fix(ci-claude-refresh): bump divergent pins instead of aborting

decide required every consumer to pin the same ci-claude tag and aborted
otherwise (pipeline 10497: [2.1.250 2.1.278]), which needed a hand fix
before the latest version could roll out. Record all distinct tags, bump
whenever any is off latest, and rewrite every version-pinned tag to the
new one with a validated x.y.z version.

Merging this is itself a push touching the pipeline file, so the refresh
runs, builds the latest image, and opens the bump PR.

Refs #889

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

.woodpecker/ci-claude-refresh.yml

@@ -14,8 +14,8 @@
 #                 and  ci-claude:latest.  The Containerfile makes this layer
 #                 byte-reproducible, so rebuilding an unchanged version dedups
 #                 in the registry instead of orphaning a fresh ~260 MB copy.
-#   3. bump-pr  — (only when the version actually changed) rewrite the 5
-#                 consumer pins to  ci-claude:<version>  and open a PR. A human
+#   3. bump-pr  — (only when any pin is off the latest version) rewrite every
+#                 consumer pin to  ci-claude:<version>  and open a PR. A human
 #                 reviews and merges it; nothing auto-merges.
 #
 # TAG SCHEME — deliberately version tags (ci-claude:<claude-version>), NOT the dated
@@ -107,31 +107,22 @@ steps:
           [0-9]*.[0-9]*.[0-9]*) : ;;
           *) echo "npm returned an implausible version '$$NEW' — aborting."; exit 1 ;;
         esac
-        # The tag every consumer currently references. They are kept identical,
-        # so this must resolve to EXACTLY ONE non-empty tag; anything else
-        # (no match, or a partial/disagreeing set) aborts rather than risk a
-        # corrupting sed later. Counting with `grep -c .` (non-empty lines)
-        # instead of `wc -l` is deliberate: an empty result yields 0 here but
-        # 1 under wc -l, which would slip past the guard.
-        CUR=$$(grep -hoE 'ci-claude:[0-9A-Za-z._-]+' $$CONSUMERS | sed 's/^ci-claude://' | sort -u)
-        NTAGS=$$(printf '%s' "$$CUR" | grep -c . || true)
-        if [ -z "$$CUR" ] || [ "$$NTAGS" -ne 1 ]; then
-          echo "Expected exactly one ci-claude tag across the consumers, got [$$CUR]."
-          echo "Refusing to guess — fix the pins by hand."; exit 1
-        fi
-        echo "latest=$$NEW  current=$$CUR  event=$$CI_PIPELINE_EVENT"
+        # Distinct tags the consumers currently reference. Divergent pins are
+        # normal (a pipeline bumped on its own); the bump rewrites all of them.
+        CUR=$$(grep -hoE 'ci-claude:[0-9][0-9A-Za-z._-]*' $$CONSUMERS | sed 's/^ci-claude://' | sort -u | tr '\n' ' ' | sed 's/ $$//')
+        [ -n "$$CUR" ] || { echo "No ci-claude pin found in the consumers — aborting."; exit 1; }
+        echo "latest=$$NEW  current=[$$CUR]  event=$$CI_PIPELINE_EVENT"
         printf '%s' "$$NEW" > "$$CI_WORKSPACE/.ci-refresh/version"
         printf '%s' "$$CUR" > "$$CI_WORKSPACE/.ci-refresh/current"
-        # Build when the version changed, or on a push (Containerfile edit must
-        # ship even if the version is unchanged). Bump the pins only when the
-        # version the consumers reference is not the latest.
+        # Build when any pin is off latest, or on a push (Containerfile edit must
+        # ship even if the version is unchanged). Bump when any pin is off latest.
         if [ "$$CUR" != "$$NEW" ] || [ "$$CI_PIPELINE_EVENT" = "push" ]; then
           touch "$$CI_WORKSPACE/.ci-refresh/do-build"; echo "will build $$NEW"
         else
           echo "already on $$NEW — nothing to build"
         fi
         if [ "$$CUR" != "$$NEW" ]; then
-          touch "$$CI_WORKSPACE/.ci-refresh/do-bump"; echo "will open bump PR $$CUR -> $$NEW"
+          touch "$$CI_WORKSPACE/.ci-refresh/do-bump"; echo "will open bump PR [$$CUR] -> $$NEW"
         else
           echo "consumers already pin $$NEW — no PR"
         fi
@@ -175,6 +166,9 @@ steps:
       - |
         [ -f "$$CI_WORKSPACE/.ci-refresh/do-bump" ] || { echo "no version change — no PR"; exit 0; }
         set -eu
+        # Secret values can carry a trailing newline; it breaks the push URL and the auth header.
+        PUSH_TOKEN=$$(printf '%s' "$$PUSH_TOKEN" | tr -d '\r\n')
+        [ -n "$$PUSH_TOKEN" ] || { echo "PUSH_TOKEN is empty — aborting"; exit 1; }
         NEW=$$(cat "$$CI_WORKSPACE/.ci-refresh/version")
         CUR=$$(cat "$$CI_WORKSPACE/.ci-refresh/current")
         # Both were validated non-empty by the decide step; re-assert before a
@@ -190,9 +184,11 @@ steps:
         # is not a maintained list.
         CONSUMERS=$$(grep -rlE 'ci-claude:[0-9]' .woodpecker)
         [ -n "$$CONSUMERS" ] || { echo "No ci-claude consumers found — refusing to continue."; exit 1; }
-        # Exact-string swap of the current tag for the new one, consumers only.
+        # NEW goes into a sed replacement: allow only a plain x.y.z version.
+        printf '%s' "$$NEW" | grep -qE '^[0-9]+\.[0-9]+\.[0-9]+$$' || { echo "refusing non-x.y.z version '$$NEW'"; exit 1; }
+        # Every version-pinned tag becomes NEW, whatever it was; consumers only.
         for f in $$CONSUMERS; do
-          sed -i "s#ci-claude:$$CUR#ci-claude:$$NEW#g" "$$f"
+          sed -i "s#ci-claude:[0-9][0-9A-Za-z._-]*#ci-claude:$$NEW#g" "$$f"
         done
         # Author is claude-bot (the PAT's account); the commit subject makes
         # the automated-bump nature clear.

