Merge pull request 'chore(deps): Update registry.k8s.io/sig-storage/snapshot-controller Docker tag to v8.7.0' (#138) from renovate/registry.k8s.io-sig-storage-snapshot-controller-8.x into main

Reviewed-on: #104

apps/wave-0/jackett.yaml

@@ -78,7 +78,7 @@ spec:
     spec:
       containers:
       - name: jackett
-        image: lscr.io/linuxserver/jackett:v0.24.2865-ls7
+        image: lscr.io/linuxserver/jackett:v0.24.3025-ls29
         ports:
         - containerPort: 9117
         volumeMounts:

apps/wave-0/pihole.yaml

@@ -62,7 +62,7 @@ spec:
     spec:
       containers:
       - name: pihole
-        image: pihole/pihole:2026.10.0
+        image: pihole/pihole:2026.10.1
         ports:
         - containerPort: 80
         env:

apps/wave-0/plex.yaml

@@ -120,7 +120,7 @@ spec:
     spec:
       containers:
       - name: plex
-        image: plexinc/pms-docker:1.43.4.10903-e5521bd8c
+        image: plexinc/pms-docker:1.43.6.11085-d1e52e169
         ports:
         - containerPort: 32400
         env:

apps/wave-0/qbittorrent.yaml

@@ -122,7 +122,7 @@ spec:
     spec:
       containers:
       - name: qbittorrent
-        image: lscr.io/linuxserver/qbittorrent:5.1.2
+        image: lscr.io/linuxserver/qbittorrent:5.3.0
         ports:
         - containerPort: 8080
         env:

apps/wave-1/radarr.yaml

@@ -122,7 +122,7 @@ spec:
     spec:
       containers:
       - name: radarr
-        image: lscr.io/linuxserver/radarr:5.21.1
+        image: lscr.io/linuxserver/radarr:5.28.0
         ports:
         - containerPort: 7878
         env:

apps/wave-1/semaphore.yaml

@@ -78,7 +78,7 @@ spec:
     spec:
       containers:
       - name: semaphore
-        image: semaphoreui/semaphore:v2.19.10
+        image: semaphoreui/semaphore:v2.19.17
         ports:
         - containerPort: 3000
         env:

apps/wave-1/sonarr.yaml

@@ -122,7 +122,7 @@ spec:
     spec:
       containers:
       - name: sonarr
-        image: lscr.io/linuxserver/sonarr:4.0.15
+        image: lscr.io/linuxserver/sonarr:4.0.20
         ports:
         - containerPort: 8989
         env:

apps/wave-2/seerr.yaml

@@ -75,7 +75,7 @@ spec:
     spec:
       containers:
       - name: seerr
-        image: ghcr.io/seerr-team/seerr:v3.4.1
+        image: ghcr.io/seerr-team/seerr:v3.5.1
         ports:
         - containerPort: 5055
         volumeMounts:

catalog/jackett.yaml

@@ -16,7 +16,7 @@
 name: jackett
 kind: container
 source:
-  image: lscr.io/linuxserver/jackett:v0.24.2865-ls7
+  image: lscr.io/linuxserver/jackett:v0.24.3025-ls29
 exposure: internal              # LAN-only web UI at jackett.${BASE_DOMAIN} (docs/13 row 4; R-DNS/R-NET)
 egress: vpn                     # indexer scraping via node PIA tunnel + kill-switch (docs/03; ADR-0015; R-NET-05/06)
 storage:

catalog/pihole.yaml

@@ -5,7 +5,7 @@
 name: pihole
 kind: container
 source:
-  image: pihole/pihole:2026.10.0
+  image: pihole/pihole:2026.10.1
 exposure: internal            # LAN-only admin UI (docs/13 row 6; R-DNS/R-NET)
 egress: internet              # normal WAN egress (docs/03; R-NET-05)
 storage:

catalog/plex.yaml

@@ -12,7 +12,7 @@
 name: plex
 kind: container
 source:
-  image: plexinc/pms-docker:1.43.4.10903-e5521bd8c
+  image: plexinc/pms-docker:1.43.6.11085-d1e52e169
 # plexinc/pms-docker env. Rendered VERBATIM onto the app container by render.py (schema env list).
 env:
   # PLEX_UID/PLEX_GID: the image boots as root (s6 PID1), chowns /config to this uid/gid, then drops

catalog/qbittorrent.yaml

@@ -30,7 +30,7 @@
 name: qbittorrent
 kind: container
 source:
-  image: lscr.io/linuxserver/qbittorrent:5.1.2   # pinned stable tag (R-UPD-01); update.range governs advancement
+  image: lscr.io/linuxserver/qbittorrent:5.3.0   # pinned stable tag (R-UPD-01); update.range governs advancement
 # LinuxServer images run their service as the user `abc`, whose uid/gid these two set. They are
 # LOAD-BEARING FOR THE BULK MOUNT, not cosmetic — exactly as on sonarr/radarr. Measured on prod
 # 2026-09-12 BEFORE this change: `id` inside the container reported the qbittorrent-nox process as

catalog/radarr.yaml

@@ -8,7 +8,7 @@
 name: radarr
 kind: container
 source:
-  image: lscr.io/linuxserver/radarr:5.21.1   # pinned stable v5 tag (R-UPD-01); update.range governs advancement
+  image: lscr.io/linuxserver/radarr:5.28.0   # pinned stable v5 tag (R-UPD-01); update.range governs advancement
 # LinuxServer images run their service as the user `abc`, whose uid/gid these two set. They are
 # LOAD-BEARING for the bulk mount, not cosmetic: see the storage note below. The default is 911,
 # which cannot write a 1000:3000-owned 0755 tree.

