clone is shallow and tree-filtered.
+        mkdir -p sources
+        git clone --quiet https://gitea.renner.uno/k.renner/homelab.git sources/homelab
+        git -c http.extraheader="AUTHORIZATION: token $$TOKEN" \
+          clone --quiet https://gitea.renner.uno/k.renner/homeassistant.git sources/homeassistant
+
+  - name: fetch-diag
+    # Read-only live-cluster access for the consolidate agent, same mechanism
+    # as issue-fix.yml: ./.ci-diag/kubectl plus a 1h ci-diagnostics token.
+    image: gitea.renner.uno/gitea_admin/ci-k8s:2026-09-08
+    environment:
+      SOPS_AGE_KEY:
+        from_secret: sops_age_key
+      S3_ACCESS_KEY_ID:
+        from_secret: hetzner_s3_access_key
+      S3_SECRET_ACCESS_KEY:
+        from_secret: hetzner_s3_secret_key
+    commands:
+      - bash scripts/ci/fetch-kubeconfig.sh
+      - bash scripts/ci/make-diag-kubeconfig.sh
 
   - name: distill
     image: gitea.renner.uno/gitea_admin/ci-claude:2.1.280
@@ -43,20 +66,25 @@ steps:
     commands:
       - |
         set -eu
+        # An empty queue must not start the agent: its startup context alone
+        # costs more than the whole audit.
+        BACKLOG=$$(ls notes/raw/*.md | grep -v _index.md | wc -l)
+        if [ "$$BACKLOG" -eq 0 ]; then
+          echo "distill: raw/ is empty, skipping the agent"
+          exit 0
+        fi
         ln -sfn "$$PWD/notes" "$$HOME/Notes"
         mkdir -p "$$HOME/.config/wiki-index"
         printf '%s' "$$WIKI_INDEX_BASIC_AUTH" | tr -d '\r\n' > "$$HOME/.config/wiki-index/basic-auth"
         chmod 600 "$$HOME/.config/wiki-index/basic-auth"
         "$$HOME/Notes/bin/wiki_rank.py" --probe-index
-      - |
-        set -eu
         MODEL=$$(sh scripts/ci/pick-model.sh "distill raw source notes into atomic wiki notes: read sources, check the wiki for existing coverage, write or merge notes; careful writing, moderate reasoning")
         if [ -n "$$MODEL" ]; then echo "distill: selected model $$MODEL"; else echo "distill: using the CLI default model"; fi
         cd notes
         cat ../ci/agents/wiki-maintenance/distill.md | claude $${MODEL:+--model $$MODEL} \
           --agent wiki-distill \
           --permission-mode acceptEdits \
-          --allowedTools "Read,Edit,Write,Glob,Grep,Bash(/root/Notes/bin/wiki_rank.py:*),Bash(/root/Notes/bin/wiki_ask.py:*),Bash(mv /root/Notes/raw/:*),Bash(mkdir -p /root/Notes/:*)" \
+          --allowedTools "Read,Edit,Write,Glob,Grep,Bash(/root/Notes/bin/wiki_rank.py:*),Bash(/root/Notes/bin/wiki_ask.py:*),Bash(mv /root/Notes/raw/:*),Bash(mkdir -p /root/Notes/:*),Bash(~/Notes/bin/wiki_rank.py:*),Bash(~/Notes/bin/wiki_ask.py:*),Bash(mv ~/Notes/raw/:*),Bash(mkdir -p ~/Notes/:*)" \
           --settings ../ci/agents/wiki-maintenance/settings.json \
           -p
 
@@ -67,6 +95,55 @@ steps:
       # 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:2.1.280
+    pull: true
+    environment:
+      CLAUDE_CODE_OAUTH_TOKEN:
+        from_secret: claude_code_oauth_token
+      TYPESAFE_API_KEY:
+        from_secret: typesafe_api_key
+      WIKI_INDEX_BASIC_AUTH:
+        from_secret: wiki_index_basic_auth
+    commands:
+      - |
+        set -eu
+        ln -sfn "$$PWD/notes" "$$HOME/Notes"
+        ln -sfn "$$PWD/sources" "$$HOME/source"
+        mkdir -p "$$HOME/.config/wiki-index"
+        printf '%s' "$$WIKI_INDEX_BASIC_AUTH" | tr -d '\r\n' > "$$HOME/.config/wiki-index/basic-auth"
+        chmod 600 "$$HOME/.config/wiki-index/basic-auth"
+        if [ -f .ci-diag/kubeconfig ]; then
+          ln -sf "$$PWD/.ci-diag/kubectl" /usr/local/bin/kubectl
+          export KUBECONFIG="$$PWD/.ci-diag/kubeconfig"
+        else
+          echo "consolidate: no ci-diag kubeconfig, live cluster checks unavailable"
+        fi
+        cd notes
+        # JSON output: the agent's report and the run's cost come out of one
+        # record at the end instead of a 45-minute silent log.
+        # One source for the Bash allowlist: the settings file (run 10608: the
+        # agent writes ~/Notes, the rules carried only /root/Notes).
+        BASH_RULES=$$(jq -r '[.permissions.allow[] | select(startswith("Bash("))] | join(",")' ../ci/agents/wiki-maintenance/consolidate-settings.json)
+        rc=0
+        cat ../ci/agents/wiki-maintenance/consolidate.md | claude \
+          --agent wiki-consolidate \
+          --permission-mode acceptEdits \
+          --allowedTools "Read,Edit,Write,Glob,Grep,Agent,$$BASH_RULES" \
+          --settings ../ci/agents/wiki-maintenance/consolidate-settings.json \
+          --output-format json \
+          -p > /tmp/consolidate.json || rc=$$?
+        # A killed or crashed claude leaves no valid JSON; report rc, not a jq error.
+        if [ -s /tmp/consolidate.json ] && jq -e . /tmp/consolidate.json > /dev/null; then
+          jq -r '.result // empty' /tmp/consolidate.json
+          jq -c '{duration_ms, num_turns, total_cost_usd, is_error}' /tmp/consolidate.json
+        else
+          echo "consolidate: no result record (exit $$rc)"; head -c 2000 /tmp/consolidate.json || true
+        fi
+        echo "consolidate: git log --oneline of the run:"
+        git log --oneline origin/main..HEAD
+        exit $$rc
+
   - name: push-notes
     image: gitea.renner.uno/gitea_admin/ci-claude:2.1.280
     pull: true
@@ -81,7 +158,11 @@ steps:
         git config user.name "Claude Bot"
         # Only the vault content is committed; anything an agent leaves elsewhere
         # in the checkout (run 10362: scratch scripts in the root) stays behind.
-        if [ -z "$$(git status --porcelain -- wiki raw output)" ]; then
+        # The consolidate agent commits its own snapshots, so HEAD may already be
+        # ahead of origin/main with a clean tree.
+        git add -A -- wiki raw output .wiki-consolidation-state.json
+        git diff --cached --quiet || git commit -q -m "wiki maintenance $$(date -u +%F): distill + audit + consolidate (CI run $$CI_PIPELINE_NUMBER)"
+        if [ "$$(git rev-list --count origin/main..HEAD)" -eq 0 ]; then
           echo "wiki-maintenance: no changes"
           exit 0
         fi
@@ -91,13 +172,11 @@ steps:
         # leaves the PR open for a human and fails the run.
         BRANCH="wiki-maintenance/$$(date -u +%F)-$$CI_PIPELINE_NUMBER"
         git checkout -q -b "$$BRANCH"
-        git add -A -- wiki raw output
-        git commit -q -m "wiki maintenance $$(date -u +%F): distill + audit (CI run $$CI_PIPELINE_NUMBER)"
         TOKEN=$$(printf '%s' "$$WIKI_BOT_TOKEN" | tr -d '\r\n')
         git -c http.extraheader="AUTHORIZATION: token $$TOKEN" push origin "HEAD:$$BRANCH"
         API="https://gitea.renner.uno/api/v1/repos/k.renner/notes"
         jq -n --arg title "wiki maintenance $$(date -u +%F) (CI run $$CI_PIPELINE_NUMBER)" \
-              --arg body "Nightly distill + audit. Merged by the pipeline; open only if the merge failed." \
+              --arg body "Nightly distill + audit + consolidate. Merged by the pipeline; open only if the merge failed." \
               --arg head "$$BRANCH" '{title: $$title, body: $$body, head: $$head, base: "main"}' > /tmp/pr.json
         code=$$(curl -s -o /tmp/pr-resp.json -w '%{http_code}' -X POST \
           -H "Authorization: token $$TOKEN" -H "Content-Type: application/json" --data @/tmp/pr.json "$$API/pulls")

ci/agents/wiki-maintenance/consolidate-settings.json

@@ -0,0 +1,120 @@
+{
+  "//": "Permission scope for the wiki-consolidate agent in CI: read the vault and the",
+  "//2": "source repos cloned under /root/source, read the live cluster through the",
+  "//3": "ci-diagnostics kubeconfig, edit wiki/, output/ and the rotation state only.",
+  "//4": "Deny rules win; git and kubectl are read-only subcommands, no network tools.",
+  "permissions": {
+    "allow": [
+      "Read(//root/Notes/**)",
+      "Read(//root/source/**)",
+      "Edit(//root/Notes/wiki/**)",
+      "Edit(//root/Notes/output/**)",
+      "Edit(//root/Notes/.wiki-consolidation-state.json)",
+      "Bash(/root/Notes/bin/wiki-snapshot.sh:*)",
+      "Bash(/root/Notes/bin/wiki_rank.py:*)",
+      "Bash(/root/Notes/bin/wiki_ask.py:*)",
+      "Bash(~/Notes/bin/wiki-snapshot.sh:*)",
+      "Bash(~/Notes/bin/wiki_rank.py:*)",
+      "Bash(~/Notes/bin/wiki_ask.py:*)",
+      "Bash(~/Notes/bin/wiki-delete.sh:*)",
+      "Bash(git -C /root/Notes log:*)",
+      "Bash(git -C /root/Notes show:*)",
+      "Bash(git -C /root/Notes diff:*)",
+      "Bash(git -C /root/Notes status:*)",
+      "Bash(git -C /root/Notes rev-parse:*)",
+      "Bash(git -C /root/Notes ls-files:*)",
+      "Bash(git -C ~/Notes log:*)",
+      "Bash(git -C ~/Notes show:*)",
+      "Bash(git -C ~/Notes diff:*)",
+      "Bash(git -C ~/Notes status:*)",
+      "Bash(git -C ~/Notes rev-parse:*)",
+      "Bash(git -C ~/Notes ls-files:*)",
+      "Bash(kubectl get:*)",
+      "Bash(kubectl describe:*)",
+      "Bash(kubectl version:*)",
+      "Bash(kubectl api-resources:*)",
+      "Bash(kubectl explain:*)",
+      "Bash(git log:*)",
+      "Bash(git show:*)",
+      "Bash(git status:*)",
+      "Bash(git diff:*)",
+      "Bash(git rev-parse:*)",
+      "Bash(git ls-files:*)",
+      "Bash(git -C /root/source/homelab log:*)",
+      "Bash(git -C /root/source/homelab show:*)",
+      "Bash(git -C /root/source/homelab diff:*)",
+      "Bash(git -C /root/source/homelab status:*)",
+      "Bash(git -C /root/source/homelab rev-parse:*)",
+      "Bash(git -C /root/source/homelab ls-files:*)",
+      "Bash(git -C /root/source/homeassistant log:*)",
+      "Bash(git -C /root/source/homeassistant show:*)",
+      "Bash(git -C /root/source/homeassistant diff:*)",
+      "Bash(git -C /root/source/homeassistant status:*)",
+      "Bash(git -C /root/source/homeassistant rev-parse:*)",
+      "Bash(git -C /root/source/homeassistant ls-files:*)",
+      "Bash(git -C ~/source/homelab log:*)",
+      "Bash(git -C ~/source/homelab show:*)",
+      "Bash(git -C ~/source/homelab diff:*)",
+      "Bash(git -C ~/source/homelab status:*)",
+      "Bash(git -C ~/source/homelab rev-parse:*)",
+      "Bash(git -C ~/source/homelab ls-files:*)",
+      "Bash(git -C ~/source/homeassistant log:*)",
+      "Bash(git -C ~/source/homeassistant show:*)",
+      "Bash(git -C ~/source/homeassistant diff:*)",
+      "Bash(git -C ~/source/homeassistant status:*)",
+      "Bash(git -C ~/source/homeassistant rev-parse:*)",
+      "Bash(git -C ~/source/homeassistant ls-files:*)",
+      "Bash(/root/Notes/bin/wiki-delete.sh:*)",
+      "Bash(ls:*)",
+      "Bash(date:*)",
+      "Bash(wc:*)",
+      "Bash(stat:*)",
+      "Bash(head:*)",
+      "Bash(tail:*)"
+    ],
+    "deny": [
+      "Read(//proc/**)",
+      "Read(//etc/**)",
+      "Read(//root/.config/**)",
+      "Read(//root/.kube/**)",
+      "Read(//woodpecker/**/.ci-diag/**)",
+      "Read(//root/Notes/.git/**)",
+      "Read(//root/source/*/.git/**)",
+      "Read(//root/Notes/_archive/**)",
+      "Edit(//root/Notes/raw/**)",
+      "Edit(//root/Notes/_archive/**)",
+      "Edit(//root/source/**)",
+      "Bash(kubectl apply:*)",
+      "Bash(kubectl delete:*)",
+      "Bash(kubectl patch:*)",
+      "Bash(kubectl edit:*)",
+      "Bash(kubectl scale:*)",
+      "Bash(kubectl rollout:*)",
+      "Bash(kubectl exec:*)",
+      "Bash(kubectl cp:*)",
+      "Bash(kubectl drain:*)",
+      "Bash(kubectl cordon:*)",
+      "Bash(kubectl label:*)",
+      "Bash(kubectl annotate:*)",
+      "Bash(git push:*)",
+      "Bash(git reset:*)",
+      "Bash(git checkout:*)",
+      "Bash(git clean:*)",
+      "Bash(git rebase:*)",
+      "Bash(git config:*)",
+      "Bash(git -C /root/Notes config:*)",
+      "Bash(git -C ~/Notes config:*)",
+      "Bash(git -C /root/source/homelab config:*)",
+      "Bash(git -C /root/source/homeassistant config:*)",
+      "Bash(git -C ~/source/homelab config:*)",
+      "Bash(git -C ~/source/homeassistant config:*)",
+      "Bash(rm:*)",
+      "Bash(rm -rf:*)",
+      "Bash(curl:*)",
+      "Bash(wget:*)",
+      "Bash(ssh:*)",
+      "Bash(tea:*)",
+      "Bash(woodpecker:*)"
+    ]
+  }
+}