.woodpecker/wiki-maintenance.yml

@@ -125,8 +125,16 @@ steps:
         echo "POST pull -> HTTP $$code"
         [ "$$code" -ge 200 ] && [ "$$code" -lt 300 ] || { cat /tmp/pr-resp.json; exit 1; }
         NUM=$$(jq -r '.number' /tmp/pr-resp.json)
+        # Merge without delete_branch_after_merge: run 10254 got HTTP 500 from that
+        # call although the merge itself had landed. Verify the PR state instead of
+        # trusting the status code, then drop the branch as a separate, best-effort step.
         code=$$(curl -s -o /tmp/merge-resp.json -w '%{http_code}' -X POST \
           -H "Authorization: token $$TOKEN" -H "Content-Type: application/json" \
-          --data '{"Do":"merge","delete_branch_after_merge":true}' "$$API/pulls/$$NUM/merge")
+          --data '{"Do":"merge"}' "$$API/pulls/$$NUM/merge")
         echo "POST merge #$$NUM -> HTTP $$code"
-        [ "$$code" -ge 200 ] && [ "$$code" -lt 300 ] || { cat /tmp/merge-resp.json; echo "PR #$$NUM left open"; exit 1; }
+        MERGED=$$(curl -s -H "Authorization: token $$TOKEN" "$$API/pulls/$$NUM" | jq -r '.merged')
+        echo "PR #$$NUM merged: $$MERGED"
+        [ "$$MERGED" = "true" ] || { cat /tmp/merge-resp.json; echo "PR #$$NUM left open"; exit 1; }
+        code=$$(curl -s -o /tmp/del-resp.json -w '%{http_code}' -X DELETE -H "Authorization: token $$TOKEN" \
+          "$$API/branches/$$(printf '%s' "$$BRANCH" | sed 's|/|%2F|g')")
+        echo "DELETE branch $$BRANCH -> HTTP $$code (best effort)"