catalog/seerr.yaml

@@ -24,7 +24,7 @@
 name: seerr
 kind: container
 source:
-  image: ghcr.io/seerr-team/seerr:v3.4.1   # Seerr: maintained Overseerr/Jellyseerr successor, Plex-native request UI (docs/13 row 5); served on 5055
+  image: ghcr.io/seerr-team/seerr:v3.5.1   # Seerr: maintained Overseerr/Jellyseerr successor, Plex-native request UI (docs/13 row 5); served on 5055
 # The ghcr.io/seerr-team/seerr image runs as the non-root user `node:node` (UID 1000 / GID 1000 —
 # the standard node base-image user; confirmed from the image config's User field). On boot the app
 # creates /app/config/logs and writes its settings/DB under the mounted /app/config PVC. A fresh

catalog/semaphore.yaml

@@ -22,7 +22,7 @@
 name: semaphore
 kind: container
 source:
-  image: semaphoreui/semaphore:v2.19.10   # pinned recent stable tag (R-UPD-01); update.range governs advancement
+  image: semaphoreui/semaphore:v2.19.17   # pinned recent stable tag (R-UPD-01); update.range governs advancement
 env:
   # --- PostgreSQL connection (the CNPG-DB pattern). DIALECT/HOST/PORT/DB/USER are literals; PASS is
   #     sourced from the in-namespace SOPS secret (the CNPG -app secret lives in ns semaphore-db,

catalog/sonarr.yaml

@@ -8,7 +8,7 @@
 name: sonarr
 kind: container
 source:
-  image: lscr.io/linuxserver/sonarr:4.0.15   # pinned stable v4 tag (R-UPD-01); update.range governs advancement
+  image: lscr.io/linuxserver/sonarr:4.0.20   # pinned stable v4 tag (R-UPD-01); update.range governs advancement
 # LinuxServer images run their service as the user `abc`, whose uid/gid these two set. They are
 # LOAD-BEARING for the bulk mount, not cosmetic: see the storage note below. The default is 911,
 # which cannot write a 1000:3000-owned 0755 tree.

decisions/2026-10-31-pm-agent-digest-99.md

@@ -0,0 +1,41 @@
+---
+date: 2026-10-31
+branch: chore/pm-agent-digest-99
+title: Pin pm-agent dispatcher and worker to the agent-runner digest built from PR #99's merge
+---
+
+## What changed
+
+- `platform/pm-agent/deployment.yaml`: the dispatcher `image:` moves from
+  `agent-runner@sha256:df36d9b7…` (images run 383) to
+  `agent-runner@sha256:14a42ba8281ecd98005f5d99ecda4fb729104c783b01584097c32e104ced1bb2`.
+  `config-generation` goes from "4" to "5" so the pod rolls.
+- `platform/pm-agent/configmap.yaml`: `PM_WORKER_IMAGE` gets the same digest. A comment line
+  records where it came from. The `# renovate-digest:` marker still sits directly above both
+  values.
+- No other values changed. `PM_DRY_RUN` stays "false". `PM_DECISION_MAX_TURNS` is not set, so
+  it keeps its in-code default of 1. No `*.sops.yaml` was touched.
+
+## What I verified
+
+- PR #99's merge commit is `466f63ec3c3df968a1dab25a8811dcd41961efde` (origin/main HEAD at
+  branch time).
+- The Gitea Actions tasks API shows the `images` workflow (images.yaml) on that commit as
+  **run 394** (task 643), with event `push` and status `success`.
+- I resolved the digest read-only from the registry by HEADing the manifests with OCI and
+  Docker Accept headers. Both `agent-runner:sha-466f63ec3c3d` and `agent-runner:main` returned
+  `200`, an `application/vnd.oci.image.manifest.v1+json` content type, and
+  `docker-content-digest: sha256:14a42ba8281ecd98005f5d99ecda4fb729104c783b01584097c32e104ced1bb2`.
+  The two are identical.
+- Toolbox gate: the rc and skipped stages are in the PR description.
+
+## What I did NOT verify
+
+- That the dispatcher actually rolls to the new digest after merge, and that Flux applies it.
+  Flux's `lastAppliedRevision` and the pod's image were not checked. That is post-merge work.
+- That the new image surfaces the triage failure's real cause. It will show only on the next
+  failing triage, in the dispatcher log.
+- That admission (rule 7, `imagePullSecrets`) admits worker Jobs from this digest. The
+  template comes from `infra/agent/` at PR #99's merge, which still carries the
+  `imagePullSecrets` entry, but no Job was created to prove it.
+- I did not run the image's own selftest against this digest.

