fix(wake): #943 whole-string validation for WAKE_SNAPSHOT_TS_FUTURE_SLACK + version 0.6.13

grep is line-oriented, so a multi-line knob value passed the per-line anchors and was still fatal in arithmetic. Replaced with a case pattern matching the whole string, so an embedded or leading newline rejects. Manifest bumped 0.6.12 -> 0.6.13: three materially different detectors had shipped under one version string, and version= is the component sole self-identity claim. Authored-by: pepper Reviewed-by: mos-dt (independent, at this head; transfer proven by blob-hash equality) Merged-by: Mos Co-authored-by: mos-dt-0 <[email protected]>
2026-07-30 11:56:18 +00:00
parent 3e47fc076f
commit 539b475a92
3 changed files with 59 additions and 13 deletions
@@ -295,16 +295,24 @@ _poll_source() {
        # is interpolated into $((...)) under set -u, so a non-numeric value
        # ('300s', '5m', 'abc') would be FATAL to the poll — the one thing this
        # block must never be. Resolve it ONCE, validate, fall back loudly.
-        local now_s slack
+        local now_s slack slack_ok
        slack="${WAKE_SNAPSHOT_TS_FUTURE_SLACK:-300}"
-        if ! printf '%s' "$slack" | grep -Eq '^[0-9]{1,9}$'; then
-          echo "detector.sh: WAKE_SNAPSHOT_TS_FUTURE_SLACK='$slack' is not a plain non-negative integer (seconds) — falling back to 300, poll continues (#940)." >&2
+        # NOT grep: grep is LINE-oriented, so ^...$ anchors bind per line and a
+        # multi-line value ($'300\n8') passes the regex yet is FATAL in $((...)).
+        # The case pattern matches the WHOLE string, newlines included. (snap_ts
+        # is immune: jq's number type-check above cannot emit an embedded newline.)
+        case "$slack" in
+        '' | *[!0-9]*) slack_ok=1 ;;
+        *) [ "${#slack}" -le 9 ] && slack_ok=0 || slack_ok=1 ;;
+        esac
+        if [ "$slack_ok" -ne 0 ]; then
+          echo "detector.sh: WAKE_SNAPSHOT_TS_FUTURE_SLACK='$slack' is not a plain non-negative integer of at most 9 digits (seconds) — falling back to 300, poll continues (#940)." >&2
          slack=300
        fi
        # Shape validation is not radix validation: bash reads a leading zero as
-        # OCTAL, so '08'/'09' pass the regex yet are FATAL in $((...)), and
+        # OCTAL, so '08'/'09' pass the shape check yet are FATAL in $((...)), and
        # '0300' silently means 192. Force base-10 so the knob means what the
-        # operator wrote (safe: the regex above guarantees pure digits).
+        # operator wrote (safe: the case pattern above guarantees pure digits).
        slack=$((10#$slack))
        now_s="$(date +%s)"
        if [ "$snap_ts" -gt $((now_s + slack)) ]; then
@@ -276,15 +276,21 @@
 #              yields a NEGATIVE age — stale-reads-fresher-than-fresh, the
 #              exact failure class #940 fixes. The SLACK knob itself is
 #              operator input interpolated into arithmetic under set -u, so it
-#              gets the same discipline (#941 §2 round 2): validated
-#              ^[0-9]{1,9}$, else LOUD fallback to 300 — a malformed knob
+#              gets the same discipline (#941 §2 round 2): shape-validated as
+#              a plain non-negative integer of at most 9 digits, else LOUD
+#              fallback to 300 — a malformed knob
 #              ('300s', '5m', 'abc') must never kill the poll, and a negative
 #              one must never invert the guard into deny-all. Shape validation
 #              is NOT radix validation (#942 review): bash reads leading zeros
-#              as OCTAL, so '08'/'09' pass the regex yet are fatal in $((...))
-#              and '0300' silently means 192 — the knob is therefore forced
-#              base-10 (10#) after validation, so it means what the operator
-#              wrote. SKEW GUARANTEE
+#              as OCTAL, so '08'/'09' pass the shape check yet are fatal in
+#              $((...)) and '0300' silently means 192 — the knob is therefore
+#              forced base-10 (10#) after validation, so it means what the
+#              operator wrote. The validator and the consumer must also agree
+#              on STRING EXTENT (#942 follow-up): grep's ^...$ anchors bind
+#              per LINE, so a multi-line value ($'300\n8') passed the regex
+#              whole yet was fatal in $((...)) — validation is a whole-string
+#              case pattern, not grep, so an embedded newline rejects.
+#              SKEW GUARANTEE
 #              (stated, not implied): the future-skew check runs against the
 #              DETECTOR's clock; consumer-side age arithmetic runs on the
 #              consumer's. A surviving snapshot_ts is therefore attested only
@@ -300,8 +306,20 @@
 #              absence of these fields.
 #              Changed: detector.sh, digest.sh (+ test-wake-detector.sh
 #              D10/D11/D12/D13, test-wake-digest-quarantine.sh Q10).
+#   0.6.13 #942/#943 SLACK-knob validation hardening, split from 0.6.12 because
+#              version= is the component's SOLE self-identity claim (no per-file
+#              hashes here) and two detector-changing merges after the 0.6.12
+#              stamp had left three materially different detectors under one
+#              version string (#943 review §2). #942: the knob is resolved once,
+#              shape-validated, LOUD fallback 300, and forced base-10 (10#) so
+#              zero-padded values mean what the operator wrote instead of octal.
+#              #943: validation is a whole-string case pattern, not grep, so an
+#              embedded newline ($'300\n8' — accepted per-line by grep's ^...$
+#              anchors, fatal in $((...))) rejects. Full rationale in the knob
+#              paragraph of the 0.6.12 entry above.
+#              Changed: detector.sh (+ test-wake-detector.sh D13).
 component=wake
-version=0.6.12
+version=0.6.13