ci/agents/wiki-maintenance/consolidate.md

@@ -0,0 +1,5 @@
+You are running as the scheduled wiki-maintenance job in CI. The Notes vault is checked out at ~/Notes (the repository k.renner/notes); the homelab and homeassistant repositories are checked out under ~/source/. `kubectl` reads the live cluster with a read-only identity.
+
+Run the wiki-consolidate agent now for today's scheduled consolidation pass. Follow its instructions exactly: snapshot the vault to git first, abort if that fails, select today's rotating cohort of 20 from the state file, verify claims against both their sources and the live systems, act on the verdicts, write the dated report to ~/Notes/output/, update the state file, and snapshot again at the end. Do not push; the pipeline pushes the run's commits.
+
+Report the counts and the coverage progress when you are done.

ci/agents/wiki-maintenance/settings.json

@@ -15,6 +15,10 @@
       "Bash(/root/Notes/bin/wiki_ask.py:*)",
       "Bash(mv /root/Notes/raw/:*)",
       "Bash(mkdir -p /root/Notes/:*)",
+      "Bash(~/Notes/bin/wiki_rank.py:*)",
+      "Bash(~/Notes/bin/wiki_ask.py:*)",
+      "Bash(mv ~/Notes/raw/:*)",
+      "Bash(mkdir -p ~/Notes/:*)",
       "Bash(ls:*)",
       "Bash(date:*)",
       "Bash(wc:*)",

ci/images/k8s/Containerfile

@@ -1,6 +1,6 @@
 FROM alpine:3.21@sha256:48b0309ca019d89d40f670aa1bc06e426dc0931948452e8491e3d65087abc07d
 
-ARG TALOS_VERSION=v1.13.9
+ARG TALOS_VERSION=v1.13.10
 ARG VELERO_VERSION=v1.16.0
 ARG KUBECTL_VERSION=v1.36.3
 ARG FLUX_VERSION=2.9.5
@@ -18,7 +18,7 @@ RUN apk add --no-cache \
 
 RUN curl -sfL -o /usr/local/bin/talosctl \
       "https://github.com/siderolabs/talos/releases/download/${TALOS_VERSION}/talosctl-linux-amd64" \
- && echo "7e1d4b7d5846964bdcf63a794e3c8161bb6ef2983d5ace58ea5322f3bf32a27e  /usr/local/bin/talosctl" | sha256sum -c - \
+ && echo "28e9ccd9aebd690fa03d8cf2582221d87ea38b2a1704f411d75a03589c58f2aa  /usr/local/bin/talosctl" | sha256sum -c - \
  && chmod +x /usr/local/bin/talosctl
 
 RUN curl -sfL -o /usr/local/bin/kubectl \

ci/images/vmtest/Containerfile

@@ -14,7 +14,7 @@ FROM alpine:3.21@sha256:48b0309ca019d89d40f670aa1bc06e426dc0931948452e8491e3d650
 # kubernetes/talos/patches/cluster.yaml. The phase reads the version from that
 # file at run time and passes it to the provisioner; this pin only decides which
 # client talks to it.
-ARG TALOS_VERSION=v1.13.9
+ARG TALOS_VERSION=v1.13.10
 ARG KUBECTL_VERSION=v1.36.2
 ARG FLUX_VERSION=2.9.2
 ARG KOPIA_VERSION=0.23.1
@@ -49,7 +49,7 @@ RUN apk add --no-cache \
 
 RUN curl -sfL -o /usr/local/bin/talosctl \
       "https://github.com/siderolabs/talos/releases/download/${TALOS_VERSION}/talosctl-linux-amd64" \
- && echo "7e1d4b7d5846964bdcf63a794e3c8161bb6ef2983d5ace58ea5322f3bf32a27e  /usr/local/bin/talosctl" | sha256sum -c - \
+ && echo "28e9ccd9aebd690fa03d8cf2582221d87ea38b2a1704f411d75a03589c58f2aa  /usr/local/bin/talosctl" | sha256sum -c - \
  && chmod +x /usr/local/bin/talosctl
 
 RUN curl -sfL -o /usr/local/bin/kubectl \

ci/images/wiki-index/Containerfile

@@ -1,10 +0,0 @@
-# wiki-index: embedding index over the Notes repo's wiki/, fed from Gitea,
-# queried by ~/Notes/bin/wiki_rank.py. Standard library only; runs unprivileged.
-FROM python:3.13-slim
-
-RUN useradd --system --no-create-home --shell /usr/sbin/nologin wikiindex
-COPY wiki_index.py /opt/wiki_index.py
-
-ENV PYTHONUNBUFFERED=1
-USER wikiindex
-ENTRYPOINT ["python3", "/opt/wiki_index.py"]

ci/images/wiki-index/test_wiki_index.py

@@ -1,178 +0,0 @@
-#!/usr/bin/env python3
-"""Unit tests for wiki_index. Run: python3 -m unittest test_wiki_index"""
-
-import hashlib
-import hmac
-import json
-import tempfile
-import unittest
-from pathlib import Path
-
-import wiki_index as wi
-
-NOTE = """---
-title: 'UDM intercepts DNS'
-type: wiki
-tags: [dns, unifi]
-aliases: [udm dns interception, dig 1.1.1.1 wrong]
----
-
-# UDM intercepts DNS
-
-The UDM answers every UDP/53 query itself.
-
-## Details
-
-More.
-"""
-
-
-class ParseTests(unittest.TestCase):
-    def test_note_text(self):
-        title, text = wi.note_text("udm-dns", NOTE)
-        self.assertEqual(title, "UDM intercepts DNS")
-        self.assertIn("udm dns UDM intercepts DNS udm dns interception", text)
-        self.assertIn("dns unifi", text)
-        self.assertTrue(text.endswith("The UDM answers every UDP/53 query itself."))
-        self.assertLessEqual(len(text), wi.EMBED_CHARS)
-
-    def test_credentials_are_stripped(self):
-        original = wi.http
-        wi.http = lambda method, url, body=None, headers=None, timeout=60.0: (
-            {"auth": {"client_token": "t"}} if url.endswith("/login")
-            else {"data": {"data": {"gitea_token": "abc\n", "webhook_secret": " s3cret\n"}}})
-        original_sa = wi.SA_TOKEN
-        try:
-            with tempfile.TemporaryDirectory() as d:
-                wi.SA_TOKEN = Path(d) / "token"
-                wi.SA_TOKEN.write_text("jwt\n")
-                self.assertEqual(wi.Credentials().fetch(), {"gitea_token": "abc", "webhook_secret": "s3cret"})
-        finally:
-            wi.http, wi.SA_TOKEN = original, original_sa
-
-    def test_tree_paging_stops_on_short_last_page(self):
-        # Gitea: truncated=true on every page including the last, "tree": null past it.
-        pages = {
-            1: {"tree": [{"path": f"wiki/n{i}.md", "type": "blob", "sha": f"s{i}"} for i in range(1000)], "truncated": True, "total_count": 1192},
-            2: {"tree": [{"path": f"wiki/n{i}.md", "type": "blob", "sha": f"s{i}"} for i in range(1000, 1192)] + [{"path": "raw/x.md", "type": "blob", "sha": "r"}, {"path": "wiki/sub/y.md", "type": "blob", "sha": "y"}], "truncated": True, "total_count": 1192},
-            3: {"tree": None, "truncated": False, "total_count": 1192},
-        }
-        calls = []
-        original = wi.http
-
-        def fake_http(method, url, body=None, headers=None, timeout=60.0):
-            page = int(url.rsplit("page=", 1)[1])
-            calls.append(page)
-            return pages[page]
-
-        wi.http = fake_http
-        try:
-            tree = wi.Gitea("t").tree("abc")
-        finally:
-            wi.http = original
-        self.assertEqual(calls, [1, 2])
-        self.assertEqual(len(tree), 1192)
-        self.assertNotIn("raw/x.md", tree)
-        self.assertNotIn("wiki/sub/y.md", tree)
-        self.assertEqual(tree["wiki/n1191.md"], "s1191")
-
-    def test_signature(self):
-        body = b'{"ref":"refs/heads/master"}'
-        sig = hmac.new(b"s3cret", body, hashlib.sha256).hexdigest()
-        self.assertTrue(wi.verify_signature("s3cret", body, sig))
-        self.assertFalse(wi.verify_signature("other", body, sig))
-        self.assertFalse(wi.verify_signature("s3cret", body, ""))
-
-
-class FakeGitea:
-    def __init__(self, head, tree, files):
-        self._head, self._tree, self.files = head, tree, files
-        self.raw_calls = []
-
-    def head(self):
-        return self._head
-
-    def tree(self, commit):
-        return self._tree
-
-    def raw(self, path, ref):
-        self.raw_calls.append(path)
-        return self.files[path]
-
-
-class IndexTests(unittest.TestCase):
-    def setUp(self):
-        self.tmp = tempfile.TemporaryDirectory()
-        self.path = Path(self.tmp.name) / "index.json"
-        self.original_embed = wi.embed
-        self.embed_calls = []
-
-        def fake_embed(texts, batch=2):
-            self.embed_calls.append(list(texts))
-            return [wi.unit([1.0, float(len(t) % 7)]) for t in texts]
-
-        wi.embed = fake_embed
-
-    def tearDown(self):
-        wi.embed = self.original_embed
-        self.tmp.cleanup()
-
-    def test_sync_is_incremental_and_persists(self):
-        files = {"wiki/udm-dns.md": NOTE, "wiki/ceph.md": "---\ntitle: Ceph\n---\n# Ceph\n\nOSD.\n", "wiki/_index.md": "---\ntitle: Wiki\n---\n"}
-        tree = {"wiki/udm-dns.md": "aaa", "wiki/ceph.md": "bbb", "wiki/_index.md": "ccc"}
-        g = FakeGitea("c1", tree, files)
-        idx = wi.Index(self.path)
-        s = idx.sync(g)
-        self.assertEqual((s["changed"], s["removed"], s["notes"]), (2, 0, 2))
-        self.assertEqual(set(idx.notes), {"udm-dns", "ceph"})
-        self.assertEqual(idx.notes["udm-dns"]["title"], "UDM intercepts DNS")
-        self.assertTrue(self.path.exists())
-
-        # head unchanged: nothing fetched
-        s = idx.sync(g)
-        self.assertEqual(s.get("skipped"), "head unchanged")
-        self.assertEqual(len(g.raw_calls), 2)
-
-        # one note changed, one removed, new head
-        g2 = FakeGitea("c2", {"wiki/udm-dns.md": "aaa2"}, {"wiki/udm-dns.md": NOTE.replace("itself", "itself!")})
-        s = idx.sync(g2)
-        self.assertEqual((s["changed"], s["removed"], s["notes"]), (1, 1, 1))
-        self.assertEqual(g2.raw_calls, ["wiki/udm-dns.md"])
-
-        # restart loads the persisted index
-        idx2 = wi.Index(self.path)
-        self.assertEqual(idx2.commit, "c2")
-        self.assertEqual(set(idx2.notes), {"udm-dns"})
-
-    def test_rank_orders_by_cosine(self):
-        idx = wi.Index(self.path)
-        idx.notes = {"a": {"sha": "1", "title": "A", "vector": wi.unit([1.0, 0.0])},
-                     "b": {"sha": "2", "title": "B", "vector": wi.unit([0.0, 1.0])}}
-        wi.embed = lambda texts, batch=2: [wi.unit([0.2, 1.0])]
-        rows = idx.rank("q", k=5)
-        self.assertEqual([r["slug"] for r in rows], ["b", "a"])
-        self.assertGreater(rows[0]["score"], rows[1]["score"])
-
-    def test_status_reports_age_and_errors(self):
-        idx = wi.Index(self.path)
-        self.assertFalse(idx.status()["ready"])
-        g = FakeGitea("c1", {"wiki/a.md": "x"}, {"wiki/a.md": "---\ntitle: A\n---\n# A\n\nt\n"})
-        idx.sync(g)
-        st = idx.status()
-        self.assertTrue(st["ready"])
-        self.assertEqual(st["notes"], 1)
-        self.assertEqual(st["commit"], "c1")
-
-        class Broken(FakeGitea):
-            def head(self):
-                raise wi.ApiError("gitea down")
-
-        with self.assertRaises(wi.ApiError):
-            idx.sync(Broken("c1", {}, {}))
-        self.assertIn("gitea down", idx.status()["last_error"])
-        self.assertEqual(idx.status()["notes"], 1)  # last good index kept
-        self.assertTrue(idx.status()["ready"])  # and still served
-
-
-if __name__ == "__main__":
-    unittest.main()