decisions/2026-10-31-pm-agent-go-live.md

@@ -0,0 +1,55 @@
+---
+date: 2026-10-31
+branch: chore/pm-agent-go-live
+title: Take pm-agent out of dry run (operator-approved); label scope and worker caps unchanged
+---
+
+## What changed
+
+- `platform/pm-agent/configmap.yaml`: `PM_DRY_RUN` `"true"` -> `"false"`. The operator approved
+  this after reading the dry-run triage of issue #97. `PM_REQUIRE_LABEL: agent`,
+  `PM_MAX_ACTIVE_WORKERS: 2`, `PM_MAX_NEW_WORKERS_PER_CYCLE: 1`, the worker image digest and every
+  other knob are unchanged. The two comments that said dry run was the only mode that worked
+  (because the run-340 digest lacked `imagePullSecrets`) now describe the run-383 digest that
+  PR #96 pinned.
+- `platform/pm-agent/deployment.yaml`: `config-generation` `"3"` -> `"4"`. Without the bump the
+  dispatcher keeps its startup config and stays in dry run.
+- `platform/pm-agent/README.md` and `docs/plans/pm-agent-issue-to-pr.md` (follow-up 3): the
+  "currently dry run" status text now says dry run is off. `runbooks/pm-agent.md` is unchanged.
+  Its "stop it: set `PM_DRY_RUN: "true"`" step and its admission-refusal troubleshooting row
+  are still accurate.
+
+## What I verified
+
+Read-only, `kubectl --context k3s-prod` through the toolbox, 2026-10-31 ~11:45 local, with Flux
+`pm-agent` and `platform-config` both at `main@1126740`:
+
+- ClusterPolicy `pm-agent-job-shape`: `Ready=True`, `validationFailureAction=Enforce`,
+  `background=false`. It has seven rules, including `worker-pull-secret-must-be-the-committed-one`.
+- RBAC: ServiceAccounts `pm-agent` and `pm-agent-worker`, Role `pm-agent` and RoleBinding
+  `pm-agent` (roleRef `pm-agent`, subject `ServiceAccount/pm-agent`) all exist. `auth can-i`
+  as `system:serviceaccount:pm-agent:pm-agent` returned `yes` for `create jobs.batch` and `no`
+  for `delete jobs.batch`.
+- Secrets (key names only): `pm-agent-registry` is `kubernetes.io/dockerconfigjson` with key
+  `.dockerconfigjson`. `pm-agent-credentials` is `Opaque` with keys `claude-code-oauth-token`
+  and `gitea-token`.
+- Egress: `default-deny` NetworkPolicy exists. CiliumNetworkPolicies `pm-agent-allow-egress`
+  and `pm-agent-worker-allow-egress` both report `Valid=True`.
+- Deployment `pm-agent` is 1/1 on `agent-runner@sha256:df36d9b7…` with
+  `config-generation: "3"` live. No Jobs exist in the namespace.
+- `platform/pm-agent/{configmap,deployment}.yaml`, README and docs do not match any
+  `sensitive_paths` glob in `infra/gitea/approval-policy.json`, so no review or override applies.
+
+## What I did NOT verify
+
+- **That a real worker Job is admitted and completes.** Nothing can show this until a labelled
+  issue gets a `start` decision after the merge. The L0 Kyverno suite shows the policy accepts
+  the committed template. Whether the API server admits the Job built from the df36d9b image's
+  baked template has not been tested live.
+- That the worker pod can pull its image with `pm-agent-registry`, reach Gitea and the model
+  through its egress policy, and push a branch and open a PR. None of this has run before.
+- The pod list also shows a stale `pm-agent-65db599649-v678g` (25d, `ContainerStatusUnknown`,
+  from an old ReplicaSet). It does not block anything, but I did not investigate it. Clearing
+  it is an operator action.
+- CI: see the PR for the gate result. Locally the best possible result is rc 3, with only
+  `gitea-settings` not run.