kubernetes/apps/paperless/paperless.yaml

@@ -27,6 +27,8 @@ data:
   PAPERLESS_ALLOWED_HOSTS: "*"
   PAPERLESS_TIME_ZONE: "Europe/Berlin"
   PAPERLESS_OCR_LANGUAGE: "deu+eng"
+  # Default is cpu_count / TASK_WORKERS, 20 on k8s-1; OCR memory scales with it.
+  PAPERLESS_THREADS_PER_WORKER: "5"
   PAPERLESS_CONSUMER_RECURSIVE: "true"
   PAPERLESS_CONSUMER_DELETE_DUPLICATES: "true"
   PAPERLESS_CONSUMER_ENABLE_BARCODES: "true"
@@ -273,7 +275,7 @@ spec:
               cpu: 200m
               memory: 512Mi
             limits:
-              memory: 2Gi
+              memory: 4Gi
           securityContext:
             runAsNonRoot: false
             allowPrivilegeEscalation: true

kubernetes/apps/paperless/redis.yaml

@@ -25,7 +25,7 @@ spec:
           type: RuntimeDefault
       containers:
         - name: redis
-          image: redis:8.10.1-alpine # {"$imagepolicy": "flux-system:redis-paperless"}
+          image: redis:8.10.2-alpine # {"$imagepolicy": "flux-system:redis-paperless"}
           args:
             - redis-server
             - --save

scripts/ci/choose-model.sh

@@ -0,0 +1,30 @@
+#!/bin/sh
+# Turn the TypeSafe picker's probability distribution into one model id.
+#
+# The judgment (how well each catalog model fits the task) comes from the
+# model; the policy lives here, in code: among the candidates whose probability
+# is within MARGIN of the best one, take the most recently released. Several
+# same-family models (Sonnet 4.5 / 4.6 / 5) split the probability for a
+# mid-weight task, and the newest of a comparable set is the one to run.
+#
+# Usage: choose-model.sh <catalog-table-file> < <systemone-response.json>
+#   The table is fetch-models.sh --table output: id \t name \t released=YYYY-MM-DD ...
+#   Prints the chosen id, or nothing when the answer is NONE / unusable.
+# Env: CHOOSE_MODEL_MARGIN (default 0.7): candidate if p >= MARGIN * p_best.
+
+set -eu
+TABLE_FILE="${1:?usage: choose-model.sh <catalog-table-file> < response.json}"
+MARGIN="${CHOOSE_MODEL_MARGIN:-0.7}"
+
+jq -r --rawfile table "$TABLE_FILE" --argjson margin "$MARGIN" '
+  ($table | split("\n") | map(select(length > 0) | split("\t")
+     | {key: .[0], value: ((.[2:] | map(select(startswith("released="))) | .[0] // "released=") | ltrimstr("released="))})
+   | from_entries) as $released
+  | (.answers.model.probabilities // {}) | to_entries
+  | map(select(.key != "NONE")) | sort_by(-.value)
+  | if length == 0 then empty
+    else (.[0].value) as $best
+      | map(select(.value >= $margin * $best))
+      | sort_by([($released[.key] // ""), .value])
+      | .[-1].key
+    end' 2>&1