ci/images/wiki-index/wiki_index.py

@@ -1,408 +0,0 @@
-#!/usr/bin/env python3
-"""wiki-index: embedding index over the Notes repo's wiki/, fed from Gitea.
-
-Source of truth is the notes repository on Gitea. The index holds, per wiki
-note, the git blob sha, title and a bge-m3 vector of slug/title/aliases/tags/
-first paragraph. A sync fetches the repo tree, embeds every note whose blob sha
-changed (via wiki-embed, in-cluster) and drops notes that left the tree; it
-runs at start, on every push webhook from Gitea, and every RESYNC_SECONDS.
-
-HTTP:
-  POST /rank     {"query": str, "k": int}   -> {"rows": [{"slug","title","score"}], "index": {...}}
-  GET  /health   -> 200 always (liveness) with {"ready", "notes", "commit", "synced_at", "age_s", "syncing", "last_error"}
-  GET  /ready    -> 200 when an index exists, else 503 (readiness)
-  POST /webhook  Gitea push event, HMAC-SHA256 in X-Gitea-Signature -> {"queued": true}
-
-Credentials (Gitea token, webhook secret) are read from OpenBao through the
-Kubernetes auth role on every use; they never land in a Secret or a log line.
-Standard library only.
-"""
-
-from __future__ import annotations
-
-import hashlib
-import hmac
-import json
-import logging
-import os
-import re
-import sys
-import threading
-import time
-import urllib.error
-import urllib.parse
-import urllib.request
-from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
-from pathlib import Path
-
-LOG = logging.getLogger("wiki-index")
-
-GITEA_URL = os.environ.get("GITEA_URL", "https://gitea.renner.uno").rstrip("/")
-NOTES_REPO = os.environ.get("NOTES_REPO", "k.renner/notes")
-NOTES_BRANCH = os.environ.get("NOTES_BRANCH", "master")
-WIKI_DIR = os.environ.get("WIKI_DIR", "wiki").strip("/")
-EMBED_URL = os.environ.get("EMBED_URL", "http://wiki-embed.ai.svc.cluster.local:8080").rstrip("/")
-EMBED_MODEL = os.environ.get("EMBED_MODEL", "bge-m3")
-EMBED_CHARS = int(os.environ.get("EMBED_CHARS", "1500"))
-INDEX_PATH = Path(os.environ.get("INDEX_PATH", "/data/index.json"))
-RESYNC_SECONDS = int(os.environ.get("RESYNC_SECONDS", "1800"))
-LISTEN_PORT = int(os.environ.get("LISTEN_PORT", "8080"))
-BAO_ADDR = os.environ.get("BAO_ADDR", "http://openbao.openbao.svc.cluster.local:8200").rstrip("/")
-BAO_ROLE = os.environ.get("BAO_ROLE", "wiki-index")
-BAO_SECRET_PATH = os.environ.get("BAO_SECRET_PATH", "homelab/data/apps/ai/wiki-index")
-SA_TOKEN = Path(os.environ.get("SA_TOKEN", "/var/run/secrets/kubernetes.io/serviceaccount/token"))
-
-
-class ApiError(Exception):
-    pass
-
-
-# ---------------------------------------------------------------- http helpers
-
-
-def http(method: str, url: str, body=None, headers=None, timeout: float = 60.0):
-    data = None
-    hdrs = dict(headers or {})
-    if body is not None:
-        data = json.dumps(body).encode("utf-8")
-        hdrs.setdefault("Content-Type", "application/json")
-    req = urllib.request.Request(url, data=data, method=method, headers=hdrs)
-    try:
-        with urllib.request.urlopen(req, timeout=timeout) as resp:
-            raw = resp.read()
-            ctype = resp.headers.get("Content-Type", "")
-    except urllib.error.HTTPError as e:
-        raise ApiError(f"{method} {url}: HTTP {e.code}: {e.read().decode('utf-8', 'replace')[:300]}") from e
-    except urllib.error.URLError as e:
-        raise ApiError(f"{method} {url}: {e.reason}") from e
-    if "json" in ctype:
-        return json.loads(raw.decode("utf-8"))
-    return raw
-
-
-# ---------------------------------------------------------------- credentials
-
-
-class Credentials:
-    """Gitea token and webhook secret from OpenBao, fetched per use."""
-
-    def __init__(self, static: dict | None = None):
-        self.static = static  # tests / local runs
-
-    def fetch(self) -> dict:
-        if self.static is not None:
-            return self.static
-        jwt = SA_TOKEN.read_text(encoding="utf-8").strip()
-        login = http("POST", f"{BAO_ADDR}/v1/auth/kubernetes/login", {"role": BAO_ROLE, "jwt": jwt})
-        token = login["auth"]["client_token"]
-        kv = http("GET", f"{BAO_ADDR}/v1/{BAO_SECRET_PATH}", headers={"X-Vault-Token": token})
-        data = {k: str(v).strip() for k, v in kv["data"]["data"].items()}  # `bao kv put key=@file` keeps the file's newline
-        for key in ("gitea_token", "webhook_secret"):
-            if not data.get(key):
-                raise ApiError(f"OpenBao {BAO_SECRET_PATH} has no key {key}")
-        return data
-
-
-# ---------------------------------------------------------------- gitea
-
-
-class Gitea:
-    def __init__(self, token: str, base: str = GITEA_URL, repo: str = NOTES_REPO, branch: str = NOTES_BRANCH):
-        self.base, self.repo, self.branch = base, repo, branch
-        self.headers = {"Authorization": f"token {token}"}
-
-    def api(self, path: str, **params):
-        q = ("?" + urllib.parse.urlencode(params)) if params else ""
-        return http("GET", f"{self.base}/api/v1/repos/{self.repo}{path}{q}", headers=self.headers)
-
-    def head(self) -> str:
-        return self.api(f"/branches/{urllib.parse.quote(self.branch, safe='')}")["commit"]["id"]
-
-    def tree(self, commit: str) -> dict[str, str]:
-        """path -> blob sha for every wiki note at that commit."""
-        out: dict[str, str] = {}
-        page, per_page, seen = 1, 1000, 0
-        while True:
-            t = self.api(f"/git/trees/{commit}", recursive="true", per_page=per_page, page=page)
-            entries = t.get("tree") or []  # Gitea answers "tree": null past the last page
-            for e in entries:
-                p = e.get("path", "")
-                if e.get("type") == "blob" and p.startswith(WIKI_DIR + "/") and p.endswith(".md") and "/" not in p[len(WIKI_DIR) + 1:]:
-                    out[p] = e["sha"]
-            seen += len(entries)
-            total = int(t.get("total_count") or 0)
-            if not entries or len(entries) < per_page or (total and seen >= total):
-                break
-            page += 1
-            if page > 50:
-                raise ApiError("tree paging runaway")
-        return out
-
-    def raw(self, path: str, ref: str) -> str:
-        data = http("GET", f"{self.base}/api/v1/repos/{self.repo}/raw/{urllib.parse.quote(path)}?ref={urllib.parse.quote(ref, safe='')}",
-                    headers=self.headers)
-        return data.decode("utf-8") if isinstance(data, bytes) else json.dumps(data)
-
-
-# ---------------------------------------------------------------- notes
-
-
-def parse_frontmatter(text: str) -> tuple[dict, str]:
-    m = re.match(r"^---[ \t]*\n(.*?)\n---[ \t]*(?:\n|$)", text, re.DOTALL)
-    if not m:
-        return {}, text
-    fm: dict = {}
-    for line in m.group(1).splitlines():
-        mm = re.match(r"^([A-Za-z_][\w-]*):\s*(.*)$", line)
-        if mm:
-            fm[mm.group(1)] = mm.group(2).strip()
-    return fm, text[m.end():]
-
-
-def as_list(value: str) -> list[str]:
-    s = (value or "").strip()
-    if s.startswith("[") and s.endswith("]"):
-        s = s[1:-1]
-    return [p.strip().strip("'\"") for p in s.split(",") if p.strip()]
-
-
-def first_paragraph(body: str) -> str:
-    para: list[str] = []
-    seen_h1 = False
-    for line in body.splitlines():
-        if line.startswith("# "):
-            seen_h1 = True
-            continue
-        if not seen_h1:
-            continue
-        if line.strip() == "" or line.startswith("#"):
-            if para:
-                break
-            continue
-        para.append(line.strip())
-    return " ".join(para)
-
-
-def note_text(slug: str, text: str) -> tuple[str, str]:
-    """(title, embedding text) for one note file."""
-    fm, body = parse_frontmatter(text)
-    title = (fm.get("title") or slug).strip().strip("'\"")
-    parts = [slug.replace("-", " "), title, " ".join(as_list(fm.get("aliases", ""))),
-             " ".join(as_list(fm.get("tags", ""))), first_paragraph(body)]
-    return title, " ".join(parts)[:EMBED_CHARS]
-
-
-# ---------------------------------------------------------------- embeddings
-
-
-def embed(texts: list[str], batch: int = 2) -> list[list[float]]:
-    out: list[list[float]] = []
-    for i in range(0, len(texts), batch):
-        resp = http("POST", f"{EMBED_URL}/v1/embeddings", {"model": EMBED_MODEL, "input": texts[i:i + batch]}, timeout=120)
-        rows = sorted(resp["data"], key=lambda d: d["index"])
-        out.extend(unit(d["embedding"]) for d in rows)
-    return out
-
-
-def unit(v: list[float]) -> list[float]:
-    n = sum(x * x for x in v) ** 0.5 or 1.0
-    return [round(x / n, 5) for x in v]
-
-
-# ---------------------------------------------------------------- index
-
-
-class Index:
-    def __init__(self, path: Path):
-        self.path = path
-        self.lock = threading.Lock()
-        self.notes: dict[str, dict] = {}  # slug -> {sha, title, vector}
-        self.commit = ""
-        self.synced_at = 0.0
-        self.syncing = False
-        self.last_error = ""
-        if path.exists():
-            try:
-                d = json.loads(path.read_text(encoding="utf-8"))
-                self.notes, self.commit, self.synced_at = d.get("notes", {}), d.get("commit", ""), d.get("synced_at", 0.0)
-                LOG.info("loaded index: %d notes at %s", len(self.notes), self.commit[:8])
-            except (OSError, ValueError) as e:
-                LOG.warning("index unreadable (%s); starting empty", e)
-
-    def save(self) -> None:
-        self.path.parent.mkdir(parents=True, exist_ok=True)
-        tmp = self.path.with_suffix(".tmp")
-        tmp.write_text(json.dumps({"notes": self.notes, "commit": self.commit, "synced_at": self.synced_at}), encoding="utf-8")
-        tmp.replace(self.path)
-
-    def sync(self, gitea: Gitea) -> dict:
-        """Bring the index to the branch head; returns a summary."""
-        with self.lock:
-            self.syncing = True
-        try:
-            head = gitea.head()
-            if head == self.commit and self.notes:
-                summary = {"commit": head, "changed": 0, "removed": 0, "notes": len(self.notes), "skipped": "head unchanged"}
-                self.synced_at = time.time()
-                self.save()
-                return summary
-            tree = gitea.tree(head)
-            slugs = {p[len(WIKI_DIR) + 1:-3]: (p, sha) for p, sha in tree.items() if not p.endswith("/_index.md")}
-            todo = [s for s, (p, sha) in slugs.items() if self.notes.get(s, {}).get("sha") != sha]
-            removed = [s for s in list(self.notes) if s not in slugs]
-            LOG.info("sync %s: %d notes, %d to embed, %d removed", head[:8], len(slugs), len(todo), len(removed))
-            fresh: dict[str, dict] = {}
-            for i in range(0, len(todo), 20):
-                chunk = todo[i:i + 20]
-                texts, titles = [], {}
-                for s in chunk:
-                    title, text = note_text(s, gitea.raw(slugs[s][0], head))
-                    titles[s] = title
-                    texts.append(text)
-                for s, vec in zip(chunk, embed(texts)):
-                    fresh[s] = {"sha": slugs[s][1], "title": titles[s], "vector": vec}
-            with self.lock:
-                for s in removed:
-                    self.notes.pop(s, None)
-                self.notes.update(fresh)
-                self.commit = head
-                self.synced_at = time.time()
-                self.last_error = ""
-                self.save()
-            return {"commit": head, "changed": len(todo), "removed": len(removed), "notes": len(self.notes)}
-        except Exception as e:
-            with self.lock:
-                self.last_error = str(e)[:300]
-            raise
-        finally:
-            with self.lock:
-                self.syncing = False
-
-    def rank(self, query: str, k: int = 60) -> list[dict]:
-        q = embed([query])[0]
-        with self.lock:
-            rows = [(s, n["title"], sum(a * b for a, b in zip(q, n["vector"]))) for s, n in self.notes.items()]
-        rows.sort(key=lambda r: -r[2])
-        return [{"slug": s, "title": t, "score": round(sc, 4)} for s, t, sc in rows[:k]]
-
-    def status(self) -> dict:
-        """`ready` = an index exists and can answer /rank; a failed sync keeps the last good index."""
-        with self.lock:
-            return {"ready": bool(self.notes), "notes": len(self.notes), "commit": self.commit,
-                    "synced_at": self.synced_at, "age_s": round(time.time() - self.synced_at) if self.synced_at else None,
-                    "syncing": self.syncing, "last_error": self.last_error or None}
-
-
-# ---------------------------------------------------------------- syncer
-
-
-class Syncer(threading.Thread):
-    """One worker: syncs on demand (webhook) and every RESYNC_SECONDS."""
-
-    def __init__(self, index: Index, creds: Credentials, interval: int):
-        super().__init__(daemon=True, name="syncer")
-        self.index, self.creds, self.interval = index, creds, interval
-        self.wake = threading.Event()
-
-    def trigger(self) -> None:
-        self.wake.set()
-
-    RETRY_SECONDS = 60
-
-    def run(self) -> None:
-        while True:
-            try:
-                data = self.creds.fetch()
-                summary = self.index.sync(Gitea(data["gitea_token"]))
-                LOG.info("sync done: %s", summary)
-                wait = self.interval
-            except Exception as e:  # keep serving the last good index; retry soon, not next interval
-                LOG.error("sync failed: %s", e)
-                wait = self.RETRY_SECONDS
-            self.wake.wait(wait)
-            self.wake.clear()
-
-
-def verify_signature(secret: str, body: bytes, signature: str) -> bool:
-    digest = hmac.new(secret.encode("utf-8"), body, hashlib.sha256).hexdigest()
-    return hmac.compare_digest(digest, (signature or "").strip())
-
-
-# ---------------------------------------------------------------- server
-
-
-def make_handler(index: Index, syncer: Syncer, creds: Credentials):
-    class Handler(BaseHTTPRequestHandler):
-        def log_message(self, fmt, *args):
-            LOG.info("%s %s", self.address_string(), fmt % args)
-
-        def send_json(self, code: int, obj) -> None:
-            data = json.dumps(obj).encode("utf-8")
-            self.send_response(code)
-            self.send_header("Content-Type", "application/json")
-            self.send_header("Content-Length", str(len(data)))
-            self.end_headers()
-            self.wfile.write(data)
-
-        def body(self) -> bytes:
-            n = int(self.headers.get("Content-Length") or 0)
-            return self.rfile.read(n) if n else b""
-
-        def do_GET(self):
-            if self.path == "/health":  # liveness: the process serves
-                return self.send_json(200, index.status())
-            if self.path == "/ready":  # readiness: an index exists
-                st = index.status()
-                return self.send_json(200 if st["ready"] else 503, st)
-            self.send_json(404, {"error": "not found"})
-
-        def do_POST(self):
-            if self.path == "/rank":
-                try:
-                    req = json.loads(self.body() or b"{}")
-                    query = str(req.get("query", "")).strip()
-                    k = max(1, min(int(req.get("k", 60)), 500))
-                    if not query:
-                        return self.send_json(400, {"error": "query required"})
-                    rows = index.rank(query, k)
-                    return self.send_json(200, {"rows": rows, "index": index.status()})
-                except ApiError as e:
-                    return self.send_json(502, {"error": str(e)})
-                except (ValueError, TypeError) as e:
-                    return self.send_json(400, {"error": str(e)})
-            if self.path == "/webhook":
-                raw = self.body()
-                try:
-                    secret = creds.fetch()["webhook_secret"]
-                except ApiError as e:
-                    return self.send_json(503, {"error": str(e)})
-                if not verify_signature(secret, raw, self.headers.get("X-Gitea-Signature", "")):
-                    return self.send_json(403, {"error": "bad signature"})
-                try:
-                    event = json.loads(raw or b"{}")
-                except ValueError:
-                    return self.send_json(400, {"error": "bad json"})
-                ref = event.get("ref", "")
-                if ref and ref != f"refs/heads/{NOTES_BRANCH}":
-                    return self.send_json(200, {"queued": False, "ref": ref})
-                syncer.trigger()
-                return self.send_json(200, {"queued": True})
-            self.send_json(404, {"error": "not found"})
-
-    return Handler
-
-
-def main() -> int:
-    logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s", stream=sys.stdout)
-    index = Index(INDEX_PATH)
-    creds = Credentials()
-    syncer = Syncer(index, creds, RESYNC_SECONDS)
-    syncer.start()
-    server = ThreadingHTTPServer(("", LISTEN_PORT), make_handler(index, syncer, creds))
-    LOG.info("listening on :%d, repo %s@%s, embed %s", LISTEN_PORT, NOTES_REPO, NOTES_BRANCH, EMBED_URL)
-    server.serve_forever()
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())