decisions/2026-10-31-pm-agent-triage-exit.md

@@ -0,0 +1,77 @@
+---
+date: 2026-10-31
+branch: fix/pm-agent-triage-exit
+title: pm-agent triage fails with "claude exited 1:" and no message; log the CLI's stdout envelope so the cause is visible
+---
+
+## What changed
+
+- `infra/agent/pm-dispatch.py`, `ask_pm()`: on a non-zero exit the error now comes from a new
+  `describe_cli_failure()`, not from `proc.stderr` alone. With `--output-format json` the CLI
+  reports its own failures as the result envelope on **stdout** and writes nothing to stderr,
+  which is why both failures today logged `claude exited 1: ` with an empty message. The new
+  line carries the envelope's `subtype`, `is_error`, `api_error_status`, `num_turns`,
+  `duration_ms`, `total_cost_usd`, `stop_reason`, its `result`/`error` text, and the tails of
+  stdout and stderr. It names silence explicitly when both streams are empty.
+- `redact()`: everything in that message, and in `extract_decision()`'s "no decision object"
+  error, passes through it. It covers `sk-ant-…`, `Bearer`/`token` values, and `user:pass@` in
+  both `http://` and `https://` URLs.
+- `PM_DECISION_MAX_TURNS`: a new knob. It defaults to 1, today's value, so behaviour is
+  unchanged, and it is bounded to 1–5. If the newly visible envelope says `error_max_turns`,
+  the remedy is a ConfigMap change rather than another image build. Documented in
+  `platform/pm-agent/README.md`.
+- Selftest: four new assertions. They cover an empty stderr with the cause on stdout, a
+  stderr-only failure, total silence, and redaction.
+
+## What I verified
+
+- **Timeline (Loki, `{namespace="pm-agent"}`, and `kubectl logs`):**
+  - **16:37:38 to 16:38:00**: pod `pm-agent-898fd8f5f-dp5hs`, image **c4eba5b3**,
+    config-generation 2, dry run. It triaged #97 in **22 s**, logged `PM says comment`, and
+    posted the 16:38:00Z comment. The thread then held only the issue body.
+  - **16:43:09 to 16:44:00**: pod `pm-agent-f7c9b7fcf-j8mzn`, image **df36d9b7**,
+    config-generation 3, **still dry run**. It logged `claude exited 1: ` with an empty
+    message after **51 s**.
+  - **16:55:42 to 16:56:36**: pod `pm-agent-7796db8bcb-p5dsm`, df36d9b7, config-generation
+    4, live. The same empty failure, after **54 s**.
+  - The only successful triage ever was the 16:38 one. Every earlier `898fd8f5f`/`5db55d558c`
+    log line is a startup crash (Gitea `GET /user` 401), not a triage.
+- **Going live is NOT the cause.** The first failure happened in dry run. `ask_pm()` has no
+  dry-run branch: the prompt, flags, tools (`--tools ""`) and cwd are identical in both
+  modes. `PM_DRY_RUN` gates only `create_job()`, which runs after the model has answered.
+- **Ruled out, with evidence:**
+  - **Timeout**: 51 to 54 s against a 900 s limit, and a timeout raises `TimeoutExpired`,
+    not rc 1.
+  - **Budget cap**: the PM call passes no `--max-budget-usd`.
+  - **Prompt size**: the thread is the issue body (293 chars) plus three comments
+    (1871 + 404 + 77 chars), and the persona is 8 KB.
+  - **Writable HOME**: HOME=`/workspace` (emptyDir), and `CLAUDE_CONFIG_DIR=/workspace/.claude`
+    was written at 16:56.
+  - **Egress**: a TLS 1.3 handshake to `api.anthropic.com:443` from the dispatcher pod
+    succeeds in 0.06 s.
+  - **Model name and CLI version**: the same `claude-opus-5` and CLI 2.1.285 succeeded at
+    16:38. Between c4eba5b and df36d9b, `infra/agent/` differs only by a template selftest
+    assertion and the toolbox base digest.
+- **A hint, not proof:** `/workspace/.claude/.claude.json` in the live pod has
+  `cachedExtraUsageDisabledReason: 'out_of_credits'`. No token was read or printed.
+- Offline selftest: `PM_SELFTEST=1` against the worktree's template and persona prints
+  `selftest OK`, including the 4 new assertions.
+- Toolbox gate: see the PR description for the rc and the stages that were skipped.
+
+## What I did NOT verify
+
+- **The root cause. UNVERIFIED.** The CLI's own message was discarded, `--no-session-persistence`
+  leaves no transcript, and I did not run `claude` in the pod. The candidates still open:
+  - **Usage or rate limit on the subscription seat.** The seat is shared with the operator's
+    interactive use. The `out_of_credits` extra-usage flag fits this. So does a ~50 s run,
+    which matches the CLI exhausting its 429/529 retries.
+  - **`error_max_turns`.** With `--max-turns 1` and `--json-schema`, an answer that fails the
+    schema cannot be retried. The failing thread now invites `implement` (a branch plus a
+    long brief), where the 16:38 one produced a short `comment`. ~50 s is about two
+    generations of the 22 s success.
+- **The 17:11 retry will NOT reveal the cause.** It runs the old image, which still discards
+  stdout. The cause becomes visible only after this PR merges, CI re-publishes agent-runner,
+  and a follow-up PR bumps the dispatcher digest (`deployment.yaml` and the `PM_WORKER_IMAGE`
+  in `configmap.yaml`, plus a `config-generation` bump).
+- That the CLI's error envelope carries exactly these key names. The parser takes whichever
+  keys are present and falls back to raw tails.

docs/plans/pm-agent-issue-to-pr.md

@@ -257,7 +257,9 @@ about runtime behaviour in this document is a design claim, not a measurement.
    bot's permission is `write`, not `admin`** — that measurement is the control that keeps
    the agent out of its own approval gate.
 3. **First run with `PM_DRY_RUN=true` and `PM_REQUIRE_LABEL=agent`**, on one issue written
-   for the purpose. Read what the PM says before letting it write anything.
+   for the purpose. Read what the PM says before letting it write anything. *Done:* dry-run
+   triage of issue #97 read; `PM_DRY_RUN=false` on 2026-10-31
+   (`decisions/2026-10-31-pm-agent-go-live.md`), `PM_REQUIRE_LABEL=agent` kept.
 4. **Tighten the admission image pin** from the `@sha256:*` wildcard to the literal digest.
    One line, reviewed.
 5. **Narrow `world:443` to `toFQDNs: api.anthropic.com`** — after verifying Cilium's DNS

infra/agent/pm-dispatch.py

@@ -214,6 +214,12 @@ class Config:
         # ConfigMap without rebuilding the image.
         self.push_on_red = env("PM_PUSH_ON_RED_GATE", "false")
         self.pm_timeout = env_int("PM_DECISION_TIMEOUT_SECONDS", 900)
+        # The PM holds no tools, so the only thing a second turn can be spent on is the CLI's
+        # structured-output step re-asking the model after an answer that failed the schema.
+        # 1 is the long-standing value; it is a knob so that, if the failure envelope now
+        # logged by describe_cli_failure() says `error_max_turns`, the remedy is a ConfigMap
+        # change rather than another image build.
+        self.pm_max_turns = env_int("PM_DECISION_MAX_TURNS", 1)
         # Opt-in gate. Empty (the default) means every open issue is in scope, which is the
         # behaviour the service was asked for. Setting it to a label name — `agent` is the
         # conventional one — narrows the agent to issues a human has explicitly handed it,
@@ -231,6 +237,8 @@ class Config:
 