 # Watch-list schema this component consumes, and the INCLUSIVE range of
 # schema_version values it supports. A wake-watch-list.json whose schema_version
@@ -644,6 +644,26 @@ EOF
  entry="$("$STORE" drain | tail -1)"
  echo "$entry" | jq -e --arg s "$goodsha" 'select(.locators.snapshot_sha==$s) | .locators | has("snapshot_ts")' >/dev/null 2>&1 \
    || fail_msg "D13: negative slack must NOT invert the guard into deny-all [$entry]"
+  # (c2) MULTI-LINE knobs — grep's ^...$ anchors bind PER LINE, so a value with
+  # an embedded newline ($'300\n8') passed the old regex whole yet is FATAL in
+  # \$((...)) ('error token is "8"'; $'300\nabc' dies as unbound variable). The
+  # case pattern matches the WHOLE string: both must fall back loudly, keep the ts.
+  printf '{"snapshot_sha":"%s","snapshot_ts":%s}\n' "$goodsha" "$(date +%s)" >"$stub/repo_r1.meta"
+  printf 'SHA-CC2\n' >"$stub/repo_r1"
+  err="$(WAKE_SNAPSHOT_TS_FUTURE_SLACK=$'300\n8' "$DET" poll-once 2>&1 >/dev/null)"; rc=$?
+  [ "$rc" -eq 0 ] || fail_msg "D13: multi-line SLACK (300\\n8) must NEVER fail the poll (rc=$rc) [$err]"
+  echo "$err" | grep -qi 'falling back to 300' || fail_msg "D13: multi-line slack must be LOUD on stderr [$err]"
+  entry="$("$STORE" drain | tail -1)"
+  echo "$entry" | jq -e --arg s "$goodsha" 'select(.locators.snapshot_sha==$s) | .locators | has("snapshot_ts")' >/dev/null 2>&1 \
+    || fail_msg "D13: valid metadata must SURVIVE a multi-line knob [$entry]"
+  printf '{"snapshot_sha":"%s","snapshot_ts":%s}\n' "$goodsha" "$(date +%s)" >"$stub/repo_r1.meta"
+  printf 'SHA-CC3\n' >"$stub/repo_r1"
+  err="$(WAKE_SNAPSHOT_TS_FUTURE_SLACK=$'300\nabc' "$DET" poll-once 2>&1 >/dev/null)"; rc=$?
+  [ "$rc" -eq 0 ] || fail_msg "D13: multi-line SLACK (300\\nabc) must NEVER fail the poll (rc=$rc) [$err]"
+  echo "$err" | grep -qi 'falling back to 300' || fail_msg "D13: multi-line non-numeric slack must be LOUD on stderr [$err]"
+  entry="$("$STORE" drain | tail -1)"
+  echo "$entry" | jq -e --arg s "$goodsha" 'select(.locators.snapshot_sha==$s) | .locators | has("snapshot_ts")' >/dev/null 2>&1 \
+    || fail_msg "D13: valid metadata must SURVIVE a multi-line non-numeric knob [$entry]"
  # (d2-pre) ZERO-PADDED knobs — shape-valid, radix-hostile. '08' passes the
  # regex but is fatal octal in \$((...)) without the 10# normalization; '0300'
  # silently means 192 (octal), so a ts +250s ahead would be WRONGLY dropped.
@@ -671,7 +691,7 @@ EOF
  entry="$("$STORE" drain | tail -1)"
  echo "$entry" | jq -e --arg s "$goodsha" 'select(.locators.snapshot_sha==$s) | .locators | has("snapshot_ts") | not' >/dev/null 2>&1 \
    || fail_msg "D13: valid SLACK=0 must drop the future ts but keep the sha [$entry]"
-  [ "$(det_seq)" = "6" ] || fail_msg "D13: all six real deltas must still have enqueued, got seq $(det_seq)"
+  [ "$(det_seq)" = "8" ] || fail_msg "D13: all eight real deltas must still have enqueued, got seq $(det_seq)"
 ) && ok

 echo