kubernetes/PROPOSAL-wiki-web-api.md

@@ -0,0 +1,315 @@
+# Wiki: local web interface and agent API, as a modular .NET solution
+
+## Goal
+
+A web interface for the Notes wiki that runs entirely in the cluster, and an
+HTTP API through which agents ask the wiki typed questions and deposit facts.
+Built as one C# solution with a MudBlazor front end, and built so that every
+external dependency is replaceable: where the notes live, which model embeds
+them, what judges a typed question, what runs an agent, how the vector index
+is stored. The first adapters are what the homelab uses today. The point of
+the design is that the next one is a project and a config line, not a
+rewrite.
+
+## Where we are
+
+- `wiki-index` (Python, ns `ai`) syncs `wiki/` from `k.renner/notes` by blob
+  SHA, embeds through `wiki-embed` (bge-m3 on llama-server), answers
+  `POST /rank`. It keeps slug, title and vector, not the text. LAN-only behind
+  Traefik BasicAuth; the Gitea webhook hits the ClusterIP.
+- `~/Notes/bin/wiki_rank.py` and `wiki_ask.py` rank through the index, build a
+  document context from a local vault checkout, send it with typed questions
+  to TypeSafe, gate on `covered`. The wiki-synth agent composes answers from
+  those judgements.
+- New knowledge enters as a file in `raw/` (facts with provenance, never
+  hypotheses), distilled nightly in CI.
+- The house C# project, shelly-manager, sets the conventions: net10.0, an
+  `.slnx` with `src/` and `test/`, xUnit, MudBlazor 9, Blazor Web App with
+  interactive server rendering, minimal APIs, an Authentik proxy-header
+  authentication handler for humans and an API-key handler for machines, a
+  multi-stage Dockerfile, `dotnet test` on every push and a kaniko release
+  pipeline to the Gitea registry. Human-facing apps sit behind an Authentik
+  outpost (`<app>-gate`) with a CNP that admits only that outpost.
+
+## Architecture: ports in the core, adapters around it
+
+```
+                 ┌──────────────────────────────────────────┐
+                 │  Wiki.Host  (ASP.NET Core + Blazor/Mud)  │  composition root,
+                 │  /api/v1, /rank, /webhook, UI pages      │  config, auth
+                 └───────────────┬──────────────────────────┘
+                                 │ uses
+                 ┌───────────────▼──────────────────────────┐
+                 │  Wiki.Application  (use cases)           │  Sync, Rank, Ask,
+                 │                                          │  DepositFact, Queue-
+                 └───────────────┬──────────────────────────┘  Question, Evaluate
+                                 │ depends only on
+                 ┌───────────────▼──────────────────────────┐
+                 │  Wiki.Core  (domain + ports)             │  Note, RawSource,
+                 │  no package references                   │  Report, LinkGraph,
+                 └──────────────────────────────────────────┘  the interfaces
+   implemented by ▲            ▲            ▲            ▲            ▲
+   Adapters.Gitea  Adapters.LlamaCpp  Adapters.TypeSafe  Adapters.FileIndex  Adapters.Anthropic
+   (later: Database, Ollama/Onnx, local Jev, pgvector/Qdrant, OpenAI-compatible answer models)
+```
+
+Rules that keep it modular, enforced by project references and a test:
+
+- `Wiki.Core` references nothing. It holds the domain types and the port
+  interfaces. Adapters reference Core only; they never reference each other
+  or the host. `Wiki.Host` is the only project that knows which adapters
+  exist.
+- Every port has a **contract test suite** in `test/Wiki.Contracts` that
+  runs against every adapter of that port. A new adapter is done when the
+  suite is green. That is what makes "swap the storage" a safe operation.
+- Adapters are selected by configuration and registered by name (keyed
+  services), so several can be active at once. The UI's lab page and the
+  evaluator use that to compare, the API uses the one marked active.
+- Nothing in Core or Application knows about HTTP, Gitea, TypeSafe, files or
+  Kubernetes.
+
+### Ports
+
+| port | what it abstracts | first adapter | examples of the next ones |
+|---|---|---|---|
+| `INoteStore` | read notes, raw sources and reports at a head; create a new document (a fact becomes a raw note in the application layer, the store only moves text) | Gitea repository API (`k.renner/notes`, blob SHA) | git checkout on a volume; a database (CNPG Postgres) with the vault imported; an Obsidian sync folder |
+| `IEmbeddingModel` | text → vector, with a model id and dimension | llama-server `/v1/embeddings` (bge-m3 via wiki-embed, the model that won the German-document comparison on accuracy per cost) | the qwen3 embedding variants from that comparison; ONNX in-process; any OpenAI-compatible endpoint |
+| `IVectorIndex` | store vectors per (model id, document), query top-k | in-memory cosine with a file snapshot per model, as today | pgvector in the database; Qdrant |
+| `IChunker` | split a document into addressable units for typed questions | paragraph splitter (headings, fences), as in `wiki_ask.py` | sentence windows; semantic chunks |
+| `IJudge` | typed questions over a state: Choice, Noul, Score, with probabilities | TypeSafe System One (`jev-latest`, cloud; the wiki records no locally hosted Jev today) | a locally hosted Jev with the same request shape, should TypeSafe offer one; a constrained-output local LLM adapter, flagged as uncalibrated |
+| `IAnswerModel` | prose from a question plus evidence: the selected paragraphs with their notes and the judgements; must cite by slug; streaming | Anthropic Messages API (Claude, model from config, Sonnet by default) | any OpenAI-compatible endpoint, including the local llama-server; a different Claude model per question |
+| `IEvaluator` | measure a retrieval or judge configuration against the labelled set (questions and cited sources in `output/`) | recall@k, hit rate, MRR, as `wiki_rank_eval.py` | judge accuracy against hand-labelled paragraphs |
+| `IIdentity` | who is calling, for attribution of facts and saved answers | Authentik proxy headers (humans), API key (machines), as in shelly-manager | OIDC bearer tokens |
+
+Two ports deserve a sentence of scope each. The judge returns judgements
+with probabilities, never prose, and the UI never presents its output as an
+answer, only as ranked, quoted evidence. The answer model turns that
+evidence into words and is allowed nothing else: it sees the selected
+paragraphs and the judgements, not the whole context, and its output is
+shown next to the evidence it was given. Both are single model calls inside
+the request. The service runs no agent: no tool loop, no vault edits. The
+wiki-synth agent in a Claude session remains the path for artifacts and for
+multi-question synthesis, and it can call `/questions` itself.
+
+### Solution layout
+
+```
+Wiki.slnx
+src/
+  Wiki.Core/               domain types, ports, frontmatter and link parsing
+  Wiki.Application/        use cases; depends on Core only
+  Wiki.Adapters.Gitea/     INoteStore (read at a head, create)
+  Wiki.Adapters.LlamaCpp/  IEmbeddingModel (OpenAI-compatible embeddings)
+  Wiki.Adapters.TypeSafe/  IJudge (System One client)
+  Wiki.Adapters.FileIndex/ IVectorIndex (memory + snapshot per model)
+  Wiki.Adapters.Anthropic/ IAnswerModel (Messages API, streaming)
+  Wiki.Host/               ASP.NET Core: API, webhook, MudBlazor UI, auth,
+                           composition root, appsettings
+test/
+  Wiki.Core.Tests/         parsing, link graph, chunker
+  Wiki.Contracts/          one suite per port, parameterised over adapters
+  Wiki.Application.Tests/  use cases with fake ports
+  Wiki.Host.Tests/         API surface, auth handlers
+```
+
+Own repository `k.renner/wiki`, same shape as shelly-manager: `Dockerfile`,
+`.woodpecker/test.yml` on pull requests, `.woodpecker/release.yml` building
+the image with kaniko into the Gitea registry on push to `main`, tagged
+`build.<unix-ts>` plus the commit SHA so Flux image automation can follow
+it. The homelab repo holds only the manifests. `claude-bot` needs write
+access to the new repository.
+
+Two things the shelly-manager history settles in advance: the TypeSafe
+client is written from the documented field contract (endpoint, bearer key,
+`jev-latest`, Noul/Choice/Score, 255-option cap, 32k-token state budget),
+there is no prior C# client to copy; and the UI needs no login page, because
+identity comes from the outpost's headers, which avoids the Blazor-circuit
+sign-in constraint shelly-manager ran into.
+
+### Configuration
+
+Adapters are declared in `appsettings` and selected by name; secrets come
+through environment variables, filled by ExternalSecret, never from the file.
+
+```json
+"Wiki": {
+  "NoteStore": { "Active": "gitea", "gitea": { "Repository": "k.renner/notes", "Branch": "main" } },
+  "Embeddings": {
+    "Active": "bge-m3",
+    "Models": {
+      "bge-m3":   { "Adapter": "LlamaCpp", "Url": "http://wiki-embed.ai.svc:8080", "Model": "bge-m3" },
+      "e5-large": { "Adapter": "Ollama",   "Url": "http://ollama.ai.svc:11434",    "Model": "multilingual-e5-large" }
+    }
+  },
+  "Judges": {
+    "Active": "typesafe",
+    "Models": {
+      "typesafe":  { "Adapter": "TypeSafe", "Url": "https://api.typesafe.ai/v1/systemone", "Model": "jev-latest" },
+      "jev-local": { "Adapter": "TypeSafe", "Url": "http://jev.ai.svc:8080/v1/systemone",  "Model": "jev" }   // illustration: same adapter, other endpoint
+    }
+  },
+  "Index": { "Active": "file", "file": { "Path": "/data/index" } },
+  "AnswerModels": {
+    "Active": "claude-sonnet",
+    "Models": {
+      "claude-sonnet": { "Adapter": "Anthropic", "Model": "claude-sonnet-5" },