         if self.max_active_workers < 1:
             die("PM_MAX_ACTIVE_WORKERS must be >= 1")
+        if not 1 <= self.pm_max_turns <= 5:
+            die("PM_DECISION_MAX_TURNS must be between 1 and 5")
         if "@sha256:" not in self.worker_image:
             # The admission policy requires a digest too, so a tag here would produce a Job
             # that is created and then DENIED — a failure visible only in the dispatcher's
@@ -437,7 +445,7 @@ def ask_pm(cfg: Config, thread: str) -> dict:
         "--system-prompt-file", cfg.persona_file,
         "--tools", "",
         "--permission-prompts", "none",
-        "--max-turns", "1",
+        "--max-turns", str(cfg.pm_max_turns),
         "--output-format", "json",
         "--json-schema", json.dumps(DECISION_SCHEMA),
         "--no-session-persistence",
@@ -445,10 +453,76 @@ def ask_pm(cfg: Config, thread: str) -> dict:
     proc = subprocess.run(cmd, input=thread, capture_output=True, text=True,
                           timeout=cfg.pm_timeout)
     if proc.returncode != 0:
-        raise RuntimeError(f"claude exited {proc.returncode}: {proc.stderr.strip()[:800]}")
+        raise RuntimeError(describe_cli_failure(proc.returncode, proc.stdout, proc.stderr))
     return extract_decision(proc.stdout)
 
 
+# Anything that could be a credential in the CLI's output. The CLI does not normally echo its
+# token, but an API error body or a proxy's HTML page is not something to bet a leak on. Both
+# schemes are matched (the http one is the lesson of a scheme-specific redaction that leaked
+# ~/.git-credentials), and `token ...` is Gitea's own header scheme.
+_SECRET_PATTERNS = [
+    (re.compile(r"sk-ant-[A-Za-z0-9_\-]+"), "sk-ant-[REDACTED]"),
+    (re.compile(r"(?i)\b(bearer|token)(\s+|=|:\s*)[A-Za-z0-9._~+/=\-]{8,}"), r"\1\2[REDACTED]"),
+    (re.compile(r"(?i)(https?://)[^/\s:@]+:[^/\s@]+@"), r"\1[REDACTED]@"),
+]
+
+
+def redact(text: str) -> str:
+    for pat, repl in _SECRET_PATTERNS:
+        text = pat.sub(repl, text)
+    return text
+
+
+def describe_cli_failure(rc: int, stdout: str, stderr: str, limit: int = 800) -> str:
+    """Say WHY `claude --print` failed, in the dispatcher log, redacted.
+
+    WHY THIS EXISTS: with `--output-format json` the CLI reports its own failures — an API
+    error, a usage limit, `error_max_turns`, a schema the model could not satisfy — as the
+    JSON result envelope on STDOUT (`is_error`, `subtype`, `result`), and writes nothing to
+    stderr. Logging only stderr therefore produced `claude exited 1: ` with an empty message
+    on 2026-10-31, twice, with the cause sitting unread in stdout. So: the envelope's
+    diagnostic fields first, then the raw tails of both streams.
+    """
+    parts = [f"claude exited {rc}"]
+    out = (stdout or "").strip()
+    env = None
+    if out:
+        try:
+            env = json.loads(out)
+        except ValueError:
+            # A stream of JSON lines, or a log line ahead of the envelope: the last line that
+            # parses as an object is the result.
+            for line in reversed(out.splitlines()):
+                try:
+                    cand = json.loads(line)
+                except ValueError:
+                    continue
+                if isinstance(cand, dict):
+                    env = cand
+                    break
+    if isinstance(env, dict):
+        fields = []
+        for key in ("subtype", "is_error", "api_error_status", "num_turns", "duration_ms",
+                    "duration_api_ms", "total_cost_usd", "stop_reason"):
+            if key in env:
+                fields.append(f"{key}={env[key]!r}")
+        if fields:
+            parts.append("envelope: " + " ".join(fields))
+        for key in ("result", "error", "errors", "message"):
+            if env.get(key):
+                val = env[key] if isinstance(env[key], str) else json.dumps(env[key])
+                parts.append(f"{key}: {val[:limit]}")
+    if out and not isinstance(env, dict):
+        parts.append(f"stdout tail: {out[-limit:]}")
+    err_text = (stderr or "").strip()
+    if err_text:
+        parts.append(f"stderr tail: {err_text[-limit:]}")
+    if len(parts) == 1:
+        parts.append("(no output on stdout or stderr)")
+    return redact(" | ".join(parts))
+
+
 def extract_decision(stdout: str) -> dict:
     """Pull the decision object out of whatever `claude --print` wrapped it in.
 