scripts/ci/pick-model.sh

@@ -51,11 +51,18 @@ if [ -n "${TYPESAFE_API_KEY:-}" ]; then
   if [ -n "${PICK_MODEL_TYPESAFE_DRYRUN:-}" ]; then printf '%s\n' "$REQ"; exit 0; fi
   RESP="$(printf '%s' "$REQ" | curl -sS --max-time 30 -X POST https://api.typesafe.ai/v1/systemone \
            -H "Authorization: Bearer $TYPESAFE_API_KEY" -H 'Content-Type: application/json' --data-binary @- || true)"
-  CHOICE="$(printf '%s' "$RESP" | jq -r '.answers.model.choice // empty' 2>&1 | head -1)"
-  CONF="$(printf '%s' "$RESP" | jq -r '.answers.model.confidence // empty' 2>&1 | head -1)"
+  # Policy in code (choose-model.sh): among candidates within a margin of the
+  # best probability, the most recently released wins. Same-family models split
+  # the probability for mid-weight tasks (live catalog: Sonnet 4.5 chosen at
+  # 0.23 over Sonnet 4.6).
+  TABLE_FILE="$(mktemp)"
+  printf '%s\n' "$TABLE" > "$TABLE_FILE"
+  CHOICE="$(printf '%s' "$RESP" | sh "$HERE/choose-model.sh" "$TABLE_FILE" | head -1)"
+  rm -f "$TABLE_FILE"
+  TOP="$(printf '%s' "$RESP" | jq -r '(.answers.model.probabilities // {}) | to_entries | sort_by(-.value) | .[0:4] | map("\(.key)=\(.value)") | join(" ")' 2>&1 | head -1)"
   VALID="$(printf '%s\n' "$TABLE" | sh "$HERE/valid-model.sh" "$CHOICE")"
   if [ -n "$VALID" ]; then
-    log "typesafe chose '$VALID' (confidence ${CONF:-?}) for: $GUIDANCE"
+    log "typesafe chose '$VALID' (top: ${TOP:-?}) for: $GUIDANCE"
     printf '%s\n' "$VALID"
     exit 0
   fi

scripts/ci/test-model-selection.sh

@@ -97,9 +97,27 @@ else
   printf 'FAIL  typesafe request: keys [%s] task [%s]\n' "$keys" "$task"; fails=$((fails + 1))
 fi
 
+# choose-model.sh: newest among comparable candidates, best otherwise, NONE -> nothing.
+TB="$(mktemp)"
+printf '%s\n' 'claude-sonnet-4-5	Claude Sonnet 4.5	released=2025-09-29	context=200000' \
+              'claude-sonnet-4-6	Claude Sonnet 4.6	released=2026-02-17	context=200000' \
+              'claude-opus-5	Claude Opus 5	released=2026-07-24	context=1000000' \
+              'claude-haiku-4-5	Claude Haiku 4.5	released=2025-10-15	context=200000' > "$TB"
+choose() { printf '%s' "$1" | sh "$HERE/choose-model.sh" "$TB" || true; }
+got="$(choose '{"answers":{"model":{"probabilities":{"claude-sonnet-4-5":0.30,"claude-sonnet-4-6":0.25,"claude-opus-5":0.10,"NONE":0.05}}}}')"
+if [ "$got" = "claude-sonnet-4-6" ]; then printf 'ok    newer sibling within margin wins\n'; else printf 'FAIL  comparable: got [%s]\n' "$got"; fails=$((fails + 1)); fi
+got="$(choose '{"answers":{"model":{"probabilities":{"claude-opus-5":0.90,"claude-haiku-4-5":0.05,"claude-sonnet-4-6":0.04,"NONE":0.01}}}}')"
+if [ "$got" = "claude-opus-5" ]; then printf 'ok    clear best is kept\n'; else printf 'FAIL  clear best: got [%s]\n' "$got"; fails=$((fails + 1)); fi
+got="$(choose '{"answers":{"model":{"probabilities":{"claude-haiku-4-5":0.60,"claude-sonnet-4-5":0.35,"NONE":0.05}}}}')"
+if [ "$got" = "claude-haiku-4-5" ]; then printf 'ok    older best outside margin is kept\n'; else printf 'FAIL  margin: got [%s]\n' "$got"; fails=$((fails + 1)); fi
+got="$(choose '{"answers":{"model":{"probabilities":{"NONE":1.0}}}}')"
+if [ -z "$got" ]; then printf 'ok    NONE yields nothing\n'; else printf 'FAIL  NONE: got [%s]\n' "$got"; fails=$((fails + 1)); fi
+rm -f "$TB"
+
 if [ "$fails" -eq 0 ]; then
   echo "All model-selection tests passed."
 else
   echo "$fails test(s) FAILED."
   exit 1
 fi
+