+      "qwen-local":    { "Adapter": "OpenAI",    "Url": "http://llama-server.ai.svc:8080/v1", "Model": "qwen3.6-35b-a3b" }
+    }
+  }
+}
+```
+
+Every embedding model gets its own index namespace. Switching the active
+model is a config change after the new index has been built in the
+background; until then both exist and can be compared. Nothing is
+re-embedded in place.
+
+## The web interface (MudBlazor)
+
+Blazor Web App, interactive server rendering, hosted in `Wiki.Host`. Static
+assets vendored into the image, no CDN. Pages:
+
+1. **Search**: a query box, results ranked by the active index with score and
+   tags; for a phrased question, optionally the paragraph-level hits from the
+   judge with their probabilities, shown as quoted evidence.
+2. **Note**: frontmatter, rendered body with `[[wikilinks]]` resolved,
+   backlinks, sources linking to their raw file.
+3. **Browse**: by tag, by `updated`, recently changed, orphans.
+4. **Answers**: a question box. The answer streams in within seconds: rank,
+   judge, compose, all in the request. Below it the evidence: the paragraphs
+   the judge selected with their notes and probabilities, and the `covered`
+   gate; a low gate is shown as "the wiki does not cover this" instead of an
+   answer. A save button writes the answer to `output/` with the wiki-synth
+   frontmatter (`question`, `sources`, `confidence`), so it joins the
+   labelled set. Underneath, the saved answers, newest first, including the
+   ones the wiki-synth agent wrote from a session.
+5. **Maintenance**: the raw queue with ages, the last consolidation and audit
+   reports, index and sync status.
+6. **Lab**: pick any registered embedding model and judge, run the same query
+   through them side by side, and run the evaluator on the labelled set to
+   get recall@k per configuration. This is the page for "play around with
+   different models".
+7. **Settings**: read-only view of the active adapters and their health.
+
+No editing of notes in the browser. The vault stays a git repository edited
+by the consolidate agent and by hand.
+
+## API v1
+
+Reads are authenticated by the hostname's gate (humans) or API key
+(machines); writes always need an API key so a fact carries its author.
+
+| method and path | purpose |
+|---|---|
+| `GET /api/v1/status` | index commit and age, counts, active adapters |
+| `GET /api/v1/notes?q=&tag=&limit=` | list; `q` ranks through the active index |
+| `GET /api/v1/notes/{slug}` | frontmatter, body, links, backlinks, sources |
+| `GET /api/v1/tags` | tags with counts |
+| `POST /api/v1/rank` | `{question, k, model?}` → ranked slugs; also served at `/rank` for the existing scripts |
+| `POST /api/v1/ask` | `{queries, questions, k, judge?, model?}` → context, typed judgements with the answering paragraphs verbatim, `covered`. For agents and code. |
+| `POST /api/v1/questions` | `{question, k?, judge?, model?, answerModel?, save?}` → the answer text with `[[slug]]` citations, the evidence (paragraphs, probabilities), `covered`, model and token usage; streamed as server-sent events when requested; with `save`, the `output/` path and commit |
+| `POST /api/v1/facts` | deposit a raw source: title, source, `kind: fact`, observed_at, content, tags → path and commit |
+| `GET /api/v1/raw` | the distill queue with ages |
+| `GET /api/v1/reports` | `output/` documents by type, newest first |
+| `POST /api/v1/lab/eval` | run the evaluator for a (model, judge) pair |
+| `POST /webhook` | Gitea push, HMAC as today |
+
+`POST /api/v1/facts` is rejected without `source`, with a `kind` other than
+`fact`, or with content under a minimum length. The raw rule is enforced by
+shape: there is no field for a hypothesis. The file gets the vault's
+provenance frontmatter with `captured_by` set from the API key's identity.
+
+`POST /api/v1/ask` is `wiki_ask.py` moved server-side, so the scripts become
+thin clients and agents no longer need a vault checkout. Its result is
+judgements and quotations, never prose.
+
+`POST /api/v1/questions` is `/ask` plus one answer-model call, in process:
+rank the question, build the context, run the default typed questions
+(answered, where, covered), hand the selected paragraphs and judgements to
+the answer model, stream the prose back. Below the `covered` threshold it
+returns the gap instead of an answer. Time is the sum of the parts, about
+0.2 s rank, 1 to 4 s judge, a few seconds of generation. Cost is one model
+call over a few thousand tokens, a few cents on Sonnet, against a quarter
+dollar for a full agent run.
+
+## Auth and network
+
+- Humans: `wiki.renner.uno`, LAN-only (no `dns.renner.uno/public` label),
+  Ingress backend `ak-outpost-wiki-gate:9000`, a `wiki-gate-egress` CNP in
+  `authentik`, the proxy-header handler trusts `X-Authentik-*` only from that
+  outpost.
+- Machines: `wiki-index.renner.uno` with the API-key handler; the workstation
+  key stays where it is. CI reaches the ClusterIP.
+- Secrets (Gitea token, webhook secret, API keys, TypeSafe key, Anthropic
+  key) reach the
+  pod as environment variables from Kubernetes Secrets filled by
+  ExternalSecret from the `openbao` ClusterSecretStore. The pod itself has
+  no OpenBao access. The Python service fetched its secrets from OpenBao
+  directly through its own Kubernetes-auth role; that role, its policy and
+  the `ai` → `openbao` CNP entry are retired with it.
+- Egress from the pod: Gitea, wiki-embed, `api.typesafe.ai:443`,
+  `api.anthropic.com:443`. Every
+  further adapter that talks to a new endpoint gets its own CNP line, which
+  is the one place adding an adapter touches the cluster.
+
+## Health endpoints
+
+Three endpoints with three different meanings, wired to the .NET health
+checks with tags so that the probes and the humans see the right thing:
+
+| endpoint | meaning | probe |
+|---|---|---|
+| `GET /health` | the process serves HTTP. Always 200 once Kestrel listens; no dependency checks. | liveness |
+| `GET /ready` | the active note store has synced at least once and the active index is loaded; 503 while the first sync or index build runs. A failed later sync keeps the last good state and stays ready. | readiness, plus a startup probe with enough budget for the first sync (the Python service was killed mid-build when its `/health` returned 503 during the initial sync) |
+| `GET /api/v1/status` | the full picture for humans and the Settings page: index commit and age, counts, queue lengths, and one entry per registered adapter with its last check result and latency. | none |
+
+Adapter checks (Gitea reachable, embeddings endpoint answering, judge
+endpoint answering, answer model answering) are reported in `/status` and
+on the Settings page and are never part of `/ready`: a judge outage must not
+take the reader down. Their failures show up as red entries, not as
+restarts.
+
+## Phases
+
+One PR each, verified before the next. The Python `wiki-index` keeps running
+until phase 3 proves parity.
+
+0. **Skeleton.** Repository, solution, `Wiki.Core` with the ports and domain
+   types, `Wiki.Contracts` with the suites, `Wiki.Host` serving `/health`,
+   `/ready` and `/api/v1/status`. CI: test and release pipelines. Verify:
+   image in the registry, pipeline green, the Deployment's three probes
+   wired and the pod Ready.
+1. **Parity with the Python service.** Gitea, LlamaCpp and FileIndex
+   adapters, the sync use case, `/rank` and `/webhook`. Verify: the 40-query
+   recall eval gives the same numbers as the Python service on the same
+   commit; `wiki_rank.py --probe-index` against the new service passes.
+2. **Read API and UI.** Notes, tags, raw, reports; Search, Note, Browse,
+   Maintenance pages; `wiki-gate`. Verify: a note renders with resolved
+   links; an unauthenticated request is redirected to Authentik.
+3. **Ask.** Chunker, TypeSafe adapter, `/api/v1/ask`, scripts as clients.
+   Verify: `test_wiki_ask.py` passes against the API; a wiki-synth run with
+   the definition unchanged. Then the Python service is retired and the
+   `wiki-index` hostname points at the new one.
+4. **Facts.** API keys as an ExternalSecret, the deposit-fact use case, `/api/v1/facts`. Verify:
+   a fact posted from the workstation shows as a `claude-bot` commit and in
+   the next distill.
+5. **Questions.** Anthropic adapter, `/api/v1/questions` with streaming,
+   the Answers page with save. Verify: a question answered in under ten
+   seconds with citations that resolve to the shown evidence; a question the
+   wiki does not cover returns the gap; a saved answer appears in `output/`
+   with the wiki-synth frontmatter and is picked up by the evaluator.
+6. **Lab.** Evaluator, a second embedding model and a second answer model
+   registered, the Lab page. Verify: two models compared on the labelled set
+   from the UI.
+
+## Not in scope
+
+- Editing notes in the browser.
+- Replacing Obsidian; the vault stays a git repository and `notes-push.path`
+  keeps pushing.
+- Public exposure; LAN and VPN only.
+- Running or triggering agents. The service makes single model calls inside
+  a request; it never runs a tool loop or edits the vault. Distill,
+  consolidate and multi-question synthesis stay Claude processes in CI or in
+  a session; the service shows their inputs and outputs and serves their API
+  calls.

kubernetes/RUNBOOK-cold-rebuild.md

@@ -107,7 +107,7 @@ config, and the nodes are addressed by name.
 ## Step 1b — boot all three machines from install media
 
 ```
-https://factory.talos.dev/image/0f6fb8bd8bb53013e9743b7c7b099d96fb9c32fd2464ced32693c2dc0ea5feb9/v1.13.9/metal-amd64.iso
+https://factory.talos.dev/image/0f6fb8bd8bb53013e9743b7c7b099d96fb9c32fd2464ced32693c2dc0ea5feb9/v1.13.10/metal-amd64.iso
 ```
 