@@ -501,7 +575,7 @@ def extract_decision(stdout: str) -> dict:
         obj = as_obj(c)
         if obj and isinstance(obj.get("action"), str):
             return obj
-    raise RuntimeError(f"no decision object in claude output: {stdout[:400]!r}")
+    raise RuntimeError(redact(f"no decision object in claude output: {stdout[-800:]!r}"))
 
 
 # --------------------------------------------------------------------------- thread
@@ -988,8 +1062,25 @@ def selftest() -> int:
         except RuntimeError:
             check(True, f"bad output refused: {label}")
 
+    # -- a failed CLI run must say why, and must not leak ---------------------
+    # The 2026-10-31 failure: rc 1, empty stderr, the cause in the stdout envelope.
+    env_err = json.dumps({"type": "result", "subtype": "error_max_turns", "is_error": True,
+                          "num_turns": 2, "result": "API Error: 429 rate_limit_error"})
+    msg = describe_cli_failure(1, env_err, "")
+    check("error_max_turns" in msg and "429" in msg,
+          "CLI failure: stdout envelope surfaced when stderr is empty")
+    msg = describe_cli_failure(1, "", "boom on stderr")
+    check("boom on stderr" in msg, "CLI failure: stderr tail surfaced")
+    msg = describe_cli_failure(1, "", "")
+    check("no output" in msg, "CLI failure: silence is named, not an empty message")
+    msg = describe_cli_failure(1, "plain text sk-ant-oat01-abcdefABCDEF_123 here",
+                               "Authorization: Bearer abcdefghijklmnop "
+                               "http://u:[email protected]/x")
+    check("sk-ant-oat01" not in msg and "abcdefghijklmnop" not in msg and ":pw@" not in msg,
+          "CLI failure: token, bearer and URL credential redacted")
+
     # -- the committed Job template -----------------------------------------
-    tmpl = os.environ.get("PM_WORKER_JOB_TEMPLATE", "/etc/pm-agent/worker-job-template.yaml")
+    tmpl =os.environ.get("PM_WORKER_JOB_TEMPLATE", "/etc/pm-agent/worker-job-template.yaml")
     try:
         selftest_template(tmpl)
         check(True, f"worker Job template satisfies its contract ({tmpl})")

platform/buildkit/deployment.yaml

@@ -60,7 +60,7 @@ spec:
           # Pinned by digest (the multi-arch index). The kubernetes manager in renovate.json5
           # tracks platform/**, so Renovate proposes bumps; the CI client (buildx, pinned in
           # versions.env) talks to any recent daemon.
-          image: docker.io/moby/buildkit:v0.34.1-rootless@sha256:f68752a5a94acfcdad2d07867b7075601a421638e17fc5f28efc1c814d0c4f89
+          image: docker.io/moby/buildkit:v0.34.2-rootless@sha256:c8252268760e1baba80780d63d738ef9f260fb7c7c0973c78494cb9ddd99eda1
           args:
             - --addr
             - unix:///run/user/1000/buildkit/buildkitd.sock   # local only: the probes below

platform/cilium/helmrelease.yaml

@@ -28,7 +28,7 @@ spec:
       chart: cilium
       # [parity] Pinned to the exact version the Ansible bootstrap installs
       # (cilium_version in roles/cilium/defaults/main.yml). Renovate bumps both together.
-      version: "1.20.1"
+      version: "1.20.4"
       sourceRef:
         kind: HelmRepository
         name: cilium

platform/crafty/deployment.yaml

@@ -61,7 +61,7 @@ spec:
         - name: crafty
           # registry.gitlab.com/crafty-controller/crafty-4 — official image. Pinned to the current
           # stable release (4.10.8, 2026-07-29; tags are bare semver, NO `v` prefix). Renovate maintains.
-          image: registry.gitlab.com/crafty-controller/crafty-4:4.10.8
+          image: registry.gitlab.com/crafty-controller/crafty-4:4.11.0
           imagePullPolicy: IfNotPresent
           env:
             - name: TZ

platform/external-snapshotter/kustomization.yaml

@@ -51,4 +51,4 @@ images:
   # Controller image == CRD version. A version bump = re-vendor crds.yaml + snapshot-controller.yaml
   # at the new tag (see header) AND bump this newTag.
   - name: registry.k8s.io/sig-storage/snapshot-controller
-    newTag: v8.2.0
+    newTag: v8.7.0

platform/external-snapshotter/snapshot-controller.yaml

@@ -194,7 +194,7 @@ spec:
       - args:
         - --v=5
         - --leader-election=true
-        image: registry.k8s.io/sig-storage/snapshot-controller:v8.0.1
+        image: registry.k8s.io/sig-storage/snapshot-controller:v8.7.0
         imagePullPolicy: IfNotPresent
         name: snapshot-controller
       serviceAccountName: snapshot-controller

platform/externaldns/ddns.yaml

@@ -51,7 +51,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: cloudflare-ddns
-          image: favonia/cloudflare-ddns:1.17.1
+          image: favonia/cloudflare-ddns:1.18.0
           imagePullPolicy: IfNotPresent
           env:
             - name: CLOUDFLARE_API_TOKEN

platform/homepage/deployment.yaml

@@ -38,7 +38,7 @@ spec:
       containers:
         - name: homepage
           # Renovate maintains this pin (ghcr.io/gethomepage/homepage). Config lives in /app/config.
-          image: ghcr.io/gethomepage/homepage:v2.1.2
+          image: ghcr.io/gethomepage/homepage:v2.7.0
           imagePullPolicy: IfNotPresent
           ports:
             - name: http

