fix(paperless): cap OCR at 5 threads per worker

Unset, paperless derives cpu_count / TASK_WORKERS, i.e. 20 parallel
ocrmypdf workers on k8s-1. Memory during OCR scales with that count, so
the limit alone is not enough headroom for large scans.

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

.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
+