 Write it to a USB stick and boot each MS-01 from it. Each comes up in

kubernetes/apps/authentik/blueprints-configmap.yaml

@@ -976,6 +976,66 @@ data:
             kubernetes_ingress_secret_name: "authentik-outpost-tls"
             kubernetes_json_patches: null
 
+      # wiki-gate: the wiki service (ns ai) behind the same passkey flows as
+      # llama-gate. The service trusts X-Authentik-Username only from pod
+      # addresses, and its CNP admits only this outpost, so the gate is the
+      # whole access control for wiki.renner.uno.
+      - id: wiki-gate-provider
+        model: authentik_providers_proxy.proxyprovider
+        identifiers:
+          name: wiki-gate
+        state: present
+        attrs:
+          authentication_flow: !Find [authentik_flows.flow, [slug, passkey-passwordless-authentication]]
+          authorization_flow: !Find [authentik_flows.flow, [slug, passkey-stepup-authorization]]
+          invalidation_flow: !Find [authentik_flows.flow, [slug, default-provider-invalidation-flow]]
+          mode: proxy
+          internal_host: http://wiki.ai.svc.cluster.local:8080
+          internal_host_ssl_validation: false
+          external_host: https://wiki.renner.uno
+          cookie_domain: renner.uno
+          access_token_validity: hours=24
+          refresh_token_validity: days=30
+          intercept_header_auth: true
+
+      - model: authentik_core.application
+        identifiers:
+          slug: wiki-gate
+        state: present
+        attrs:
+          name: Wiki
+          slug: wiki-gate
+          provider: !KeyOf wiki-gate-provider
+          meta_launch_url: https://wiki.renner.uno
+          meta_description: "Notes wiki: search, notes, answers, maintenance"
+
+      - model: authentik_outposts.outpost
+        identifiers:
+          name: wiki-gate
+        state: present
+        attrs:
+          type: proxy
+          service_connection: !KeyOf k8s-conn
+          providers:
+            - !KeyOf wiki-gate-provider
+          config:
+            log_level: info
+            authentik_host: "http://authentik-server.authentik.svc.cluster.local"
+            authentik_host_insecure: false
+            authentik_host_browser: "https://auth.renner.uno/"
+            refresh_interval: "minutes=5"
+            container_image: null
+            object_naming_template: "ak-outpost-%(name)s"
+            kubernetes_namespace: authentik
+            kubernetes_replicas: 1
+            kubernetes_service_type: ClusterIP
+            kubernetes_disabled_components: ["ingress"]
+            kubernetes_image_pull_secrets: []
+            kubernetes_ingress_annotations: {}
+            kubernetes_ingress_class_name: null
+            kubernetes_ingress_secret_name: "authentik-outpost-tls"
+            kubernetes_json_patches: null
+
       - model: authentik_outposts.outpost
         identifiers:
           name: authentik Embedded Outpost

kubernetes/apps/authentik/kustomization.yaml

@@ -16,6 +16,7 @@ resources:
   - prometheus-gate-egress.yaml
   - wordpress-gate-egress.yaml
   - llama-gate-egress.yaml
+  - wiki-gate-egress.yaml
   - ldap-outpost-cert.yaml
   - ldap-outpost-lb.yaml
   - ldap-outpost-cnp.yaml

kubernetes/apps/authentik/wiki-gate-egress.yaml

@@ -0,0 +1,21 @@
+# Lets the wiki-gate outpost reach the wiki service. The authentik namespace
+# baseline CNP otherwise stops any authentik pod from entering ai. Scoped to
+# this outpost's pod label; the matching ingress rule is in ai-ns.yaml.
+apiVersion: cilium.io/v2
+kind: CiliumNetworkPolicy
+metadata:
+  name: wiki-gate-egress
+  namespace: authentik
+spec:
+  endpointSelector:
+    matchLabels:
+      goauthentik.io/outpost-name: wiki-gate
+  egress:
+    - toEndpoints:
+        - matchLabels:
+            "k8s:io.kubernetes.pod.namespace": ai
+            app.kubernetes.io/name: wiki
+      toPorts:
+        - ports:
+            - port: "8080"
+              protocol: TCP

kubernetes/apps/gatus/deployment.yaml

@@ -46,7 +46,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: gatus
-          image: twinproduction/gatus:v5.36.0 # {"$imagepolicy": "flux-system:gatus"}
+          image: twinproduction/gatus:v5.37.0 # {"$imagepolicy": "flux-system:gatus"}
           securityContext:
             allowPrivilegeEscalation: false
             capabilities:

kubernetes/apps/gitea/kustomization.yaml

@@ -6,7 +6,6 @@ kind: Kustomization
 # and verified. See MIGRATION-gitea-woodpecker.md.
 resources:
   - statefulset.yaml
-  - pdb.yaml
   - service.yaml
   - ingressroute-ssh.yaml
   - ingress.yaml

kubernetes/apps/gitea/pdb.yaml

@@ -1,23 +0,0 @@
----
-# Eviction protection for the single-replica Gitea StatefulSet.
-#
-# Gitea runs on SQLite (single writer) and its repos + DB live on a single
-# ReadWriteOnce PVC, so it is deliberately replicas:1 and cannot fail over.
-# With no PDB, a node drain / maintenance evicts the pod abruptly, mid-write,
-# with zero coordination. minAvailable:1 on a 1-replica workload makes the
-# eviction API refuse *voluntary* evictions: `kubectl drain` blocks and
-# surfaces this pod, forcing a conscious decision (drain with
-# --disable-eviction, or scale down first) instead of yanking the live DB.
-# It does NOT block involuntary disruptions (node crash, OOM).
-apiVersion: policy/v1
-kind: PodDisruptionBudget
-metadata:
-  name: gitea
-  namespace: gitea
-  labels:
-    app.kubernetes.io/name: gitea
-spec:
-  minAvailable: 1
-  selector:
-    matchLabels:
-      app.kubernetes.io/name: gitea

kubernetes/apps/grafana-db/postgres.yaml

@@ -4,7 +4,9 @@ metadata:
   name: gf-pg
   namespace: monitoring
 spec:
-  instances: 1
+  instances: 2
+  smartShutdownTimeout: 10
+  stopDelay: 60
   imageName: ghcr.io/cloudnative-pg/postgresql:16
   storage:
     storageClass: ceph-block

kubernetes/apps/home-assistant/ha-pg-cluster.yaml

@@ -30,7 +30,9 @@ metadata:
   name: ha-pg
   namespace: home-assistant
 spec:
-  instances: 1
+  instances: 2
+  smartShutdownTimeout: 10
+  stopDelay: 60
   imageName: ghcr.io/cloudnative-pg/postgresql:16
   storage:
     storageClass: ceph-block
@@ -124,8 +126,7 @@ spec:
       # padding rather than data.
       #
       # The cost is RPO: up to 30min of WAL is unrecoverable if this cluster and
-      # its volume are lost outright. This is a single-instance cluster, so the
-      # archive is the only off-node copy.
+      # its volumes are lost outright.
       archive_timeout: "30min"
       # Fewer checkpoints => fewer full-page writes, since a page is only
       # fully-logged on its first modification after a checkpoint.

kubernetes/apps/immich/cluster.yaml

@@ -59,8 +59,7 @@ spec:
       # padding rather than data.
       #
       # The cost is RPO: up to 30min of WAL is unrecoverable if this cluster and
-      # its volume are lost outright. This is a single-instance cluster, so the
-      # archive is the only off-node copy.
+      # its volumes are lost outright.
       archive_timeout: "30min"
       # Write-reduction tuning. These databases are largely idle, and the
       # Postgres defaults favour throughput over storage that wears out.

kubernetes/apps/influxdb/helmrelease.yaml

@@ -61,6 +61,9 @@ spec:
       enabled: true
       storageClass: ceph-block
       size: 50Gi
+    # A minAvailable:1 PDB on a single replica blocks every node drain.
+    pdb:
+      create: false
     # Bootstrap admin/org/bucket on the fresh PVC. Admin password + token come
     # from the influxdb-bootstrap Secret (OpenBao via ESO), deterministic across
     # rebuilds so the bootstrap token is the live admin token. `influx setup`

kubernetes/apps/monitoring/helmrelease-prometheus.yaml

@@ -304,6 +304,10 @@ spec:
             - matchers:
                 - alertname = "KubeCPUOvercommit"
               receiver: 'null'
+            # Helper alert that only drives the info inhibit rule below.
+            - matchers:
+                - alertname = "InfoInhibitor"
+              receiver: 'null'
             # Flux notification-controller posts info-severity events
             # here (e.g. image-automation commits). Keep them visible
             # but don't repeat-spam every 12h on the same event.
@@ -313,6 +317,23 @@ spec:
               group_wait: 1m
               group_interval: 10m
               repeat_interval: 24h
+        # From kube-prometheus manifests/alertmanager-secret.yaml.
+        inhibit_rules:
+          - source_matchers:
+              - severity = "critical"
+            target_matchers:
+              - severity =~ "warning|info"
+            equal: ['namespace', 'alertname']
+          - source_matchers:
+              - severity = "warning"
+            target_matchers:
+              - severity = "info"
+            equal: ['namespace', 'alertname']
+          - source_matchers:
+              - alertname = "InfoInhibitor"
+            target_matchers:
+              - severity = "info"
+            equal: ['namespace']
         receivers:
           - name: email
             email_configs:

kubernetes/apps/paperless/kustomization.yaml

@@ -11,7 +11,6 @@ resources:
   - protonmail-bridge.yaml
   - ftp-scanner.yaml
   - syncthing.yaml
-  - pdb.yaml
   - network-policy.yaml
   # pprl-pg CNPG Postgres + data/media/consume/redis PVCs (moved here from the
   # retired seed-paperless KS; each carries prune: disabled so ownership

kubernetes/apps/paperless/pdb.yaml

@@ -1,37 +0,0 @@
----
-# Eviction protection for the single-replica stateful paperless sidecars.
-#
-# protonmail-bridge and syncthing each hold state on a single RWO PVC and run
-# replicas:1. minAvailable:1 makes the eviction API refuse voluntary evictions,
-# so a node drain blocks and surfaces these pods instead of evicting them
-# abruptly. Involuntary disruptions (node crash) are not affected.
-#
-# NOTE: the other single-replica paperless pods (paperless, redis, gotenberg,
-# tika, ftp-scanner) are intentionally omitted — they are caches / stateless
-# converters where a blocking PDB would only wedge node drains with no
-# recoverability benefit.
-apiVersion: policy/v1
-kind: PodDisruptionBudget
-metadata:
-  name: protonmail-bridge
-  namespace: paperless
-  labels:
-    app.kubernetes.io/name: protonmail-bridge
-spec:
-  minAvailable: 1
-  selector:
-    matchLabels:
-      app.kubernetes.io/name: protonmail-bridge
----
-apiVersion: policy/v1
-kind: PodDisruptionBudget
-metadata:
-  name: syncthing
-  namespace: paperless
-  labels:
-    app.kubernetes.io/name: syncthing
-spec:
-  minAvailable: 1
-  selector:
-    matchLabels:
-      app.kubernetes.io/name: syncthing

kubernetes/apps/trmnl/cluster.yaml

@@ -4,7 +4,7 @@ metadata:
   name: tr-pg
   namespace: trmnl
 spec:
-  instances: 1
+  instances: 2
   smartShutdownTimeout: 10
   stopDelay: 60
   # PG 18, NOT the repo-standard 16. Terminus ships a committed
@@ -47,8 +47,7 @@ spec:
       # padding rather than data.
       #
       # The cost is RPO: up to 30min of WAL is unrecoverable if this cluster and
-      # its volume are lost outright. This is a single-instance cluster, so the
-      # archive is the only off-node copy.
+      # its volumes are lost outright.
       archive_timeout: "30min"
       # Write-reduction tuning. These databases are largely idle, and the
       # Postgres defaults favour throughput over storage that wears out.