platform/intel-gpu-plugin/intel-gpu-plugin.yaml

@@ -63,7 +63,7 @@ spec:
           valueFrom:
             fieldRef:
               fieldPath: status.hostIP
-        image: intel/intel-gpu-plugin:0.37.0
+        image: intel/intel-gpu-plugin:0.37.1
         imagePullPolicy: IfNotPresent
         name: intel-gpu-plugin
         resources:

platform/intel-gpu-plugin/kustomization.yaml

@@ -96,4 +96,4 @@ images:
   - name: intel/intel-gpu-plugin
     newName: docker.io/intel/intel-gpu-plugin
     # renovate: datasource=github-releases depName=intel/intel-device-plugins-for-kubernetes
-    newTag: "0.37.0"
+    newTag: "0.37.1"

platform/kubevirt/kustomization.yaml

@@ -33,6 +33,6 @@ apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 resources:
   # renovate: datasource=github-releases depName=kubevirt/kubevirt
-  - https://github.com/kubevirt/kubevirt/releases/download/v1.9.0/kubevirt-operator.yaml
+  - https://github.com/kubevirt/kubevirt/releases/download/v1.9.1/kubevirt-operator.yaml
   # renovate: datasource=github-releases depName=kubevirt/containerized-data-importer
-  - https://github.com/kubevirt/containerized-data-importer/releases/download/v1.66.0/cdi-operator.yaml
+  - https://github.com/kubevirt/containerized-data-importer/releases/download/v1.66.1/cdi-operator.yaml

platform/oauth2-proxy/helmrelease.yaml

@@ -95,7 +95,7 @@ spec:
     # OIDC bootstrap hooks. (ci: flux-postbuild-substitution enforces it.)
     extraInitContainers:
       - name: wait-for-idp
-        image: docker.io/library/alpine:3.22
+        image: docker.io/library/alpine:3.24
         imagePullPolicy: IfNotPresent
         command: ["/bin/sh", "-c"]
         args:

platform/pm-agent/README.md

@@ -46,11 +46,12 @@ waive the sensitive-path human review on its own pull request.
 Both are deliberate, and both fail **visibly** rather than silently:
 
 1. **The image is published by CI, not by a person.** `platform/pm-agent/deployment.yaml` and
-   `PM_WORKER_IMAGE` in `configmap.yaml` carry the digest of the **first** publish (images
-   run 340, `sha-523cd9118f95`), pinned once on 2026-10-30 so going live did not wait on
-   Renovate's first run; every later bump is Renovate's. That digest predates the worker
-   template's `imagePullSecrets` entry, so worker Jobs built from it are refused by
-   admission — which is why `PM_DRY_RUN` starts `true` (see `configmap.yaml`). `.gitea/workflows/images.yaml` builds `agent-runner` on rootless BuildKit
+   `PM_WORKER_IMAGE` in `configmap.yaml` first carried the run-340 publish
+   (`sha-523cd9118f95`), whose baked template predated the `imagePullSecrets` entry admission
+   requires, so the service ran with `PM_DRY_RUN=true`. PR #96 pinned the run-383 digest
+   (`df36d9b`, `sha-ddd04d460ef6`), whose template carries the entry, and dry run was turned
+   off on 2026-10-31 (`decisions/2026-10-31-pm-agent-go-live.md`); every later bump is
+   Renovate's. `.gitea/workflows/images.yaml` builds `agent-runner` on rootless BuildKit
    (`platform/buildkit/`) — the same Containerfile, and the same `verify` stage, that
    `infra/agent/build-image.sh` builds locally — and on a push to `main` publishes it to
    `gitea.home.keithjackson.dev/home-network/agent-runner` under `sha-<commit>` and `main`.
@@ -249,6 +250,12 @@ five that matter:
 | `PM_MAX_ACTIVE_WORKERS` | `2` | concurrent workers. RAM is the binding constraint (2Gi limit each) and the subscription seat's rate limits are shared with every other use of that seat |
 | `PM_MAX_NEW_WORKERS_PER_CYCLE` | `1` | drains a backlog one issue at a time instead of in one stampede the first minute the credentials work |
 | `PM_PUSH_ON_RED_GATE` | `false` | a change the gate refused is not pushed; the issue gets the gate log instead |
+| `PM_DECISION_MAX_TURNS` | `1` (unset) | turns the triage call may take (1–5). The PM holds no tools, so a second turn is only ever the CLI re-asking after an answer that failed the decision schema. Raise it if a triage error logs `subtype='error_max_turns'` |
+
+**When a triage fails**, the `[error] issue #N: claude exited …` line carries the CLI's result
+envelope (`subtype`, `is_error`, `api_error_status`, `num_turns`, `result`) and the tails of
+stdout and stderr, redacted. Before 2026-10-31 it logged stderr only, which is empty under
+`--output-format json` — see `decisions/2026-10-31-pm-agent-triage-exit.md`.
 