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:0.74.0 # {"$imagepolicy": "flux-system:terminus"}
+          image: ghcr.io/usetrmnl/terminus:0.75.0 # {"$imagepolicy": "flux-system:terminus"}
           ports:
             - name: http
               containerPort: 2345
@@ -197,7 +197,7 @@ spec:
             capabilities:
               drop: ["ALL"]
         - name: sidekiq
-          image: ghcr.io/usetrmnl/terminus:0.74.0 # {"$imagepolicy": "flux-system:terminus"}
+          image: ghcr.io/usetrmnl/terminus:0.75.0 # {"$imagepolicy": "flux-system:terminus"}
           command: ["bundle", "exec", "sidekiq", "-r", "./config/sidekiq.rb"]
           envFrom:
             - configMapRef:

kubernetes/apps/wiki-index/deployment.yaml

@@ -1,137 +0,0 @@
----
-# ServiceAccount is the OpenBao identity (auth/kubernetes/role/wiki-index); no
-# Kubernetes API access needed.
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: wiki-index
-  namespace: ai
-  labels:
-    app.kubernetes.io/name: wiki-index
----
-# Index (~17 MB JSON for 1700 notes). Survives restarts so a pod start does not
-# re-embed the wiki; a lost volume only costs one full sync (~5 min).
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  name: wiki-index-data
-  namespace: ai
-spec:
-  accessModes:
-    - ReadWriteOnce
-  storageClassName: ceph-block
-  resources:
-    requests:
-      storage: 1Gi
----
-# Embedding index over the Notes repo's wiki/ (ci/images/wiki-index). Syncs from
-# Gitea on push webhook and every RESYNC_SECONDS, embeds via wiki-embed, serves
-# POST /rank to ~/Notes/bin/wiki_rank.py through wiki-index.renner.uno.
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: wiki-index
-  namespace: ai
-  labels:
-    app.kubernetes.io/name: wiki-index
-spec:
-  replicas: 1
-  strategy:
-    type: Recreate
-  selector:
-    matchLabels:
-      app.kubernetes.io/name: wiki-index
-  template:
-    metadata:
-      labels:
-        app.kubernetes.io/name: wiki-index
-    spec:
-      serviceAccountName: wiki-index
-      securityContext:
-        runAsNonRoot: true
-        runAsUser: 65534
-        runAsGroup: 65534
-        fsGroup: 65534
-        seccompProfile:
-          type: RuntimeDefault
-      containers:
-        - name: wiki-index
-          # Per-commit tag (build-ci-images.yml): immutable, no same-day overwrite.
-          image: gitea.renner.uno/gitea_admin/wiki-index:2026-09-20-4b529cd1
-          securityContext:
-            allowPrivilegeEscalation: false
-            readOnlyRootFilesystem: true
-            capabilities:
-              drop: ["ALL"]
-          env:
-            - name: GITEA_URL
-              value: https://gitea.renner.uno
-            - name: NOTES_REPO
-              value: k.renner/notes
-            - name: NOTES_BRANCH
-              value: main
-            - name: EMBED_URL
-              value: http://wiki-embed.ai.svc.cluster.local:8080
-            - name: BAO_ADDR
-              value: http://openbao.openbao.svc.cluster.local:8200
-            - name: BAO_ROLE
-              value: wiki-index
-            - name: BAO_SECRET_PATH
-              value: homelab/data/apps/ai/wiki-index
-            - name: INDEX_PATH
-              value: /data/index.json
-            - name: RESYNC_SECONDS
-              value: "1800"
-          ports:
-            - name: http
-              containerPort: 8080
-          # Pure-Python cosine over 1700 x 1024 floats per query; the index itself is ~60 MB in memory.
-          resources:
-            requests:
-              cpu: 100m
-              memory: 256Mi
-            limits:
-              cpu: "1"
-              memory: 512Mi
-          # /health: the process serves (liveness). /ready: an index exists; a cold
-          # start on an empty PVC embeds every note (~5 min) before traffic arrives.
-          startupProbe:
-            httpGet:
-              path: /health
-              port: http
-            periodSeconds: 5
-            failureThreshold: 12
-          readinessProbe:
-            httpGet:
-              path: /ready
-              port: http
-            periodSeconds: 10
-          livenessProbe:
-            httpGet:
-              path: /health
-              port: http
-            periodSeconds: 60
-            timeoutSeconds: 10
-            failureThreshold: 3
-          volumeMounts:
-            - name: data
-              mountPath: /data
-      volumes:
-        - name: data
-          persistentVolumeClaim:
-            claimName: wiki-index-data
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: wiki-index
-  namespace: ai
-  labels:
-    app.kubernetes.io/name: wiki-index
-spec:
-  selector:
-    app.kubernetes.io/name: wiki-index
-  ports:
-    - name: http
-      port: 8080
-      targetPort: http

kubernetes/apps/wiki-index/ingress.yaml

@@ -1,56 +0,0 @@
----
-# wiki-index.renner.uno — LAN-only (no dns.renner.uno/public label), machine
-# client (bin/wiki_rank.py), so Traefik BasicAuth like wiki-embed.renner.uno.
-# Gitea's webhook does not pass here; it targets the ClusterIP Service directly.
-apiVersion: traefik.io/v1alpha1
-kind: Middleware
-metadata:
-  name: wiki-index-basic-auth
-  namespace: ai
-spec:
-  basicAuth:
-    secret: wiki-index-basic-auth
-    realm: wiki-index
----
-# OpenBao key apps/ai/wiki-index-basic-auth, field `users` = htpasswd line.
-apiVersion: external-secrets.io/v1
-kind: ExternalSecret
-metadata:
-  name: wiki-index-basic-auth
-  namespace: ai
-spec:
-  refreshInterval: 1h
-  secretStoreRef:
-    kind: ClusterSecretStore
-    name: openbao
-  target:
-    name: wiki-index-basic-auth
-  dataFrom:
-    - extract:
-        key: apps/ai/wiki-index-basic-auth
----
-apiVersion: networking.k8s.io/v1
-kind: Ingress
-metadata:
-  name: wiki-index
-  namespace: ai
-  annotations:
-    cert-manager.io/cluster-issuer: letsencrypt-cluster
-    traefik.ingress.kubernetes.io/router.middlewares: ai-wiki-index-basic-auth@kubernetescrd
-spec:
-  ingressClassName: traefik
-  tls:
-    - hosts:
-        - wiki-index.renner.uno
-      secretName: wiki-index-tls
-  rules:
-    - host: wiki-index.renner.uno
-      http:
-        paths:
-          - path: /
-            pathType: Prefix
-            backend:
-              service:
-                name: wiki-index
-                port:
-                  number: 8080

kubernetes/apps/wiki/deployment.yaml

@@ -0,0 +1,143 @@
+---
+# Index snapshots per embedding model and the document catalog. A lost volume
+# costs one full sync from Gitea (~10 min).
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: wiki-data
+  namespace: ai
+spec:
+  accessModes:
+    - ReadWriteOnce
+  storageClassName: ceph-block
+  resources:
+    requests:
+      storage: 1Gi
+---
+# Wiki service (konairius/Wiki): mirrors the Notes repo from Gitea, embeds
+# wiki/ via wiki-embed, serves /rank, /api/v1 and the MudBlazor UI. Adapters
+# are selected in appsettings (Wiki__* env overrides); secrets arrive as env
+# from ExternalSecrets, the pod has no OpenBao access.
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: wiki
+  namespace: ai
+  annotations:
+    # Keys, tokens and the Anthropic key arrive via envFrom; a rotated Secret rolls the pod.
+    secret.reloader.stakater.com/reload: wiki-gitea,wiki-api-keys,wiki-typesafe,wiki-anthropic
+  labels:
+    app.kubernetes.io/name: wiki
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: wiki
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: wiki
+    spec:
+      automountServiceAccountToken: false
+      securityContext:
+        runAsNonRoot: true
+        runAsUser: 65534
+        runAsGroup: 65534
+        fsGroup: 65534
+        seccompProfile:
+          type: RuntimeDefault
+      containers:
+        - name: wiki
+          # build.<unix-ts> tags from the Wiki repo's release pipeline (Wiki PR #5).
+          image: gitea.renner.uno/konairius/wiki:build.1790257574
+          securityContext:
+            allowPrivilegeEscalation: false
+            readOnlyRootFilesystem: true
+            capabilities:
+              drop: ["ALL"]
+          env:
+            - name: HOME
+              value: /tmp
+            - name: Wiki__Index__File__Directory
+              value: /data
+            - name: Wiki__NoteStore__Gitea__BaseUrl
+              value: https://gitea.renner.uno
+            - name: Wiki__NoteStore__Gitea__Repository
+              value: k.renner/notes
+            - name: Wiki__NoteStore__Gitea__Branch
+              value: main
+            - name: Wiki__Embeddings__Models__bge-m3__Url
+              value: http://wiki-embed.ai.svc.cluster.local:8080
+            # Pod networks: the CNP admits only the wiki-gate outpost and Gitea.
+            - name: Auth__ReverseProxy__TrustedProxies__0
+              value: fd10:244::/48
+            - name: Auth__ReverseProxy__TrustedProxies__1
+              value: 10.244.0.0/16
+          envFrom:
+            - secretRef:
+                name: wiki-gitea
+            - secretRef:
+                name: wiki-api-keys
+            - secretRef:
+                name: wiki-typesafe
+            - secretRef:
+                name: wiki-anthropic
+                optional: true
+          ports:
+            - name: http
+              containerPort: 8080
+          resources:
+            requests:
+              cpu: 200m
+              memory: 256Mi
+            limits:
+              cpu: "1"
+              memory: 1Gi
+          # /health: the process serves (liveness). /ready: catalog synced once and the
+          # active index loaded; a cold start syncs the whole vault first (~10 min).
+          startupProbe:
+            httpGet:
+              path: /ready
+              port: http
+            periodSeconds: 10
+            failureThreshold: 120
+          readinessProbe:
+            httpGet:
+              path: /ready
+              port: http
+            periodSeconds: 10
+          livenessProbe:
+            httpGet:
+              path: /health
+              port: http
+            periodSeconds: 60
+            timeoutSeconds: 10
+            failureThreshold: 3
+          volumeMounts:
+            - name: data
+              mountPath: /data
+            - name: tmp
+              mountPath: /tmp
+      volumes:
+        - name: data
+          persistentVolumeClaim:
+            claimName: wiki-data
+        - name: tmp
+          emptyDir: {}
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: wiki
+  namespace: ai
+  labels:
+    app.kubernetes.io/name: wiki
+spec:
+  selector:
+    app.kubernetes.io/name: wiki
+  ports:
+    - name: http
+      port: 8080
+      targetPort: http

kubernetes/apps/wiki/externalsecrets.yaml

@@ -0,0 +1,100 @@
+---
+# Gitea token (claude-bot, write:repository: the service creates raw/ files for
+# deposited facts) and the notes webhook secret. Secret keys are the
+# configuration paths the host reads.
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: wiki-gitea
+  namespace: ai
+spec:
+  refreshInterval: 1h
+  secretStoreRef:
+    kind: ClusterSecretStore
+    name: openbao
+  target:
+    name: wiki-gitea
+  data:
+    - secretKey: Wiki__NoteStore__Gitea__Token
+      remoteRef:
+        key: apps/ai/wiki-service
+        property: gitea_token
+    - secretKey: Wiki__Webhook__Secret
+      remoteRef:
+        key: apps/ai/wiki-index
+        property: webhook_secret
+---
+# One API key per machine identity: OpenBao apps/ai/wiki-api-keys, field = name.
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: wiki-api-keys
+  namespace: ai
+spec:
+  refreshInterval: 1h
+  secretStoreRef:
+    kind: ClusterSecretStore
+    name: openbao
+  target:
+    name: wiki-api-keys
+  data:
+    - secretKey: Auth__ApiKeys__workstation
+      remoteRef:
+        key: apps/ai/wiki-api-keys
+        property: workstation
+---
+# TypeSafe System One key for the judge adapter (Wiki:Judges:Models:typesafe).
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: wiki-typesafe
+  namespace: ai
+spec:
+  refreshInterval: 1h
+  secretStoreRef:
+    kind: ClusterSecretStore
+    name: openbao
+  target:
+    name: wiki-typesafe
+  data:
+    - secretKey: Wiki__Judges__Models__typesafe__ApiKey
+      remoteRef:
+        key: apps/ai/wiki-typesafe
+        property: api_key
+---
+# Answer model: Wiki:AnswerModels:Models:claude-sonnet. The pod starts without it (optional
+# secretRef); the questions endpoint answers 503 until the key is placed.
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: wiki-anthropic
+  namespace: ai
+spec:
+  refreshInterval: 1h
+  secretStoreRef:
+    kind: ClusterSecretStore
+    name: openbao
+  target:
+    name: wiki-anthropic
+  data:
+    - secretKey: Wiki__AnswerModels__Models__claude-sonnet__ApiKey
+      remoteRef:
+        key: apps/ai/wiki-anthropic
+        property: api_key
+---
+# BasicAuth users for the machine door; same OpenBao key as the Python service used.
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: wiki-api-basic-auth
+  namespace: ai
+spec:
+  refreshInterval: 1h
+  secretStoreRef:
+    kind: ClusterSecretStore
+    name: openbao
+  target:
+    name: wiki-api-basic-auth
+  dataFrom:
+    - extract:
+        key: apps/ai/wiki-index-basic-auth