 Changing a knob requires bumping the `config-generation` annotation in `deployment.yaml` in
 the same commit — the process reads its configuration once, at startup, so without the bump

platform/pm-agent/configmap.yaml

@@ -58,13 +58,16 @@ data:
   # request that also moves the Deployment's image (same marker, same branch). Nobody pushes
   # this image from a workstation.
   #
-  # READ BEFORE TURNING PM_DRY_RUN OFF: this digest PREDATES the worker template's
-  # `imagePullSecrets` entry (PR #61). Its baked template has none, and admission now REQUIRES
-  # it — so a worker Job built from this image is DENIED. The merge that adds the entry
-  # changes infra/agent/**, CI re-publishes agent-runner, and Renovate's bump to that digest
-  # is what makes worker Jobs admissible. Until then, dry run is the only mode that works.
+  # The run-340 digest predated the worker template's `imagePullSecrets` entry (PR #61), which
+  # admission REQUIRES, so its worker Jobs were DENIED. The digest below (df36d9b, run 383,
+  # agent-runner:sha-ddd04d460ef6, pinned in PR #96) bakes a template that carries
+  # `imagePullSecrets: pm-agent-registry`, which is what made turning PM_DRY_RUN off possible
+  # (decisions/2026-10-31-pm-agent-runner-digest.md). A digest older than that would be DENIED.
+  # The digest below (14a42ba, images run 394, agent-runner:sha-466f63ec3c3d = PR #99's merge)
+  # adds the CLI failure envelope to triage errors and the PM_DECISION_MAX_TURNS knob
+  # (decisions/2026-10-31-pm-agent-digest-99.md).
   # renovate-digest: image=gitea.home.keithjackson.dev/home-network/agent-runner tag=main
-  PM_WORKER_IMAGE: "gitea.home.keithjackson.dev/home-network/agent-runner@sha256:df36d9b7fef56d141220a387f64fb864cede8e5af30513ebfeb3ab566d3f771d"
+  PM_WORKER_IMAGE: "gitea.home.keithjackson.dev/home-network/agent-runner@sha256:14a42ba8281ecd98005f5d99ecda4fb729104c783b01584097c32e104ced1bb2"
 
   # --- the model -------------------------------------------------------------
   # The PM only reads a thread and answers with one JSON object, so it holds no tools and
@@ -120,10 +123,11 @@ data:
   # no worker Job and so changes no code. The honest way to watch this service for a day
   # before letting it write anything.
   #
-  # "true" FOR THE FIRST RUN, and not only for caution: the pinned digest above cannot yet
-  # create an admissible worker Job (see the PM_WORKER_IMAGE comment). Flip to "false" in the
-  # same pull request as — or after — Renovate's first agent-runner digest bump.
-  PM_DRY_RUN: "true"
+  # "true" for the first run (2026-10-30 .. 2026-10-31); dry-run triage of issue #97 was read
+  # and the operator approved going live. "false" since decisions/2026-10-31-pm-agent-go-live.md.
+  # Setting it back to "true" (plus a config-generation bump) is the gentlest stop — see
+  # runbooks/pm-agent.md.
+  PM_DRY_RUN: "false"
 
   # If the gate refuses a worker's change, the branch is NOT pushed by default and the issue
   # gets the gate log instead. Set to "true" to push anyway and open a red pull request —

platform/pm-agent/deployment.yaml

@@ -48,7 +48,7 @@ spec:
         # It is a hand-maintained marker rather than a computed hash because Flux's
         # Kustomization here does not run a configmap generator; bump it in the same commit
         # as a change to configmap.yaml.
-        pm-agent.homelab.keithjackson.dev/config-generation: "3"
+        pm-agent.homelab.keithjackson.dev/config-generation: "5"
     spec:
       serviceAccountName: pm-agent
       # The kubelet's credential for pulling this image. Not the agent's Gitea credential —
@@ -78,7 +78,7 @@ spec:
           # the registry's manifest endpoint on 2026-10-30 and pinned by hand once so the
           # dispatcher does not wait on Renovate's first run; every later bump is Renovate's.
           # renovate-digest: image=gitea.home.keithjackson.dev/home-network/agent-runner tag=main
-          image: gitea.home.keithjackson.dev/home-network/agent-runner@sha256:df36d9b7fef56d141220a387f64fb864cede8e5af30513ebfeb3ab566d3f771d
+          image: gitea.home.keithjackson.dev/home-network/agent-runner@sha256:14a42ba8281ecd98005f5d99ecda4fb729104c783b01584097c32e104ced1bb2
           imagePullPolicy: IfNotPresent
           command:
             - /usr/local/bin/pm-dispatch

platform/velero/helmrelease.yaml

@@ -88,7 +88,7 @@ spec:
     # rather than becoming a fifth per-environment knob. ---
     initContainers:
       - name: velero-plugin-for-aws
-        image: velero/velero-plugin-for-aws:v1.14.3-rc.2
+        image: velero/velero-plugin-for-aws:v1.14.4
         imagePullPolicy: IfNotPresent
         volumeMounts:
           - mountPath: /target

runbooks/serving/deployment.yaml

@@ -87,7 +87,7 @@ spec:
           # Renovate maintains this pin. nginx-unprivileged (not nginx) so the container can honour
           # runAsNonRoot: the stock nginx image's entrypoint needs root to drop privileges and to
           # bind :80. `stable-alpine` branch, pinned exactly.
-          image: nginxinc/nginx-unprivileged:1.30.4-alpine
+          image: nginxinc/nginx-unprivileged:1.31.7-alpine
           imagePullPolicy: IfNotPresent
           ports:
             - name: http