kubernetes/apps/wiki/gate-service.yaml

@@ -0,0 +1,20 @@
+# ExternalName mirror so the ai-namespace Ingress can backend to the wiki-gate
+# outpost in the authentik namespace.
+#
+#   browser → traefik (wiki.renner.uno)
+#           → ak-outpost-wiki-gate (ExternalName → authentik ns)
+#           → outpost validates the session + passkey step-up, sets X-Authentik-Username
+#           → http://wiki.ai.svc.cluster.local:8080
+#
+# In-cluster clients (CI agents, the Gitea webhook) address the Service directly.
+apiVersion: v1
+kind: Service
+metadata:
+  name: ak-outpost-wiki-gate
+  namespace: ai
+spec:
+  type: ExternalName
+  externalName: ak-outpost-wiki-gate.authentik.svc.cluster.local
+  ports:
+    - port: 9000
+      targetPort: 9000

kubernetes/apps/wiki/ingress.yaml

@@ -0,0 +1,75 @@
+# wiki.renner.uno — LAN-only (no dns.renner.uno/public label). Traefik backends
+# the wiki-gate outpost, never the Service; the ai CNP admits only that outpost.
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: wiki
+  namespace: ai
+  annotations:
+    cert-manager.io/cluster-issuer: letsencrypt-cluster
+spec:
+  ingressClassName: traefik
+  tls:
+    - hosts:
+        - wiki.renner.uno
+      secretName: wiki-tls
+  rules:
+    - host: wiki.renner.uno
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: ak-outpost-wiki-gate
+                port:
+                  number: 9000
+---
+# wiki-index.renner.uno — the machine door (bin/wiki_rank.py, wiki_ask.py):
+# Traefik BasicAuth, and the identity header stripped so only the outpost path
+# can carry X-Authentik-Username to the service.
+apiVersion: traefik.io/v1alpha1
+kind: Middleware
+metadata:
+  name: wiki-api-basic-auth
+  namespace: ai
+spec:
+  basicAuth:
+    secret: wiki-api-basic-auth
+    realm: wiki
+---
+apiVersion: traefik.io/v1alpha1
+kind: Middleware
+metadata:
+  name: wiki-api-strip-identity
+  namespace: ai
+spec:
+  headers:
+    customRequestHeaders:
+      X-Authentik-Username: ""
+---
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: wiki-api
+  namespace: ai
+  annotations:
+    cert-manager.io/cluster-issuer: letsencrypt-cluster
+    traefik.ingress.kubernetes.io/router.middlewares: ai-wiki-api-strip-identity@kubernetescrd,ai-wiki-api-basic-auth@kubernetescrd
+spec:
+  ingressClassName: traefik
+  tls:
+    - hosts:
+        - wiki-index.renner.uno
+      secretName: wiki-api-tls
+  rules:
+    - host: wiki-index.renner.uno
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: wiki
+                port:
+                  number: 8080

kubernetes/apps/wiki/kustomization.yaml

@@ -1,5 +1,7 @@
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources:
+  - externalsecrets.yaml
   - deployment.yaml
+  - gate-service.yaml
   - ingress.yaml

kubernetes/apps/woodpecker/cluster.yaml

@@ -22,7 +22,9 @@ metadata:
     # migration deliberately withheld this while a rollback still existed.
     kustomize.toolkit.fluxcd.io/prune: disabled
 spec:
-  instances: 1
+  instances: 2
+  smartShutdownTimeout: 10
+  stopDelay: 60
   imageName: ghcr.io/cloudnative-pg/postgresql:16
   storage:
     storageClass: ceph-block
@@ -91,8 +93,7 @@ spec:
       # padding rather than data.
       #
       # The cost is RPO: up to 30min of WAL is unrecoverable if this cluster and
-      # its volume are lost outright. This is a single-instance cluster, so the
-      # archive is the only off-node copy.
+      # its volumes are lost outright.
       archive_timeout: "30min"
   resources:
     requests:

kubernetes/apps/woodpecker/kustomization.yaml

@@ -3,7 +3,6 @@ kind: Kustomization
 resources:
   - rbac.yaml
   - server.yaml
-  - pdb.yaml
   - agent.yaml
   - service.yaml
   - ingress.yaml
@@ -22,7 +21,7 @@ resources:
   # OpenBao access, no NetworkPolicy needed. server.yaml/agent.yaml keep their
   # Reloader annotations; externalsecret.yaml keeps the 10m refreshInterval.
   # --- namespace migration, stages 1-2 (issue #433) ---
-  # Stage 2 has moved the workloads above (server, agent, service, ingress, pdb,
+  # Stage 2 has moved the workloads above (server, agent, service, ingress,
   # rbac, secrets, policies) into the `woodpecker` namespace and pointed the
   # server's DSN at wp-pg-rw.woodpecker.svc. Stage 3 retired the `apps`
   # originals; these four now describe the surviving cluster. History and the

kubernetes/apps/woodpecker/pdb.yaml

@@ -1,27 +0,0 @@
----
-# Eviction protection for the single-replica Woodpecker server StatefulSet.
-#
-# The server is SQLite-backed (single writer) on a single RWO PVC, so it is
-# deliberately replicas:1. minAvailable:1 makes the eviction API refuse
-# voluntary evictions so a node drain blocks and surfaces this pod rather
-# than yanking the live CI DB mid-write. Involuntary disruptions are not
-# affected.
-#
-# The selector MUST include app.kubernetes.io/component: server: the agent
-# Deployment in this same namespace shares app.kubernetes.io/name: woodpecker
-# (component: agent), and a name-only selector would wrongly also cover the
-# stateless, disposable agents.
-apiVersion: policy/v1
-kind: PodDisruptionBudget
-metadata:
-  name: woodpecker-server
-  namespace: woodpecker
-  labels:
-    app.kubernetes.io/name: woodpecker
-    app.kubernetes.io/component: server
-spec:
-  minAvailable: 1
-  selector:
-    matchLabels:
-      app.kubernetes.io/name: woodpecker
-      app.kubernetes.io/component: server

kubernetes/clusters/homelab/wiki.yaml

@@ -1,17 +1,17 @@
 apiVersion: kustomize.toolkit.fluxcd.io/v1
 kind: Kustomization
 metadata:
-  name: wiki-index
+  name: wiki
   namespace: flux-system
 spec:
   interval: 10m
   retryInterval: 1m
-  # First start on an empty PVC embeds every note (~5 min) before /health is 200.
-  timeout: 20m
+  # First start on an empty PVC syncs and embeds the whole vault before /ready is 200.
+  timeout: 25m
   sourceRef:
     kind: GitRepository
     name: flux-system
-  path: ./kubernetes/apps/wiki-index
+  path: ./kubernetes/apps/wiki
   prune: true
   wait: true
   dependsOn:

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

@@ -149,20 +149,24 @@ spec:
             - port: "8080"
               protocol: TCP
 ---
-# wiki-index: Traefik (LAN clients behind BasicAuth) and Gitea (push webhook)
-# may reach it; it reaches OpenBao for its credentials. Gitea itself is reached
-# through Traefik, which the namespace egress above already allows.
+# wiki: the wiki-gate outpost (humans, after Authentik), Traefik (the machine
+# door wiki-index.renner.uno, BasicAuth with X-Authentik-Username stripped) and
+# Gitea (push webhook) may reach it. Gitea and wiki-embed are reached through
+# the namespace egress above; no OpenBao access.
 apiVersion: cilium.io/v2
 kind: CiliumNetworkPolicy
 metadata:
-  name: wiki-index
+  name: wiki
   namespace: ai
 spec:
   endpointSelector:
     matchLabels:
-      app.kubernetes.io/name: wiki-index
+      app.kubernetes.io/name: wiki
   ingress:
     - fromEndpoints:
+        - matchLabels:
+            "k8s:io.kubernetes.pod.namespace": authentik
+            goauthentik.io/outpost-name: wiki-gate
         - matchLabels:
             "k8s:io.kubernetes.pod.namespace": ingress
             app.kubernetes.io/name: traefik
@@ -173,12 +177,3 @@ spec:
         - ports:
             - port: "8080"
               protocol: TCP
-  egress:
-    - toEndpoints:
-        - matchLabels:
-            "k8s:io.kubernetes.pod.namespace": openbao
-            app.kubernetes.io/name: openbao
-      toPorts:
-        - ports:
-            - port: "8200"
-              protocol: TCP

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

@@ -65,11 +65,11 @@ spec:
               protocol: UDP
             - port: "53"
               protocol: TCP
-    # Push webhook of the notes repo to wiki-index.
+    # Push webhook of the notes repo to the wiki service.
     - toEndpoints:
         - matchLabels:
             "k8s:io.kubernetes.pod.namespace": ai
-            app.kubernetes.io/name: wiki-index
+            app.kubernetes.io/name: wiki
       toPorts:
         - ports:
             - port: "8080"

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

@@ -31,16 +31,6 @@ spec:
         - ports:
             - port: "8200"
               protocol: TCP
-    # wiki-index (ns ai) logs in via auth/kubernetes/role/wiki-index and reads
-    # its Gitea token and webhook secret on every sync.
-    - fromEndpoints:
-        - matchLabels:
-            "k8s:io.kubernetes.pod.namespace": ai
-            app.kubernetes.io/name: wiki-index
-      toPorts:
-        - ports:
-            - port: "8200"
-              protocol: TCP
     # netbird-service-sync logs in via auth/kubernetes/role/netbird-service-sync
     # and reads the NetBird PAT on every pass.
     - fromEndpoints:

kubernetes/infrastructure/openbao/policies/wiki-index.hcl

@@ -1,21 +0,0 @@
-# OpenBao policy: wiki-index
-#
-# The wiki-index Deployment (namespace ai) reads its Gitea token and the
-# webhook HMAC secret on every use. Read-only on that one path.
-#
-# NOT applied by Flux. Apply ONCE with an admin token:
-#
-#   bao policy write wiki-index kubernetes/infrastructure/openbao/policies/wiki-index.hcl
-#   bao write auth/kubernetes/role/wiki-index \
-#     bound_service_account_names=wiki-index \
-#     bound_service_account_namespaces=ai \
-#     policies=wiki-index ttl=15m
-#
-# Secret: homelab/apps/ai/wiki-index, keys `gitea_token` (read:repository on
-# the notes repo) and `webhook_secret` (the Gitea webhook's secret).
-#
-# Do NOT set token_no_default_policy=true (kv-v2 preflight needs the default policy).
-
-path "homelab/data/apps/ai/wiki-index" {
-  capabilities = ["read"]
-}

kubernetes/infrastructure/rook-ceph-cluster/cephcluster.yaml

@@ -21,17 +21,29 @@ spec:
     modules:
       - name: pg_autoscaler
         enabled: true
-  # Rotates daemon keys to aes256k for CVE-2025-30156 (#527). Opt-in; disabled
-  # by default. Increment keyGeneration to rotate again.
-  #
-  # Daemon keys only — aes256k over the CSI mount path needs kernel 7.0+ and
-  # these nodes run 6.18, so CSI stays on aes and the client-key checks stay
-  # raised. keyType is unset so Rook picks it.
+  # CephX keys on aes256k for CVE-2025-30156 (#527). Increment keyGeneration
+  # to rotate again. CSI kernel mounts need aes256k in libceph: Talos
+  # >= v1.13.10 backports it to 6.18 (siderolabs/pkgs 2da2cdc).
   security:
     cephx:
+      # auth_allowed_ciphers. Every key must be aes256k first, or the cluster
+      # locks itself out; recovery is in Rook's cephx-key-rotation doc.
+      allowedCiphers:
+        - aes256k
       daemon:
         keyRotationPolicy: KeyGeneration
         keyGeneration: 2
+      csi:
+        keyRotationPolicy: KeyGeneration
+        keyGeneration: 2
+        keyType: aes256k
+        # 0 deletes prior keys. Set 1 before the next rotation so PVCs
+        # mounted with the old key keep working until they are remounted.
+        keepPriorKeyCountMax: 0
+      rbdMirrorPeer:
+        keyRotationPolicy: KeyGeneration
+        keyGeneration: 2
+        keyType: aes256k
   # CephFS cloner pool raised from the default 4. Velero clones a
   # VolumeSnapshot per PVC, and 4 threads stall a multi-PVC backup with
   # `rados: "all cloner threads are busy"`.

kubernetes/talos/patches/cluster.yaml

@@ -24,7 +24,7 @@ machine:
   # The Kubernetes version is a separate decision, moved by
   # `talosctl upgrade-k8s`.
   install:
-    image: factory.talos.dev/metal-installer/0f6fb8bd8bb53013e9743b7c7b099d96fb9c32fd2464ced32693c2dc0ea5feb9:v1.13.9
+    image: factory.talos.dev/metal-installer/0f6fb8bd8bb53013e9743b7c7b099d96fb9c32fd2464ced32693c2dc0ea5feb9:v1.13.10
   features:
     rbac: true
     # stableHostname is NOT here: it is the v1alpha1 spelling of what the